From 0abee5260babe0a12d468b485a28336551697925 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Wed, 15 Sep 2010 19:24:50 +0200 Subject: netfilter: nf_nat: add nf_nat_csum() Add a static function nf_nat_csum() to replace the duplicate code in nf_nat_mangle_udp_packet() and __nf_nat_mangle_tcp_packet(). Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 4a0c6b5..31427fb 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -153,6 +153,35 @@ void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); +static void nf_nat_csum(struct sk_buff *skb, struct iphdr *iph, void *data, + int datalen, __sum16 *check, int oldlen) +{ + struct rtable *rt = skb_rtable(skb); + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(rt->rt_flags & RTCF_LOCAL) && + skb->dev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + + skb_network_offset(skb) + + iph->ihl * 4; + skb->csum_offset = (void *)check - data; + *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, iph->protocol, 0); + } else { + *check = 0; + *check = csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, iph->protocol, + csum_partial(data, datalen, + 0)); + if (iph->protocol == IPPROTO_UDP && !*check) + *check = CSUM_MANGLED_0; + } + } else + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), 1); +} + /* Generic function for mangling variable-length address changes inside * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX * command in FTP). @@ -169,7 +198,6 @@ int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len, bool adjust) { - struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct tcphdr *tcph; int oldlen, datalen; @@ -192,26 +220,7 @@ int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, match_offset, match_len, rep_buffer, rep_len); datalen = skb->len - iph->ihl*4; - if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(rt->rt_flags & RTCF_LOCAL) && - skb->dev->features & NETIF_F_V4_CSUM) { - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + - skb_network_offset(skb) + - iph->ihl * 4; - skb->csum_offset = offsetof(struct tcphdr, check); - tcph->check = ~tcp_v4_check(datalen, - iph->saddr, iph->daddr, 0); - } else { - tcph->check = 0; - tcph->check = tcp_v4_check(datalen, - iph->saddr, iph->daddr, - csum_partial(tcph, - datalen, 0)); - } - } else - inet_proto_csum_replace2(&tcph->check, skb, - htons(oldlen), htons(datalen), 1); + nf_nat_csum(skb, iph, tcph, datalen, &tcph->check, oldlen); if (adjust && rep_len != match_len) nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, @@ -240,7 +249,6 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct udphdr *udph; int datalen, oldlen; @@ -274,29 +282,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) return 1; - if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(rt->rt_flags & RTCF_LOCAL) && - skb->dev->features & NETIF_F_V4_CSUM) { - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + - skb_network_offset(skb) + - iph->ihl * 4; - skb->csum_offset = offsetof(struct udphdr, check); - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - datalen, IPPROTO_UDP, - 0); - } else { - udph->check = 0; - udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, - datalen, IPPROTO_UDP, - csum_partial(udph, - datalen, 0)); - if (!udph->check) - udph->check = CSUM_MANGLED_0; - } - } else - inet_proto_csum_replace2(&udph->check, skb, - htons(oldlen), htons(datalen), 1); + nf_nat_csum(skb, iph, udph, datalen, &udph->check, oldlen); return 1; } -- cgit v0.10.2 From 70a851667dbd7aa3f7be9609d6580ca9861230b3 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 16 Sep 2010 19:37:30 +0200 Subject: netfilter: use NFPROTO_IPV4 instead of AF_INET The field family of xt_target should be NFPROTO_IPV4, though NFPROTO_IPV4 and AF_INET are the same. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index c61294d..21bb2af 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -76,7 +76,7 @@ static int tproxy_tg_check(const struct xt_tgchk_param *par) static struct xt_target tproxy_tg_reg __read_mostly = { .name = "TPROXY", - .family = AF_INET, + .family = NFPROTO_IPV4, .table = "mangle", .target = tproxy_tg, .targetsize = sizeof(struct xt_tproxy_target_info), -- cgit v0.10.2 From 99ad3c53b36a056a472927de9c79eda231ecc6fe Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 16 Sep 2010 19:45:19 +0200 Subject: netfilter: nf_nat_core: don't check if the tuple is used if there is no other choice Eliminate nf_nat_used_tuple() to save some CPU cycles when there is no other choice. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 8c8632d..2c084b3 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -262,11 +262,17 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, proto = __nf_nat_proto_find(orig_tuple->dst.protonum); /* Only bother mapping if it's not already in range and unique */ - if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM) && - (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || - proto->in_range(tuple, maniptype, &range->min, &range->max)) && - !nf_nat_used_tuple(tuple, ct)) - goto out; + if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { + if (range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) { + if (proto->in_range(tuple, maniptype, &range->min, + &range->max) && + (range->min.all == range->max.all || + !nf_nat_used_tuple(tuple, ct))) + goto out; + } else if (!nf_nat_used_tuple(tuple, ct)) { + goto out; + } + } /* Last change: get protocol to try to obtain unique tuple. */ proto->unique_tuple(tuple, range, maniptype, ct); -- cgit v0.10.2 From ed0b6d7581b54455062f09ccac123814e70cd02f Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 16 Sep 2010 19:47:51 +0200 Subject: netfilter: nf_nat: no IP_NAT_RANGE_MAP_IPS flags when alloc_null_binding() When alloc_null_binding(), no IP_NAT_RNAGE_MAP_IPS in flags means no IP address translation is needed. It isn't necessary to specify the address explicitly. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index ebbd319..21c3042 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -106,16 +106,15 @@ alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) { /* Force range to this IP; let proto decide mapping for per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). - Use reply in case it's already been mangled (eg local packet). */ - __be32 ip - = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC - ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip - : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); - struct nf_nat_range range - = { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } }; - - pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, &ip); + struct nf_nat_range range; + + range.flags = 0; + pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, + HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ? + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip : + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); + return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); } -- cgit v0.10.2 From b23909695c33f53df5f1d16696b1aa5b874c1904 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 16 Sep 2010 19:55:03 +0200 Subject: netfilter: nf_conntrack: fix the hash random initializing race nf_conntrack_alloc() isn't called with nf_conntrack_lock locked, so hash random initializing code maybe executed more than once on different CPUs. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index df3eedb..4c0ad9b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -65,8 +65,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_max); DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked); EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); -static int nf_conntrack_hash_rnd_initted; -static unsigned int nf_conntrack_hash_rnd; +static unsigned int nf_conntrack_hash_rnd __read_mostly; static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, u16 zone, unsigned int size, unsigned int rnd) @@ -574,10 +573,18 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, { struct nf_conn *ct; - if (unlikely(!nf_conntrack_hash_rnd_initted)) { - get_random_bytes(&nf_conntrack_hash_rnd, - sizeof(nf_conntrack_hash_rnd)); - nf_conntrack_hash_rnd_initted = 1; + if (unlikely(!nf_conntrack_hash_rnd)) { + unsigned int rand; + + /* + * Why not initialize nf_conntrack_rnd in a "init()" function ? + * Because there isn't enough entropy when system initializing, + * and we initialize it as late as possible. + */ + do { + get_random_bytes(&rand, sizeof(rand)); + } while (!rand); + cmpxchg(&nf_conntrack_hash_rnd, 0, rand); } /* We don't want any race condition at early drop stage */ -- cgit v0.10.2 From 3575792e005dc9994f15ae72c1c6f401d134177d Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 17 Sep 2010 14:18:16 +0200 Subject: ipvs: extend connection flags to 32 bits - the sync protocol supports 16 bits only, so bits 0..15 should be used only for flags that should go to backup server, bits 16 and above should be allocated for flags not sent to backup. - use IP_VS_CONN_F_DEST_MASK as mask of connection flags in destination that can be changed by user space - allow IP_VS_CONN_F_ONE_PACKET to be set in destination Signed-off-by: Julian Anastasov Signed-off-by: Patrick McHardy diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 9708de2..003d75f 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -70,6 +70,7 @@ /* * IPVS Connection Flags + * Only flags 0..15 are sent to backup server */ #define IP_VS_CONN_F_FWD_MASK 0x0007 /* mask for the fwd methods */ #define IP_VS_CONN_F_MASQ 0x0000 /* masquerading/NAT */ @@ -88,6 +89,13 @@ #define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */ #define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */ +/* Flags that are not sent to backup server start from bit 16 */ + +/* Connection flags from destination that can be changed by user space */ +#define IP_VS_CONN_F_DEST_MASK (IP_VS_CONN_F_FWD_MASK | \ + IP_VS_CONN_F_ONE_PACKET | \ + 0) + #define IP_VS_SCHEDNAME_MAXLEN 16 #define IP_VS_IFNAME_MAXLEN 16 diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f976885..62698a9 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -366,6 +366,7 @@ struct ip_vs_conn { union nf_inet_addr caddr; /* client address */ union nf_inet_addr vaddr; /* virtual address */ union nf_inet_addr daddr; /* destination address */ + volatile __u32 flags; /* status flags */ __be16 cport; __be16 vport; __be16 dport; @@ -378,7 +379,6 @@ struct ip_vs_conn { /* Flags and state transition */ spinlock_t lock; /* lock for state transition */ - volatile __u16 flags; /* status flags */ volatile __u16 state; /* state info */ volatile __u16 old_state; /* old state, to be used for * state transition triggerd diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index b71c69a..9fe1da7 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -505,6 +505,8 @@ static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest) static inline void ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) { + unsigned int conn_flags; + /* if dest is NULL, then return directly */ if (!dest) return; @@ -512,16 +514,18 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) /* Increase the refcnt counter of the dest */ atomic_inc(&dest->refcnt); + conn_flags = atomic_read(&dest->conn_flags); + if (cp->protocol != IPPROTO_UDP) + conn_flags &= ~IP_VS_CONN_F_ONE_PACKET; /* Bind with the destination and its corresponding transmitter */ - if ((cp->flags & IP_VS_CONN_F_SYNC) && - (!(cp->flags & IP_VS_CONN_F_TEMPLATE))) + if (cp->flags & IP_VS_CONN_F_SYNC) { /* if the connection is not template and is created * by sync, preserve the activity flag. */ - cp->flags |= atomic_read(&dest->conn_flags) & - (~IP_VS_CONN_F_INACTIVE); - else - cp->flags |= atomic_read(&dest->conn_flags); + if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) + conn_flags &= ~IP_VS_CONN_F_INACTIVE; + } + cp->flags |= conn_flags; cp->dest = dest; IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d " diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0c043b6..319991d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -194,7 +194,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport; /* destination port to forward */ - __be16 flags; + unsigned int flags; union nf_inet_addr snet; /* source network of the client, after masking */ @@ -382,7 +382,8 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; struct ip_vs_dest *dest; - __be16 _ports[2], *pptr, flags; + __be16 _ports[2], *pptr; + unsigned int flags; ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); @@ -473,9 +474,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) { int ret, cs; struct ip_vs_conn *cp; - __u16 flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && - iph.protocol == IPPROTO_UDP)? - IP_VS_CONN_F_ONE_PACKET : 0; + unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && + iph.protocol == IPPROTO_UDP)? + IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; ip_vs_service_put(svc); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ca8ec8c..7bd41d2 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -765,7 +765,8 @@ __ip_vs_update_dest(struct ip_vs_service *svc, /* set the weight and the flags */ atomic_set(&dest->weight, udest->weight); - conn_flags = udest->conn_flags | IP_VS_CONN_F_INACTIVE; + conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; + conn_flags |= IP_VS_CONN_F_INACTIVE; /* check if local node and update the flags */ #ifdef CONFIG_IP_VS_IPV6 @@ -782,7 +783,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, } /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ - if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != 0) { + if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { /* -- cgit v0.10.2 From f4bc17cdd205ebaa3807c2aa973719bb5ce6a5b2 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 21 Sep 2010 17:35:41 +0200 Subject: ipvs: netfilter connection tracking changes Add more code to IPVS to work with Netfilter connection tracking and fix some problems. - Allow IPVS to be compiled without connection tracking as in 2.6.35 and before. This can avoid keeping conntracks for all IPVS connections because this costs memory. ip_vs_ftp still depends on connection tracking and NAT as implemented for 2.6.36. - Add sysctl var "conntrack" to enable connection tracking for all IPVS connections. For loaded IPVS directors it needs tuning of nf_conntrack_max limit. - Add IP_VS_CONN_F_NFCT connection flag to request the connection to use connection tracking. This allows user space to provide this flag, for example, in dest->conn_flags. This can be useful to request connection tracking per real server instead of forcing it for all connections with the "conntrack" sysctl. This flag is set currently only by ip_vs_ftp and of course by "conntrack" sysctl. - Add ip_vs_nfct.c file to hold all connection tracking code, by this way main code should not depend of netfilter conntrack support. - Return back the ip_vs_post_routing handler as in 2.6.35 and use skb->ipvs_property=1 to allow IPVS to work without connection tracking Connection tracking: - most of the code is already in 2.6.36-rc - alter conntrack reply tuple for LVS-NAT connections when first packet from client is forwarded and conntrack state is NEW or RELATED. Additionally, alter reply for RELATED connections from real server, again for packet in original direction. - add IP_VS_XMIT_TUNNEL to confirm conntrack (without altering reply) for LVS-TUN early because we want to call nf_reset. It is needed because we add IPIP header and the original conntrack should be preserved, not destroyed. The transmitted IPIP packets can reuse same conntrack, so we do not set skb->ipvs_property. - try to destroy conntrack when the IPVS connection is destroyed. It is not fatal if conntrack disappears before that, it depends on the used timers. Fix problems from long time: - add skb->ip_summed = CHECKSUM_NONE for the LVS-TUN transmitters Signed-off-by: Julian Anastasov Signed-off-by: Patrick McHardy diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 003d75f..df77286 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -90,10 +90,12 @@ #define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */ /* Flags that are not sent to backup server start from bit 16 */ +#define IP_VS_CONN_F_NFCT (1 << 16) /* use netfilter conntrack */ /* Connection flags from destination that can be changed by user space */ #define IP_VS_CONN_F_DEST_MASK (IP_VS_CONN_F_FWD_MASK | \ IP_VS_CONN_F_ONE_PACKET | \ + IP_VS_CONN_F_NFCT | \ 0) #define IP_VS_SCHEDNAME_MAXLEN 16 diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 62698a9..e8ec523 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,7 +25,9 @@ #include #include /* for struct ipv6hdr */ #include /* for ipv6_addr_copy */ - +#ifdef CONFIG_IP_VS_NFCT +#include +#endif /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; @@ -798,6 +800,7 @@ extern int sysctl_ip_vs_expire_nodest_conn; extern int sysctl_ip_vs_expire_quiescent_template; extern int sysctl_ip_vs_sync_threshold[2]; extern int sysctl_ip_vs_nat_icmp_send; +extern int sysctl_ip_vs_conntrack; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; @@ -955,8 +958,47 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +#ifdef CONFIG_IP_VS_NFCT +/* + * Netfilter connection tracking + * (from ip_vs_nfct.c) + */ +static inline int ip_vs_conntrack_enabled(void) +{ + return sysctl_ip_vs_conntrack; +} + extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin); +extern int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp); +extern void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct, + struct ip_vs_conn *cp, u_int8_t proto, + const __be16 port, int from_rs); +extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp); + +#else + +static inline int ip_vs_conntrack_enabled(void) +{ + return 0; +} + +static inline void ip_vs_update_conntrack(struct sk_buff *skb, + struct ip_vs_conn *cp, int outin) +{ +} + +static inline int ip_vs_confirm_conntrack(struct sk_buff *skb, + struct ip_vs_conn *cp) +{ + return NF_ACCEPT; +} + +static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) +{ +} +/* CONFIG_IP_VS_NFCT */ +#endif #endif /* __KERNEL__ */ diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 46a77d5..af3c9f4 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -3,7 +3,7 @@ # menuconfig IP_VS tristate "IP virtual server support" - depends on NET && INET && NETFILTER && NF_CONNTRACK + depends on NET && INET && NETFILTER ---help--- IP Virtual Server support will let you build a high-performance virtual server based on cluster of two or more real servers. This @@ -235,7 +235,8 @@ comment 'IPVS application helper' config IP_VS_FTP tristate "FTP protocol helper" - depends on IP_VS_PROTO_TCP && NF_NAT + depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT + select IP_VS_NFCT ---help--- FTP is a protocol that transfers IP address and/or port number in the payload. In the virtual server via Network Address Translation, @@ -247,4 +248,12 @@ config IP_VS_FTP If you want to compile it in kernel, say Y. To compile it as a module, choose M here. If unsure, say N. +config IP_VS_NFCT + bool "Netfilter connection tracking" + depends on NF_CONNTRACK + ---help--- + The Netfilter connection tracking support allows the IPVS + connection state to be exported to the Netfilter framework + for filtering purposes. + endif # IP_VS diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index e3baefd..349fe88 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -9,10 +9,13 @@ ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_UDP) += ip_vs_proto_udp.o ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_AH_ESP) += ip_vs_proto_ah_esp.o ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_SCTP) += ip_vs_proto_sctp.o +ip_vs-extra_objs-y := +ip_vs-extra_objs-$(CONFIG_IP_VS_NFCT) += ip_vs_nfct.o + ip_vs-objs := ip_vs_conn.o ip_vs_core.o ip_vs_ctl.o ip_vs_sched.o \ ip_vs_xmit.o ip_vs_app.o ip_vs_sync.o \ ip_vs_est.o ip_vs_proto.o \ - $(ip_vs_proto-objs-y) + $(ip_vs_proto-objs-y) $(ip_vs-extra_objs-y) # IPVS core diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 9fe1da7..a970d96 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -721,6 +721,9 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->control) ip_vs_control_del(cp); + if (cp->flags & IP_VS_CONN_F_NFCT) + ip_vs_conn_drop_conntrack(cp); + if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); @@ -816,6 +819,16 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, if (unlikely(pp && atomic_read(&pp->appcnt))) ip_vs_bind_app(cp, pp); + /* + * Allow conntrack to be preserved. By default, conntrack + * is created and destroyed for every packet. + * Sometimes keeping conntrack can be useful for + * IP_VS_CONN_F_ONE_PACKET too. + */ + + if (ip_vs_conntrack_enabled()) + cp->flags |= IP_VS_CONN_F_NFCT; + /* Hash it in the ip_vs_conn_tab finally */ ip_vs_conn_hash(cp); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 319991d..7fbc80d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -537,6 +537,23 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, return NF_DROP; } +/* + * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING + * chain and is used to avoid double NAT and confirmation when we do + * not want to keep the conntrack structure + */ +static unsigned int ip_vs_post_routing(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (!skb->ipvs_property) + return NF_ACCEPT; + /* The packet was sent from IPVS, exit this chain */ + return NF_STOP; +} + __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); @@ -695,7 +712,10 @@ static int handle_response_icmp(int af, struct sk_buff *skb, /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); - skb->ipvs_property = 1; + if (!(cp->flags & IP_VS_CONN_F_NFCT)) + skb->ipvs_property = 1; + else + ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; out: @@ -928,17 +948,19 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); - ip_vs_update_conntrack(skb, cp, 0); + if (!(cp->flags & IP_VS_CONN_F_NFCT)) + skb->ipvs_property = 1; + else + ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); - skb->ipvs_property = 1; - LeaveFunction(11); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); + LeaveFunction(11); return NF_STOLEN; } @@ -1483,6 +1505,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_FORWARD, .priority = 99, }, + /* Before the netfilter connection tracking, exit from POST_ROUTING */ + { + .hook = ip_vs_post_routing, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC-1, + }, #ifdef CONFIG_IP_VS_IPV6 /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1511,6 +1541,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_FORWARD, .priority = 99, }, + /* Before the netfilter connection tracking, exit from POST_ROUTING */ + { + .hook = ip_vs_post_routing, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC-1, + }, #endif }; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7bd41d2..d2d842f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -88,6 +88,9 @@ int sysctl_ip_vs_expire_nodest_conn = 0; int sysctl_ip_vs_expire_quiescent_template = 0; int sysctl_ip_vs_sync_threshold[2] = { 3, 50 }; int sysctl_ip_vs_nat_icmp_send = 0; +#ifdef CONFIG_IP_VS_NFCT +int sysctl_ip_vs_conntrack; +#endif #ifdef CONFIG_IP_VS_DEBUG @@ -1580,6 +1583,15 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_do_defense_mode, }, +#ifdef CONFIG_IP_VS_NFCT + { + .procname = "conntrack", + .data = &sysctl_ip_vs_conntrack, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif { .procname = "secure_tcp", .data = &sysctl_ip_vs_secure_tcp, diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 7e9af5b..9cd375f 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -20,17 +20,6 @@ * * Author: Wouter Gadeyne * - * - * Code for ip_vs_expect_related and ip_vs_expect_callback is taken from - * http://www.ssi.bg/~ja/nfct/: - * - * ip_vs_nfct.c: Netfilter connection tracking support for IPVS - * - * Portions Copyright (C) 2001-2002 - * Antefacto Ltd, 181 Parnell St, Dublin 1, Ireland. - * - * Portions Copyright (C) 2003-2008 - * Julian Anastasov */ #define KMSG_COMPONENT "IPVS" @@ -58,16 +47,6 @@ #define SERVER_STRING "227 Entering Passive Mode (" #define CLIENT_STRING "PORT " -#define FMT_TUPLE "%pI4:%u->%pI4:%u/%u" -#define ARG_TUPLE(T) &(T)->src.u3.ip, ntohs((T)->src.u.all), \ - &(T)->dst.u3.ip, ntohs((T)->dst.u.all), \ - (T)->dst.protonum - -#define FMT_CONN "%pI4:%u->%pI4:%u->%pI4:%u/%u:%u" -#define ARG_CONN(C) &((C)->caddr.ip), ntohs((C)->cport), \ - &((C)->vaddr.ip), ntohs((C)->vport), \ - &((C)->daddr.ip), ntohs((C)->dport), \ - (C)->protocol, (C)->state /* * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper @@ -85,6 +64,8 @@ static int ip_vs_ftp_pasv; static int ip_vs_ftp_init_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) { + /* We use connection tracking for the command connection */ + cp->flags |= IP_VS_CONN_F_NFCT; return 0; } @@ -149,120 +130,6 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, } /* - * Called from init_conntrack() as expectfn handler. - */ -static void -ip_vs_expect_callback(struct nf_conn *ct, - struct nf_conntrack_expect *exp) -{ - struct nf_conntrack_tuple *orig, new_reply; - struct ip_vs_conn *cp; - - if (exp->tuple.src.l3num != PF_INET) - return; - - /* - * We assume that no NF locks are held before this callback. - * ip_vs_conn_out_get and ip_vs_conn_in_get should match their - * expectations even if they use wildcard values, now we provide the - * actual values from the newly created original conntrack direction. - * The conntrack is confirmed when packet reaches IPVS hooks. - */ - - /* RS->CLIENT */ - orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum, - &orig->src.u3, orig->src.u.tcp.port, - &orig->dst.u3, orig->dst.u.tcp.port); - if (cp) { - /* Change reply CLIENT->RS to CLIENT->VS */ - new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", " - FMT_TUPLE ", found inout cp=" FMT_CONN "\n", - __func__, ct, ct->status, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); - new_reply.dst.u3 = cp->vaddr; - new_reply.dst.u.tcp.port = cp->vport; - IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE - ", inout cp=" FMT_CONN "\n", - __func__, ct, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); - goto alter; - } - - /* CLIENT->VS */ - cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum, - &orig->src.u3, orig->src.u.tcp.port, - &orig->dst.u3, orig->dst.u.tcp.port); - if (cp) { - /* Change reply VS->CLIENT to RS->CLIENT */ - new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", " - FMT_TUPLE ", found outin cp=" FMT_CONN "\n", - __func__, ct, ct->status, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); - new_reply.src.u3 = cp->daddr; - new_reply.src.u.tcp.port = cp->dport; - IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", " - FMT_TUPLE ", outin cp=" FMT_CONN "\n", - __func__, ct, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); - goto alter; - } - - IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuple=" FMT_TUPLE - " - unknown expect\n", - __func__, ct, ct->status, ARG_TUPLE(orig)); - return; - -alter: - /* Never alter conntrack for non-NAT conns */ - if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ) - nf_conntrack_alter_reply(ct, &new_reply); - ip_vs_conn_put(cp); - return; -} - -/* - * Create NF conntrack expectation with wildcard (optional) source port. - * Then the default callback function will alter the reply and will confirm - * the conntrack entry when the first packet comes. - */ -static void -ip_vs_expect_related(struct sk_buff *skb, struct nf_conn *ct, - struct ip_vs_conn *cp, u_int8_t proto, - const __be16 *port, int from_rs) -{ - struct nf_conntrack_expect *exp; - - BUG_ON(!ct || ct == &nf_conntrack_untracked); - - exp = nf_ct_expect_alloc(ct); - if (!exp) - return; - - if (from_rs) - nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, - nf_ct_l3num(ct), &cp->daddr, &cp->caddr, - proto, port, &cp->cport); - else - nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, - nf_ct_l3num(ct), &cp->caddr, &cp->vaddr, - proto, port, &cp->vport); - - exp->expectfn = ip_vs_expect_callback; - - IP_VS_DBG(7, "%s(): ct=%p, expect tuple=" FMT_TUPLE "\n", - __func__, ct, ARG_TUPLE(&exp->tuple)); - nf_ct_expect_related(exp); - nf_ct_expect_put(exp); -} - -/* * Look at outgoing ftp packets to catch the response to a PASV command * from the server (inside-to-outside). * When we see one, we build a connection entry with the client address, @@ -335,7 +202,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, &cp->caddr, 0, &cp->vaddr, port, &from, port, - IP_VS_CONN_F_NO_CPORT, + IP_VS_CONN_F_NO_CPORT | + IP_VS_CONN_F_NFCT, cp->dest); if (!n_cp) return 0; @@ -371,8 +239,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, start-data, end-start, buf, buf_len); if (ret) - ip_vs_expect_related(skb, ct, n_cp, - IPPROTO_TCP, NULL, 0); + ip_vs_nfct_expect_related(skb, ct, n_cp, + IPPROTO_TCP, 0, 0); } /* @@ -487,7 +355,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &cp->daddr, htons(ntohs(cp->dport)-1), - 0, + IP_VS_CONN_F_NFCT, cp->dest); if (!n_cp) return 0; diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c new file mode 100644 index 0000000..c038458 --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -0,0 +1,292 @@ +/* + * ip_vs_nfct.c: Netfilter connection tracking support for IPVS + * + * Portions Copyright (C) 2001-2002 + * Antefacto Ltd, 181 Parnell St, Dublin 1, Ireland. + * + * Portions Copyright (C) 2003-2010 + * Julian Anastasov + * + * + * This code is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * + * Authors: + * Ben North + * Julian Anastasov Reorganize and sync with latest kernels + * Hannes Eder Extend NFCT support for FTP, ipvs match + * + * + * Current status: + * + * - provide conntrack confirmation for new and related connections, by + * this way we can see their proper conntrack state in all hooks + * - support for all forwarding methods, not only NAT + * - FTP support (NAT), ability to support other NAT apps with expectations + * - to correctly create expectations for related NAT connections the proper + * NF conntrack support must be already installed, eg. ip_vs_ftp requires + * nf_conntrack_ftp ... iptables_nat for the same ports (but no iptables + * NAT rules are needed) + * - alter reply for NAT when forwarding packet in original direction: + * conntrack from client in NEW or RELATED (Passive FTP DATA) state or + * when RELATED conntrack is created from real server (Active FTP DATA) + * - if iptables_nat is not loaded the Passive FTP will not work (the + * PASV response can not be NAT-ed) but Active FTP should work + * + */ + +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +#define FMT_TUPLE "%pI4:%u->%pI4:%u/%u" +#define ARG_TUPLE(T) &(T)->src.u3.ip, ntohs((T)->src.u.all), \ + &(T)->dst.u3.ip, ntohs((T)->dst.u.all), \ + (T)->dst.protonum + +#define FMT_CONN "%pI4:%u->%pI4:%u->%pI4:%u/%u:%u" +#define ARG_CONN(C) &((C)->caddr.ip), ntohs((C)->cport), \ + &((C)->vaddr.ip), ntohs((C)->vport), \ + &((C)->daddr.ip), ntohs((C)->dport), \ + (C)->protocol, (C)->state + +void +ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conntrack_tuple new_tuple; + + if (ct == NULL || nf_ct_is_confirmed(ct) || nf_ct_is_untracked(ct) || + nf_ct_is_dying(ct)) + return; + + /* Never alter conntrack for non-NAT conns */ + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) + return; + + /* Alter reply only in original direction */ + if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) + return; + + /* + * The connection is not yet in the hashtable, so we update it. + * CIP->VIP will remain the same, so leave the tuple in + * IP_CT_DIR_ORIGINAL untouched. When the reply comes back from the + * real-server we will see RIP->DIP. + */ + new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; + /* + * This will also take care of UDP and other protocols. + */ + if (outin) { + new_tuple.src.u3 = cp->daddr; + if (new_tuple.dst.protonum != IPPROTO_ICMP && + new_tuple.dst.protonum != IPPROTO_ICMPV6) + new_tuple.src.u.tcp.port = cp->dport; + } else { + new_tuple.dst.u3 = cp->vaddr; + if (new_tuple.dst.protonum != IPPROTO_ICMP && + new_tuple.dst.protonum != IPPROTO_ICMPV6) + new_tuple.dst.u.tcp.port = cp->vport; + } + IP_VS_DBG(7, "%s: Updating conntrack ct=%p, status=0x%lX, " + "ctinfo=%d, old reply=" FMT_TUPLE + ", new reply=" FMT_TUPLE ", cp=" FMT_CONN "\n", + __func__, ct, ct->status, ctinfo, + ARG_TUPLE(&ct->tuplehash[IP_CT_DIR_REPLY].tuple), + ARG_TUPLE(&new_tuple), ARG_CONN(cp)); + nf_conntrack_alter_reply(ct, &new_tuple); +} + +int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) +{ + return nf_conntrack_confirm(skb); +} + +/* + * Called from init_conntrack() as expectfn handler. + */ +static void ip_vs_nfct_expect_callback(struct nf_conn *ct, + struct nf_conntrack_expect *exp) +{ + struct nf_conntrack_tuple *orig, new_reply; + struct ip_vs_conn *cp; + + if (exp->tuple.src.l3num != PF_INET) + return; + + /* + * We assume that no NF locks are held before this callback. + * ip_vs_conn_out_get and ip_vs_conn_in_get should match their + * expectations even if they use wildcard values, now we provide the + * actual values from the newly created original conntrack direction. + * The conntrack is confirmed when packet reaches IPVS hooks. + */ + + /* RS->CLIENT */ + orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum, + &orig->src.u3, orig->src.u.tcp.port, + &orig->dst.u3, orig->dst.u.tcp.port); + if (cp) { + /* Change reply CLIENT->RS to CLIENT->VS */ + new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; + IP_VS_DBG(7, "%s: ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", " + FMT_TUPLE ", found inout cp=" FMT_CONN "\n", + __func__, ct, ct->status, + ARG_TUPLE(orig), ARG_TUPLE(&new_reply), + ARG_CONN(cp)); + new_reply.dst.u3 = cp->vaddr; + new_reply.dst.u.tcp.port = cp->vport; + IP_VS_DBG(7, "%s: ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE + ", inout cp=" FMT_CONN "\n", + __func__, ct, + ARG_TUPLE(orig), ARG_TUPLE(&new_reply), + ARG_CONN(cp)); + goto alter; + } + + /* CLIENT->VS */ + cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum, + &orig->src.u3, orig->src.u.tcp.port, + &orig->dst.u3, orig->dst.u.tcp.port); + if (cp) { + /* Change reply VS->CLIENT to RS->CLIENT */ + new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; + IP_VS_DBG(7, "%s: ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", " + FMT_TUPLE ", found outin cp=" FMT_CONN "\n", + __func__, ct, ct->status, + ARG_TUPLE(orig), ARG_TUPLE(&new_reply), + ARG_CONN(cp)); + new_reply.src.u3 = cp->daddr; + new_reply.src.u.tcp.port = cp->dport; + IP_VS_DBG(7, "%s: ct=%p, new tuples=" FMT_TUPLE ", " + FMT_TUPLE ", outin cp=" FMT_CONN "\n", + __func__, ct, + ARG_TUPLE(orig), ARG_TUPLE(&new_reply), + ARG_CONN(cp)); + goto alter; + } + + IP_VS_DBG(7, "%s: ct=%p, status=0x%lX, tuple=" FMT_TUPLE + " - unknown expect\n", + __func__, ct, ct->status, ARG_TUPLE(orig)); + return; + +alter: + /* Never alter conntrack for non-NAT conns */ + if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ) + nf_conntrack_alter_reply(ct, &new_reply); + ip_vs_conn_put(cp); + return; +} + +/* + * Create NF conntrack expectation with wildcard (optional) source port. + * Then the default callback function will alter the reply and will confirm + * the conntrack entry when the first packet comes. + * Use port 0 to expect connection from any port. + */ +void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct, + struct ip_vs_conn *cp, u_int8_t proto, + const __be16 port, int from_rs) +{ + struct nf_conntrack_expect *exp; + + if (ct == NULL || nf_ct_is_untracked(ct)) + return; + + exp = nf_ct_expect_alloc(ct); + if (!exp) + return; + + nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), + from_rs ? &cp->daddr : &cp->caddr, + from_rs ? &cp->caddr : &cp->vaddr, + proto, port ? &port : NULL, + from_rs ? &cp->cport : &cp->vport); + + exp->expectfn = ip_vs_nfct_expect_callback; + + IP_VS_DBG(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&exp->tuple)); + nf_ct_expect_related(exp); + nf_ct_expect_put(exp); +} +EXPORT_SYMBOL(ip_vs_nfct_expect_related); + +/* + * Our connection was terminated, try to drop the conntrack immediately + */ +void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) +{ + struct nf_conntrack_tuple_hash *h; + struct nf_conn *ct; + struct nf_conntrack_tuple tuple; + + if (!cp->cport) + return; + + tuple = (struct nf_conntrack_tuple) { + .dst = { .protonum = cp->protocol, .dir = IP_CT_DIR_ORIGINAL } }; + tuple.src.u3 = cp->caddr; + tuple.src.u.all = cp->cport; + tuple.src.l3num = cp->af; + tuple.dst.u3 = cp->vaddr; + tuple.dst.u.all = cp->vport; + + IP_VS_DBG(7, "%s: dropping conntrack with tuple=" FMT_TUPLE + " for conn " FMT_CONN "\n", + __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); + + h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple); + if (h) { + ct = nf_ct_tuplehash_to_ctrack(h); + /* Show what happens instead of calling nf_ct_kill() */ + if (del_timer(&ct->timeout)) { + IP_VS_DBG(7, "%s: ct=%p, deleted conntrack timer for tuple=" + FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&tuple)); + if (ct->timeout.function) + ct->timeout.function(ct->timeout.data); + } else { + IP_VS_DBG(7, "%s: ct=%p, no conntrack timer for tuple=" + FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&tuple)); + } + nf_ct_put(ct); + } else { + IP_VS_DBG(7, "%s: no conntrack for tuple=" FMT_TUPLE "\n", + __func__, ARG_TUPLE(&tuple)); + } +} + diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 49df6be..8817afa 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include @@ -194,12 +193,37 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) dst_release(old_dst); } -#define IP_VS_XMIT(pf, skb, rt) \ +#define IP_VS_XMIT_TUNNEL(skb, cp) \ +({ \ + int __ret = NF_ACCEPT; \ + \ + if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \ + __ret = ip_vs_confirm_conntrack(skb, cp); \ + if (__ret == NF_ACCEPT) { \ + nf_reset(skb); \ + (skb)->ip_summed = CHECKSUM_NONE; \ + } \ + __ret; \ +}) + +#define IP_VS_XMIT_NAT(pf, skb, cp) \ do { \ - (skb)->ipvs_property = 1; \ + if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ + (skb)->ipvs_property = 1; \ + else \ + ip_vs_update_conntrack(skb, cp, 1); \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ - (rt)->dst.dev, dst_output); \ + skb_dst(skb)->dev, dst_output); \ +} while (0) + +#define IP_VS_XMIT(pf, skb, cp) \ +do { \ + if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ + (skb)->ipvs_property = 1; \ + skb_forward_csum(skb); \ + NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ + skb_dst(skb)->dev, dst_output); \ } while (0) @@ -271,7 +295,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, rt); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp); LeaveFunction(10); return NF_STOLEN; @@ -335,7 +359,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, rt); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp); LeaveFunction(10); return NF_STOLEN; @@ -349,36 +373,6 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } #endif -void -ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) -{ - struct nf_conn *ct = (struct nf_conn *)skb->nfct; - struct nf_conntrack_tuple new_tuple; - - if (ct == NULL || nf_ct_is_untracked(ct) || nf_ct_is_confirmed(ct)) - return; - - /* - * The connection is not yet in the hashtable, so we update it. - * CIP->VIP will remain the same, so leave the tuple in - * IP_CT_DIR_ORIGINAL untouched. When the reply comes back from the - * real-server we will see RIP->DIP. - */ - new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - if (outin) - new_tuple.src.u3 = cp->daddr; - else - new_tuple.dst.u3 = cp->vaddr; - /* - * This will also take care of UDP and other protocols. - */ - if (outin) - new_tuple.src.u.tcp.port = cp->dport; - else - new_tuple.dst.u.tcp.port = cp->vport; - nf_conntrack_alter_reply(ct, &new_tuple); -} - /* * NAT transmitter (only for outside-to-inside nat forwarding) * Not used for related ICMP @@ -434,8 +428,6 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp, 1); - /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still MTU problem. */ @@ -443,7 +435,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, rt); + IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp); LeaveFunction(10); return NF_STOLEN; @@ -451,8 +443,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, tx_error_icmp: dst_link_failure(skb); tx_error: - LeaveFunction(10); kfree_skb(skb); + LeaveFunction(10); return NF_STOLEN; tx_error_put: ip_rt_put(rt); @@ -512,8 +504,6 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp, 1); - /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still MTU problem. */ @@ -521,7 +511,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, rt); + IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp); LeaveFunction(10); return NF_STOLEN; @@ -571,6 +561,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; + int ret; EnterFunction(10); @@ -655,7 +646,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - ip_local_out(skb); + ret = IP_VS_XMIT_TUNNEL(skb, cp); + if (ret == NF_ACCEPT) + ip_local_out(skb); + else if (ret == NF_DROP) + kfree_skb(skb); LeaveFunction(10); @@ -681,6 +676,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ipv6hdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; + int ret; EnterFunction(10); @@ -761,7 +757,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - ip6_local_out(skb); + ret = IP_VS_XMIT_TUNNEL(skb, cp); + if (ret == NF_ACCEPT) + ip6_local_out(skb); + else if (ret == NF_DROP) + kfree_skb(skb); LeaveFunction(10); @@ -820,7 +820,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, rt); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp); LeaveFunction(10); return NF_STOLEN; @@ -873,7 +873,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, rt); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp); LeaveFunction(10); return NF_STOLEN; @@ -947,7 +947,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, rt); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp); rc = NF_STOLEN; goto out; @@ -1022,7 +1022,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, rt); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp); rc = NF_STOLEN; goto out; -- cgit v0.10.2 From 8a8030407f55a6aaedb51167c1a2383311fcd707 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 21 Sep 2010 17:38:57 +0200 Subject: ipvs: make rerouting optional with snat_reroute Add new sysctl flag "snat_reroute". Recent kernels use ip_route_me_harder() to route LVS-NAT responses properly by VIP when there are multiple paths to client. But setups that do not have alternative default routes can skip this routing lookup by using snat_reroute=0. Signed-off-by: Julian Anastasov Signed-off-by: Patrick McHardy diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e8ec523..3915a4f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -801,6 +801,7 @@ extern int sysctl_ip_vs_expire_quiescent_template; extern int sysctl_ip_vs_sync_threshold[2]; extern int sysctl_ip_vs_nat_icmp_send; extern int sysctl_ip_vs_conntrack; +extern int sysctl_ip_vs_snat_reroute; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 7fbc80d..06c388b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -929,20 +929,31 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_send_check(ip_hdr(skb)); } + /* + * nf_iterate does not expect change in the skb->dst->dev. + * It looks like it is not fatal to enable this code for hooks + * where our handlers are at the end of the chain list and + * when all next handlers use skb->dst->dev and not outdev. + * It will definitely route properly the inout NAT traffic + * when multiple paths are used. + */ + /* For policy routing, packets originating from this * machine itself may be routed differently to packets * passing through. We want this packet to be routed as * if it came from this machine itself. So re-compute * the routing information. */ + if (sysctl_ip_vs_snat_reroute) { #ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (ip6_route_me_harder(skb) != 0) - goto drop; - } else + if (af == AF_INET6) { + if (ip6_route_me_harder(skb) != 0) + goto drop; + } else #endif - if (ip_route_me_harder(skb, RTN_LOCAL) != 0) - goto drop; + if (ip_route_me_harder(skb, RTN_LOCAL) != 0) + goto drop; + } IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT"); @@ -991,8 +1002,13 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related, verdict = ip_vs_out_icmp_v6(skb, &related); - if (related) + if (related) { + if (sysctl_ip_vs_snat_reroute && + NF_ACCEPT == verdict && + ip6_route_me_harder(skb)) + verdict = NF_DROP; return verdict; + } ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } } else @@ -1000,8 +1016,13 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related, verdict = ip_vs_out_icmp(skb, &related); - if (related) + if (related) { + if (sysctl_ip_vs_snat_reroute && + NF_ACCEPT == verdict && + ip_route_me_harder(skb, RTN_LOCAL)) + verdict = NF_DROP; return verdict; + } ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index d2d842f..e637cd0 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -91,6 +91,7 @@ int sysctl_ip_vs_nat_icmp_send = 0; #ifdef CONFIG_IP_VS_NFCT int sysctl_ip_vs_conntrack; #endif +int sysctl_ip_vs_snat_reroute = 1; #ifdef CONFIG_IP_VS_DEBUG @@ -1599,6 +1600,13 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_do_defense_mode, }, + { + .procname = "snat_reroute", + .data = &sysctl_ip_vs_snat_reroute, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, #if 0 { .procname = "timeout_established", -- cgit v0.10.2 From 99f07e91bef34db0fc8b1a224096e97f02dc0d56 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 21 Sep 2010 17:49:20 +0200 Subject: netfilter: save the hash of the tuple in the original direction for latter use Since we don't change the tuple in the original direction, we can save it in ct->tuplehash[IP_CT_DIR_REPLY].hnode.pprev for __nf_conntrack_confirm() use. __hash_conntrack() is split into two steps: hash_conntrack_raw() is used to get the raw hash, and __hash_bucket() is used to get the bucket id. In SYN-flood case, early_drop() doesn't need to recompute the hash again. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 4c0ad9b..1eacf8d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -67,29 +67,40 @@ EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); static unsigned int nf_conntrack_hash_rnd __read_mostly; -static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, - u16 zone, unsigned int size, unsigned int rnd) +static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone) { unsigned int n; - u_int32_t h; /* The direction must be ignored, so we hash everything up to the * destination ports (which is a multiple of 4) and treat the last * three bytes manually. */ n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32); - h = jhash2((u32 *)tuple, n, - zone ^ rnd ^ (((__force __u16)tuple->dst.u.all << 16) | - tuple->dst.protonum)); + return jhash2((u32 *)tuple, n, zone ^ nf_conntrack_hash_rnd ^ + (((__force __u16)tuple->dst.u.all << 16) | + tuple->dst.protonum)); +} + +static u32 __hash_bucket(u32 hash, unsigned int size) +{ + return ((u64)hash * size) >> 32; +} + +static u32 hash_bucket(u32 hash, const struct net *net) +{ + return __hash_bucket(hash, net->ct.htable_size); +} - return ((u64)h * size) >> 32; +static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, + u16 zone, unsigned int size) +{ + return __hash_bucket(hash_conntrack_raw(tuple, zone), size); } static inline u_int32_t hash_conntrack(const struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { - return __hash_conntrack(tuple, zone, net->ct.htable_size, - nf_conntrack_hash_rnd); + return __hash_conntrack(tuple, zone, net->ct.htable_size); } bool @@ -291,20 +302,20 @@ static void death_by_timeout(unsigned long ul_conntrack) * OR * - Caller must lock nf_conntrack_lock before calling this function */ -struct nf_conntrack_tuple_hash * -__nf_conntrack_find(struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple) +static struct nf_conntrack_tuple_hash * +____nf_conntrack_find(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple, u32 hash) { struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(net, zone, tuple); + unsigned int bucket = hash_bucket(hash, net); /* Disable BHs the entire time since we normally need to disable them * at least once for the stats anyway. */ local_bh_disable(); begin: - hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { + hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) { if (nf_ct_tuple_equal(tuple, &h->tuple) && nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) { NF_CT_STAT_INC(net, found); @@ -318,7 +329,7 @@ begin: * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ - if (get_nulls_value(n) != hash) { + if (get_nulls_value(n) != bucket) { NF_CT_STAT_INC(net, search_restart); goto begin; } @@ -326,19 +337,27 @@ begin: return NULL; } + +struct nf_conntrack_tuple_hash * +__nf_conntrack_find(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) +{ + return ____nf_conntrack_find(net, zone, tuple, + hash_conntrack_raw(tuple, zone)); +} EXPORT_SYMBOL_GPL(__nf_conntrack_find); /* Find a connection corresponding to a tuple. */ -struct nf_conntrack_tuple_hash * -nf_conntrack_find_get(struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple) +static struct nf_conntrack_tuple_hash * +__nf_conntrack_find_get(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple, u32 hash) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; rcu_read_lock(); begin: - h = __nf_conntrack_find(net, zone, tuple); + h = ____nf_conntrack_find(net, zone, tuple, hash); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); if (unlikely(nf_ct_is_dying(ct) || @@ -356,6 +375,14 @@ begin: return h; } + +struct nf_conntrack_tuple_hash * +nf_conntrack_find_get(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) +{ + return __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, zone)); +} EXPORT_SYMBOL_GPL(nf_conntrack_find_get); static void __nf_conntrack_hash_insert(struct nf_conn *ct, @@ -408,8 +435,11 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + /* reuse the hash saved before */ + hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; + hash = hash_bucket(hash, net); + repl_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); /* We're not in hash table, and we refuse to set up related connections for unconfirmed conns. But packet copies and @@ -566,10 +596,11 @@ static noinline int early_drop(struct net *net, unsigned int hash) return dropped; } -struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, - const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_tuple *repl, - gfp_t gfp) +static struct nf_conn * +__nf_conntrack_alloc(struct net *net, u16 zone, + const struct nf_conntrack_tuple *orig, + const struct nf_conntrack_tuple *repl, + gfp_t gfp, u32 hash) { struct nf_conn *ct; @@ -585,6 +616,9 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, get_random_bytes(&rand, sizeof(rand)); } while (!rand); cmpxchg(&nf_conntrack_hash_rnd, 0, rand); + + /* recompute the hash as nf_conntrack_hash_rnd is initialized */ + hash = hash_conntrack_raw(orig, zone); } /* We don't want any race condition at early drop stage */ @@ -592,8 +626,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { - unsigned int hash = hash_conntrack(net, zone, orig); - if (!early_drop(net, hash)) { + if (!early_drop(net, hash_bucket(hash, net))) { atomic_dec(&net->ct.count); if (net_ratelimit()) printk(KERN_WARNING @@ -623,7 +656,8 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl; - ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL; + /* save hash for reusing when confirming */ + *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; /* Don't set timer yet: wait for confirmation */ setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct); write_pnet(&ct->ct_net, net); @@ -650,6 +684,14 @@ out_free: return ERR_PTR(-ENOMEM); #endif } + +struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, + const struct nf_conntrack_tuple *orig, + const struct nf_conntrack_tuple *repl, + gfp_t gfp) +{ + return __nf_conntrack_alloc(net, zone, orig, repl, gfp, 0); +} EXPORT_SYMBOL_GPL(nf_conntrack_alloc); void nf_conntrack_free(struct nf_conn *ct) @@ -671,7 +713,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, u32 hash) { struct nf_conn *ct; struct nf_conn_help *help; @@ -685,7 +727,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, return NULL; } - ct = nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC); + ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC, + hash); if (IS_ERR(ct)) { pr_debug("Can't allocate conntrack.\n"); return (struct nf_conntrack_tuple_hash *)ct; @@ -762,6 +805,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; + u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, protonum, &tuple, l3proto, @@ -771,10 +815,11 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, } /* look for tuple match */ - h = nf_conntrack_find_get(net, zone, &tuple); + hash = hash_conntrack_raw(&tuple, zone); + h = __nf_conntrack_find_get(net, zone, &tuple, hash); if (!h) { h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, - skb, dataoff); + skb, dataoff, hash); if (!h) return NULL; if (IS_ERR(h)) @@ -1314,8 +1359,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); bucket = __hash_conntrack(&h->tuple, nf_ct_zone(ct), - hashsize, - nf_conntrack_hash_rnd); + hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } -- cgit v0.10.2 From 26c15cfd291f8b4ee40b4bbdf5e3772adfd704f5 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 21 Sep 2010 18:12:30 +0200 Subject: ipvs: changes related to service usecnt Change the usage of svc usecnt during command execution: - we check if svc is registered but we do not need to hold usecnt reference while under __ip_vs_mutex, only the packet handling needs it during scheduling - change __ip_vs_service_get to __ip_vs_service_find and __ip_vs_svc_fwm_get to __ip_vs_svc_fwm_find because now caller will increase svc->usecnt - put common code that calls update_service in __ip_vs_update_dest - put common code in ip_vs_unlink_service() and use it to unregister the service - add comment that svc should not be accessed after ip_vs_del_service anymore - all IP_VS_WAIT_WHILE calls are now unified: usecnt > 0 - Properly log the app ports As result, some problems are fixed: - possible use-after-free of svc in ip_vs_genl_set_cmd after ip_vs_del_service because our usecnt reference does not guarantee that svc is not freed on refcnt==0, eg. when no dests are moved to trash - possible usecnt leak in do_ip_vs_set_ctl after ip_vs_del_service when the service is not freed now, for example, when some destionations are moved into trash and svc->refcnt remains above 0. It is harmless because svc is not in hash anymore. Signed-off-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Patrick McHardy diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index e76f87f..a475ede 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -103,8 +103,8 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) goto out; list_add(&inc->a_list, &app->incs_list); - IP_VS_DBG(9, "%s application %s:%u registered\n", - pp->name, inc->name, inc->port); + IP_VS_DBG(9, "%s App %s:%u registered\n", + pp->name, inc->name, ntohs(inc->port)); return 0; @@ -130,7 +130,7 @@ ip_vs_app_inc_release(struct ip_vs_app *inc) pp->unregister_app(inc); IP_VS_DBG(9, "%s App %s:%u unregistered\n", - pp->name, inc->name, inc->port); + pp->name, inc->name, ntohs(inc->port)); list_del(&inc->a_list); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e637cd0..e4ec8f3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -405,7 +405,7 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) * Get service by {proto,addr,port} in the service table. */ static inline struct ip_vs_service * -__ip_vs_service_get(int af, __u16 protocol, const union nf_inet_addr *vaddr, +__ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { unsigned hash; @@ -420,7 +420,6 @@ __ip_vs_service_get(int af, __u16 protocol, const union nf_inet_addr *vaddr, && (svc->port == vport) && (svc->protocol == protocol)) { /* HIT */ - atomic_inc(&svc->usecnt); return svc; } } @@ -433,7 +432,7 @@ __ip_vs_service_get(int af, __u16 protocol, const union nf_inet_addr *vaddr, * Get service by {fwmark} in the service table. */ static inline struct ip_vs_service * -__ip_vs_svc_fwm_get(int af, __u32 fwmark) +__ip_vs_svc_fwm_find(int af, __u32 fwmark) { unsigned hash; struct ip_vs_service *svc; @@ -444,7 +443,6 @@ __ip_vs_svc_fwm_get(int af, __u32 fwmark) list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) { if (svc->fwmark == fwmark && svc->af == af) { /* HIT */ - atomic_inc(&svc->usecnt); return svc; } } @@ -463,14 +461,14 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, /* * Check the table hashed by fwmark first */ - if (fwmark && (svc = __ip_vs_svc_fwm_get(af, fwmark))) + if (fwmark && (svc = __ip_vs_svc_fwm_find(af, fwmark))) goto out; /* * Check the table hashed by * for "full" addressed entries */ - svc = __ip_vs_service_get(af, protocol, vaddr, vport); + svc = __ip_vs_service_find(af, protocol, vaddr, vport); if (svc == NULL && protocol == IPPROTO_TCP @@ -480,7 +478,7 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, * Check if ftp service entry exists, the packet * might belong to FTP data connections. */ - svc = __ip_vs_service_get(af, protocol, vaddr, FTPPORT); + svc = __ip_vs_service_find(af, protocol, vaddr, FTPPORT); } if (svc == NULL @@ -488,10 +486,12 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, /* * Check if the catch-all port (port zero) exists */ - svc = __ip_vs_service_get(af, protocol, vaddr, 0); + svc = __ip_vs_service_find(af, protocol, vaddr, 0); } out: + if (svc) + atomic_inc(&svc->usecnt); read_unlock(&__ip_vs_svc_lock); IP_VS_DBG_BUF(9, "lookup service: fwm %u %s %s:%u %s\n", @@ -510,14 +510,19 @@ __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) dest->svc = svc; } -static inline void +static void __ip_vs_unbind_svc(struct ip_vs_dest *dest) { struct ip_vs_service *svc = dest->svc; dest->svc = NULL; - if (atomic_dec_and_test(&svc->refcnt)) + if (atomic_dec_and_test(&svc->refcnt)) { + IP_VS_DBG_BUF(3, "Removing service %u/%s:%u usecnt=%d\n", + svc->fwmark, + IP_VS_DBG_ADDR(svc->af, &svc->addr), + ntohs(svc->port), atomic_read(&svc->usecnt)); kfree(svc); + } } @@ -762,8 +767,8 @@ ip_vs_zero_stats(struct ip_vs_stats *stats) * Update a destination in the given service */ static void -__ip_vs_update_dest(struct ip_vs_service *svc, - struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest) +__ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, + struct ip_vs_dest_user_kern *udest, int add) { int conn_flags; @@ -818,6 +823,25 @@ __ip_vs_update_dest(struct ip_vs_service *svc, dest->flags &= ~IP_VS_DEST_F_OVERLOAD; dest->u_threshold = udest->u_threshold; dest->l_threshold = udest->l_threshold; + + if (add) + ip_vs_new_estimator(&dest->stats); + + write_lock_bh(&__ip_vs_svc_lock); + + /* Wait until all other svc users go away */ + IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0); + + if (add) { + list_add(&dest->n_list, &svc->destinations); + svc->num_dests++; + } + + /* call the update_service, because server weight may be changed */ + if (svc->scheduler->update_service) + svc->scheduler->update_service(svc); + + write_unlock_bh(&__ip_vs_svc_lock); } @@ -865,13 +889,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atomic_set(&dest->activeconns, 0); atomic_set(&dest->inactconns, 0); atomic_set(&dest->persistconns, 0); - atomic_set(&dest->refcnt, 0); + atomic_set(&dest->refcnt, 1); INIT_LIST_HEAD(&dest->d_list); spin_lock_init(&dest->dst_lock); spin_lock_init(&dest->stats.lock); - __ip_vs_update_dest(svc, dest, udest); - ip_vs_new_estimator(&dest->stats); + __ip_vs_update_dest(svc, dest, udest, 1); *dest_p = dest; @@ -931,65 +954,22 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) IP_VS_DBG_ADDR(svc->af, &dest->vaddr), ntohs(dest->vport)); - __ip_vs_update_dest(svc, dest, udest); - /* * Get the destination from the trash */ list_del(&dest->n_list); - ip_vs_new_estimator(&dest->stats); - - write_lock_bh(&__ip_vs_svc_lock); - + __ip_vs_update_dest(svc, dest, udest, 1); + ret = 0; + } else { /* - * Wait until all other svc users go away. + * Allocate and initialize the dest structure */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); - - list_add(&dest->n_list, &svc->destinations); - svc->num_dests++; - - /* call the update_service function of its scheduler */ - if (svc->scheduler->update_service) - svc->scheduler->update_service(svc); - - write_unlock_bh(&__ip_vs_svc_lock); - return 0; - } - - /* - * Allocate and initialize the dest structure - */ - ret = ip_vs_new_dest(svc, udest, &dest); - if (ret) { - return ret; + ret = ip_vs_new_dest(svc, udest, &dest); } - - /* - * Add the dest entry into the list - */ - atomic_inc(&dest->refcnt); - - write_lock_bh(&__ip_vs_svc_lock); - - /* - * Wait until all other svc users go away. - */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); - - list_add(&dest->n_list, &svc->destinations); - svc->num_dests++; - - /* call the update_service function of its scheduler */ - if (svc->scheduler->update_service) - svc->scheduler->update_service(svc); - - write_unlock_bh(&__ip_vs_svc_lock); - LeaveFunction(2); - return 0; + return ret; } @@ -1028,19 +1008,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return -ENOENT; } - __ip_vs_update_dest(svc, dest, udest); - - write_lock_bh(&__ip_vs_svc_lock); - - /* Wait until all other svc users go away */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); - - /* call the update_service, because server weight may be changed */ - if (svc->scheduler->update_service) - svc->scheduler->update_service(svc); - - write_unlock_bh(&__ip_vs_svc_lock); - + __ip_vs_update_dest(svc, dest, udest, 0); LeaveFunction(2); return 0; @@ -1067,6 +1035,10 @@ static void __ip_vs_del_dest(struct ip_vs_dest *dest) * the destination into the trash. */ if (atomic_dec_and_test(&dest->refcnt)) { + IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u\n", + dest->vfwmark, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port)); ip_vs_dst_reset(dest); /* simply decrease svc->refcnt here, let the caller check and release the service if nobody refers to it. @@ -1133,7 +1105,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Wait until all other svc users go away. */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); + IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0); /* * Unlink dest from the service @@ -1190,7 +1162,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, } /* I'm the first user of the service */ - atomic_set(&svc->usecnt, 1); + atomic_set(&svc->usecnt, 0); atomic_set(&svc->refcnt, 0); svc->af = u->af; @@ -1284,7 +1256,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) /* * Wait until all other svc users go away. */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); + IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0); /* * Set the flags and timeout value @@ -1383,21 +1355,23 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) /* * Free the service if nobody refers to it */ - if (atomic_read(&svc->refcnt) == 0) + if (atomic_read(&svc->refcnt) == 0) { + IP_VS_DBG_BUF(3, "Removing service %u/%s:%u usecnt=%d\n", + svc->fwmark, + IP_VS_DBG_ADDR(svc->af, &svc->addr), + ntohs(svc->port), atomic_read(&svc->usecnt)); kfree(svc); + } /* decrease the module use count */ ip_vs_use_count_dec(); } /* - * Delete a service from the service list + * Unlink a service from list and try to delete it if its refcnt reached 0 */ -static int ip_vs_del_service(struct ip_vs_service *svc) +static void ip_vs_unlink_service(struct ip_vs_service *svc) { - if (svc == NULL) - return -EEXIST; - /* * Unhash it from the service table */ @@ -1408,11 +1382,21 @@ static int ip_vs_del_service(struct ip_vs_service *svc) /* * Wait until all the svc users go away. */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1); + IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0); __ip_vs_del_service(svc); write_unlock_bh(&__ip_vs_svc_lock); +} + +/* + * Delete a service from the service list + */ +static int ip_vs_del_service(struct ip_vs_service *svc) +{ + if (svc == NULL) + return -EEXIST; + ip_vs_unlink_service(svc); return 0; } @@ -1431,14 +1415,7 @@ static int ip_vs_flush(void) */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], s_list) { - write_lock_bh(&__ip_vs_svc_lock); - ip_vs_svc_unhash(svc); - /* - * Wait until all the svc users go away. - */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0); - __ip_vs_del_service(svc); - write_unlock_bh(&__ip_vs_svc_lock); + ip_vs_unlink_service(svc); } } @@ -1448,14 +1425,7 @@ static int ip_vs_flush(void) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry_safe(svc, nxt, &ip_vs_svc_fwm_table[idx], f_list) { - write_lock_bh(&__ip_vs_svc_lock); - ip_vs_svc_unhash(svc); - /* - * Wait until all the svc users go away. - */ - IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0); - __ip_vs_del_service(svc); - write_unlock_bh(&__ip_vs_svc_lock); + ip_vs_unlink_service(svc); } } @@ -2168,15 +2138,15 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Lookup the exact service by or fwmark */ if (usvc.fwmark == 0) - svc = __ip_vs_service_get(usvc.af, usvc.protocol, - &usvc.addr, usvc.port); + svc = __ip_vs_service_find(usvc.af, usvc.protocol, + &usvc.addr, usvc.port); else - svc = __ip_vs_svc_fwm_get(usvc.af, usvc.fwmark); + svc = __ip_vs_svc_fwm_find(usvc.af, usvc.fwmark); if (cmd != IP_VS_SO_SET_ADD && (svc == NULL || svc->protocol != usvc.protocol)) { ret = -ESRCH; - goto out_drop_service; + goto out_unlock; } switch (cmd) { @@ -2210,10 +2180,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) ret = -EINVAL; } -out_drop_service: - if (svc) - ip_vs_service_put(svc); - out_unlock: mutex_unlock(&__ip_vs_mutex); out_dec: @@ -2306,10 +2272,10 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, int ret = 0; if (get->fwmark) - svc = __ip_vs_svc_fwm_get(AF_INET, get->fwmark); + svc = __ip_vs_svc_fwm_find(AF_INET, get->fwmark); else - svc = __ip_vs_service_get(AF_INET, get->protocol, &addr, - get->port); + svc = __ip_vs_service_find(AF_INET, get->protocol, &addr, + get->port); if (svc) { int count = 0; @@ -2337,7 +2303,6 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, } count++; } - ip_vs_service_put(svc); } else ret = -ESRCH; return ret; @@ -2458,15 +2423,14 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) entry = (struct ip_vs_service_entry *)arg; addr.ip = entry->addr; if (entry->fwmark) - svc = __ip_vs_svc_fwm_get(AF_INET, entry->fwmark); + svc = __ip_vs_svc_fwm_find(AF_INET, entry->fwmark); else - svc = __ip_vs_service_get(AF_INET, entry->protocol, - &addr, entry->port); + svc = __ip_vs_service_find(AF_INET, entry->protocol, + &addr, entry->port); if (svc) { ip_vs_copy_service(entry, svc); if (copy_to_user(user, entry, sizeof(*entry)) != 0) ret = -EFAULT; - ip_vs_service_put(svc); } else ret = -ESRCH; } @@ -2733,10 +2697,12 @@ nla_put_failure: } static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, - struct nlattr *nla, int full_entry) + struct nlattr *nla, int full_entry, + struct ip_vs_service **ret_svc) { struct nlattr *attrs[IPVS_SVC_ATTR_MAX + 1]; struct nlattr *nla_af, *nla_port, *nla_fwmark, *nla_protocol, *nla_addr; + struct ip_vs_service *svc; /* Parse mandatory identifying service fields first */ if (nla == NULL || @@ -2772,12 +2738,18 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, usvc->fwmark = 0; } + if (usvc->fwmark) + svc = __ip_vs_svc_fwm_find(usvc->af, usvc->fwmark); + else + svc = __ip_vs_service_find(usvc->af, usvc->protocol, + &usvc->addr, usvc->port); + *ret_svc = svc; + /* If a full entry was requested, check for the additional fields */ if (full_entry) { struct nlattr *nla_sched, *nla_flags, *nla_timeout, *nla_netmask; struct ip_vs_flags flags; - struct ip_vs_service *svc; nla_sched = attrs[IPVS_SVC_ATTR_SCHED_NAME]; nla_flags = attrs[IPVS_SVC_ATTR_FLAGS]; @@ -2790,16 +2762,8 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, nla_memcpy(&flags, nla_flags, sizeof(flags)); /* prefill flags from service if it already exists */ - if (usvc->fwmark) - svc = __ip_vs_svc_fwm_get(usvc->af, usvc->fwmark); - else - svc = __ip_vs_service_get(usvc->af, usvc->protocol, - &usvc->addr, usvc->port); - if (svc) { + if (svc) usvc->flags = svc->flags; - ip_vs_service_put(svc); - } else - usvc->flags = 0; /* set new flags from userland */ usvc->flags = (usvc->flags & ~flags.mask) | @@ -2815,17 +2779,11 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, static struct ip_vs_service *ip_vs_genl_find_service(struct nlattr *nla) { struct ip_vs_service_user_kern usvc; + struct ip_vs_service *svc; int ret; - ret = ip_vs_genl_parse_service(&usvc, nla, 0); - if (ret) - return ERR_PTR(ret); - - if (usvc.fwmark) - return __ip_vs_svc_fwm_get(usvc.af, usvc.fwmark); - else - return __ip_vs_service_get(usvc.af, usvc.protocol, - &usvc.addr, usvc.port); + ret = ip_vs_genl_parse_service(&usvc, nla, 0, &svc); + return ret ? ERR_PTR(ret) : svc; } static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) @@ -2916,7 +2874,6 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, nla_put_failure: cb->args[0] = idx; - ip_vs_service_put(svc); out_err: mutex_unlock(&__ip_vs_mutex); @@ -3129,17 +3086,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ret = ip_vs_genl_parse_service(&usvc, info->attrs[IPVS_CMD_ATTR_SERVICE], - need_full_svc); + need_full_svc, &svc); if (ret) goto out; - /* Lookup the exact service by or fwmark */ - if (usvc.fwmark == 0) - svc = __ip_vs_service_get(usvc.af, usvc.protocol, - &usvc.addr, usvc.port); - else - svc = __ip_vs_svc_fwm_get(usvc.af, usvc.fwmark); - /* Unless we're adding a new service, the service must already exist */ if ((cmd != IPVS_CMD_NEW_SERVICE) && (svc == NULL)) { ret = -ESRCH; @@ -3173,6 +3123,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) break; case IPVS_CMD_DEL_SERVICE: ret = ip_vs_del_service(svc); + /* do not use svc, it can be freed */ break; case IPVS_CMD_NEW_DEST: ret = ip_vs_add_dest(svc, &udest); @@ -3191,8 +3142,6 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) } out: - if (svc) - ip_vs_service_put(svc); mutex_unlock(&__ip_vs_mutex); return ret; @@ -3238,7 +3187,6 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) goto out_err; } else if (svc) { ret = ip_vs_genl_fill_service(msg, svc); - ip_vs_service_put(svc); if (ret) goto nla_put_failure; } else { -- cgit v0.10.2 From 5b92b61f3891517d18d0573ad2c939c81b59ecfe Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 22 Sep 2010 08:34:12 +0200 Subject: netfilter: nf_nat: better error handling of nf_ct_expect_related() in helpers This patch improves the situation in which the expectation table is full for conntrack NAT helpers. Basically, we give up if we don't find a place in the table instead of looping over nf_ct_expect_related() with a different port (we should only do this if it returns -EBUSY, for -EMFILE or -ESHUTDOWN I think that it's better to skip this). Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index c31b876..0f23b3f 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -44,9 +44,16 @@ static unsigned int help(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index 86e0e84..dc73abb 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -79,9 +79,16 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 5045196..790f316 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -222,13 +222,24 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, /* Try to get a pair of ports. */ for (nated_port = ntohs(rtp_exp->tuple.dst.u.udp.port); nated_port != 0; nated_port += 2) { + int ret; + rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - if (nf_ct_expect_related(rtp_exp) == 0) { + ret = nf_ct_expect_related(rtp_exp); + if (ret == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - if (nf_ct_expect_related(rtcp_exp) == 0) + ret = nf_ct_expect_related(rtcp_exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + nated_port = 0; break; - nf_ct_unexpect_related(rtp_exp); + } + } else if (ret != -EBUSY) { + nated_port = 0; + break; } } @@ -284,9 +295,16 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nated_port = 0; break; + } } if (nated_port == 0) { /* No port available */ @@ -334,9 +352,16 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) break; + else if (ret != -EBUSY) { + nated_port = 0; + break; + } } if (nated_port == 0) { /* No port available */ @@ -418,9 +443,16 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nated_port = 0; break; + } } if (nated_port == 0) { /* No port available */ @@ -500,9 +532,16 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (nated_port = ntohs(port); nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) break; + else if (ret != -EBUSY) { + nated_port = 0; + break; + } } if (nated_port == 0) { /* No port available */ diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index ea83a88..535e1a8 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -45,9 +45,16 @@ static unsigned int help(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 11b538d..e40cf78 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -307,9 +307,16 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, exp->expectfn = ip_nat_sip_expected; for (; port != 0; port++) { + int ret; + exp->tuple.dst.u.udp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) @@ -480,13 +487,25 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff, /* Try to get same pair of ports: if not, try to change them. */ for (port = ntohs(rtp_exp->tuple.dst.u.udp.port); port != 0; port += 2) { + int ret; + rtp_exp->tuple.dst.u.udp.port = htons(port); - if (nf_ct_expect_related(rtp_exp) != 0) + ret = nf_ct_expect_related(rtp_exp); + if (ret == -EBUSY) continue; + else if (ret < 0) { + port = 0; + break; + } rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - if (nf_ct_expect_related(rtcp_exp) == 0) + ret = nf_ct_expect_related(rtcp_exp); + if (ret == 0) break; - nf_ct_unexpect_related(rtp_exp); + else if (ret != -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + port = 0; + break; + } } if (port == 0) -- cgit v0.10.2 From bcac0dfab191cb53b3f9b43c8014a34070ed58ff Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 22 Sep 2010 08:35:36 +0200 Subject: netfilter: ctnetlink: missing validation of CTA_EXPECT_ZONE attribute This patch adds the missing validation of the CTA_EXPECT_ZONE attribute in the ctnetlink code. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 5bae1cd..37533a3 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1733,6 +1733,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING }, + [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, }; static int -- cgit v0.10.2 From 8b008faf92ac8f7eeb65e8cd36077601af7c46db Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 22 Sep 2010 08:36:59 +0200 Subject: netfilter: ctnetlink: allow to specify the expectation flags With this patch, you can specify the expectation flags for user-space created expectations. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 1afd18c..fdc50ca 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -100,6 +100,10 @@ enum ip_conntrack_expect_events { IPEXP_NEW, /* new expectation */ }; +/* expectation flags */ +#define NF_CT_EXPECT_PERMANENT 0x1 +#define NF_CT_EXPECT_INACTIVE 0x2 + #ifdef __KERNEL__ struct ip_conntrack_stat { unsigned int searched; diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 9ed534c..455f0ce4 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -161,6 +161,7 @@ enum ctattr_expect { CTA_EXPECT_ID, CTA_EXPECT_HELP_NAME, CTA_EXPECT_ZONE, + CTA_EXPECT_FLAGS, __CTA_EXPECT_MAX }; #define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1) diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 11e8150..96bb42a 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -67,9 +67,6 @@ struct nf_conntrack_expect_policy { #define NF_CT_EXPECT_CLASS_DEFAULT 0 -#define NF_CT_EXPECT_PERMANENT 0x1 -#define NF_CT_EXPECT_INACTIVE 0x2 - int nf_conntrack_expect_init(struct net *net); void nf_conntrack_expect_fini(struct net *net); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 37533a3..0804e0e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1577,6 +1577,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, NLA_PUT_BE32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)); NLA_PUT_BE32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)); + NLA_PUT_BE32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)); helper = rcu_dereference(nfct_help(master)->helper); if (helper) NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name); @@ -1734,6 +1735,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_ID] = { .type = NLA_U32 }, [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, + [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, }; static int @@ -1933,9 +1935,13 @@ ctnetlink_create_expect(struct net *net, u16 zone, goto out; } + if (cda[CTA_EXPECT_FLAGS]) + exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); + else + exp->flags = 0; + exp->class = 0; exp->expectfn = NULL; - exp->flags = 0; exp->master = ct; exp->helper = NULL; memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple)); -- cgit v0.10.2 From bc01befdcf3e40979eb518085a075cbf0aacede0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 28 Sep 2010 21:06:34 +0200 Subject: netfilter: ctnetlink: add support for user-space expectation helpers This patch adds the basic infrastructure to support user-space expectation helpers via ctnetlink and the netfilter queuing infrastructure NFQUEUE. Basically, this patch: * adds NF_CT_EXPECT_USERSPACE flag to identify user-space created expectations. I have also added a sanity check in __nf_ct_expect_check() to avoid that kernel-space helpers may create an expectation if the master conntrack has no helper assigned. * adds some branches to check if the master conntrack helper exists, otherwise we skip the code that refers to kernel-space helper such as the local expectation list and the expectation policy. * allows to set the timeout for user-space expectations with no helper assigned. * a list of expectations created from user-space that depends on ctnetlink (if this module is removed, they are deleted). * includes USERSPACE in the /proc output for expectations that have been created by a user-space helper. This patch also modifies ctnetlink to skip including the helper name in the Netlink messages if no kernel-space helper is set (since no user-space expectation has not kernel-space kernel assigned). You can access an example user-space FTP conntrack helper at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-userspace-POC.tar.bz Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index fdc50ca..23a1a08 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -103,6 +103,7 @@ enum ip_conntrack_expect_events { /* expectation flags */ #define NF_CT_EXPECT_PERMANENT 0x1 #define NF_CT_EXPECT_INACTIVE 0x2 +#define NF_CT_EXPECT_USERSPACE 0x4 #ifdef __KERNEL__ struct ip_conntrack_stat { diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 96bb42a..416b838 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -85,6 +85,7 @@ nf_ct_find_expectation(struct net *net, u16 zone, void nf_ct_unlink_expect(struct nf_conntrack_expect *exp); void nf_ct_remove_expectations(struct nf_conn *ct); void nf_ct_unexpect_related(struct nf_conntrack_expect *exp); +void nf_ct_remove_userspace_expectations(void); /* Allocate space for an expectation: this is mandatory before calling nf_ct_expect_related. You will have to call put afterwards. */ diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index acb29cc..b30a1f2 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -38,20 +38,23 @@ static int nf_ct_expect_hash_rnd_initted __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; +static HLIST_HEAD(nf_ct_userspace_expect_list); + /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) { struct nf_conn_help *master_help = nfct_help(exp->master); struct net *net = nf_ct_exp_net(exp); - NF_CT_ASSERT(master_help); NF_CT_ASSERT(!timer_pending(&exp->timeout)); hlist_del_rcu(&exp->hnode); net->ct.expect_count--; hlist_del(&exp->lnode); - master_help->expecting[exp->class]--; + if (!(exp->flags & NF_CT_EXPECT_USERSPACE)) + master_help->expecting[exp->class]--; + nf_ct_expect_put(exp); NF_CT_STAT_INC(net, expect_delete); @@ -320,16 +323,21 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) atomic_inc(&exp->use); - hlist_add_head(&exp->lnode, &master_help->expectations); - master_help->expecting[exp->class]++; + if (master_help) { + hlist_add_head(&exp->lnode, &master_help->expectations); + master_help->expecting[exp->class]++; + } else if (exp->flags & NF_CT_EXPECT_USERSPACE) + hlist_add_head(&exp->lnode, &nf_ct_userspace_expect_list); hlist_add_head_rcu(&exp->hnode, &net->ct.expect_hash[h]); net->ct.expect_count++; setup_timer(&exp->timeout, nf_ct_expectation_timed_out, (unsigned long)exp); - p = &master_help->helper->expect_policy[exp->class]; - exp->timeout.expires = jiffies + p->timeout * HZ; + if (master_help) { + p = &master_help->helper->expect_policy[exp->class]; + exp->timeout.expires = jiffies + p->timeout * HZ; + } add_timer(&exp->timeout); atomic_inc(&exp->use); @@ -380,7 +388,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) unsigned int h; int ret = 1; - if (!master_help->helper) { + /* Don't allow expectations created from kernel-space with no helper */ + if (!(expect->flags & NF_CT_EXPECT_USERSPACE) && + (!master_help || (master_help && !master_help->helper))) { ret = -ESHUTDOWN; goto out; } @@ -398,13 +408,16 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } } /* Will be over limit? */ - p = &master_help->helper->expect_policy[expect->class]; - if (p->max_expected && - master_help->expecting[expect->class] >= p->max_expected) { - evict_oldest_expect(master, expect); - if (master_help->expecting[expect->class] >= p->max_expected) { - ret = -EMFILE; - goto out; + if (master_help) { + p = &master_help->helper->expect_policy[expect->class]; + if (p->max_expected && + master_help->expecting[expect->class] >= p->max_expected) { + evict_oldest_expect(master, expect); + if (master_help->expecting[expect->class] + >= p->max_expected) { + ret = -EMFILE; + goto out; + } } } @@ -439,6 +452,21 @@ out: } EXPORT_SYMBOL_GPL(nf_ct_expect_related_report); +void nf_ct_remove_userspace_expectations(void) +{ + struct nf_conntrack_expect *exp; + struct hlist_node *n, *next; + + hlist_for_each_entry_safe(exp, n, next, + &nf_ct_userspace_expect_list, lnode) { + if (del_timer(&exp->timeout)) { + nf_ct_unlink_expect(exp); + nf_ct_expect_put(exp); + } + } +} +EXPORT_SYMBOL_GPL(nf_ct_remove_userspace_expectations); + #ifdef CONFIG_PROC_FS struct ct_expect_iter_state { struct seq_net_private p; @@ -529,8 +557,12 @@ static int exp_seq_show(struct seq_file *s, void *v) seq_printf(s, "PERMANENT"); delim = ","; } - if (expect->flags & NF_CT_EXPECT_INACTIVE) + if (expect->flags & NF_CT_EXPECT_INACTIVE) { seq_printf(s, "%sINACTIVE", delim); + delim = ","; + } + if (expect->flags & NF_CT_EXPECT_USERSPACE) + seq_printf(s, "%sUSERSPACE", delim); helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 0804e0e..b4077be 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1560,8 +1560,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; - struct nf_conntrack_helper *helper; long timeout = (exp->timeout.expires - jiffies) / HZ; + struct nf_conn_help *help; if (timeout < 0) timeout = 0; @@ -1578,9 +1578,14 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, NLA_PUT_BE32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)); NLA_PUT_BE32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)); NLA_PUT_BE32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)); - helper = rcu_dereference(nfct_help(master)->helper); - if (helper) - NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name); + help = nfct_help(master); + if (help) { + struct nf_conntrack_helper *helper; + + helper = rcu_dereference(help->helper); + if (helper) + NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name); + } return 0; @@ -1921,24 +1926,32 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); - help = nfct_help(ct); - - if (!help || !help->helper) { - /* such conntrack hasn't got any helper, abort */ - err = -EOPNOTSUPP; - goto out; - } - exp = nf_ct_expect_alloc(ct); if (!exp) { err = -ENOMEM; goto out; } + help = nfct_help(ct); + if (!help) { + if (!cda[CTA_EXPECT_TIMEOUT]) { + err = -EINVAL; + goto out; + } + exp->timeout.expires = + jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; - if (cda[CTA_EXPECT_FLAGS]) - exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); - else - exp->flags = 0; + exp->flags = NF_CT_EXPECT_USERSPACE; + if (cda[CTA_EXPECT_FLAGS]) { + exp->flags |= + ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); + } + } else { + if (cda[CTA_EXPECT_FLAGS]) { + exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); + exp->flags &= ~NF_CT_EXPECT_USERSPACE; + } else + exp->flags = 0; + } exp->class = 0; exp->expectfn = NULL; @@ -2109,6 +2122,7 @@ static void __exit ctnetlink_exit(void) { pr_info("ctnetlink: unregistering from nfnetlink.\n"); + nf_ct_remove_userspace_expectations(); #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_ct_expect_unregister_notifier(&ctnl_notifier_exp); nf_conntrack_unregister_notifier(&ctnl_notifier); -- cgit v0.10.2 From 5adbb9fb0c35c38022f79e09fecf15ba8f65f069 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:51 +0900 Subject: netfilter: nf_conntrack_sip: Allow ct_sip_get_header() to be called with a null ct argument Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 53d8922..2fd1ea2 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -152,6 +152,9 @@ static int parse_addr(const struct nf_conn *ct, const char *cp, const char *end; int ret = 0; + if (!ct) + return 0; + memset(addr, 0, sizeof(*addr)); switch (nf_ct_l3num(ct)) { case AF_INET: -- cgit v0.10.2 From 001985b2c0cfad48e1dec8e30f4d432eac240dd2 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:51 +0900 Subject: netfilter: nf_conntrack_sip: Add callid parser Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index ff8cfbc..0ce91d5 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -89,6 +89,7 @@ enum sip_header_types { SIP_HDR_VIA_TCP, SIP_HDR_EXPIRES, SIP_HDR_CONTENT_LENGTH, + SIP_HDR_CALL_ID, }; enum sdp_header_types { diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 2fd1ea2..715ce54 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -130,6 +130,44 @@ static int digits_len(const struct nf_conn *ct, const char *dptr, return len; } +static int iswordc(const char c) +{ + if (isalnum(c) || c == '!' || c == '"' || c == '%' || + (c >= '(' && c <= '/') || c == ':' || c == '<' || c == '>' || + c == '?' || (c >= '[' && c <= ']') || c == '_' || c == '`' || + c == '{' || c == '}' || c == '~') + return 1; + return 0; +} + +static int word_len(const char *dptr, const char *limit) +{ + int len = 0; + while (dptr < limit && iswordc(*dptr)) { + dptr++; + len++; + } + return len; +} + +static int callid_len(const struct nf_conn *ct, const char *dptr, + const char *limit, int *shift) +{ + int len, domain_len; + + len = word_len(dptr, limit); + dptr += len; + if (!len || dptr == limit || *dptr != '@') + return len; + dptr++; + len++; + + domain_len = word_len(dptr, limit); + if (!domain_len) + return 0; + return len + domain_len; +} + /* get media type + port length */ static int media_len(const struct nf_conn *ct, const char *dptr, const char *limit, int *shift) @@ -299,6 +337,7 @@ static const struct sip_header ct_sip_hdrs[] = { [SIP_HDR_VIA_TCP] = SIP_HDR("Via", "v", "TCP ", epaddr_len), [SIP_HDR_EXPIRES] = SIP_HDR("Expires", NULL, NULL, digits_len), [SIP_HDR_CONTENT_LENGTH] = SIP_HDR("Content-Length", "l", NULL, digits_len), + [SIP_HDR_CALL_ID] = SIP_HDR("Call-Id", "i", NULL, callid_len), }; static const char *sip_follow_continuation(const char *dptr, const char *limit) -- cgit v0.10.2 From 5b57a98c1f0d78a4c238d83c4ac70de3bd237b2f Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:51 +0900 Subject: IPVS: compact ip_vs_sched_persist() Compact ip_vs_sched_persist() by setting up parameters and calling functions once. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 06c388b..70a5cac 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -193,10 +193,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc, struct ip_vs_iphdr iph; struct ip_vs_dest *dest; struct ip_vs_conn *ct; - __be16 dport; /* destination port to forward */ + int protocol = iph.protocol; + __be16 dport = 0; /* destination port to forward */ + __be16 vport = 0; /* virtual service port */ unsigned int flags; union nf_inet_addr snet; /* source network of the client, after masking */ + const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; + const union nf_inet_addr *vaddr = &iph.daddr; ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); @@ -227,119 +231,61 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * service, and a template like * is created for other persistent services. */ - if (ports[1] == svc->port) { - /* Check if a template already exists */ - if (svc->port != FTPPORT) - ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0, - &iph.daddr, ports[1]); - else - ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0, - &iph.daddr, 0); - - if (!ct || !ip_vs_check_template(ct)) { - /* - * No template found or the dest of the connection - * template is not available. - */ - dest = svc->scheduler->schedule(svc, skb); - if (dest == NULL) { - IP_VS_DBG(1, "p-schedule: no dest found.\n"); - return NULL; - } - - /* - * Create a template like for non-ftp service, - * and - * for ftp service. + { + if (ports[1] == svc->port) { + /* non-FTP template: + * + * FTP template: + * */ if (svc->port != FTPPORT) - ct = ip_vs_conn_new(svc->af, iph.protocol, - &snet, 0, - &iph.daddr, - ports[1], - &dest->addr, dest->port, - IP_VS_CONN_F_TEMPLATE, - dest); - else - ct = ip_vs_conn_new(svc->af, iph.protocol, - &snet, 0, - &iph.daddr, 0, - &dest->addr, 0, - IP_VS_CONN_F_TEMPLATE, - dest); - if (ct == NULL) - return NULL; - - ct->timeout = svc->timeout; + vport = ports[1]; } else { - /* set destination with the found template */ - dest = ct->dest; + /* Note: persistent fwmark-based services and + * persistent port zero service are handled here. + * fwmark template: + * + * port zero template: + * + */ + if (svc->fwmark) { + protocol = IPPROTO_IP; + vaddr = &fwmark; + } } - dport = dest->port; - } else { - /* - * Note: persistent fwmark-based services and persistent - * port zero service are handled here. - * fwmark template: - * port zero template: + } + + /* Check if a template already exists */ + ct = ip_vs_ct_in_get(svc->af, protocol, &snet, 0, vaddr, vport); + + if (!ct || !ip_vs_check_template(ct)) { + /* No template found or the dest of the connection + * template is not available. */ - if (svc->fwmark) { - union nf_inet_addr fwmark = { - .ip = htonl(svc->fwmark) - }; + dest = svc->scheduler->schedule(svc, skb); + if (!dest) { + IP_VS_DBG(1, "p-schedule: no dest found.\n"); + return NULL; + } - ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0, - &fwmark, 0); - } else - ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0, - &iph.daddr, 0); + if (ports[1] == svc->port && svc->port != FTPPORT) + dport = dest->port; - if (!ct || !ip_vs_check_template(ct)) { - /* - * If it is not persistent port zero, return NULL, - * otherwise create a connection template. - */ - if (svc->port) - return NULL; + /* Create a template */ + ct = ip_vs_conn_new(svc->af, protocol, &snet, 0,vaddr, vport, + &dest->addr, dport, + IP_VS_CONN_F_TEMPLATE, dest); + if (ct == NULL) + return NULL; - dest = svc->scheduler->schedule(svc, skb); - if (dest == NULL) { - IP_VS_DBG(1, "p-schedule: no dest found.\n"); - return NULL; - } + ct->timeout = svc->timeout; + } else + /* set destination with the found template */ + dest = ct->dest; - /* - * Create a template according to the service - */ - if (svc->fwmark) { - union nf_inet_addr fwmark = { - .ip = htonl(svc->fwmark) - }; - - ct = ip_vs_conn_new(svc->af, IPPROTO_IP, - &snet, 0, - &fwmark, 0, - &dest->addr, 0, - IP_VS_CONN_F_TEMPLATE, - dest); - } else - ct = ip_vs_conn_new(svc->af, iph.protocol, - &snet, 0, - &iph.daddr, 0, - &dest->addr, 0, - IP_VS_CONN_F_TEMPLATE, - dest); - if (ct == NULL) - return NULL; - - ct->timeout = svc->timeout; - } else { - /* set destination with the found template */ - dest = ct->dest; - } - dport = ports[1]; - } + dport = ports[1]; + if (dport == svc->port && dest->port) + dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph.protocol == IPPROTO_UDP)? -- cgit v0.10.2 From f11017ec2d1859c661f4e2b12c4a8d250e1f47cf Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:52 +0900 Subject: IPVS: Add struct ip_vs_conn_param Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3915a4f..d4da774 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -357,6 +357,15 @@ struct ip_vs_protocol { extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto); +struct ip_vs_conn_param { + const union nf_inet_addr *caddr; + const union nf_inet_addr *vaddr; + __be16 cport; + __be16 vport; + __u16 protocol; + u16 af; +}; + /* * IP_VS structure allocated for each dynamically scheduled connection */ @@ -626,13 +635,23 @@ enum { IP_VS_DIR_LAST, }; -extern struct ip_vs_conn *ip_vs_conn_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port); +static inline void ip_vs_conn_fill_param(int af, int protocol, + const union nf_inet_addr *caddr, + __be16 cport, + const union nf_inet_addr *vaddr, + __be16 vport, + struct ip_vs_conn_param *p) +{ + p->af = af; + p->protocol = protocol; + p->caddr = caddr; + p->cport = cport; + p->vaddr = vaddr; + p->vport = vport; +} -extern struct ip_vs_conn *ip_vs_ct_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port); +struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); +struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, @@ -640,9 +659,7 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, unsigned int proto_off, int inverse); -extern struct ip_vs_conn *ip_vs_conn_out_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port); +struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, @@ -658,11 +675,10 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp) extern void ip_vs_conn_put(struct ip_vs_conn *cp); extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); -extern struct ip_vs_conn * -ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, - const union nf_inet_addr *vaddr, __be16 vport, - const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest); +struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, + const union nf_inet_addr *daddr, + __be16 dport, unsigned flags, + struct ip_vs_dest *dest); extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp); extern const char * ip_vs_state_name(__u16 proto, int state); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a970d96..deeb906 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -218,27 +218,26 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) /* * Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab. * Called for pkts coming from OUTside-to-INside. - * s_addr, s_port: pkt source address (foreign host) - * d_addr, d_port: pkt dest address (load balancer) + * p->caddr, p->cport: pkt source address (foreign host) + * p->vaddr, p->vport: pkt dest address (load balancer) */ -static inline struct ip_vs_conn *__ip_vs_conn_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +static inline struct ip_vs_conn * +__ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { unsigned hash; struct ip_vs_conn *cp; - hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); + hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (cp->af == af && - ip_vs_addr_equal(af, s_addr, &cp->caddr) && - ip_vs_addr_equal(af, d_addr, &cp->vaddr) && - s_port == cp->cport && d_port == cp->vport && - ((!s_port) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && - protocol == cp->protocol) { + if (cp->af == p->af && + ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && + ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && + p->cport == cp->cport && p->vport == cp->vport && + ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && + p->protocol == cp->protocol) { /* HIT */ atomic_inc(&cp->refcnt); ct_read_unlock(hash); @@ -251,71 +250,82 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get return NULL; } -struct ip_vs_conn *ip_vs_conn_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { struct ip_vs_conn *cp; - cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port); - if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) - cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr, - d_port); + cp = __ip_vs_conn_in_get(p); + if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) { + struct ip_vs_conn_param cport_zero_p = *p; + cport_zero_p.cport = 0; + cp = __ip_vs_conn_in_get(&cport_zero_p); + } IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n", - ip_vs_proto_name(protocol), - IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port), - IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port), + ip_vs_proto_name(p->protocol), + IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport), + IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), cp ? "hit" : "not hit"); return cp; } +static int +ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, + const struct ip_vs_iphdr *iph, + unsigned int proto_off, int inverse, + struct ip_vs_conn_param *p) +{ + __be16 _ports[2], *pptr; + + pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); + if (pptr == NULL) + return 1; + + if (likely(!inverse)) + ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0], + &iph->daddr, pptr[1], p); + else + ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1], + &iph->saddr, pptr[0], p); + return 0; +} + struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { - __be16 _ports[2], *pptr; + struct ip_vs_conn_param p; - pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); - if (pptr == NULL) + if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p)) return NULL; - if (likely(!inverse)) - return ip_vs_conn_in_get(af, iph->protocol, - &iph->saddr, pptr[0], - &iph->daddr, pptr[1]); - else - return ip_vs_conn_in_get(af, iph->protocol, - &iph->daddr, pptr[1], - &iph->saddr, pptr[0]); + return ip_vs_conn_in_get(&p); } EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto); /* Get reference to connection template */ -struct ip_vs_conn *ip_vs_ct_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) { unsigned hash; struct ip_vs_conn *cp; - hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); + hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (cp->af == af && - ip_vs_addr_equal(af, s_addr, &cp->caddr) && + if (cp->af == p->af && + ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && /* protocol should only be IPPROTO_IP if - * d_addr is a fwmark */ - ip_vs_addr_equal(protocol == IPPROTO_IP ? AF_UNSPEC : af, - d_addr, &cp->vaddr) && - s_port == cp->cport && d_port == cp->vport && + * p->vaddr is a fwmark */ + ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC : + p->af, p->vaddr, &cp->vaddr) && + p->cport == cp->cport && p->vport == cp->vport && cp->flags & IP_VS_CONN_F_TEMPLATE && - protocol == cp->protocol) { + p->protocol == cp->protocol) { /* HIT */ atomic_inc(&cp->refcnt); goto out; @@ -327,23 +337,19 @@ struct ip_vs_conn *ip_vs_ct_in_get ct_read_unlock(hash); IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n", - ip_vs_proto_name(protocol), - IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port), - IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port), + ip_vs_proto_name(p->protocol), + IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport), + IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), cp ? "hit" : "not hit"); return cp; } -/* - * Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab. - * Called for pkts coming from inside-to-OUTside. - * s_addr, s_port: pkt source address (inside host) - * d_addr, d_port: pkt dest address (foreign host) - */ -struct ip_vs_conn *ip_vs_conn_out_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +/* Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab. + * Called for pkts coming from inside-to-OUTside. + * p->caddr, p->cport: pkt source address (inside host) + * p->vaddr, p->vport: pkt dest address (foreign host) */ +struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) { unsigned hash; struct ip_vs_conn *cp, *ret=NULL; @@ -351,16 +357,16 @@ struct ip_vs_conn *ip_vs_conn_out_get /* * Check for "full" addressed entries */ - hash = ip_vs_conn_hashkey(af, protocol, d_addr, d_port); + hash = ip_vs_conn_hashkey(p->af, p->protocol, p->vaddr, p->vport); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (cp->af == af && - ip_vs_addr_equal(af, d_addr, &cp->caddr) && - ip_vs_addr_equal(af, s_addr, &cp->daddr) && - d_port == cp->cport && s_port == cp->dport && - protocol == cp->protocol) { + if (cp->af == p->af && + ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && + ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && + p->vport == cp->cport && p->cport == cp->dport && + p->protocol == cp->protocol) { /* HIT */ atomic_inc(&cp->refcnt); ret = cp; @@ -371,9 +377,9 @@ struct ip_vs_conn *ip_vs_conn_out_get ct_read_unlock(hash); IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n", - ip_vs_proto_name(protocol), - IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port), - IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port), + ip_vs_proto_name(p->protocol), + IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport), + IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), ret ? "hit" : "not hit"); return ret; @@ -385,20 +391,12 @@ ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { - __be16 _ports[2], *pptr; + struct ip_vs_conn_param p; - pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); - if (pptr == NULL) + if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p)) return NULL; - if (likely(!inverse)) - return ip_vs_conn_out_get(af, iph->protocol, - &iph->saddr, pptr[0], - &iph->daddr, pptr[1]); - else - return ip_vs_conn_out_get(af, iph->protocol, - &iph->daddr, pptr[1], - &iph->saddr, pptr[0]); + return ip_vs_conn_out_get(&p); } EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); @@ -758,13 +756,12 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) * Create a new connection entry and hash it into the ip_vs_conn_tab */ struct ip_vs_conn * -ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, - const union nf_inet_addr *vaddr, __be16 vport, +ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, struct ip_vs_dest *dest) { struct ip_vs_conn *cp; - struct ip_vs_protocol *pp = ip_vs_proto_get(proto); + struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol); cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); if (cp == NULL) { @@ -774,14 +771,14 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, INIT_LIST_HEAD(&cp->c_list); setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); - cp->af = af; - cp->protocol = proto; - ip_vs_addr_copy(af, &cp->caddr, caddr); - cp->cport = cport; - ip_vs_addr_copy(af, &cp->vaddr, vaddr); - cp->vport = vport; + cp->af = p->af; + cp->protocol = p->protocol; + ip_vs_addr_copy(p->af, &cp->caddr, p->caddr); + cp->cport = p->cport; + ip_vs_addr_copy(p->af, &cp->vaddr, p->vaddr); + cp->vport = p->vport; /* proto should only be IPPROTO_IP if d_addr is a fwmark */ - ip_vs_addr_copy(proto == IPPROTO_IP ? AF_UNSPEC : af, + ip_vs_addr_copy(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; @@ -810,7 +807,7 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, /* Bind its packet transmitter */ #ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) + if (p->af == AF_INET6) ip_vs_bind_xmit_v6(cp); else #endif diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 70a5cac..87602a6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -193,14 +193,11 @@ ip_vs_sched_persist(struct ip_vs_service *svc, struct ip_vs_iphdr iph; struct ip_vs_dest *dest; struct ip_vs_conn *ct; - int protocol = iph.protocol; __be16 dport = 0; /* destination port to forward */ - __be16 vport = 0; /* virtual service port */ unsigned int flags; + struct ip_vs_conn_param param; union nf_inet_addr snet; /* source network of the client, after masking */ - const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; - const union nf_inet_addr *vaddr = &iph.daddr; ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); @@ -232,6 +229,11 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * is created for other persistent services. */ { + int protocol = iph.protocol; + const union nf_inet_addr *vaddr = &iph.daddr; + const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; + __be16 vport = 0; + if (ports[1] == svc->port) { /* non-FTP template: * @@ -253,11 +255,12 @@ ip_vs_sched_persist(struct ip_vs_service *svc, vaddr = &fwmark; } } + ip_vs_conn_fill_param(svc->af, protocol, &snet, 0, + vaddr, vport, ¶m); } /* Check if a template already exists */ - ct = ip_vs_ct_in_get(svc->af, protocol, &snet, 0, vaddr, vport); - + ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct)) { /* No template found or the dest of the connection * template is not available. @@ -272,8 +275,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, dport = dest->port; /* Create a template */ - ct = ip_vs_conn_new(svc->af, protocol, &snet, 0,vaddr, vport, - &dest->addr, dport, + ct = ip_vs_conn_new(¶m, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest); if (ct == NULL) return NULL; @@ -294,12 +296,9 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - cp = ip_vs_conn_new(svc->af, iph.protocol, - &iph.saddr, ports[0], - &iph.daddr, ports[1], - &dest->addr, dport, - flags, - dest); + ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0], + &iph.daddr, ports[1], ¶m); + cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest); if (cp == NULL) { ip_vs_conn_put(ct); return NULL; @@ -366,14 +365,16 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* * Create a connection entry. */ - cp = ip_vs_conn_new(svc->af, iph.protocol, - &iph.saddr, pptr[0], - &iph.daddr, pptr[1], - &dest->addr, dest->port ? dest->port : pptr[1], - flags, - dest); - if (cp == NULL) - return NULL; + { + struct ip_vs_conn_param p; + ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, + pptr[0], &iph.daddr, pptr[1], &p); + cp = ip_vs_conn_new(&p, &dest->addr, + dest->port ? dest->port : pptr[1], + flags, dest); + if (!cp) + return NULL; + } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", @@ -429,14 +430,17 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); - cp = ip_vs_conn_new(svc->af, iph.protocol, - &iph.saddr, pptr[0], - &iph.daddr, pptr[1], - &daddr, 0, - IP_VS_CONN_F_BYPASS | flags, - NULL); - if (cp == NULL) - return NF_DROP; + { + struct ip_vs_conn_param p; + ip_vs_conn_fill_param(svc->af, iph.protocol, + &iph.saddr, pptr[0], + &iph.daddr, pptr[1], &p); + cp = ip_vs_conn_new(&p, &daddr, 0, + IP_VS_CONN_F_BYPASS | flags, + NULL); + if (!cp) + return NF_DROP; + } /* statistics */ ip_vs_in_stats(cp, skb); diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 9cd375f..090889a 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -195,13 +195,17 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, /* * Now update or create an connection entry for it */ - n_cp = ip_vs_conn_out_get(AF_INET, iph->protocol, &from, port, - &cp->caddr, 0); + { + struct ip_vs_conn_param p; + ip_vs_conn_fill_param(AF_INET, iph->protocol, + &from, port, &cp->caddr, 0, &p); + n_cp = ip_vs_conn_out_get(&p); + } if (!n_cp) { - n_cp = ip_vs_conn_new(AF_INET, IPPROTO_TCP, - &cp->caddr, 0, - &cp->vaddr, port, - &from, port, + struct ip_vs_conn_param p; + ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr, + 0, &cp->vaddr, port, &p); + n_cp = ip_vs_conn_new(&p, &from, port, IP_VS_CONN_F_NO_CPORT | IP_VS_CONN_F_NFCT, cp->dest); @@ -347,21 +351,22 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, ip_vs_proto_name(iph->protocol), &to.ip, ntohs(port), &cp->vaddr.ip, 0); - n_cp = ip_vs_conn_in_get(AF_INET, iph->protocol, - &to, port, - &cp->vaddr, htons(ntohs(cp->vport)-1)); - if (!n_cp) { - n_cp = ip_vs_conn_new(AF_INET, IPPROTO_TCP, - &to, port, + { + struct ip_vs_conn_param p; + ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), - &cp->daddr, htons(ntohs(cp->dport)-1), - IP_VS_CONN_F_NFCT, - cp->dest); - if (!n_cp) - return 0; + &p); + n_cp = ip_vs_conn_in_get(&p); + if (!n_cp) { + n_cp = ip_vs_conn_new(&p, &cp->daddr, + htons(ntohs(cp->dport)-1), + IP_VS_CONN_F_NFCT, cp->dest); + if (!n_cp) + return 0; - /* add its controller */ - ip_vs_control_add(n_cp, cp); + /* add its controller */ + ip_vs_control_add(n_cp, cp); + } } /* diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index c038458..4680647 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -140,6 +140,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, { struct nf_conntrack_tuple *orig, new_reply; struct ip_vs_conn *cp; + struct ip_vs_conn_param p; if (exp->tuple.src.l3num != PF_INET) return; @@ -154,9 +155,10 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, /* RS->CLIENT */ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum, - &orig->src.u3, orig->src.u.tcp.port, - &orig->dst.u3, orig->dst.u.tcp.port); + ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum, + &orig->src.u3, orig->src.u.tcp.port, + &orig->dst.u3, orig->dst.u.tcp.port, &p); + cp = ip_vs_conn_out_get(&p); if (cp) { /* Change reply CLIENT->RS to CLIENT->VS */ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; @@ -176,9 +178,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, } /* CLIENT->VS */ - cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum, - &orig->src.u3, orig->src.u.tcp.port, - &orig->dst.u3, orig->dst.u.tcp.port); + cp = ip_vs_conn_in_get(&p); if (cp) { /* Change reply VS->CLIENT to RS->CLIENT */ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 1892dfc..8956ef3 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -40,6 +40,19 @@ struct isakmp_hdr { #define PORT_ISAKMP 500 +static void +ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph, + int inverse, struct ip_vs_conn_param *p) +{ + if (likely(!inverse)) + ip_vs_conn_fill_param(af, IPPROTO_UDP, + &iph->saddr, htons(PORT_ISAKMP), + &iph->daddr, htons(PORT_ISAKMP), p); + else + ip_vs_conn_fill_param(af, IPPROTO_UDP, + &iph->daddr, htons(PORT_ISAKMP), + &iph->saddr, htons(PORT_ISAKMP), p); +} static struct ip_vs_conn * ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, @@ -47,21 +60,10 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, int inverse) { struct ip_vs_conn *cp; + struct ip_vs_conn_param p; - if (likely(!inverse)) { - cp = ip_vs_conn_in_get(af, IPPROTO_UDP, - &iph->saddr, - htons(PORT_ISAKMP), - &iph->daddr, - htons(PORT_ISAKMP)); - } else { - cp = ip_vs_conn_in_get(af, IPPROTO_UDP, - &iph->daddr, - htons(PORT_ISAKMP), - &iph->saddr, - htons(PORT_ISAKMP)); - } - + ah_esp_conn_fill_param_proto(af, iph, inverse, &p); + cp = ip_vs_conn_in_get(&p); if (!cp) { /* * We are not sure if the packet is from our @@ -87,21 +89,10 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb, int inverse) { struct ip_vs_conn *cp; + struct ip_vs_conn_param p; - if (likely(!inverse)) { - cp = ip_vs_conn_out_get(af, IPPROTO_UDP, - &iph->saddr, - htons(PORT_ISAKMP), - &iph->daddr, - htons(PORT_ISAKMP)); - } else { - cp = ip_vs_conn_out_get(af, IPPROTO_UDP, - &iph->daddr, - htons(PORT_ISAKMP), - &iph->saddr, - htons(PORT_ISAKMP)); - } - + ah_esp_conn_fill_param_proto(af, iph, inverse, &p); + cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " "%s%s %s->%s\n", diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 7ba0693..f68631f 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -301,6 +301,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_dest *dest; + struct ip_vs_conn_param param; char *p; int i; @@ -370,18 +371,17 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) } } - if (!(flags & IP_VS_CONN_F_TEMPLATE)) - cp = ip_vs_conn_in_get(AF_INET, s->protocol, - (union nf_inet_addr *)&s->caddr, - s->cport, - (union nf_inet_addr *)&s->vaddr, - s->vport); - else - cp = ip_vs_ct_in_get(AF_INET, s->protocol, - (union nf_inet_addr *)&s->caddr, - s->cport, - (union nf_inet_addr *)&s->vaddr, - s->vport); + { + ip_vs_conn_fill_param(AF_INET, s->protocol, + (union nf_inet_addr *)&s->caddr, + s->cport, + (union nf_inet_addr *)&s->vaddr, + s->vport, ¶m); + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + cp = ip_vs_conn_in_get(¶m); + else + cp = ip_vs_ct_in_get(¶m); + } if (!cp) { /* * Find the appropriate destination for the connection. @@ -406,14 +406,9 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) else flags &= ~IP_VS_CONN_F_INACTIVE; } - cp = ip_vs_conn_new(AF_INET, s->protocol, - (union nf_inet_addr *)&s->caddr, - s->cport, - (union nf_inet_addr *)&s->vaddr, - s->vport, + cp = ip_vs_conn_new(¶m, (union nf_inet_addr *)&s->daddr, - s->dport, - flags, dest); + s->dport, flags, dest); if (dest) atomic_dec(&dest->refcnt); if (!cp) { -- cgit v0.10.2 From 6e08bfb879574524cc9a67be960c684989fd986c Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:52 +0900 Subject: IPVS: Allow null argument to ip_vs_scheduler_put() This simplifies caller logic sightly. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e4ec8f3..f7afcfe 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1144,7 +1144,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, if (sched == NULL) { pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); ret = -ENOENT; - goto out_mod_dec; + goto out_err; } #ifdef CONFIG_IP_VS_IPV6 @@ -1204,7 +1204,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, *svc_p = svc; return 0; - out_err: + out_err: if (svc != NULL) { if (svc->scheduler) ip_vs_unbind_scheduler(svc); @@ -1217,7 +1217,6 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, } ip_vs_scheduler_put(sched); - out_mod_dec: /* decrease the module use count */ ip_vs_use_count_dec(); @@ -1300,10 +1299,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) #ifdef CONFIG_IP_VS_IPV6 out: #endif - - if (old_sched) - ip_vs_scheduler_put(old_sched); - + ip_vs_scheduler_put(old_sched); return ret; } @@ -1327,8 +1323,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) /* Unbind scheduler */ old_sched = svc->scheduler; ip_vs_unbind_scheduler(svc); - if (old_sched) - ip_vs_scheduler_put(old_sched); + ip_vs_scheduler_put(old_sched); /* Unbind app inc */ if (svc->inc) { diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 727e45b..9f94e32 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -159,7 +159,7 @@ struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name) void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) { - if (scheduler->module) + if (scheduler && scheduler->module) module_put(scheduler->module); } -- cgit v0.10.2 From 2fabf35bfcd89445c54cf1e6a5437dd3cf924a92 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:52 +0900 Subject: IPVS: ip_vs_{un,}bind_scheduler NULL arguments In general NULL arguments aren't passed by the few callers that exist, so don't test for them. The exception is to make passing NULL to ip_vs_unbind_scheduler() a noop. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index f7afcfe..5f20caf 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1206,8 +1206,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, out_err: if (svc != NULL) { - if (svc->scheduler) - ip_vs_unbind_scheduler(svc); + ip_vs_unbind_scheduler(svc); if (svc->inc) { local_bh_disable(); ip_vs_app_inc_put(svc->inc); diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 9f94e32..076ebe0 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -46,15 +46,6 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc, { int ret; - if (svc == NULL) { - pr_err("%s(): svc arg NULL\n", __func__); - return -EINVAL; - } - if (scheduler == NULL) { - pr_err("%s(): scheduler arg NULL\n", __func__); - return -EINVAL; - } - svc->scheduler = scheduler; if (scheduler->init_service) { @@ -74,18 +65,10 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc, */ int ip_vs_unbind_scheduler(struct ip_vs_service *svc) { - struct ip_vs_scheduler *sched; + struct ip_vs_scheduler *sched = svc->scheduler; - if (svc == NULL) { - pr_err("%s(): svc arg NULL\n", __func__); - return -EINVAL; - } - - sched = svc->scheduler; - if (sched == NULL) { - pr_err("%s(): svc isn't bound\n", __func__); - return -EINVAL; - } + if (!sched) + return 0; if (sched->done_service) { if (sched->done_service(svc) != 0) { -- cgit v0.10.2 From 85999283a21ab2dd37427fdd8c8e8af57223977c Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:53 +0900 Subject: IPVS: Add struct ip_vs_pe Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index df77286..0a9c44d 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -99,8 +99,10 @@ 0) #define IP_VS_SCHEDNAME_MAXLEN 16 +#define IP_VS_PENAME_MAXLEN 16 #define IP_VS_IFNAME_MAXLEN 16 +#define IP_VS_PEDATA_MAXLEN 255 /* * The struct ip_vs_service_user and struct ip_vs_dest_user are diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d4da774..b6b309d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -364,6 +364,10 @@ struct ip_vs_conn_param { __be16 vport; __u16 protocol; u16 af; + + const struct ip_vs_pe *pe; + char *pe_data; + __u8 pe_data_len; }; /* @@ -416,6 +420,9 @@ struct ip_vs_conn { void *app_data; /* Application private data */ struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ + + char *pe_data; + __u8 pe_data_len; }; @@ -486,6 +493,9 @@ struct ip_vs_service { struct ip_vs_scheduler *scheduler; /* bound scheduler object */ rwlock_t sched_lock; /* lock sched_data */ void *sched_data; /* scheduler application data */ + + /* alternate persistence engine */ + struct ip_vs_pe *pe; }; @@ -549,6 +559,20 @@ struct ip_vs_scheduler { const struct sk_buff *skb); }; +/* The persistence engine object */ +struct ip_vs_pe { + struct list_head n_list; /* d-linked list head */ + char *name; /* scheduler name */ + atomic_t refcnt; /* reference counter */ + struct module *module; /* THIS_MODULE/NULL */ + + /* get the connection template, if any */ + int (*fill_param)(struct ip_vs_conn_param *p, struct sk_buff *skb); + bool (*ct_match)(const struct ip_vs_conn_param *p, + struct ip_vs_conn *ct); + u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval, + bool inverse); +}; /* * The application module object (a.k.a. app incarnation) @@ -648,6 +672,8 @@ static inline void ip_vs_conn_fill_param(int af, int protocol, p->cport = cport; p->vaddr = vaddr; p->vport = vport; + p->pe = NULL; + p->pe_data = NULL; } struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); @@ -803,7 +829,7 @@ extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc); extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * -ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb); +ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_protocol *pp); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index deeb906..06da21e 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -148,6 +148,42 @@ static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, & ip_vs_conn_tab_mask; } +static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, + bool inverse) +{ + const union nf_inet_addr *addr; + __be16 port; + + if (p->pe && p->pe->hashkey_raw) + return p->pe->hashkey_raw(p, ip_vs_conn_rnd, inverse) & + ip_vs_conn_tab_mask; + + if (likely(!inverse)) { + addr = p->caddr; + port = p->cport; + } else { + addr = p->vaddr; + port = p->vport; + } + + return ip_vs_conn_hashkey(p->af, p->protocol, addr, port); +} + +static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) +{ + struct ip_vs_conn_param p; + + ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport, + NULL, 0, &p); + + if (cp->dest && cp->dest->svc->pe) { + p.pe = cp->dest->svc->pe; + p.pe_data = cp->pe_data; + p.pe_data_len = cp->pe_data_len; + } + + return ip_vs_conn_hashkey_param(&p, false); +} /* * Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port. @@ -162,7 +198,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) return 0; /* Hash by protocol, client address and port */ - hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport); + hash = ip_vs_conn_hashkey_conn(cp); ct_write_lock(hash); spin_lock(&cp->lock); @@ -195,7 +231,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) int ret; /* unhash it and decrease its reference counter */ - hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport); + hash = ip_vs_conn_hashkey_conn(cp); ct_write_lock(hash); spin_lock(&cp->lock); @@ -227,7 +263,7 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) unsigned hash; struct ip_vs_conn *cp; - hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport); + hash = ip_vs_conn_hashkey_param(p, false); ct_read_lock(hash); @@ -312,11 +348,17 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) unsigned hash; struct ip_vs_conn *cp; - hash = ip_vs_conn_hashkey(p->af, p->protocol, p->caddr, p->cport); + hash = ip_vs_conn_hashkey_param(p, false); ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + if (p->pe && p->pe->ct_match) { + if (p->pe->ct_match(p, cp)) + goto out; + continue; + } + if (cp->af == p->af && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && /* protocol should only be IPPROTO_IP if @@ -325,15 +367,14 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) p->af, p->vaddr, &cp->vaddr) && p->cport == cp->cport && p->vport == cp->vport && cp->flags & IP_VS_CONN_F_TEMPLATE && - p->protocol == cp->protocol) { - /* HIT */ - atomic_inc(&cp->refcnt); + p->protocol == cp->protocol) goto out; - } } cp = NULL; out: + if (cp) + atomic_inc(&cp->refcnt); ct_read_unlock(hash); IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n", @@ -357,7 +398,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) /* * Check for "full" addressed entries */ - hash = ip_vs_conn_hashkey(p->af, p->protocol, p->vaddr, p->vport); + hash = ip_vs_conn_hashkey_param(p, true); ct_read_lock(hash); @@ -722,6 +763,7 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->flags & IP_VS_CONN_F_NFCT) ip_vs_conn_drop_conntrack(cp); + kfree(cp->pe_data); if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); @@ -782,6 +824,10 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; + if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) { + cp->pe_data = p->pe_data; + cp->pe_data_len = p->pe_data_len; + } spin_lock_init(&cp->lock); /* @@ -832,7 +878,6 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, return cp; } - /* * /proc/net/ip_vs_conn entries */ @@ -848,7 +893,7 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (pos-- == 0) { seq->private = &ip_vs_conn_tab[idx]; - return cp; + return cp; } } ct_read_unlock_bh(idx); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 87602a6..ab98893 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -176,6 +176,19 @@ ip_vs_set_state(struct ip_vs_conn *cp, int direction, return pp->state_transition(cp, direction, skb, pp); } +static inline int +ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, + struct sk_buff *skb, int protocol, + const union nf_inet_addr *caddr, __be16 cport, + const union nf_inet_addr *vaddr, __be16 vport, + struct ip_vs_conn_param *p) +{ + ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p); + p->pe = svc->pe; + if (p->pe && p->pe->fill_param) + return p->pe->fill_param(p, skb); + return 0; +} /* * IPVS persistent scheduling function @@ -186,7 +199,7 @@ ip_vs_set_state(struct ip_vs_conn *cp, int direction, */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, - const struct sk_buff *skb, + struct sk_buff *skb, __be16 ports[2]) { struct ip_vs_conn *cp = NULL; @@ -255,8 +268,9 @@ ip_vs_sched_persist(struct ip_vs_service *svc, vaddr = &fwmark; } } - ip_vs_conn_fill_param(svc->af, protocol, &snet, 0, - vaddr, vport, ¶m); + if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, + vaddr, vport, ¶m)) + return NULL; } /* Check if a template already exists */ @@ -268,22 +282,30 @@ ip_vs_sched_persist(struct ip_vs_service *svc, dest = svc->scheduler->schedule(svc, skb); if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); + kfree(param.pe_data); return NULL; } if (ports[1] == svc->port && svc->port != FTPPORT) dport = dest->port; - /* Create a template */ + /* Create a template + * This adds param.pe_data to the template, + * and thus param.pe_data will be destroyed + * when the template expires */ ct = ip_vs_conn_new(¶m, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest); - if (ct == NULL) + if (ct == NULL) { + kfree(param.pe_data); return NULL; + } ct->timeout = svc->timeout; - } else + } else { /* set destination with the found template */ dest = ct->dest; + kfree(param.pe_data); + } dport = ports[1]; if (dport == svc->port && dest->port) @@ -322,7 +344,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * Protocols supported: TCP, UDP */ struct ip_vs_conn * -ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) +ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb) { struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index f68631f..ab85aed 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -288,6 +288,16 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) ip_vs_sync_conn(cp->control); } +static inline int +ip_vs_conn_fill_param_sync(int af, int protocol, + const union nf_inet_addr *caddr, __be16 cport, + const union nf_inet_addr *vaddr, __be16 vport, + struct ip_vs_conn_param *p) +{ + /* XXX: Need to take into account persistence engine */ + ip_vs_conn_fill_param(af, protocol, caddr, cport, vaddr, vport, p); + return 0; +} /* * Process received multicast message and create the corresponding @@ -372,11 +382,14 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) } { - ip_vs_conn_fill_param(AF_INET, s->protocol, + if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol, (union nf_inet_addr *)&s->caddr, s->cport, (union nf_inet_addr *)&s->vaddr, - s->vport, ¶m); + s->vport, ¶m)) { + pr_err("ip_vs_conn_fill_param_sync failed"); + return; + } if (!(flags & IP_VS_CONN_F_TEMPLATE)) cp = ip_vs_conn_in_get(¶m); else -- cgit v0.10.2 From a3c918acd29a96aba3b46bf50136e7953a480d17 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:53 +0900 Subject: IPVS: Add persistence engine data to /proc/net/ip_vs_conn This shouldn't break compatibility with userspace as the new data is at the end of the line. I have confirmed that this doesn't break ipvsadm, the main (only?) user-space user of this data. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b6b309d..974daf5 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -572,6 +572,7 @@ struct ip_vs_pe { struct ip_vs_conn *ct); u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval, bool inverse); + int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf); }; /* diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 06da21e..4adedef 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -950,30 +950,45 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) seq_puts(seq, - "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires\n"); + "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires PEName PEData\n"); else { const struct ip_vs_conn *cp = v; + char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3]; + size_t len = 0; + + if (cp->dest && cp->dest->svc->pe && + cp->dest->svc->pe->show_pe_data) { + pe_data[0] = ' '; + len = strlen(cp->dest->svc->pe->name); + memcpy(pe_data + 1, cp->dest->svc->pe->name, len); + pe_data[len + 1] = ' '; + len += 2; + len += cp->dest->svc->pe->show_pe_data(cp, + pe_data + len); + } + pe_data[len] = '\0'; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) - seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X %pI6 %04X %-11s %7lu\n", + seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X " + "%pI6 %04X %-11s %7lu%s\n", ip_vs_proto_name(cp->protocol), &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), &cp->daddr.in6, ntohs(cp->dport), ip_vs_state_name(cp->protocol, cp->state), - (cp->timer.expires-jiffies)/HZ); + (cp->timer.expires-jiffies)/HZ, pe_data); else #endif seq_printf(seq, "%-3s %08X %04X %08X %04X" - " %08X %04X %-11s %7lu\n", + " %08X %04X %-11s %7lu%s\n", ip_vs_proto_name(cp->protocol), ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), ntohl(cp->daddr.ip), ntohs(cp->dport), ip_vs_state_name(cp->protocol, cp->state), - (cp->timer.expires-jiffies)/HZ); + (cp->timer.expires-jiffies)/HZ, pe_data); } return 0; } -- cgit v0.10.2 From 8be67a6617b3403551fccb67b1c624c659419515 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:54 +0900 Subject: IPVS: management of persistence engine modules This is based heavily on the scheduler management code Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 974daf5..a6b93a2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -796,6 +796,12 @@ extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb); extern int ip_vs_app_init(void); extern void ip_vs_app_cleanup(void); +void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); +void ip_vs_unbind_pe(struct ip_vs_service *svc); +int register_ip_vs_pe(struct ip_vs_pe *pe); +int unregister_ip_vs_pe(struct ip_vs_pe *pe); +extern struct ip_vs_pe *ip_vs_pe_get(const char *name); +extern void ip_vs_pe_put(struct ip_vs_pe *pe); /* * IPVS protocol functions (from ip_vs_proto.c) diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index 349fe88..4a87bf3 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -14,7 +14,7 @@ ip_vs-extra_objs-$(CONFIG_IP_VS_NFCT) += ip_vs_nfct.o ip_vs-objs := ip_vs_conn.o ip_vs_core.o ip_vs_ctl.o ip_vs_sched.o \ ip_vs_xmit.o ip_vs_app.o ip_vs_sync.o \ - ip_vs_est.o ip_vs_proto.o \ + ip_vs_est.o ip_vs_proto.o ip_vs_pe.o \ $(ip_vs_proto-objs-y) $(ip_vs-extra_objs-y) diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c new file mode 100644 index 0000000..3414af7 --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -0,0 +1,147 @@ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include +#include +#include +#include +#include + +#include + +/* IPVS pe list */ +static LIST_HEAD(ip_vs_pe); + +/* lock for service table */ +static DEFINE_SPINLOCK(ip_vs_pe_lock); + +/* Bind a service with a pe */ +void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe) +{ + svc->pe = pe; +} + +/* Unbind a service from its pe */ +void ip_vs_unbind_pe(struct ip_vs_service *svc) +{ + svc->pe = NULL; +} + +/* Get pe in the pe list by name */ +static struct ip_vs_pe * +ip_vs_pe_getbyname(const char *pe_name) +{ + struct ip_vs_pe *pe; + + IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__, + pe_name); + + spin_lock_bh(&ip_vs_pe_lock); + + list_for_each_entry(pe, &ip_vs_pe, n_list) { + /* Test and get the modules atomically */ + if (pe->module && + !try_module_get(pe->module)) { + /* This pe is just deleted */ + continue; + } + if (strcmp(pe_name, pe->name)==0) { + /* HIT */ + spin_unlock_bh(&ip_vs_pe_lock); + return pe; + } + if (pe->module) + module_put(pe->module); + } + + spin_unlock_bh(&ip_vs_pe_lock); + return NULL; +} + +/* Lookup pe and try to load it if it doesn't exist */ +struct ip_vs_pe *ip_vs_pe_get(const char *name) +{ + struct ip_vs_pe *pe; + + /* Search for the pe by name */ + pe = ip_vs_pe_getbyname(name); + + /* If pe not found, load the module and search again */ + if (!pe) { + request_module("ip_vs_pe_%s", name); + pe = ip_vs_pe_getbyname(name); + } + + return pe; +} + +void ip_vs_pe_put(struct ip_vs_pe *pe) +{ + if (pe && pe->module) + module_put(pe->module); +} + +/* Register a pe in the pe list */ +int register_ip_vs_pe(struct ip_vs_pe *pe) +{ + struct ip_vs_pe *tmp; + + /* increase the module use count */ + ip_vs_use_count_inc(); + + spin_lock_bh(&ip_vs_pe_lock); + + if (!list_empty(&pe->n_list)) { + spin_unlock_bh(&ip_vs_pe_lock); + ip_vs_use_count_dec(); + pr_err("%s(): [%s] pe already linked\n", + __func__, pe->name); + return -EINVAL; + } + + /* Make sure that the pe with this name doesn't exist + * in the pe list. + */ + list_for_each_entry(tmp, &ip_vs_pe, n_list) { + if (strcmp(tmp->name, pe->name) == 0) { + spin_unlock_bh(&ip_vs_pe_lock); + ip_vs_use_count_dec(); + pr_err("%s(): [%s] pe already existed " + "in the system\n", __func__, pe->name); + return -EINVAL; + } + } + /* Add it into the d-linked pe list */ + list_add(&pe->n_list, &ip_vs_pe); + spin_unlock_bh(&ip_vs_pe_lock); + + pr_info("[%s] pe registered.\n", pe->name); + + return 0; +} +EXPORT_SYMBOL_GPL(register_ip_vs_pe); + +/* Unregister a pe from the pe list */ +int unregister_ip_vs_pe(struct ip_vs_pe *pe) +{ + spin_lock_bh(&ip_vs_pe_lock); + if (list_empty(&pe->n_list)) { + spin_unlock_bh(&ip_vs_pe_lock); + pr_err("%s(): [%s] pe is not in the list. failed\n", + __func__, pe->name); + return -EINVAL; + } + + /* Remove it from the d-linked pe list */ + list_del(&pe->n_list); + spin_unlock_bh(&ip_vs_pe_lock); + + /* decrease the module use count */ + ip_vs_use_count_dec(); + + pr_info("[%s] pe unregistered.\n", pe->name); + + return 0; +} +EXPORT_SYMBOL_GPL(unregister_ip_vs_pe); -- cgit v0.10.2 From 0d1e71b04a04b6912e50926b9987c1e72facb1f3 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:54 +0900 Subject: IPVS: Allow configuration of persistence engines Allow the persistence engine of a virtual service to be set, edited and unset. This feature only works with the netlink user-space interface. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 0a9c44d..5f43a3b 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -336,6 +336,9 @@ enum { IPVS_SVC_ATTR_NETMASK, /* persistent netmask */ IPVS_SVC_ATTR_STATS, /* nested attribute for service stats */ + + IPVS_SVC_ATTR_PE_NAME, /* name of ct retriever */ + __IPVS_SVC_ATTR_MAX, }; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a6b93a2..52fbe23 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -444,6 +444,7 @@ struct ip_vs_service_user_kern { /* virtual service options */ char *sched_name; + char *pe_name; unsigned flags; /* virtual service flags */ unsigned timeout; /* persistent timeout in sec */ u32 netmask; /* persistent netmask */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5f20caf..a697591 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1134,6 +1134,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, { int ret = 0; struct ip_vs_scheduler *sched = NULL; + struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; /* increase the module use count */ @@ -1147,6 +1148,16 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, goto out_err; } + if (u->pe_name && *u->pe_name) { + pe = ip_vs_pe_get(u->pe_name); + if (pe == NULL) { + pr_info("persistence engine module ip_vs_pe_%s " + "not found\n", u->pe_name); + ret = -ENOENT; + goto out_err; + } + } + #ifdef CONFIG_IP_VS_IPV6 if (u->af == AF_INET6 && (u->netmask < 1 || u->netmask > 128)) { ret = -EINVAL; @@ -1184,6 +1195,10 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, goto out_err; sched = NULL; + /* Bind the ct retriever */ + ip_vs_bind_pe(svc, pe); + pe = NULL; + /* Update the virtual service counters */ if (svc->port == FTPPORT) atomic_inc(&ip_vs_ftpsvc_counter); @@ -1215,6 +1230,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, kfree(svc); } ip_vs_scheduler_put(sched); + ip_vs_pe_put(pe); /* decrease the module use count */ ip_vs_use_count_dec(); @@ -1230,6 +1246,7 @@ static int ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { struct ip_vs_scheduler *sched, *old_sched; + struct ip_vs_pe *pe = NULL, *old_pe = NULL; int ret = 0; /* @@ -1242,6 +1259,17 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) } old_sched = sched; + if (u->pe_name && *u->pe_name) { + pe = ip_vs_pe_get(u->pe_name); + if (pe == NULL) { + pr_info("persistence engine module ip_vs_pe_%s " + "not found\n", u->pe_name); + ret = -ENOENT; + goto out; + } + old_pe = pe; + } + #ifdef CONFIG_IP_VS_IPV6 if (u->af == AF_INET6 && (u->netmask < 1 || u->netmask > 128)) { ret = -EINVAL; @@ -1293,12 +1321,17 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) } } + old_pe = svc->pe; + if (pe != old_pe) { + ip_vs_unbind_pe(svc); + ip_vs_bind_pe(svc, pe); + } + out_unlock: write_unlock_bh(&__ip_vs_svc_lock); -#ifdef CONFIG_IP_VS_IPV6 out: -#endif ip_vs_scheduler_put(old_sched); + ip_vs_pe_put(old_pe); return ret; } @@ -1312,6 +1345,9 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) { struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; + struct ip_vs_pe *old_pe; + + pr_info("%s: enter\n", __func__); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) @@ -1324,6 +1360,11 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) ip_vs_unbind_scheduler(svc); ip_vs_scheduler_put(old_sched); + /* Unbind persistence engine */ + old_pe = svc->pe; + ip_vs_unbind_pe(svc); + ip_vs_pe_put(old_pe); + /* Unbind app inc */ if (svc->inc) { ip_vs_app_inc_put(svc->inc); @@ -2026,6 +2067,8 @@ static const unsigned char set_arglen[SET_CMDID(IP_VS_SO_SET_MAX)+1] = { static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc, struct ip_vs_service_user *usvc_compat) { + memset(usvc, 0, sizeof(*usvc)); + usvc->af = AF_INET; usvc->protocol = usvc_compat->protocol; usvc->addr.ip = usvc_compat->addr; @@ -2043,6 +2086,8 @@ static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc, static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest, struct ip_vs_dest_user *udest_compat) { + memset(udest, 0, sizeof(*udest)); + udest->addr.ip = udest_compat->addr; udest->port = udest_compat->port; udest->conn_flags = udest_compat->conn_flags; @@ -2539,6 +2584,8 @@ static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = { [IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 }, [IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING, .len = IP_VS_SCHEDNAME_MAXLEN }, + [IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING, + .len = IP_VS_PENAME_MAXLEN }, [IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY, .len = sizeof(struct ip_vs_flags) }, [IPVS_SVC_ATTR_TIMEOUT] = { .type = NLA_U32 }, @@ -2615,6 +2662,8 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, } NLA_PUT_STRING(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name); + if (svc->pe) + NLA_PUT_STRING(skb, IPVS_SVC_ATTR_PE_NAME, svc->pe->name); NLA_PUT(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags); NLA_PUT_U32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ); NLA_PUT_U32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask); @@ -2741,11 +2790,12 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, /* If a full entry was requested, check for the additional fields */ if (full_entry) { - struct nlattr *nla_sched, *nla_flags, *nla_timeout, + struct nlattr *nla_sched, *nla_flags, *nla_pe, *nla_timeout, *nla_netmask; struct ip_vs_flags flags; nla_sched = attrs[IPVS_SVC_ATTR_SCHED_NAME]; + nla_pe = attrs[IPVS_SVC_ATTR_PE_NAME]; nla_flags = attrs[IPVS_SVC_ATTR_FLAGS]; nla_timeout = attrs[IPVS_SVC_ATTR_TIMEOUT]; nla_netmask = attrs[IPVS_SVC_ATTR_NETMASK]; @@ -2763,6 +2813,7 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, usvc->flags = (usvc->flags & ~flags.mask) | (flags.flags & flags.mask); usvc->sched_name = nla_data(nla_sched); + usvc->pe_name = nla_pe ? nla_data(nla_pe) : NULL; usvc->timeout = nla_get_u32(nla_timeout); usvc->netmask = nla_get_u32(nla_netmask); } -- cgit v0.10.2 From f71499aa11f884255b69ce6c3b3c398c821591a1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:54 +0900 Subject: IPVS: Fallback if persistence engine fails Fall back to normal persistence handling if the persistence engine fails to recognise a packet. This way, at least the packet will go somewhere. It is envisaged that iptables could be used to block packets such if this is not desired although nf_conntrack_sip would likely need to be enhanced first. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4adedef..1d1a529 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -154,7 +154,7 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, const union nf_inet_addr *addr; __be16 port; - if (p->pe && p->pe->hashkey_raw) + if (p->pe_data && p->pe->hashkey_raw) return p->pe->hashkey_raw(p, ip_vs_conn_rnd, inverse) & ip_vs_conn_tab_mask; @@ -353,7 +353,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (p->pe && p->pe->ct_match) { + if (p->pe_data && p->pe->ct_match) { if (p->pe->ct_match(p, cp)) goto out; continue; @@ -956,7 +956,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3]; size_t len = 0; - if (cp->dest && cp->dest->svc->pe && + if (cp->dest && cp->pe_data && cp->dest->svc->pe->show_pe_data) { pe_data[0] = ' '; len = strlen(cp->dest->svc->pe->name); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index ab98893..e5fef7a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -176,7 +176,7 @@ ip_vs_set_state(struct ip_vs_conn *cp, int direction, return pp->state_transition(cp, direction, skb, pp); } -static inline int +static inline void ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, @@ -186,8 +186,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = svc->pe; if (p->pe && p->pe->fill_param) - return p->pe->fill_param(p, skb); - return 0; + p->pe->fill_param(p, skb); } /* @@ -268,9 +267,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc, vaddr = &fwmark; } } - if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, - vaddr, vport, ¶m)) - return NULL; + ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, + vaddr, vport, ¶m); } /* Check if a template already exists */ -- cgit v0.10.2 From 758ff03387228824617cef9507e5682488bf9e0c Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sun, 22 Aug 2010 21:37:55 +0900 Subject: IPVS: sip persistence engine Add the SIP callid as a key for persistence. This allows multiple connections from the same IP address to be differentiated on the basis of the callid. When used in conjunction with the persistence mask, it allows connections from different IP addresses to be aggregated on the basis of the callid. It is envisaged that a persistence mask of 0.0.0.0 will be a useful setting. That is, ignore the source IP address when checking for persistence. It is envisaged that this option will be used in conjunction with one-packet scheduling. This only works with UDP and cannot be made to work with TCP within the current framework. Signed-off-by: Simon Horman Acked-by: Julian Anastasov diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index af3c9f4..a22dac2 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -256,4 +256,11 @@ config IP_VS_NFCT connection state to be exported to the Netfilter framework for filtering purposes. +config IP_VS_PE_SIP + tristate "SIP persistence engine" + depends on IP_VS_PROTO_UDP + depends on NF_CONNTRACK_SIP + ---help--- + Allow persistence based on the SIP Call-ID + endif # IP_VS diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index 4a87bf3..34ee602 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -35,3 +35,6 @@ obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o # IPVS application helpers obj-$(CONFIG_IP_VS_FTP) += ip_vs_ftp.o + +# IPVS connection template retrievers +obj-$(CONFIG_IP_VS_PE_SIP) += ip_vs_pe_sip.o diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c new file mode 100644 index 0000000..a0539f1 --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -0,0 +1,167 @@ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include + +#include +#include +#include + +static const char *ip_vs_dbg_callid(char *buf, size_t buf_len, + const char *callid, size_t callid_len, + int *idx) +{ + size_t len = min(min(callid_len, (size_t)64), buf_len - *idx - 1); + memcpy(buf + *idx, callid, len); + buf[*idx+len] = '\0'; + *idx += len + 1; + return buf + *idx - len; +} + +#define IP_VS_DEBUG_CALLID(callid, len) \ + ip_vs_dbg_callid(ip_vs_dbg_buf, sizeof(ip_vs_dbg_buf), \ + callid, len, &ip_vs_dbg_idx) + +static int get_callid(const char *dptr, unsigned int dataoff, + unsigned int datalen, + unsigned int *matchoff, unsigned int *matchlen) +{ + /* Find callid */ + while (1) { + int ret = ct_sip_get_header(NULL, dptr, dataoff, datalen, + SIP_HDR_CALL_ID, matchoff, + matchlen); + if (ret > 0) + break; + if (!ret) + return 0; + dataoff += *matchoff; + } + + /* Empty callid is useless */ + if (!*matchlen) + return -EINVAL; + + /* Too large is useless */ + if (*matchlen > IP_VS_PEDATA_MAXLEN) + return -EINVAL; + + /* SIP headers are always followed by a line terminator */ + if (*matchoff + *matchlen == datalen) + return -EINVAL; + + /* RFC 2543 allows lines to be terminated with CR, LF or CRLF, + * RFC 3261 allows only CRLF, we support both. */ + if (*(dptr + *matchoff + *matchlen) != '\r' && + *(dptr + *matchoff + *matchlen) != '\n') + return -EINVAL; + + IP_VS_DBG_BUF(9, "SIP callid %s (%d bytes)\n", + IP_VS_DEBUG_CALLID(dptr + *matchoff, *matchlen), + *matchlen); + return 0; +} + +static int +ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) +{ + struct ip_vs_iphdr iph; + unsigned int dataoff, datalen, matchoff, matchlen; + const char *dptr; + + ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph); + + /* Only useful with UDP */ + if (iph.protocol != IPPROTO_UDP) + return -EINVAL; + + /* No Data ? */ + dataoff = iph.len + sizeof(struct udphdr); + if (dataoff >= skb->len) + return -EINVAL; + + dptr = skb->data + dataoff; + datalen = skb->len - dataoff; + + if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen)) + return -EINVAL; + + p->pe_data = kmalloc(matchlen, GFP_ATOMIC); + if (!p->pe_data) + return -ENOMEM; + + /* N.B: pe_data is only set on success, + * this allows fallback to the default persistence logic on failure + */ + memcpy(p->pe_data, dptr + matchoff, matchlen); + p->pe_data_len = matchlen; + + return 0; +} + +static bool ip_vs_sip_ct_match(const struct ip_vs_conn_param *p, + struct ip_vs_conn *ct) + +{ + bool ret = 0; + + if (ct->af == p->af && + ip_vs_addr_equal(p->af, p->caddr, &ct->caddr) && + /* protocol should only be IPPROTO_IP if + * d_addr is a fwmark */ + ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, + p->vaddr, &ct->vaddr) && + ct->vport == p->vport && + ct->flags & IP_VS_CONN_F_TEMPLATE && + ct->protocol == p->protocol && + ct->pe_data && ct->pe_data_len == p->pe_data_len && + !memcmp(ct->pe_data, p->pe_data, p->pe_data_len)) + ret = 1; + + IP_VS_DBG_BUF(9, "SIP template match %s %s->%s:%d %s\n", + ip_vs_proto_name(p->protocol), + IP_VS_DEBUG_CALLID(p->pe_data, p->pe_data_len), + IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), + ret ? "hit" : "not hit"); + + return ret; +} + +static u32 ip_vs_sip_hashkey_raw(const struct ip_vs_conn_param *p, + u32 initval, bool inverse) +{ + return jhash(p->pe_data, p->pe_data_len, initval); +} + +static int ip_vs_sip_show_pe_data(const struct ip_vs_conn *cp, char *buf) +{ + memcpy(buf, cp->pe_data, cp->pe_data_len); + return cp->pe_data_len; +} + +static struct ip_vs_pe ip_vs_sip_pe = +{ + .name = "sip", + .refcnt = ATOMIC_INIT(0), + .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_sip_pe.n_list), + .fill_param = ip_vs_sip_fill_param, + .ct_match = ip_vs_sip_ct_match, + .hashkey_raw = ip_vs_sip_hashkey_raw, + .show_pe_data = ip_vs_sip_show_pe_data, +}; + +static int __init ip_vs_sip_init(void) +{ + return register_ip_vs_pe(&ip_vs_sip_pe); +} + +static void __exit ip_vs_sip_cleanup(void) +{ + unregister_ip_vs_pe(&ip_vs_sip_pe); +} + +module_init(ip_vs_sip_init); +module_exit(ip_vs_sip_cleanup); +MODULE_LICENSE("GPL"); -- cgit v0.10.2 From 0c200d935346fe0ebde9b6dffbb683dddd166fb9 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 4 Oct 2010 20:53:18 +0200 Subject: netfilter: nf_nat: make find/put static The functions nf_nat_proto_find_get and nf_nat_proto_put are only used internally in nf_nat_core. This might break some out of tree NAT module. Signed-off-by: Stephen Hemminger Signed-off-by: Patrick McHardy diff --git a/include/net/netfilter/nf_nat_protocol.h b/include/net/netfilter/nf_nat_protocol.h index df17bac..93cc90d 100644 --- a/include/net/netfilter/nf_nat_protocol.h +++ b/include/net/netfilter/nf_nat_protocol.h @@ -45,9 +45,6 @@ struct nf_nat_protocol { extern int nf_nat_protocol_register(const struct nf_nat_protocol *proto); extern void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto); -extern const struct nf_nat_protocol *nf_nat_proto_find_get(u_int8_t protocol); -extern void nf_nat_proto_put(const struct nf_nat_protocol *proto); - /* Built-in protocols. */ extern const struct nf_nat_protocol nf_nat_protocol_tcp; extern const struct nf_nat_protocol nf_nat_protocol_udp; diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 2c084b3..e2e00c4 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -47,7 +47,7 @@ __nf_nat_proto_find(u_int8_t protonum) return rcu_dereference(nf_nat_protos[protonum]); } -const struct nf_nat_protocol * +static const struct nf_nat_protocol * nf_nat_proto_find_get(u_int8_t protonum) { const struct nf_nat_protocol *p; @@ -60,14 +60,12 @@ nf_nat_proto_find_get(u_int8_t protonum) return p; } -EXPORT_SYMBOL_GPL(nf_nat_proto_find_get); -void +static void nf_nat_proto_put(const struct nf_nat_protocol *p) { module_put(p->me); } -EXPORT_SYMBOL_GPL(nf_nat_proto_put); /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int -- cgit v0.10.2 From a8defca048fd11eb2d1a17ab61a60a856292dd4e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Oct 2010 20:56:05 +0200 Subject: netfilter: ipt_LOG: add bufferisation to call printk() once ipt_LOG & ip6t_LOG use lot of calls to printk() and use a lock in a hope several cpus wont mix their output in syslog. printk() being very expensive [1], its better to call it once, on a prebuilt and complete line. Also, with mixed IPv4 and IPv6 trafic, separate IPv4/IPv6 locks dont avoid garbage. I used an allocation of a 1024 bytes structure, sort of seq_printf() but with a fixed size limit. Use a static buffer if dynamic allocation failed. Emit a once time alert if buffer size happens to be too short. [1]: printk() has various features like printk_delay()... Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 915fc17..72ffc8f 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -24,16 +24,15 @@ #include #include #include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team "); MODULE_DESCRIPTION("Xtables: IPv4 packet logging to syslog"); -/* Use lock to serialize, so printks don't overlap */ -static DEFINE_SPINLOCK(log_lock); - /* One level of recursion won't kill us */ -static void dump_packet(const struct nf_loginfo *info, +static void dump_packet(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { @@ -48,32 +47,32 @@ static void dump_packet(const struct nf_loginfo *info, ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); if (ih == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Important fields: * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ - printk("SRC=%pI4 DST=%pI4 ", + sb_add(m, "SRC=%pI4 DST=%pI4 ", &ih->saddr, &ih->daddr); /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ - printk("LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", + sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); /* Max length: 6 "CE DF MF " */ if (ntohs(ih->frag_off) & IP_CE) - printk("CE "); + sb_add(m, "CE "); if (ntohs(ih->frag_off) & IP_DF) - printk("DF "); + sb_add(m, "DF "); if (ntohs(ih->frag_off) & IP_MF) - printk("MF "); + sb_add(m, "MF "); /* Max length: 11 "FRAG:65535 " */ if (ntohs(ih->frag_off) & IP_OFFSET) - printk("FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); + sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); if ((logflags & IPT_LOG_IPOPT) && ih->ihl * 4 > sizeof(struct iphdr)) { @@ -85,15 +84,15 @@ static void dump_packet(const struct nf_loginfo *info, op = skb_header_pointer(skb, iphoff+sizeof(_iph), optsize, _opt); if (op == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); + sb_add(m, "OPT ("); for (i = 0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); } switch (ih->protocol) { @@ -102,7 +101,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct tcphdr *th; /* Max length: 10 "PROTO=TCP " */ - printk("PROTO=TCP "); + sb_add(m, "PROTO=TCP "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -111,41 +110,41 @@ static void dump_packet(const struct nf_loginfo *info, th = skb_header_pointer(skb, iphoff + ih->ihl * 4, sizeof(_tcph), &_tcph); if (th == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u ", + sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ if (logflags & IPT_LOG_TCPSEQ) - printk("SEQ=%u ACK=%u ", + sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); /* Max length: 13 "WINDOW=65535 " */ - printk("WINDOW=%u ", ntohs(th->window)); + sb_add(m, "WINDOW=%u ", ntohs(th->window)); /* Max length: 9 "RES=0x3F " */ - printk("RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); + sb_add(m, "RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ if (th->cwr) - printk("CWR "); + sb_add(m, "CWR "); if (th->ece) - printk("ECE "); + sb_add(m, "ECE "); if (th->urg) - printk("URG "); + sb_add(m, "URG "); if (th->ack) - printk("ACK "); + sb_add(m, "ACK "); if (th->psh) - printk("PSH "); + sb_add(m, "PSH "); if (th->rst) - printk("RST "); + sb_add(m, "RST "); if (th->syn) - printk("SYN "); + sb_add(m, "SYN "); if (th->fin) - printk("FIN "); + sb_add(m, "FIN "); /* Max length: 11 "URGP=65535 " */ - printk("URGP=%u ", ntohs(th->urg_ptr)); + sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); if ((logflags & IPT_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { @@ -158,15 +157,15 @@ static void dump_packet(const struct nf_loginfo *info, iphoff+ih->ihl*4+sizeof(_tcph), optsize, _opt); if (op == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); + sb_add(m, "OPT ("); for (i = 0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); } break; } @@ -177,9 +176,9 @@ static void dump_packet(const struct nf_loginfo *info, if (ih->protocol == IPPROTO_UDP) /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP " ); + sb_add(m, "PROTO=UDP " ); else /* Max length: 14 "PROTO=UDPLITE " */ - printk("PROTO=UDPLITE "); + sb_add(m, "PROTO=UDPLITE "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -188,13 +187,13 @@ static void dump_packet(const struct nf_loginfo *info, uh = skb_header_pointer(skb, iphoff+ih->ihl*4, sizeof(_udph), &_udph); if (uh == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u LEN=%u ", + sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); break; @@ -221,7 +220,7 @@ static void dump_packet(const struct nf_loginfo *info, [ICMP_ADDRESSREPLY] = 12 }; /* Max length: 11 "PROTO=ICMP " */ - printk("PROTO=ICMP "); + sb_add(m, "PROTO=ICMP "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -230,19 +229,19 @@ static void dump_packet(const struct nf_loginfo *info, ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, sizeof(_icmph), &_icmph); if (ich == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Max length: 18 "TYPE=255 CODE=255 " */ - printk("TYPE=%u CODE=%u ", ich->type, ich->code); + sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ if (ich->type <= NR_ICMP_TYPES && required_len[ich->type] && skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } @@ -251,35 +250,35 @@ static void dump_packet(const struct nf_loginfo *info, case ICMP_ECHOREPLY: case ICMP_ECHO: /* Max length: 19 "ID=65535 SEQ=65535 " */ - printk("ID=%u SEQ=%u ", + sb_add(m, "ID=%u SEQ=%u ", ntohs(ich->un.echo.id), ntohs(ich->un.echo.sequence)); break; case ICMP_PARAMETERPROB: /* Max length: 14 "PARAMETER=255 " */ - printk("PARAMETER=%u ", + sb_add(m, "PARAMETER=%u ", ntohl(ich->un.gateway) >> 24); break; case ICMP_REDIRECT: /* Max length: 24 "GATEWAY=255.255.255.255 " */ - printk("GATEWAY=%pI4 ", &ich->un.gateway); + sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); /* Fall through */ case ICMP_DEST_UNREACH: case ICMP_SOURCE_QUENCH: case ICMP_TIME_EXCEEDED: /* Max length: 3+maxlen */ if (!iphoff) { /* Only recurse once. */ - printk("["); - dump_packet(info, skb, + sb_add(m, "["); + dump_packet(m, info, skb, iphoff + ih->ihl*4+sizeof(_icmph)); - printk("] "); + sb_add(m, "] "); } /* Max length: 10 "MTU=65535 " */ if (ich->type == ICMP_DEST_UNREACH && ich->code == ICMP_FRAG_NEEDED) - printk("MTU=%u ", ntohs(ich->un.frag.mtu)); + sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); } break; } @@ -292,19 +291,19 @@ static void dump_packet(const struct nf_loginfo *info, break; /* Max length: 9 "PROTO=AH " */ - printk("PROTO=AH "); + sb_add(m, "PROTO=AH "); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ ah = skb_header_pointer(skb, iphoff+ih->ihl*4, sizeof(_ahdr), &_ahdr); if (ah == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Length: 15 "SPI=0xF1234567 " */ - printk("SPI=0x%x ", ntohl(ah->spi)); + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); break; } case IPPROTO_ESP: { @@ -312,7 +311,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct ip_esp_hdr *eh; /* Max length: 10 "PROTO=ESP " */ - printk("PROTO=ESP "); + sb_add(m, "PROTO=ESP "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -321,25 +320,25 @@ static void dump_packet(const struct nf_loginfo *info, eh = skb_header_pointer(skb, iphoff+ih->ihl*4, sizeof(_esph), &_esph); if (eh == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Length: 15 "SPI=0xF1234567 " */ - printk("SPI=0x%x ", ntohl(eh->spi)); + sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); break; } /* Max length: 10 "PROTO 255 " */ default: - printk("PROTO=%u ", ih->protocol); + sb_add(m, "PROTO=%u ", ih->protocol); } /* Max length: 15 "UID=4294967295 " */ if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) { read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) - printk("UID=%u GID=%u ", + sb_add(m, "UID=%u GID=%u ", skb->sk->sk_socket->file->f_cred->fsuid, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); @@ -347,7 +346,7 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!iphoff && skb->mark) - printk("MARK=0x%x ", skb->mark); + sb_add(m, "MARK=0x%x ", skb->mark); /* Proto Max log string length */ /* IP: 40+46+6+11+127 = 230 */ @@ -364,7 +363,8 @@ static void dump_packet(const struct nf_loginfo *info, /* maxlen = 230+ 91 + 230 + 252 = 803 */ } -static void dump_mac_header(const struct nf_loginfo *info, +static void dump_mac_header(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -378,7 +378,7 @@ static void dump_mac_header(const struct nf_loginfo *info, switch (dev->type) { case ARPHRD_ETHER: - printk("MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, ntohs(eth_hdr(skb)->h_proto)); return; @@ -387,17 +387,17 @@ static void dump_mac_header(const struct nf_loginfo *info, } fallback: - printk("MAC="); + sb_add(m, "MAC="); if (dev->hard_header_len && skb->mac_header != skb->network_header) { const unsigned char *p = skb_mac_header(skb); unsigned int i; - printk("%02x", *p++); + sb_add(m, "%02x", *p++); for (i = 1; i < dev->hard_header_len; i++, p++) - printk(":%02x", *p); + sb_add(m, ":%02x", *p); } - printk(" "); + sb_add(m, " "); } static struct nf_loginfo default_loginfo = { @@ -419,11 +419,12 @@ ipt_log_packet(u_int8_t pf, const struct nf_loginfo *loginfo, const char *prefix) { + struct sbuff *m = sb_open(); + if (!loginfo) loginfo = &default_loginfo; - spin_lock_bh(&log_lock); - printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, prefix, in ? in->name : "", out ? out->name : ""); @@ -434,20 +435,20 @@ ipt_log_packet(u_int8_t pf, physindev = skb->nf_bridge->physindev; if (physindev && in != physindev) - printk("PHYSIN=%s ", physindev->name); + sb_add(m, "PHYSIN=%s ", physindev->name); physoutdev = skb->nf_bridge->physoutdev; if (physoutdev && out != physoutdev) - printk("PHYSOUT=%s ", physoutdev->name); + sb_add(m, "PHYSOUT=%s ", physoutdev->name); } #endif /* MAC logging for input path only. */ if (in && !out) - dump_mac_header(loginfo, skb); + dump_mac_header(m, loginfo, skb); + + dump_packet(m, loginfo, skb, 0); - dump_packet(loginfo, skb, 0); - printk("\n"); - spin_unlock_bh(&log_lock); + sb_close(m); } static unsigned int diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 0a07ae7..09c8889 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -23,6 +23,7 @@ #include #include #include +#include MODULE_AUTHOR("Jan Rekorajski "); MODULE_DESCRIPTION("Xtables: IPv6 packet logging to syslog"); @@ -32,11 +33,9 @@ struct in_device; #include #include -/* Use lock to serialize, so printks don't overlap */ -static DEFINE_SPINLOCK(log_lock); - /* One level of recursion won't kill us */ -static void dump_packet(const struct nf_loginfo *info, +static void dump_packet(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int ip6hoff, int recurse) { @@ -55,15 +54,15 @@ static void dump_packet(const struct nf_loginfo *info, ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); if (ih == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ - printk("SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ - printk("LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", ntohs(ih->payload_len) + sizeof(struct ipv6hdr), (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, ih->hop_limit, @@ -78,35 +77,35 @@ static void dump_packet(const struct nf_loginfo *info, hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); if (hp == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 48 "OPT (...) " */ if (logflags & IP6T_LOG_IPOPT) - printk("OPT ( "); + sb_add(m, "OPT ( "); switch (currenthdr) { case IPPROTO_FRAGMENT: { struct frag_hdr _fhdr; const struct frag_hdr *fh; - printk("FRAG:"); + sb_add(m, "FRAG:"); fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), &_fhdr); if (fh == NULL) { - printk("TRUNCATED "); + sb_add(m, "TRUNCATED "); return; } /* Max length: 6 "65535 " */ - printk("%u ", ntohs(fh->frag_off) & 0xFFF8); + sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); /* Max length: 11 "INCOMPLETE " */ if (fh->frag_off & htons(0x0001)) - printk("INCOMPLETE "); + sb_add(m, "INCOMPLETE "); - printk("ID:%08x ", ntohl(fh->identification)); + sb_add(m, "ID:%08x ", ntohl(fh->identification)); if (ntohs(fh->frag_off) & 0xFFF8) fragment = 1; @@ -120,7 +119,7 @@ static void dump_packet(const struct nf_loginfo *info, case IPPROTO_HOPOPTS: if (fragment) { if (logflags & IP6T_LOG_IPOPT) - printk(")"); + sb_add(m, ")"); return; } hdrlen = ipv6_optlen(hp); @@ -132,10 +131,10 @@ static void dump_packet(const struct nf_loginfo *info, const struct ip_auth_hdr *ah; /* Max length: 3 "AH " */ - printk("AH "); + sb_add(m, "AH "); if (fragment) { - printk(")"); + sb_add(m, ")"); return; } @@ -146,13 +145,13 @@ static void dump_packet(const struct nf_loginfo *info, * Max length: 26 "INCOMPLETE [65535 * bytes] )" */ - printk("INCOMPLETE [%u bytes] )", + sb_add(m, "INCOMPLETE [%u bytes] )", skb->len - ptr); return; } /* Length: 15 "SPI=0xF1234567 */ - printk("SPI=0x%x ", ntohl(ah->spi)); + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); } @@ -164,10 +163,10 @@ static void dump_packet(const struct nf_loginfo *info, const struct ip_esp_hdr *eh; /* Max length: 4 "ESP " */ - printk("ESP "); + sb_add(m, "ESP "); if (fragment) { - printk(")"); + sb_add(m, ")"); return; } @@ -177,23 +176,23 @@ static void dump_packet(const struct nf_loginfo *info, eh = skb_header_pointer(skb, ptr, sizeof(_esph), &_esph); if (eh == NULL) { - printk("INCOMPLETE [%u bytes] )", + sb_add(m, "INCOMPLETE [%u bytes] )", skb->len - ptr); return; } /* Length: 16 "SPI=0xF1234567 )" */ - printk("SPI=0x%x )", ntohl(eh->spi) ); + sb_add(m, "SPI=0x%x )", ntohl(eh->spi) ); } return; default: /* Max length: 20 "Unknown Ext Hdr 255" */ - printk("Unknown Ext Hdr %u", currenthdr); + sb_add(m, "Unknown Ext Hdr %u", currenthdr); return; } if (logflags & IP6T_LOG_IPOPT) - printk(") "); + sb_add(m, ") "); currenthdr = hp->nexthdr; ptr += hdrlen; @@ -205,7 +204,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct tcphdr *th; /* Max length: 10 "PROTO=TCP " */ - printk("PROTO=TCP "); + sb_add(m, "PROTO=TCP "); if (fragment) break; @@ -213,40 +212,40 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 25 "INCOMPLETE [65535 bytes] " */ th = skb_header_pointer(skb, ptr, sizeof(_tcph), &_tcph); if (th == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); return; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u ", + sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ if (logflags & IP6T_LOG_TCPSEQ) - printk("SEQ=%u ACK=%u ", + sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); /* Max length: 13 "WINDOW=65535 " */ - printk("WINDOW=%u ", ntohs(th->window)); + sb_add(m, "WINDOW=%u ", ntohs(th->window)); /* Max length: 9 "RES=0x3C " */ - printk("RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); + sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ if (th->cwr) - printk("CWR "); + sb_add(m, "CWR "); if (th->ece) - printk("ECE "); + sb_add(m, "ECE "); if (th->urg) - printk("URG "); + sb_add(m, "URG "); if (th->ack) - printk("ACK "); + sb_add(m, "ACK "); if (th->psh) - printk("PSH "); + sb_add(m, "PSH "); if (th->rst) - printk("RST "); + sb_add(m, "RST "); if (th->syn) - printk("SYN "); + sb_add(m, "SYN "); if (th->fin) - printk("FIN "); + sb_add(m, "FIN "); /* Max length: 11 "URGP=65535 " */ - printk("URGP=%u ", ntohs(th->urg_ptr)); + sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); if ((logflags & IP6T_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { @@ -260,15 +259,15 @@ static void dump_packet(const struct nf_loginfo *info, ptr + sizeof(struct tcphdr), optsize, _opt); if (op == NULL) { - printk("OPT (TRUNCATED)"); + sb_add(m, "OPT (TRUNCATED)"); return; } /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); + sb_add(m, "OPT ("); for (i =0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); } break; } @@ -279,9 +278,9 @@ static void dump_packet(const struct nf_loginfo *info, if (currenthdr == IPPROTO_UDP) /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP " ); + sb_add(m, "PROTO=UDP " ); else /* Max length: 14 "PROTO=UDPLITE " */ - printk("PROTO=UDPLITE "); + sb_add(m, "PROTO=UDPLITE "); if (fragment) break; @@ -289,12 +288,12 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 25 "INCOMPLETE [65535 bytes] " */ uh = skb_header_pointer(skb, ptr, sizeof(_udph), &_udph); if (uh == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); return; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u LEN=%u ", + sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); break; @@ -304,7 +303,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct icmp6hdr *ic; /* Max length: 13 "PROTO=ICMPv6 " */ - printk("PROTO=ICMPv6 "); + sb_add(m, "PROTO=ICMPv6 "); if (fragment) break; @@ -312,18 +311,18 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 25 "INCOMPLETE [65535 bytes] " */ ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); if (ic == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); return; } /* Max length: 18 "TYPE=255 CODE=255 " */ - printk("TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); + sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); switch (ic->icmp6_type) { case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: /* Max length: 19 "ID=65535 SEQ=65535 " */ - printk("ID=%u SEQ=%u ", + sb_add(m, "ID=%u SEQ=%u ", ntohs(ic->icmp6_identifier), ntohs(ic->icmp6_sequence)); break; @@ -334,35 +333,35 @@ static void dump_packet(const struct nf_loginfo *info, case ICMPV6_PARAMPROB: /* Max length: 17 "POINTER=ffffffff " */ - printk("POINTER=%08x ", ntohl(ic->icmp6_pointer)); + sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); /* Fall through */ case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: /* Max length: 3+maxlen */ if (recurse) { - printk("["); - dump_packet(info, skb, ptr + sizeof(_icmp6h), - 0); - printk("] "); + sb_add(m, "["); + dump_packet(m, info, skb, + ptr + sizeof(_icmp6h), 0); + sb_add(m, "] "); } /* Max length: 10 "MTU=65535 " */ if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) - printk("MTU=%u ", ntohl(ic->icmp6_mtu)); + sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); } break; } /* Max length: 10 "PROTO=255 " */ default: - printk("PROTO=%u ", currenthdr); + sb_add(m, "PROTO=%u ", currenthdr); } /* Max length: 15 "UID=4294967295 " */ if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) { read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) - printk("UID=%u GID=%u ", + sb_add(m, "UID=%u GID=%u ", skb->sk->sk_socket->file->f_cred->fsuid, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); @@ -370,10 +369,11 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!recurse && skb->mark) - printk("MARK=0x%x ", skb->mark); + sb_add(m, "MARK=0x%x ", skb->mark); } -static void dump_mac_header(const struct nf_loginfo *info, +static void dump_mac_header(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -387,7 +387,7 @@ static void dump_mac_header(const struct nf_loginfo *info, switch (dev->type) { case ARPHRD_ETHER: - printk("MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, ntohs(eth_hdr(skb)->h_proto)); return; @@ -396,7 +396,7 @@ static void dump_mac_header(const struct nf_loginfo *info, } fallback: - printk("MAC="); + sb_add(m, "MAC="); if (dev->hard_header_len && skb->mac_header != skb->network_header) { const unsigned char *p = skb_mac_header(skb); @@ -408,19 +408,19 @@ fallback: p = NULL; if (p != NULL) { - printk("%02x", *p++); + sb_add(m, "%02x", *p++); for (i = 1; i < len; i++) - printk(":%02x", p[i]); + sb_add(m, ":%02x", p[i]); } - printk(" "); + sb_add(m, " "); if (dev->type == ARPHRD_SIT) { const struct iphdr *iph = (struct iphdr *)skb_mac_header(skb); - printk("TUNNEL=%pI4->%pI4 ", &iph->saddr, &iph->daddr); + sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, &iph->daddr); } } else - printk(" "); + sb_add(m, " "); } static struct nf_loginfo default_loginfo = { @@ -442,22 +442,23 @@ ip6t_log_packet(u_int8_t pf, const struct nf_loginfo *loginfo, const char *prefix) { + struct sbuff *m = sb_open(); + if (!loginfo) loginfo = &default_loginfo; - spin_lock_bh(&log_lock); - printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); + sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + prefix, + in ? in->name : "", + out ? out->name : ""); /* MAC logging for input path only. */ if (in && !out) - dump_mac_header(loginfo, skb); + dump_mac_header(m, loginfo, skb); + + dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); - dump_packet(loginfo, skb, skb_network_offset(skb), 1); - printk("\n"); - spin_unlock_bh(&log_lock); + sb_close(m); } static unsigned int -- cgit v0.10.2 From e55df53dd62c73185af46fb6ffa7074b05ceefc4 Mon Sep 17 00:00:00 2001 From: Nicolas Kaiser Date: Mon, 4 Oct 2010 21:00:42 +0200 Subject: netfilter: remove duplicated include Remove duplicated include. Signed-off-by: Nicolas Kaiser Signed-off-by: Patrick McHardy diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 7a4d66d..9127a3d 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include -- cgit v0.10.2 From f68c53015c5b9aa98ffd87a34009f89bdbbd7160 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Mon, 4 Oct 2010 22:24:12 +0200 Subject: netfilter: unregister nf hooks, matches and targets in the reverse order Since we register nf hooks, matches and targets in order, we'd better unregister them in the reverse order. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 78b505d..8f014f2 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -105,10 +105,8 @@ EXPORT_SYMBOL(nf_register_hooks); void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) { - unsigned int i; - - for (i = 0; i < n; i++) - nf_unregister_hook(®[i]); + while (n-- > 0) + nf_unregister_hook(®[n]); } EXPORT_SYMBOL(nf_unregister_hooks); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index e34622f..8046350 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -116,10 +116,8 @@ EXPORT_SYMBOL(xt_register_targets); void xt_unregister_targets(struct xt_target *target, unsigned int n) { - unsigned int i; - - for (i = 0; i < n; i++) - xt_unregister_target(&target[i]); + while (n-- > 0) + xt_unregister_target(&target[n]); } EXPORT_SYMBOL(xt_unregister_targets); @@ -174,10 +172,8 @@ EXPORT_SYMBOL(xt_register_matches); void xt_unregister_matches(struct xt_match *match, unsigned int n) { - unsigned int i; - - for (i = 0; i < n; i++) - xt_unregister_match(&match[i]); + while (n-- > 0) + xt_unregister_match(&match[n]); } EXPORT_SYMBOL(xt_unregister_matches); -- cgit v0.10.2 From eecc545856c8a0f27783a440d25f4ceaa1f95ce8 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 4 Oct 2010 23:24:21 +0200 Subject: netfilter: add missing xt_log.h file Forgot to add xt_log.h in commit a8defca0 (netfilter: ipt_LOG: add bufferisation to call printk() once) Signed-off-by: Patrick McHardy diff --git a/include/net/netfilter/xt_log.h b/include/net/netfilter/xt_log.h new file mode 100644 index 0000000..0dfb34a --- /dev/null +++ b/include/net/netfilter/xt_log.h @@ -0,0 +1,54 @@ +#define S_SIZE (1024 - (sizeof(unsigned int) + 1)) + +struct sbuff { + unsigned int count; + char buf[S_SIZE + 1]; +}; +static struct sbuff emergency, *emergency_ptr = &emergency; + +static int sb_add(struct sbuff *m, const char *f, ...) +{ + va_list args; + int len; + + if (likely(m->count < S_SIZE)) { + va_start(args, f); + len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); + va_end(args); + if (likely(m->count + len < S_SIZE)) { + m->count += len; + return 0; + } + } + m->count = S_SIZE; + printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); + return -1; +} + +static struct sbuff *sb_open(void) +{ + struct sbuff *m = kmalloc(sizeof(*m), GFP_ATOMIC); + + if (unlikely(!m)) { + local_bh_disable(); + do { + m = xchg(&emergency_ptr, NULL); + } while (!m); + } + m->count = 0; + return m; +} + +static void sb_close(struct sbuff *m) +{ + m->buf[m->count] = 0; + printk("%s\n", m->buf); + + if (likely(m != &emergency)) + kfree(m); + else { + xchg(&emergency_ptr, m); + local_bh_enable(); + } +} + -- cgit v0.10.2 From 12b00c2c025b8af697d9a022ea2e928cad889ef1 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 15:56:56 +0200 Subject: netfilter: xtables: resolve indirect macros 1/3 Many of the used macros are just there for userspace compatibility. Substitute the in-kernel code to directly use the terminal macro and stuff the defines into #ifndef __KERNEL__ sections. Signed-off-by: Jan Engelhardt diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index e9948c0..8193860 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -21,8 +21,10 @@ #include +#ifndef __KERNEL__ #define ARPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN #define ARPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN +#endif #define ARPT_DEV_ADDR_LEN_MAX 16 @@ -134,7 +136,7 @@ struct arpt_entry /* The argument to ARPT_SO_GET_INFO */ struct arpt_getinfo { /* Which table: caller fills this in. */ - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* Kernel fills these in. */ /* Which hook entry points are valid: bitmask */ @@ -156,7 +158,7 @@ struct arpt_getinfo { /* The argument to ARPT_SO_SET_REPLACE. */ struct arpt_replace { /* Which table. */ - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* Which hook entry points are valid: bitmask. You can't change this. */ @@ -191,7 +193,7 @@ struct arpt_replace { /* The argument to ARPT_SO_GET_ENTRIES. */ struct arpt_get_entries { /* Which table: user fills this in. */ - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* User fills this in: total entry size. */ unsigned int size; @@ -230,7 +232,7 @@ struct arpt_standard { struct arpt_error_target { struct arpt_entry_target target; - char errorname[ARPT_FUNCTION_MAXNAMELEN]; + char errorname[XT_FUNCTION_MAXNAMELEN]; }; struct arpt_error { diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 704a7b6..1b7cdf1 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -27,12 +27,14 @@ #include +#ifndef __KERNEL__ #define IPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN #define IPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN #define ipt_match xt_match #define ipt_target xt_target #define ipt_table xt_table #define ipt_get_revision xt_get_revision +#endif /* Yes, Virginia, you have to zero the padding. */ struct ipt_ip { @@ -146,7 +148,7 @@ struct ipt_icmp { /* The argument to IPT_SO_GET_INFO */ struct ipt_getinfo { /* Which table: caller fills this in. */ - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* Kernel fills these in. */ /* Which hook entry points are valid: bitmask */ @@ -168,7 +170,7 @@ struct ipt_getinfo { /* The argument to IPT_SO_SET_REPLACE. */ struct ipt_replace { /* Which table. */ - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* Which hook entry points are valid: bitmask. You can't change this. */ @@ -202,7 +204,7 @@ struct ipt_replace { /* The argument to IPT_SO_GET_ENTRIES. */ struct ipt_get_entries { /* Which table: user fills this in. */ - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* User fills this in: total entry size. */ unsigned int size; @@ -254,7 +256,7 @@ struct ipt_standard { struct ipt_error_target { struct ipt_entry_target target; - char errorname[IPT_FUNCTION_MAXNAMELEN]; + char errorname[XT_FUNCTION_MAXNAMELEN]; }; struct ipt_error { diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 18442ff..abe31d0 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -27,13 +27,14 @@ #include +#ifndef __KERNEL__ #define IP6T_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN #define IP6T_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN - #define ip6t_match xt_match #define ip6t_target xt_target #define ip6t_table xt_table #define ip6t_get_revision xt_get_revision +#endif /* Yes, Virginia, you have to zero the padding. */ struct ip6t_ip6 { @@ -117,7 +118,7 @@ struct ip6t_standard { struct ip6t_error_target { struct ip6t_entry_target target; - char errorname[IP6T_FUNCTION_MAXNAMELEN]; + char errorname[XT_FUNCTION_MAXNAMELEN]; }; struct ip6t_error { @@ -203,7 +204,7 @@ struct ip6t_icmp { /* The argument to IP6T_SO_GET_INFO */ struct ip6t_getinfo { /* Which table: caller fills this in. */ - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* Kernel fills these in. */ /* Which hook entry points are valid: bitmask */ @@ -225,7 +226,7 @@ struct ip6t_getinfo { /* The argument to IP6T_SO_SET_REPLACE. */ struct ip6t_replace { /* Which table. */ - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* Which hook entry points are valid: bitmask. You can't change this. */ @@ -259,7 +260,7 @@ struct ip6t_replace { /* The argument to IP6T_SO_GET_ENTRIES. */ struct ip6t_get_entries { /* Which table: user fills this in. */ - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; /* User fills this in: total entry size. */ unsigned int size; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e8f4f9a..e427a9e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -895,7 +895,7 @@ static int compat_table_info(const struct xt_table_info *info, static int get_info(struct net *net, void __user *user, const int *len, int compat) { - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; @@ -908,7 +908,7 @@ static int get_info(struct net *net, void __user *user, if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; - name[ARPT_TABLE_MAXNAMELEN-1] = '\0'; + name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT if (compat) xt_compat_lock(NFPROTO_ARP); @@ -1474,7 +1474,7 @@ out_unlock: } struct compat_arpt_replace { - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; @@ -1628,7 +1628,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, } struct compat_arpt_get_entries { - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_arpt_entry entrytable[0]; }; @@ -1840,7 +1840,7 @@ static struct xt_target arpt_builtin_tg[] __read_mostly = { { .name = ARPT_ERROR_TARGET, .target = arpt_error, - .targetsize = ARPT_FUNCTION_MAXNAMELEN, + .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_ARP, }, }; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d163f2e..2efd41b 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1092,7 +1092,7 @@ static int compat_table_info(const struct xt_table_info *info, static int get_info(struct net *net, void __user *user, const int *len, int compat) { - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; @@ -1105,7 +1105,7 @@ static int get_info(struct net *net, void __user *user, if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; - name[IPT_TABLE_MAXNAMELEN-1] = '\0'; + name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT if (compat) xt_compat_lock(AF_INET); @@ -1400,7 +1400,7 @@ do_add_counters(struct net *net, const void __user *user, #ifdef CONFIG_COMPAT struct compat_ipt_replace { - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; @@ -1884,7 +1884,7 @@ compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, } struct compat_ipt_get_entries { - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ipt_entry entrytable[0]; }; @@ -2039,7 +2039,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { - struct ipt_get_revision rev; + struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { @@ -2188,7 +2188,7 @@ static struct xt_target ipt_builtin_tg[] __read_mostly = { { .name = IPT_ERROR_TARGET, .target = ipt_error, - .targetsize = IPT_FUNCTION_MAXNAMELEN, + .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV4, }, }; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 8e754be..4b973e1 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1105,7 +1105,7 @@ static int compat_table_info(const struct xt_table_info *info, static int get_info(struct net *net, void __user *user, const int *len, int compat) { - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; @@ -1118,7 +1118,7 @@ static int get_info(struct net *net, void __user *user, if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; - name[IP6T_TABLE_MAXNAMELEN-1] = '\0'; + name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT if (compat) xt_compat_lock(AF_INET6); @@ -1415,7 +1415,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, #ifdef CONFIG_COMPAT struct compat_ip6t_replace { - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; @@ -1899,7 +1899,7 @@ compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, } struct compat_ip6t_get_entries { - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[0]; }; @@ -2054,7 +2054,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { - struct ip6t_get_revision rev; + struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { @@ -2203,7 +2203,7 @@ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { .name = IP6T_ERROR_TARGET, .target = ip6t_error, - .targetsize = IP6T_FUNCTION_MAXNAMELEN, + .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; -- cgit v0.10.2 From 87a2e70db62fec7348c6e5545eb7b7650c33d81b Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 16:11:22 +0200 Subject: netfilter: xtables: resolve indirect macros 2/3 Signed-off-by: Jan Engelhardt diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 8193860..7e193c9 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -24,6 +24,8 @@ #ifndef __KERNEL__ #define ARPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN #define ARPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN +#define arpt_entry_target xt_entry_target +#define arpt_standard_target xt_standard_target #endif #define ARPT_DEV_ADDR_LEN_MAX 16 @@ -65,9 +67,6 @@ struct arpt_arp { u_int16_t invflags; }; -#define arpt_entry_target xt_entry_target -#define arpt_standard_target xt_standard_target - /* Values for "flag" field in struct arpt_ip (general arp structure). * No flags defined yet. */ @@ -208,7 +207,7 @@ struct arpt_get_entries { #define ARPT_ERROR_TARGET XT_ERROR_TARGET /* Helper functions */ -static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e) +static __inline__ struct xt_entry_target *arpt_get_target(struct arpt_entry *e) { return (void *)e + e->target_offset; } @@ -227,11 +226,11 @@ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e /* Standard entry. */ struct arpt_standard { struct arpt_entry entry; - struct arpt_standard_target target; + struct xt_standard_target target; }; struct arpt_error_target { - struct arpt_entry_target target; + struct xt_entry_target target; char errorname[XT_FUNCTION_MAXNAMELEN]; }; @@ -250,7 +249,7 @@ struct arpt_error { { \ .entry = ARPT_ENTRY_INIT(sizeof(struct arpt_standard)), \ .target = XT_TARGET_INIT(ARPT_STANDARD_TARGET, \ - sizeof(struct arpt_standard_target)), \ + sizeof(struct xt_standard_target)), \ .target.verdict = -(__verdict) - 1, \ } @@ -287,7 +286,7 @@ struct compat_arpt_entry { unsigned char elems[0]; }; -static inline struct arpt_entry_target * +static inline struct xt_entry_target * compat_arpt_get_target(struct compat_arpt_entry *e) { return (void *)e + e->target_offset; diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 1b7cdf1..ec50691 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -34,6 +34,10 @@ #define ipt_target xt_target #define ipt_table xt_table #define ipt_get_revision xt_get_revision +#define ipt_entry_match xt_entry_match +#define ipt_entry_target xt_entry_target +#define ipt_standard_target xt_standard_target +#define ipt_counters xt_counters #endif /* Yes, Virginia, you have to zero the padding. */ @@ -54,12 +58,6 @@ struct ipt_ip { u_int8_t invflags; }; -#define ipt_entry_match xt_entry_match -#define ipt_entry_target xt_entry_target -#define ipt_standard_target xt_standard_target - -#define ipt_counters xt_counters - /* Values for "flag" field in struct ipt_ip (general ip structure). */ #define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */ #define IPT_F_GOTO 0x02 /* Set if jump is a goto */ @@ -219,7 +217,7 @@ struct ipt_get_entries { #define IPT_ERROR_TARGET XT_ERROR_TARGET /* Helper functions */ -static __inline__ struct ipt_entry_target * +static __inline__ struct xt_entry_target * ipt_get_target(struct ipt_entry *e) { return (void *)e + e->target_offset; @@ -251,11 +249,11 @@ extern void ipt_unregister_table(struct net *net, struct xt_table *table); /* Standard entry. */ struct ipt_standard { struct ipt_entry entry; - struct ipt_standard_target target; + struct xt_standard_target target; }; struct ipt_error_target { - struct ipt_entry_target target; + struct xt_entry_target target; char errorname[XT_FUNCTION_MAXNAMELEN]; }; @@ -309,7 +307,7 @@ struct compat_ipt_entry { }; /* Helper functions */ -static inline struct ipt_entry_target * +static inline struct xt_entry_target * compat_ipt_get_target(struct compat_ipt_entry *e) { return (void *)e + e->target_offset; diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index abe31d0..40d11fa 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -34,6 +34,10 @@ #define ip6t_target xt_target #define ip6t_table xt_table #define ip6t_get_revision xt_get_revision +#define ip6t_entry_match xt_entry_match +#define ip6t_entry_target xt_entry_target +#define ip6t_standard_target xt_standard_target +#define ip6t_counters xt_counters #endif /* Yes, Virginia, you have to zero the padding. */ @@ -63,12 +67,6 @@ struct ip6t_ip6 { u_int8_t invflags; }; -#define ip6t_entry_match xt_entry_match -#define ip6t_entry_target xt_entry_target -#define ip6t_standard_target xt_standard_target - -#define ip6t_counters xt_counters - /* Values for "flag" field in struct ip6t_ip6 (general ip6 structure). */ #define IP6T_F_PROTO 0x01 /* Set if rule cares about upper protocols */ @@ -113,11 +111,11 @@ struct ip6t_entry { /* Standard entry */ struct ip6t_standard { struct ip6t_entry entry; - struct ip6t_standard_target target; + struct xt_standard_target target; }; struct ip6t_error_target { - struct ip6t_entry_target target; + struct xt_entry_target target; char errorname[XT_FUNCTION_MAXNAMELEN]; }; @@ -136,7 +134,7 @@ struct ip6t_error { { \ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_standard)), \ .target = XT_TARGET_INIT(IP6T_STANDARD_TARGET, \ - sizeof(struct ip6t_standard_target)), \ + sizeof(struct xt_standard_target)), \ .target.verdict = -(__verdict) - 1, \ } @@ -275,7 +273,7 @@ struct ip6t_get_entries { #define IP6T_ERROR_TARGET XT_ERROR_TARGET /* Helper functions */ -static __inline__ struct ip6t_entry_target * +static __inline__ struct xt_entry_target * ip6t_get_target(struct ip6t_entry *e) { return (void *)e + e->target_offset; @@ -332,7 +330,7 @@ struct compat_ip6t_entry { unsigned char elems[0]; }; -static inline struct ip6t_entry_target * +static inline struct xt_entry_target * compat_ip6t_get_target(struct compat_ip6t_entry *e) { return (void *)e + e->target_offset; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e427a9e..ed178cb 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -228,7 +228,7 @@ arpt_error(struct sk_buff *skb, const struct xt_action_param *par) return NF_DROP; } -static inline const struct arpt_entry_target * +static inline const struct xt_entry_target * arpt_get_target_c(const struct arpt_entry *e) { return arpt_get_target((struct arpt_entry *)e); @@ -282,7 +282,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, arp = arp_hdr(skb); do { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { e = arpt_next_entry(e); @@ -297,7 +297,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, if (!t->u.kernel.target->target) { int v; - v = ((struct arpt_standard_target *)t)->verdict; + v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != ARPT_RETURN) { @@ -377,7 +377,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - const struct arpt_standard_target *t + const struct xt_standard_target *t = (void *)arpt_get_target_c(e); int visited = e->comefrom & (1 << hook); @@ -464,14 +464,14 @@ static int mark_source_chains(const struct xt_table_info *newinfo, static inline int check_entry(const struct arpt_entry *e, const char *name) { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; if (!arp_checkentry(&e->arp)) { duprintf("arp_tables: arp check failed %p %s.\n", e, name); return -EINVAL; } - if (e->target_offset + sizeof(struct arpt_entry_target) > e->next_offset) + if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; t = arpt_get_target_c(e); @@ -483,7 +483,7 @@ static inline int check_entry(const struct arpt_entry *e, const char *name) static inline int check_target(struct arpt_entry *e, const char *name) { - struct arpt_entry_target *t = arpt_get_target(e); + struct xt_entry_target *t = arpt_get_target(e); int ret; struct xt_tgchk_param par = { .table = name, @@ -506,7 +506,7 @@ static inline int check_target(struct arpt_entry *e, const char *name) static inline int find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; int ret; @@ -536,7 +536,7 @@ out: static bool check_underflow(const struct arpt_entry *e) { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(&e->arp)) @@ -544,7 +544,7 @@ static bool check_underflow(const struct arpt_entry *e) t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; - verdict = ((struct arpt_standard_target *)t)->verdict; + verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } @@ -566,7 +566,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, } if (e->next_offset - < sizeof(struct arpt_entry) + sizeof(struct arpt_entry_target)) { + < sizeof(struct arpt_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; @@ -598,7 +598,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, static inline void cleanup_entry(struct arpt_entry *e) { struct xt_tgdtor_param par; - struct arpt_entry_target *t; + struct xt_entry_target *t; t = arpt_get_target(e); par.target = t->u.kernel.target; @@ -794,7 +794,7 @@ static int copy_entries_to_user(unsigned int total_size, /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ - const struct arpt_entry_target *t; + const struct xt_entry_target *t; e = (struct arpt_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -807,7 +807,7 @@ static int copy_entries_to_user(unsigned int total_size, t = arpt_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct arpt_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -844,7 +844,7 @@ static int compat_calc_entry(const struct arpt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; @@ -1204,7 +1204,7 @@ static int do_add_counters(struct net *net, const void __user *user, #ifdef CONFIG_COMPAT static inline void compat_release_entry(struct compat_arpt_entry *e) { - struct arpt_entry_target *t; + struct xt_entry_target *t; t = compat_arpt_get_target(e); module_put(t->u.kernel.target->me); @@ -1220,7 +1220,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, const unsigned int *underflows, const char *name) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; int ret, off, h; @@ -1288,7 +1288,7 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, unsigned int *size, const char *name, struct xt_table_info *newinfo, unsigned char *base) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; struct arpt_entry *de; unsigned int origsize; @@ -1567,7 +1567,7 @@ static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr, struct xt_counters *counters, unsigned int i) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct compat_arpt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2efd41b..cb10888 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -186,7 +186,7 @@ static inline bool unconditional(const struct ipt_ip *ip) } /* for const-correctness */ -static inline const struct ipt_entry_target * +static inline const struct xt_entry_target * ipt_get_target_c(const struct ipt_entry *e) { return ipt_get_target((struct ipt_entry *)e); @@ -230,7 +230,7 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - const struct ipt_standard_target *t = (void *)ipt_get_target_c(s); + const struct xt_standard_target *t = (void *)ipt_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, IPT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ @@ -346,7 +346,7 @@ ipt_do_table(struct sk_buff *skb, get_entry(table_base, private->underflow[hook])); do { - const struct ipt_entry_target *t; + const struct xt_entry_target *t; const struct xt_entry_match *ematch; IP_NF_ASSERT(e); @@ -380,7 +380,7 @@ ipt_do_table(struct sk_buff *skb, if (!t->u.kernel.target->target) { int v; - v = ((struct ipt_standard_target *)t)->verdict; + v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != IPT_RETURN) { @@ -461,7 +461,7 @@ mark_source_chains(const struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - const struct ipt_standard_target *t + const struct xt_standard_target *t = (void *)ipt_get_target_c(e); int visited = e->comefrom & (1 << hook); @@ -552,7 +552,7 @@ mark_source_chains(const struct xt_table_info *newinfo, return 1; } -static void cleanup_match(struct ipt_entry_match *m, struct net *net) +static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; @@ -568,14 +568,14 @@ static void cleanup_match(struct ipt_entry_match *m, struct net *net) static int check_entry(const struct ipt_entry *e, const char *name) { - const struct ipt_entry_target *t; + const struct xt_entry_target *t; if (!ip_checkentry(&e->ip)) { duprintf("ip check failed %p %s.\n", e, par->match->name); return -EINVAL; } - if (e->target_offset + sizeof(struct ipt_entry_target) > + if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; @@ -587,7 +587,7 @@ check_entry(const struct ipt_entry *e, const char *name) } static int -check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) +check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; int ret; @@ -605,7 +605,7 @@ check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) } static int -find_check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) +find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; @@ -630,7 +630,7 @@ err: static int check_target(struct ipt_entry *e, struct net *net, const char *name) { - struct ipt_entry_target *t = ipt_get_target(e); + struct xt_entry_target *t = ipt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, @@ -656,7 +656,7 @@ static int find_check_entry(struct ipt_entry *e, struct net *net, const char *name, unsigned int size) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; @@ -707,7 +707,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, static bool check_underflow(const struct ipt_entry *e) { - const struct ipt_entry_target *t; + const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(&e->ip)) @@ -715,7 +715,7 @@ static bool check_underflow(const struct ipt_entry *e) t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; - verdict = ((struct ipt_standard_target *)t)->verdict; + verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } @@ -738,7 +738,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, } if (e->next_offset - < sizeof(struct ipt_entry) + sizeof(struct ipt_entry_target)) { + < sizeof(struct ipt_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; @@ -771,7 +771,7 @@ static void cleanup_entry(struct ipt_entry *e, struct net *net) { struct xt_tgdtor_param par; - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -972,8 +972,8 @@ copy_entries_to_user(unsigned int total_size, /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; - const struct ipt_entry_match *m; - const struct ipt_entry_target *t; + const struct xt_entry_match *m; + const struct xt_entry_target *t; e = (struct ipt_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -990,7 +990,7 @@ copy_entries_to_user(unsigned int total_size, m = (void *)e + i; if (copy_to_user(userptr + off + i - + offsetof(struct ipt_entry_match, + + offsetof(struct xt_entry_match, u.user.name), m->u.kernel.match->name, strlen(m->u.kernel.match->name)+1) @@ -1002,7 +1002,7 @@ copy_entries_to_user(unsigned int total_size, t = ipt_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct ipt_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -1040,7 +1040,7 @@ static int compat_calc_entry(const struct ipt_entry *e, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; - const struct ipt_entry_target *t; + const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; @@ -1407,7 +1407,7 @@ struct compat_ipt_replace { u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; - compat_uptr_t counters; /* struct ipt_counters * */ + compat_uptr_t counters; /* struct xt_counters * */ struct compat_ipt_entry entries[0]; }; @@ -1416,7 +1416,7 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct compat_ipt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; @@ -1451,7 +1451,7 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, } static int -compat_find_calc_match(struct ipt_entry_match *m, +compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ipt_ip *ip, unsigned int hookmask, @@ -1473,7 +1473,7 @@ compat_find_calc_match(struct ipt_entry_match *m, static void compat_release_entry(struct compat_ipt_entry *e) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -1494,7 +1494,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, const char *name) { struct xt_entry_match *ematch; - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; @@ -1576,7 +1576,7 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, unsigned int *size, const char *name, struct xt_table_info *newinfo, unsigned char *base) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; struct ipt_entry *de; unsigned int origsize; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 4b973e1..c7334c1 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -215,7 +215,7 @@ static inline bool unconditional(const struct ip6t_ip6 *ipv6) return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; } -static inline const struct ip6t_entry_target * +static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); @@ -260,7 +260,7 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - const struct ip6t_standard_target *t = (void *)ip6t_get_target_c(s); + const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ @@ -369,7 +369,7 @@ ip6t_do_table(struct sk_buff *skb, e = get_entry(table_base, private->hook_entry[hook]); do { - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; const struct xt_entry_match *ematch; IP_NF_ASSERT(e); @@ -403,7 +403,7 @@ ip6t_do_table(struct sk_buff *skb, if (!t->u.kernel.target->target) { int v; - v = ((struct ip6t_standard_target *)t)->verdict; + v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != IP6T_RETURN) { @@ -474,7 +474,7 @@ mark_source_chains(const struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - const struct ip6t_standard_target *t + const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); @@ -565,7 +565,7 @@ mark_source_chains(const struct xt_table_info *newinfo, return 1; } -static void cleanup_match(struct ip6t_entry_match *m, struct net *net) +static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; @@ -581,14 +581,14 @@ static void cleanup_match(struct ip6t_entry_match *m, struct net *net) static int check_entry(const struct ip6t_entry *e, const char *name) { - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; if (!ip6_checkentry(&e->ipv6)) { duprintf("ip_tables: ip check failed %p %s.\n", e, name); return -EINVAL; } - if (e->target_offset + sizeof(struct ip6t_entry_target) > + if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; @@ -599,7 +599,7 @@ check_entry(const struct ip6t_entry *e, const char *name) return 0; } -static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) +static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; int ret; @@ -618,7 +618,7 @@ static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) } static int -find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) +find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; @@ -643,7 +643,7 @@ err: static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { - struct ip6t_entry_target *t = ip6t_get_target(e); + struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, @@ -670,7 +670,7 @@ static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; @@ -721,7 +721,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, static bool check_underflow(const struct ip6t_entry *e) { - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(&e->ipv6)) @@ -729,7 +729,7 @@ static bool check_underflow(const struct ip6t_entry *e) t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; - verdict = ((struct ip6t_standard_target *)t)->verdict; + verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } @@ -752,7 +752,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, } if (e->next_offset - < sizeof(struct ip6t_entry) + sizeof(struct ip6t_entry_target)) { + < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; @@ -784,7 +784,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -985,8 +985,8 @@ copy_entries_to_user(unsigned int total_size, /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; - const struct ip6t_entry_match *m; - const struct ip6t_entry_target *t; + const struct xt_entry_match *m; + const struct xt_entry_target *t; e = (struct ip6t_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -1003,7 +1003,7 @@ copy_entries_to_user(unsigned int total_size, m = (void *)e + i; if (copy_to_user(userptr + off + i - + offsetof(struct ip6t_entry_match, + + offsetof(struct xt_entry_match, u.user.name), m->u.kernel.match->name, strlen(m->u.kernel.match->name)+1) @@ -1015,7 +1015,7 @@ copy_entries_to_user(unsigned int total_size, t = ip6t_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct ip6t_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -1053,7 +1053,7 @@ static int compat_calc_entry(const struct ip6t_entry *e, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; @@ -1422,7 +1422,7 @@ struct compat_ip6t_replace { u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; - compat_uptr_t counters; /* struct ip6t_counters * */ + compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[0]; }; @@ -1431,7 +1431,7 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; @@ -1466,7 +1466,7 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, } static int -compat_find_calc_match(struct ip6t_entry_match *m, +compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ip6t_ip6 *ipv6, unsigned int hookmask, @@ -1488,7 +1488,7 @@ compat_find_calc_match(struct ip6t_entry_match *m, static void compat_release_entry(struct compat_ip6t_entry *e) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -1509,7 +1509,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, const char *name) { struct xt_entry_match *ematch; - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; @@ -1591,7 +1591,7 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, const char *name, struct xt_table_info *newinfo, unsigned char *base) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; struct ip6t_entry *de; unsigned int origsize; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index c7e59e6..f6d464f 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -39,7 +39,7 @@ static struct tcf_hashinfo ipt_hash_info = { .lock = &ipt_lock, }; -static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) +static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) { struct xt_tgchk_param par; struct xt_target *target; @@ -66,7 +66,7 @@ static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int return 0; } -static void ipt_destroy_target(struct ipt_entry_target *t) +static void ipt_destroy_target(struct xt_entry_target *t) { struct xt_tgdtor_param par = { .target = t->u.kernel.target, @@ -99,7 +99,7 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ }, [TCA_IPT_HOOK] = { .type = NLA_U32 }, [TCA_IPT_INDEX] = { .type = NLA_U32 }, - [TCA_IPT_TARG] = { .len = sizeof(struct ipt_entry_target) }, + [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, @@ -108,7 +108,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; struct tcf_common *pc; - struct ipt_entry_target *td, *t; + struct xt_entry_target *td, *t; char *tname; int ret = 0, err; u32 hook = 0; @@ -126,7 +126,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, if (tb[TCA_IPT_TARG] == NULL) return -EINVAL; - td = (struct ipt_entry_target *)nla_data(tb[TCA_IPT_TARG]); + td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) return -EINVAL; @@ -249,7 +249,7 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int { unsigned char *b = skb_tail_pointer(skb); struct tcf_ipt *ipt = a->priv; - struct ipt_entry_target *t; + struct xt_entry_target *t; struct tcf_t tm; struct tc_cnt c; -- cgit v0.10.2 From 243bf6e29eef642de0ff62f1ebf58bc2396d6d6e Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 16:28:00 +0200 Subject: netfilter: xtables: resolve indirect macros 3/3 diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 7e193c9..6e2341a 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -26,6 +26,14 @@ #define ARPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN #define arpt_entry_target xt_entry_target #define arpt_standard_target xt_standard_target +#define ARPT_CONTINUE XT_CONTINUE +#define ARPT_RETURN XT_RETURN +#define arpt_counters_info xt_counters_info +#define arpt_counters xt_counters +#define ARPT_STANDARD_TARGET XT_STANDARD_TARGET +#define ARPT_ERROR_TARGET XT_ERROR_TARGET +#define ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct arpt_entry, entries, size, fn, ## args) #endif #define ARPT_DEV_ADDR_LEN_MAX 16 @@ -126,12 +134,6 @@ struct arpt_entry #define ARPT_SO_GET_REVISION_TARGET (ARPT_BASE_CTL + 3) #define ARPT_SO_GET_MAX (ARPT_SO_GET_REVISION_TARGET) -/* CONTINUE verdict for targets */ -#define ARPT_CONTINUE XT_CONTINUE - -/* For standard target */ -#define ARPT_RETURN XT_RETURN - /* The argument to ARPT_SO_GET_INFO */ struct arpt_getinfo { /* Which table: caller fills this in. */ @@ -185,10 +187,6 @@ struct arpt_replace { struct arpt_entry entries[0]; }; -/* The argument to ARPT_SO_ADD_COUNTERS. */ -#define arpt_counters_info xt_counters_info -#define arpt_counters xt_counters - /* The argument to ARPT_SO_GET_ENTRIES. */ struct arpt_get_entries { /* Which table: user fills this in. */ @@ -201,23 +199,12 @@ struct arpt_get_entries { struct arpt_entry entrytable[0]; }; -/* Standard return verdict, or do jump. */ -#define ARPT_STANDARD_TARGET XT_STANDARD_TARGET -/* Error verdict. */ -#define ARPT_ERROR_TARGET XT_ERROR_TARGET - /* Helper functions */ static __inline__ struct xt_entry_target *arpt_get_target(struct arpt_entry *e) { return (void *)e + e->target_offset; } -#ifndef __KERNEL__ -/* fn returns 0 to continue iteration */ -#define ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ - XT_ENTRY_ITERATE(struct arpt_entry, entries, size, fn, ## args) -#endif - /* * Main firewall chains definitions and global var's definitions. */ @@ -248,7 +235,7 @@ struct arpt_error { #define ARPT_STANDARD_INIT(__verdict) \ { \ .entry = ARPT_ENTRY_INIT(sizeof(struct arpt_standard)), \ - .target = XT_TARGET_INIT(ARPT_STANDARD_TARGET, \ + .target = XT_TARGET_INIT(XT_STANDARD_TARGET, \ sizeof(struct xt_standard_target)), \ .target.verdict = -(__verdict) - 1, \ } @@ -256,7 +243,7 @@ struct arpt_error { #define ARPT_ERROR_INIT \ { \ .entry = ARPT_ENTRY_INIT(sizeof(struct arpt_error)), \ - .target = XT_TARGET_INIT(ARPT_ERROR_TARGET, \ + .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ sizeof(struct arpt_error_target)), \ .target.errorname = "ERROR", \ } diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index ec50691..ee54b3b 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -38,6 +38,36 @@ #define ipt_entry_target xt_entry_target #define ipt_standard_target xt_standard_target #define ipt_counters xt_counters +#define IPT_CONTINUE XT_CONTINUE +#define IPT_RETURN XT_RETURN + +/* This group is older than old (iptables < v1.4.0-rc1~89) */ +#include +#define ipt_udp xt_udp +#define ipt_tcp xt_tcp +#define IPT_TCP_INV_SRCPT XT_TCP_INV_SRCPT +#define IPT_TCP_INV_DSTPT XT_TCP_INV_DSTPT +#define IPT_TCP_INV_FLAGS XT_TCP_INV_FLAGS +#define IPT_TCP_INV_OPTION XT_TCP_INV_OPTION +#define IPT_TCP_INV_MASK XT_TCP_INV_MASK +#define IPT_UDP_INV_SRCPT XT_UDP_INV_SRCPT +#define IPT_UDP_INV_DSTPT XT_UDP_INV_DSTPT +#define IPT_UDP_INV_MASK XT_UDP_INV_MASK + +/* The argument to IPT_SO_ADD_COUNTERS. */ +#define ipt_counters_info xt_counters_info +/* Standard return verdict, or do jump. */ +#define IPT_STANDARD_TARGET XT_STANDARD_TARGET +/* Error verdict. */ +#define IPT_ERROR_TARGET XT_ERROR_TARGET + +/* fn returns 0 to continue iteration */ +#define IPT_MATCH_ITERATE(e, fn, args...) \ + XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args) + +/* fn returns 0 to continue iteration */ +#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) #endif /* Yes, Virginia, you have to zero the padding. */ @@ -116,23 +146,6 @@ struct ipt_entry { #define IPT_SO_GET_REVISION_TARGET (IPT_BASE_CTL + 3) #define IPT_SO_GET_MAX IPT_SO_GET_REVISION_TARGET -#define IPT_CONTINUE XT_CONTINUE -#define IPT_RETURN XT_RETURN - -#include -#define ipt_udp xt_udp -#define ipt_tcp xt_tcp - -#define IPT_TCP_INV_SRCPT XT_TCP_INV_SRCPT -#define IPT_TCP_INV_DSTPT XT_TCP_INV_DSTPT -#define IPT_TCP_INV_FLAGS XT_TCP_INV_FLAGS -#define IPT_TCP_INV_OPTION XT_TCP_INV_OPTION -#define IPT_TCP_INV_MASK XT_TCP_INV_MASK - -#define IPT_UDP_INV_SRCPT XT_UDP_INV_SRCPT -#define IPT_UDP_INV_DSTPT XT_UDP_INV_DSTPT -#define IPT_UDP_INV_MASK XT_UDP_INV_MASK - /* ICMP matching stuff */ struct ipt_icmp { u_int8_t type; /* type to match */ @@ -196,9 +209,6 @@ struct ipt_replace { struct ipt_entry entries[0]; }; -/* The argument to IPT_SO_ADD_COUNTERS. */ -#define ipt_counters_info xt_counters_info - /* The argument to IPT_SO_GET_ENTRIES. */ struct ipt_get_entries { /* Which table: user fills this in. */ @@ -211,11 +221,6 @@ struct ipt_get_entries { struct ipt_entry entrytable[0]; }; -/* Standard return verdict, or do jump. */ -#define IPT_STANDARD_TARGET XT_STANDARD_TARGET -/* Error verdict. */ -#define IPT_ERROR_TARGET XT_ERROR_TARGET - /* Helper functions */ static __inline__ struct xt_entry_target * ipt_get_target(struct ipt_entry *e) @@ -223,16 +228,6 @@ ipt_get_target(struct ipt_entry *e) return (void *)e + e->target_offset; } -#ifndef __KERNEL__ -/* fn returns 0 to continue iteration */ -#define IPT_MATCH_ITERATE(e, fn, args...) \ - XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args) - -/* fn returns 0 to continue iteration */ -#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ - XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) -#endif - /* * Main firewall chains definitions and global var's definitions. */ @@ -271,7 +266,7 @@ struct ipt_error { #define IPT_STANDARD_INIT(__verdict) \ { \ .entry = IPT_ENTRY_INIT(sizeof(struct ipt_standard)), \ - .target = XT_TARGET_INIT(IPT_STANDARD_TARGET, \ + .target = XT_TARGET_INIT(XT_STANDARD_TARGET, \ sizeof(struct xt_standard_target)), \ .target.verdict = -(__verdict) - 1, \ } @@ -279,7 +274,7 @@ struct ipt_error { #define IPT_ERROR_INIT \ { \ .entry = IPT_ENTRY_INIT(sizeof(struct ipt_error)), \ - .target = XT_TARGET_INIT(IPT_ERROR_TARGET, \ + .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ sizeof(struct ipt_error_target)), \ .target.errorname = "ERROR", \ } diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 40d11fa..ac2b411 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -38,6 +38,29 @@ #define ip6t_entry_target xt_entry_target #define ip6t_standard_target xt_standard_target #define ip6t_counters xt_counters +#define IP6T_CONTINUE XT_CONTINUE +#define IP6T_RETURN XT_RETURN + +/* Pre-iptables-1.4.0 */ +#include +#define ip6t_tcp xt_tcp +#define ip6t_udp xt_udp +#define IP6T_TCP_INV_SRCPT XT_TCP_INV_SRCPT +#define IP6T_TCP_INV_DSTPT XT_TCP_INV_DSTPT +#define IP6T_TCP_INV_FLAGS XT_TCP_INV_FLAGS +#define IP6T_TCP_INV_OPTION XT_TCP_INV_OPTION +#define IP6T_TCP_INV_MASK XT_TCP_INV_MASK +#define IP6T_UDP_INV_SRCPT XT_UDP_INV_SRCPT +#define IP6T_UDP_INV_DSTPT XT_UDP_INV_DSTPT +#define IP6T_UDP_INV_MASK XT_UDP_INV_MASK + +#define ip6t_counters_info xt_counters_info +#define IP6T_STANDARD_TARGET XT_STANDARD_TARGET +#define IP6T_ERROR_TARGET XT_ERROR_TARGET +#define IP6T_MATCH_ITERATE(e, fn, args...) \ + XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args) +#define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args) #endif /* Yes, Virginia, you have to zero the padding. */ @@ -133,7 +156,7 @@ struct ip6t_error { #define IP6T_STANDARD_INIT(__verdict) \ { \ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_standard)), \ - .target = XT_TARGET_INIT(IP6T_STANDARD_TARGET, \ + .target = XT_TARGET_INIT(XT_STANDARD_TARGET, \ sizeof(struct xt_standard_target)), \ .target.verdict = -(__verdict) - 1, \ } @@ -141,7 +164,7 @@ struct ip6t_error { #define IP6T_ERROR_INIT \ { \ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_error)), \ - .target = XT_TARGET_INIT(IP6T_ERROR_TARGET, \ + .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ sizeof(struct ip6t_error_target)), \ .target.errorname = "ERROR", \ } @@ -165,30 +188,6 @@ struct ip6t_error { #define IP6T_SO_GET_REVISION_TARGET (IP6T_BASE_CTL + 5) #define IP6T_SO_GET_MAX IP6T_SO_GET_REVISION_TARGET -/* CONTINUE verdict for targets */ -#define IP6T_CONTINUE XT_CONTINUE - -/* For standard target */ -#define IP6T_RETURN XT_RETURN - -/* TCP/UDP matching stuff */ -#include - -#define ip6t_tcp xt_tcp -#define ip6t_udp xt_udp - -/* Values for "inv" field in struct ipt_tcp. */ -#define IP6T_TCP_INV_SRCPT XT_TCP_INV_SRCPT -#define IP6T_TCP_INV_DSTPT XT_TCP_INV_DSTPT -#define IP6T_TCP_INV_FLAGS XT_TCP_INV_FLAGS -#define IP6T_TCP_INV_OPTION XT_TCP_INV_OPTION -#define IP6T_TCP_INV_MASK XT_TCP_INV_MASK - -/* Values for "invflags" field in struct ipt_udp. */ -#define IP6T_UDP_INV_SRCPT XT_UDP_INV_SRCPT -#define IP6T_UDP_INV_DSTPT XT_UDP_INV_DSTPT -#define IP6T_UDP_INV_MASK XT_UDP_INV_MASK - /* ICMP matching stuff */ struct ip6t_icmp { u_int8_t type; /* type to match */ @@ -252,9 +251,6 @@ struct ip6t_replace { struct ip6t_entry entries[0]; }; -/* The argument to IP6T_SO_ADD_COUNTERS. */ -#define ip6t_counters_info xt_counters_info - /* The argument to IP6T_SO_GET_ENTRIES. */ struct ip6t_get_entries { /* Which table: user fills this in. */ @@ -267,11 +263,6 @@ struct ip6t_get_entries { struct ip6t_entry entrytable[0]; }; -/* Standard return verdict, or do jump. */ -#define IP6T_STANDARD_TARGET XT_STANDARD_TARGET -/* Error verdict. */ -#define IP6T_ERROR_TARGET XT_ERROR_TARGET - /* Helper functions */ static __inline__ struct xt_entry_target * ip6t_get_target(struct ip6t_entry *e) @@ -279,16 +270,6 @@ ip6t_get_target(struct ip6t_entry *e) return (void *)e + e->target_offset; } -#ifndef __KERNEL__ -/* fn returns 0 to continue iteration */ -#define IP6T_MATCH_ITERATE(e, fn, args...) \ - XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args) - -/* fn returns 0 to continue iteration */ -#define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ - XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args) -#endif - /* * Main firewall chains definitions and global var's definitions. */ diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index ed178cb..d756eda 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -300,7 +300,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ - if (v != ARPT_RETURN) { + if (v != XT_RETURN) { verdict = (unsigned)(-v) - 1; break; } @@ -332,7 +332,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, /* Target might have changed stuff. */ arp = arp_hdr(skb); - if (verdict == ARPT_CONTINUE) + if (verdict == XT_CONTINUE) e = arpt_next_entry(e); else /* Verdict */ @@ -392,13 +392,13 @@ static int mark_source_chains(const struct xt_table_info *newinfo, /* Unconditional return/END. */ if ((e->target_offset == sizeof(struct arpt_entry) && (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < 0 && unconditional(&e->arp)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -433,7 +433,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && newpos >= 0) { if (newpos > newinfo->size - sizeof(struct arpt_entry)) { @@ -1828,7 +1828,7 @@ void arpt_unregister_table(struct xt_table *table) /* The built-in targets: standard (NULL) and error. */ static struct xt_target arpt_builtin_tg[] __read_mostly = { { - .name = ARPT_STANDARD_TARGET, + .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_ARP, #ifdef CONFIG_COMPAT @@ -1838,7 +1838,7 @@ static struct xt_target arpt_builtin_tg[] __read_mostly = { #endif }, { - .name = ARPT_ERROR_TARGET, + .name = XT_ERROR_TARGET, .target = arpt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_ARP, diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index e1be7dd..b8ddcc4 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -63,7 +63,7 @@ static int checkentry(const struct xt_tgchk_param *par) return false; if (mangle->target != NF_DROP && mangle->target != NF_ACCEPT && - mangle->target != ARPT_CONTINUE) + mangle->target != XT_CONTINUE) return false; return true; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cb10888..d31b007 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -232,7 +232,7 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, { const struct xt_standard_target *t = (void *)ipt_get_target_c(s); - if (strcmp(t->target.u.kernel.target->name, IPT_ERROR_TARGET) == 0) { + if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; @@ -241,7 +241,7 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, if (s->target_offset == sizeof(struct ipt_entry) && strcmp(t->target.u.kernel.target->name, - IPT_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && t->verdict < 0 && unconditional(&s->ip)) { /* Tail of chains: STANDARD target (return/policy) */ @@ -383,7 +383,7 @@ ipt_do_table(struct sk_buff *skb, v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ - if (v != IPT_RETURN) { + if (v != XT_RETURN) { verdict = (unsigned)(-v) - 1; break; } @@ -421,7 +421,7 @@ ipt_do_table(struct sk_buff *skb, verdict = t->u.kernel.target->target(skb, &acpar); /* Target might have changed stuff. */ ip = ip_hdr(skb); - if (verdict == IPT_CONTINUE) + if (verdict == XT_CONTINUE) e = ipt_next_entry(e); else /* Verdict */ @@ -475,13 +475,13 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Unconditional return/END. */ if ((e->target_offset == sizeof(struct ipt_entry) && (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < 0 && unconditional(&e->ip)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -524,7 +524,7 @@ mark_source_chains(const struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ipt_entry)) { @@ -2176,7 +2176,7 @@ static int icmp_checkentry(const struct xt_mtchk_param *par) static struct xt_target ipt_builtin_tg[] __read_mostly = { { - .name = IPT_STANDARD_TARGET, + .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV4, #ifdef CONFIG_COMPAT @@ -2186,7 +2186,7 @@ static struct xt_target ipt_builtin_tg[] __read_mostly = { #endif }, { - .name = IPT_ERROR_TARGET, + .name = XT_ERROR_TARGET, .target = ipt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV4, diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index c7334c1..c683e9e 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -262,7 +262,7 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, { const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); - if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) { + if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; @@ -271,7 +271,7 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, if (s->target_offset == sizeof(struct ip6t_entry) && strcmp(t->target.u.kernel.target->name, - IP6T_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && t->verdict < 0 && unconditional(&s->ipv6)) { /* Tail of chains: STANDARD target (return/policy) */ @@ -406,7 +406,7 @@ ip6t_do_table(struct sk_buff *skb, v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ - if (v != IP6T_RETURN) { + if (v != XT_RETURN) { verdict = (unsigned)(-v) - 1; break; } @@ -434,7 +434,7 @@ ip6t_do_table(struct sk_buff *skb, acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); - if (verdict == IP6T_CONTINUE) + if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ @@ -488,13 +488,13 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Unconditional return/END. */ if ((e->target_offset == sizeof(struct ip6t_entry) && (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < 0 && unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -537,7 +537,7 @@ mark_source_chains(const struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ip6t_entry)) { @@ -2191,7 +2191,7 @@ static int icmp6_checkentry(const struct xt_mtchk_param *par) /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { - .name = IP6T_STANDARD_TARGET, + .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_COMPAT @@ -2201,7 +2201,7 @@ static struct xt_target ip6t_builtin_tg[] __read_mostly = { #endif }, { - .name = IP6T_ERROR_TARGET, + .name = XT_ERROR_TARGET, .target = ip6t_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index f6d464f..8daef96 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -230,7 +230,7 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, result = TC_ACT_SHOT; ipt->tcf_qstats.drops++; break; - case IPT_CONTINUE: + case XT_CONTINUE: result = TC_ACT_PIPE; break; default: -- cgit v0.10.2 From 75f0a0fd787bfa3ea1a916ca632a5b9e0007cbb7 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 16:37:45 +0200 Subject: netfilter: xtables: unify {ip,ip6,arp}t_error_target Unification of struct *_error_target was forgotten in v2.6.16-1689-g1e30a01. Signed-off-by: Jan Engelhardt diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 24e5d01..742bec0 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -66,6 +66,11 @@ struct xt_standard_target { int verdict; }; +struct xt_error_target { + struct xt_entry_target target; + char errorname[XT_FUNCTION_MAXNAMELEN]; +}; + /* The argument to IPT_SO_GET_REVISION_*. Returns highest revision * kernel supports, if >= revision. */ struct xt_get_revision { diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 6e2341a..f02d574 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -26,6 +26,7 @@ #define ARPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN #define arpt_entry_target xt_entry_target #define arpt_standard_target xt_standard_target +#define arpt_error_target xt_error_target #define ARPT_CONTINUE XT_CONTINUE #define ARPT_RETURN XT_RETURN #define arpt_counters_info xt_counters_info @@ -216,14 +217,9 @@ struct arpt_standard { struct xt_standard_target target; }; -struct arpt_error_target { - struct xt_entry_target target; - char errorname[XT_FUNCTION_MAXNAMELEN]; -}; - struct arpt_error { struct arpt_entry entry; - struct arpt_error_target target; + struct xt_error_target target; }; #define ARPT_ENTRY_INIT(__size) \ @@ -244,7 +240,7 @@ struct arpt_error { { \ .entry = ARPT_ENTRY_INIT(sizeof(struct arpt_error)), \ .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ - sizeof(struct arpt_error_target)), \ + sizeof(struct xt_error_target)), \ .target.errorname = "ERROR", \ } diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index ee54b3b..d0fef0a 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -37,6 +37,7 @@ #define ipt_entry_match xt_entry_match #define ipt_entry_target xt_entry_target #define ipt_standard_target xt_standard_target +#define ipt_error_target xt_error_target #define ipt_counters xt_counters #define IPT_CONTINUE XT_CONTINUE #define IPT_RETURN XT_RETURN @@ -247,14 +248,9 @@ struct ipt_standard { struct xt_standard_target target; }; -struct ipt_error_target { - struct xt_entry_target target; - char errorname[XT_FUNCTION_MAXNAMELEN]; -}; - struct ipt_error { struct ipt_entry entry; - struct ipt_error_target target; + struct xt_error_target target; }; #define IPT_ENTRY_INIT(__size) \ @@ -275,7 +271,7 @@ struct ipt_error { { \ .entry = IPT_ENTRY_INIT(sizeof(struct ipt_error)), \ .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ - sizeof(struct ipt_error_target)), \ + sizeof(struct xt_error_target)), \ .target.errorname = "ERROR", \ } diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index ac2b411..dca1118 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -37,6 +37,7 @@ #define ip6t_entry_match xt_entry_match #define ip6t_entry_target xt_entry_target #define ip6t_standard_target xt_standard_target +#define ip6t_error_target xt_error_target #define ip6t_counters xt_counters #define IP6T_CONTINUE XT_CONTINUE #define IP6T_RETURN XT_RETURN @@ -137,14 +138,9 @@ struct ip6t_standard { struct xt_standard_target target; }; -struct ip6t_error_target { - struct xt_entry_target target; - char errorname[XT_FUNCTION_MAXNAMELEN]; -}; - struct ip6t_error { struct ip6t_entry entry; - struct ip6t_error_target target; + struct xt_error_target target; }; #define IP6T_ENTRY_INIT(__size) \ @@ -165,7 +161,7 @@ struct ip6t_error { { \ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_error)), \ .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ - sizeof(struct ip6t_error_target)), \ + sizeof(struct xt_error_target)), \ .target.errorname = "ERROR", \ } -- cgit v0.10.2 From 9ecdafd883db3c43296797382fc0b2c868144070 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 16:42:02 +0200 Subject: netfilter: xtables: remove unused defines Signed-off-by: Jan Engelhardt diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index f02d574..adbf4bf 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -255,8 +255,6 @@ extern unsigned int arpt_do_table(struct sk_buff *skb, const struct net_device *out, struct xt_table *table); -#define ARPT_ALIGN(s) XT_ALIGN(s) - #ifdef CONFIG_COMPAT #include @@ -275,8 +273,6 @@ compat_arpt_get_target(struct compat_arpt_entry *e) return (void *)e + e->target_offset; } -#define COMPAT_ARPT_ALIGN(s) COMPAT_XT_ALIGN(s) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _ARPTABLES_H */ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index d0fef0a..64a5d95 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -282,8 +282,6 @@ extern unsigned int ipt_do_table(struct sk_buff *skb, const struct net_device *out, struct xt_table *table); -#define IPT_ALIGN(s) XT_ALIGN(s) - #ifdef CONFIG_COMPAT #include @@ -304,8 +302,6 @@ compat_ipt_get_target(struct compat_ipt_entry *e) return (void *)e + e->target_offset; } -#define COMPAT_IPT_ALIGN(s) COMPAT_XT_ALIGN(s) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IPTABLES_H */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index dca1118..c9784f7 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -292,8 +292,6 @@ extern int ip6t_ext_hdr(u8 nexthdr); extern int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff); -#define IP6T_ALIGN(s) XT_ALIGN(s) - #ifdef CONFIG_COMPAT #include @@ -313,8 +311,6 @@ compat_ip6t_get_target(struct compat_ip6t_entry *e) return (void *)e + e->target_offset; } -#define COMPAT_IP6T_ALIGN(s) COMPAT_XT_ALIGN(s) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IP6_TABLES_H */ -- cgit v0.10.2 From a91fd267e327ca7599654b4e9ed7b62c5adaccee Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 13 Oct 2010 21:22:35 +0200 Subject: IPVS: ip_vs_dbg_callid() is only needed for debugging ip_vs_dbg_callid() and IP_VS_DEBUG_CALLID() are only needed it CONFIG_IP_VS_DEBUG is defined. This resolves the following build warning when CONFIG_IP_VS_DEBUG is not defined. net/netfilter/ipvs/ip_vs_pe_sip.c:11: warning: 'ip_vs_dbg_callid' defined but not used Reported-by: Patrick McHardy Signed-off-by: Simon Horman Signed-off-by: Patrick McHardy diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index a0539f1..b8b4e96 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -8,6 +8,7 @@ #include #include +#ifdef CONFIG_IP_VS_DEBUG static const char *ip_vs_dbg_callid(char *buf, size_t buf_len, const char *callid, size_t callid_len, int *idx) @@ -22,6 +23,7 @@ static const char *ip_vs_dbg_callid(char *buf, size_t buf_len, #define IP_VS_DEBUG_CALLID(callid, len) \ ip_vs_dbg_callid(ip_vs_dbg_buf, sizeof(ip_vs_dbg_buf), \ callid, len, &ip_vs_dbg_idx) +#endif static int get_callid(const char *dptr, unsigned int dataoff, unsigned int datalen, -- cgit v0.10.2 From 76b6717bc6ccb715b04e36efc26566a6313ede5f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 18 Oct 2010 11:13:30 +0200 Subject: netfilter: fix kconfig unmet dependency warning Fix netfilter kconfig unmet dependencies warning & spell out "compatible" while there. warning: (IP_NF_TARGET_TTL && NET && INET && NETFILTER && IP_NF_IPTABLES && NETFILTER_ADVANCED || IP6_NF_TARGET_HL && NET && INET && IPV6 && NETFILTER && IP6_NF_IPTABLES && NETFILTER_ADVANCED) selects NETFILTER_XT_TARGET_HL which has unmet direct dependencies ((IP_NF_MANGLE || IP6_NF_MANGLE) && NETFILTER_ADVANCED) Signed-off-by: Randy Dunlap Signed-off-by: Patrick McHardy diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1833bdb..8e33506 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -324,10 +324,10 @@ config IP_NF_TARGET_ECN config IP_NF_TARGET_TTL tristate '"TTL" target support' - depends on NETFILTER_ADVANCED + depends on NETFILTER_ADVANCED && IP_NF_MANGLE select NETFILTER_XT_TARGET_HL ---help--- - This is a backwards-compat option for the user's convenience + This is a backwards-compatible option for the user's convenience (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 29d643b..44d2eea 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -132,10 +132,10 @@ config IP6_NF_MATCH_RT # The targets config IP6_NF_TARGET_HL tristate '"HL" hoplimit target support' - depends on NETFILTER_ADVANCED + depends on NETFILTER_ADVANCED && IP6_NF_MANGLE select NETFILTER_XT_TARGET_HL ---help--- - This is a backwards-compat option for the user's convenience + This is a backwards-compatible option for the user's convenience (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. -- cgit v0.10.2 From 43f974cdb4ab6d65f849610deb9ef738d62b2e65 Mon Sep 17 00:00:00 2001 From: Nick Bowler Date: Mon, 18 Oct 2010 11:22:05 +0200 Subject: netfilter: install missing ebtables headers for userspace The ebt_ip6.h and ebt_nflog.h headers are not not known to Kbuild and therefore not installed by make headers_install. Fix that up. Signed-off-by: Nick Bowler Signed-off-by: Patrick McHardy diff --git a/include/linux/netfilter_bridge/Kbuild b/include/linux/netfilter_bridge/Kbuild index d4d7867..e48f1a3 100644 --- a/include/linux/netfilter_bridge/Kbuild +++ b/include/linux/netfilter_bridge/Kbuild @@ -3,11 +3,13 @@ header-y += ebt_among.h header-y += ebt_arp.h header-y += ebt_arpreply.h header-y += ebt_ip.h +header-y += ebt_ip6.h header-y += ebt_limit.h header-y += ebt_log.h header-y += ebt_mark_m.h header-y += ebt_mark_t.h header-y += ebt_nat.h +header-y += ebt_nflog.h header-y += ebt_pkttype.h header-y += ebt_redirect.h header-y += ebt_stp.h -- cgit v0.10.2 From ebbf41df4aabb6d506fa18ea8cb4c2b4388a18b9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 19 Oct 2010 10:19:06 +0200 Subject: netfilter: ctnetlink: add expectation deletion events This patch allows to listen to events that inform about expectations destroyed. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 23a1a08..50cdc25 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -98,6 +98,7 @@ enum ip_conntrack_events { enum ip_conntrack_expect_events { IPEXP_NEW, /* new expectation */ + IPEXP_DESTROY, /* destroyed expectation */ }; /* expectation flags */ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 416b838..0f8a8c5 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -82,7 +82,13 @@ struct nf_conntrack_expect * nf_ct_find_expectation(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple); -void nf_ct_unlink_expect(struct nf_conntrack_expect *exp); +void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, + u32 pid, int report); +static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) +{ + nf_ct_unlink_expect_report(exp, 0, 0); +} + void nf_ct_remove_expectations(struct nf_conn *ct); void nf_ct_unexpect_related(struct nf_conntrack_expect *exp); void nf_ct_remove_userspace_expectations(void); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index b30a1f2..46e8966 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -41,7 +41,8 @@ static struct kmem_cache *nf_ct_expect_cachep __read_mostly; static HLIST_HEAD(nf_ct_userspace_expect_list); /* nf_conntrack_expect helper functions */ -void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) +void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, + u32 pid, int report) { struct nf_conn_help *master_help = nfct_help(exp->master); struct net *net = nf_ct_exp_net(exp); @@ -55,11 +56,12 @@ void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) if (!(exp->flags & NF_CT_EXPECT_USERSPACE)) master_help->expecting[exp->class]--; + nf_ct_expect_event_report(IPEXP_DESTROY, exp, pid, report); nf_ct_expect_put(exp); NF_CT_STAT_INC(net, expect_delete); } -EXPORT_SYMBOL_GPL(nf_ct_unlink_expect); +EXPORT_SYMBOL_GPL(nf_ct_unlink_expect_report); static void nf_ct_expectation_timed_out(unsigned long ul_expect) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index b4077be..62bad22 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1632,17 +1632,20 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct sk_buff *skb; - unsigned int type; + unsigned int type, group; int flags = 0; - if (events & (1 << IPEXP_NEW)) { + if (events & (1 << IPEXP_DESTROY)) { + type = IPCTNL_MSG_EXP_DELETE; + group = NFNLGRP_CONNTRACK_EXP_DESTROY; + } else if (events & (1 << IPEXP_NEW)) { type = IPCTNL_MSG_EXP_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; + group = NFNLGRP_CONNTRACK_EXP_NEW; } else return 0; - if (!item->report && - !nfnetlink_has_listeners(net, NFNLGRP_CONNTRACK_EXP_NEW)) + if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); @@ -1665,8 +1668,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - nfnetlink_send(skb, net, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, - item->report, GFP_ATOMIC); + nfnetlink_send(skb, net, item->pid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: @@ -1849,7 +1851,13 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } /* after list removal, usage count == 1 */ - nf_ct_unexpect_related(exp); + spin_lock_bh(&nf_conntrack_lock); + if (del_timer(&exp->timeout)) { + nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).pid, + nlmsg_report(nlh)); + nf_ct_expect_put(exp); + } + spin_unlock_bh(&nf_conntrack_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); @@ -1866,7 +1874,9 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, m_help = nfct_help(exp->master); if (!strcmp(m_help->helper->name, name) && del_timer(&exp->timeout)) { - nf_ct_unlink_expect(exp); + nf_ct_unlink_expect_report(exp, + NETLINK_CB(skb).pid, + nlmsg_report(nlh)); nf_ct_expect_put(exp); } } @@ -1880,7 +1890,9 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, &net->ct.expect_hash[i], hnode) { if (del_timer(&exp->timeout)) { - nf_ct_unlink_expect(exp); + nf_ct_unlink_expect_report(exp, + NETLINK_CB(skb).pid, + nlmsg_report(nlh)); nf_ct_expect_put(exp); } } -- cgit v0.10.2 From 714f095f74582764d629785f03b459a3d0503624 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 19 Oct 2010 10:38:48 +0200 Subject: ipvs: IPv6 tunnel mode IPv6 encapsulation uses a bad source address for the tunnel. i.e. VIP will be used as local-addr and encap. dst addr. Decapsulation will not accept this. Example LVS (eth1 2003::2:0:1/96, VIP 2003::2:0:100) (eth0 2003::1:0:1/96) RS (ethX 2003::1:0:5/96) tcpdump 2003::2:0:100 > 2003::1:0:5: IP6 (hlim 63, next-header TCP (6) payload length: 40) 2003::3:0:10.50991 > 2003::2:0:100.http: Flags [S], cksum 0x7312 (correct), seq 3006460279, win 5760, options [mss 1440,sackOK,TS val 1904932 ecr 0,nop,wscale 3], length 0 In Linux IPv6 impl. you can't have a tunnel with an any cast address receiving packets (I have not tried to interpret RFC 2473) To have receive capabilities the tunnel must have: - Local address set as multicast addr or an unicast addr - Remote address set as an unicast addr. - Loop back addres or Link local address are not allowed. This causes us to setup a tunnel in the Real Server with the LVS as the remote address, here you can't use the VIP address since it's used inside the tunnel. Solution Use outgoing interface IPv6 address (match against the destination). i.e. use ip6_route_output() to look up the route cache and then use ipv6_dev_get_saddr(...) to set the source address of the encapsulated packet. Additionally, cache the results in new destination fields: dst_cookie and dst_saddr and properly check the returned dst from ip6_route_output. We now add xfrm_lookup call only for the tunneling method where the source address is a local one. Signed-off-by:Hans Schillstrom Signed-off-by: Patrick McHardy diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 52fbe23..6e8a619 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -529,6 +529,10 @@ struct ip_vs_dest { spinlock_t dst_lock; /* lock of dst_cache */ struct dst_entry *dst_cache; /* destination cache entry */ u32 dst_rtos; /* RT_TOS(tos) for dst */ + u32 dst_cookie; +#ifdef CONFIG_IP_VS_IPV6 + struct in6_addr dst_saddr; +#endif /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 8817afa..b0bd8af 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -26,6 +26,7 @@ #include /* for ip_route_output */ #include #include +#include #include #include #include @@ -37,26 +38,27 @@ * Destination cache to speed up outgoing route lookup */ static inline void -__ip_vs_dst_set(struct ip_vs_dest *dest, u32 rtos, struct dst_entry *dst) +__ip_vs_dst_set(struct ip_vs_dest *dest, u32 rtos, struct dst_entry *dst, + u32 dst_cookie) { struct dst_entry *old_dst; old_dst = dest->dst_cache; dest->dst_cache = dst; dest->dst_rtos = rtos; + dest->dst_cookie = dst_cookie; dst_release(old_dst); } static inline struct dst_entry * -__ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos, u32 cookie) +__ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos) { struct dst_entry *dst = dest->dst_cache; if (!dst) return NULL; - if ((dst->obsolete - || (dest->af == AF_INET && rtos != dest->dst_rtos)) && - dst->ops->check(dst, cookie) == NULL) { + if ((dst->obsolete || rtos != dest->dst_rtos) && + dst->ops->check(dst, dest->dst_cookie) == NULL) { dest->dst_cache = NULL; dst_release(dst); return NULL; @@ -66,15 +68,16 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos, u32 cookie) } static struct rtable * -__ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) +__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_conn *cp, u32 rtos) { + struct net *net = dev_net(skb->dev); struct rtable *rt; /* Route to the other host */ struct ip_vs_dest *dest = cp->dest; if (dest) { spin_lock(&dest->dst_lock); if (!(rt = (struct rtable *) - __ip_vs_dst_check(dest, rtos, 0))) { + __ip_vs_dst_check(dest, rtos))) { struct flowi fl = { .oif = 0, .nl_u = { @@ -84,13 +87,13 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) .tos = rtos, } }, }; - if (ip_route_output_key(&init_net, &rt, &fl)) { + if (ip_route_output_key(net, &rt, &fl)) { spin_unlock(&dest->dst_lock); IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &dest->addr.ip); return NULL; } - __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst)); + __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0); IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n", &dest->addr.ip, atomic_read(&rt->dst.__refcnt), rtos); @@ -106,7 +109,7 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) .tos = rtos, } }, }; - if (ip_route_output_key(&init_net, &rt, &fl)) { + if (ip_route_output_key(net, &rt, &fl)) { IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &cp->daddr.ip); return NULL; @@ -117,62 +120,79 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) } #ifdef CONFIG_IP_VS_IPV6 + +static struct dst_entry * +__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, + struct in6_addr *ret_saddr, int do_xfrm) +{ + struct dst_entry *dst; + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip6_u = { + .daddr = *daddr, + }, + }, + }; + + dst = ip6_route_output(net, NULL, &fl); + if (dst->error) + goto out_err; + if (!ret_saddr) + return dst; + if (ipv6_addr_any(&fl.fl6_src) && + ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev, + &fl.fl6_dst, 0, &fl.fl6_src) < 0) + goto out_err; + if (do_xfrm && xfrm_lookup(net, &dst, &fl, NULL, 0) < 0) + goto out_err; + ipv6_addr_copy(ret_saddr, &fl.fl6_src); + return dst; + +out_err: + dst_release(dst); + IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr); + return NULL; +} + static struct rt6_info * -__ip_vs_get_out_rt_v6(struct ip_vs_conn *cp) +__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_conn *cp, + struct in6_addr *ret_saddr, int do_xfrm) { + struct net *net = dev_net(skb->dev); struct rt6_info *rt; /* Route to the other host */ struct ip_vs_dest *dest = cp->dest; + struct dst_entry *dst; if (dest) { spin_lock(&dest->dst_lock); - rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0, 0); + rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0); if (!rt) { - struct flowi fl = { - .oif = 0, - .nl_u = { - .ip6_u = { - .daddr = dest->addr.in6, - .saddr = { - .s6_addr32 = - { 0, 0, 0, 0 }, - }, - }, - }, - }; + u32 cookie; - rt = (struct rt6_info *)ip6_route_output(&init_net, - NULL, &fl); - if (!rt) { + dst = __ip_vs_route_output_v6(net, &dest->addr.in6, + &dest->dst_saddr, + do_xfrm); + if (!dst) { spin_unlock(&dest->dst_lock); - IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", - &dest->addr.in6); return NULL; } - __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst)); - IP_VS_DBG(10, "new dst %pI6, refcnt=%d\n", - &dest->addr.in6, + rt = (struct rt6_info *) dst; + cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie); + IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", + &dest->addr.in6, &dest->dst_saddr, atomic_read(&rt->dst.__refcnt)); } + if (ret_saddr) + ipv6_addr_copy(ret_saddr, &dest->dst_saddr); spin_unlock(&dest->dst_lock); } else { - struct flowi fl = { - .oif = 0, - .nl_u = { - .ip6_u = { - .daddr = cp->daddr.in6, - .saddr = { - .s6_addr32 = { 0, 0, 0, 0 }, - }, - }, - }, - }; - - rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); - if (!rt) { - IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", - &cp->daddr.in6); + dst = __ip_vs_route_output_v6(net, &cp->daddr.in6, ret_saddr, + do_xfrm); + if (!dst) return NULL; - } + rt = (struct rt6_info *) dst; } return rt; @@ -248,6 +268,7 @@ int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { + struct net *net = dev_net(skb->dev); struct rtable *rt; /* Route to the other host */ struct iphdr *iph = ip_hdr(skb); u8 tos = iph->tos; @@ -263,7 +284,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (ip_route_output_key(&init_net, &rt, &fl)) { + if (ip_route_output_key(net, &rt, &fl)) { IP_VS_DBG_RL("%s(): ip_route_output error, dest: %pI4\n", __func__, &iph->daddr); goto tx_error_icmp; @@ -313,25 +334,18 @@ int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { + struct net *net = dev_net(skb->dev); + struct dst_entry *dst; struct rt6_info *rt; /* Route to the other host */ struct ipv6hdr *iph = ipv6_hdr(skb); int mtu; - struct flowi fl = { - .oif = 0, - .nl_u = { - .ip6_u = { - .daddr = iph->daddr, - .saddr = { .s6_addr32 = {0, 0, 0, 0} }, } }, - }; EnterFunction(10); - rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); - if (!rt) { - IP_VS_DBG_RL("%s(): ip6_route_output error, dest: %pI6\n", - __func__, &iph->daddr); + dst = __ip_vs_route_output_v6(net, &iph->daddr, NULL, 0); + if (!dst) goto tx_error_icmp; - } + rt = (struct rt6_info *) dst; /* MTU checking */ mtu = dst_mtu(&rt->dst); @@ -397,7 +411,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } - if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(iph->tos)))) goto tx_error_icmp; /* MTU checking */ @@ -472,7 +486,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } - rt = __ip_vs_get_out_rt_v6(cp); + rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0); if (!rt) goto tx_error_icmp; @@ -557,7 +571,6 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct iphdr *old_iph = ip_hdr(skb); u8 tos = old_iph->tos; __be16 df = old_iph->frag_off; - sk_buff_data_t old_transport_header = skb->transport_header; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; @@ -572,7 +585,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } - if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(tos)))) goto tx_error_icmp; tdev = rt->dst.dev; @@ -616,7 +629,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, old_iph = ip_hdr(skb); } - skb->transport_header = old_transport_header; + skb->transport_header = skb->network_header; /* fix old IP header checksum */ ip_send_check(old_iph); @@ -670,9 +683,9 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rt6_info *rt; /* Route to the other host */ + struct in6_addr saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct ipv6hdr *old_iph = ipv6_hdr(skb); - sk_buff_data_t old_transport_header = skb->transport_header; struct ipv6hdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; @@ -687,17 +700,17 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } - rt = __ip_vs_get_out_rt_v6(cp); + rt = __ip_vs_get_out_rt_v6(skb, cp, &saddr, 1); if (!rt) goto tx_error_icmp; tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); - /* TODO IPv6: do we need this check in IPv6? */ - if (mtu < 1280) { + if (mtu < IPV6_MIN_MTU) { dst_release(&rt->dst); - IP_VS_DBG_RL("%s(): mtu less than 1280\n", __func__); + IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__, + IPV6_MIN_MTU); goto tx_error; } if (skb_dst(skb)) @@ -730,7 +743,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, old_iph = ipv6_hdr(skb); } - skb->transport_header = old_transport_header; + skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); @@ -750,8 +763,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); - iph->daddr = rt->rt6i_dst.addr; - iph->saddr = cp->vaddr.in6; /* rt->rt6i_src.addr; */ + ipv6_addr_copy(&iph->daddr, &cp->daddr.in6); + ipv6_addr_copy(&iph->saddr, &saddr); iph->hop_limit = old_iph->hop_limit; /* Another hack: avoid icmp_send in ip_fragment */ @@ -791,7 +804,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(iph->tos)))) goto tx_error_icmp; /* MTU checking */ @@ -843,7 +856,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - rt = __ip_vs_get_out_rt_v6(cp); + rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0); if (!rt) goto tx_error_icmp; @@ -919,7 +932,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ - if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(ip_hdr(skb)->tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(ip_hdr(skb)->tos)))) goto tx_error_icmp; /* MTU checking */ @@ -993,7 +1006,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ - rt = __ip_vs_get_out_rt_v6(cp); + rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0); if (!rt) goto tx_error_icmp; -- cgit v0.10.2 From d86bef73b4a24e59e7c1f896a72bbf38430ac2c6 Mon Sep 17 00:00:00 2001 From: Eduardo Blanco Date: Tue, 19 Oct 2010 10:26:47 +0100 Subject: Fixed race condition at ip_vs.ko module init. Lists were initialized after the module was registered. Multiple ipvsadm processes at module load triggered a race condition that resulted in a null pointer dereference in do_ip_vs_get_ctl(). As a result, __ip_vs_mutex was left locked preventing all further ipvsadm commands. Signed-off-by: Eduardo J. Blanco Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index a697591..0b884d3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3400,6 +3400,16 @@ int __init ip_vs_control_init(void) EnterFunction(2); + /* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */ + for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + INIT_LIST_HEAD(&ip_vs_svc_table[idx]); + INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); + } + for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++) { + INIT_LIST_HEAD(&ip_vs_rtable[idx]); + } + smp_wmb(); + ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); @@ -3418,15 +3428,6 @@ int __init ip_vs_control_init(void) sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars); - /* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */ - for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { - INIT_LIST_HEAD(&ip_vs_svc_table[idx]); - INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); - } - for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++) { - INIT_LIST_HEAD(&ip_vs_rtable[idx]); - } - ip_vs_new_estimator(&ip_vs_stats); /* Hook the defense timer */ -- cgit v0.10.2 From 5bc9068e9d962ca6b8bec3f0eb6f60ab4dee1d04 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:14:31 +0300 Subject: ipvs: fix CHECKSUM_PARTIAL for TCP, UDP Fix CHECKSUM_PARTIAL handling. Tested for IPv4 TCP, UDP not tested because it needs network card with HW CSUM support. May be fixes problem where IPVS can not be used in virtual boxes. Problem appears with DNAT to local address when the local stack sends reply in CHECKSUM_PARTIAL mode. Fix tcp_dnat_handler and udp_dnat_handler to provide vaddr and daddr in right order (old and new IP) when calling tcp_partial_csum_update/udp_partial_csum_update (CHECKSUM_PARTIAL). Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 282d24d..318d011 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -101,15 +101,15 @@ tcp_partial_csum_update(int af, struct tcphdr *tcph, #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = - csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, + ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldlen, newlen, - ~csum_unfold(tcph->check)))); + csum_unfold(tcph->check)))); else #endif tcph->check = - csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, + ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldlen, newlen, - ~csum_unfold(tcph->check)))); + csum_unfold(tcph->check)))); } @@ -223,7 +223,7 @@ tcp_dnat_handler(struct sk_buff *skb, * Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { - tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, + tcp_partial_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!cp->app) { diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 8553231..f929089 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -102,15 +102,15 @@ udp_partial_csum_update(int af, struct udphdr *uhdr, #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) uhdr->check = - csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, + ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldlen, newlen, - ~csum_unfold(uhdr->check)))); + csum_unfold(uhdr->check)))); else #endif uhdr->check = - csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, + ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldlen, newlen, - ~csum_unfold(uhdr->check)))); + csum_unfold(uhdr->check)))); } @@ -229,7 +229,7 @@ udp_dnat_handler(struct sk_buff *skb, * Adjust UDP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { - udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, + udp_partial_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - udphoff)); } else if (!cp->app && (udph->check != 0)) { -- cgit v0.10.2 From 8b27b10f5863a5b63e46304a71aa01463d1efac4 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:17:20 +0300 Subject: ipvs: optimize checksums for apps Avoid full checksum calculation for apps that can provide info whether csum was broken after payload mangling. For now only ip_vs_ftp mangles payload and it updates the csum, so the full recalculation is avoided for all packets. Add CHECKSUM_UNNECESSARY for snat_handler (TCP and UDP). It is needed to support SNAT from local address for the case when csum is fully recalculated. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 6e8a619..adcdba9 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -597,11 +597,19 @@ struct ip_vs_app { __be16 port; /* port number in net order */ atomic_t usecnt; /* usage counter */ - /* output hook: return false if can't linearize. diff set for TCP. */ + /* + * output hook: Process packet in inout direction, diff set for TCP. + * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok, + * 2=Mangled but checksum was not updated + */ int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *, struct sk_buff *, int *diff); - /* input hook: return false if can't linearize. diff set for TCP. */ + /* + * input hook: Process packet in outin direction, diff set for TCP. + * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok, + * 2=Mangled but checksum was not updated + */ int (*pkt_in)(struct ip_vs_app *, struct ip_vs_conn *, struct sk_buff *, int *diff); diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 090889a..7545500 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -242,9 +242,14 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, start-data, end-start, buf, buf_len); - if (ret) + if (ret) { ip_vs_nfct_expect_related(skb, ct, n_cp, IPPROTO_TCP, 0, 0); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* csum is updated */ + ret = 1; + } } /* diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 318d011..64dc295 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -120,6 +120,7 @@ tcp_snat_handler(struct sk_buff *skb, struct tcphdr *tcph; unsigned int tcphoff; int oldlen; + int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -134,13 +135,20 @@ tcp_snat_handler(struct sk_buff *skb, return 0; if (unlikely(cp->app != NULL)) { + int ret; + /* Some checks before mangling */ if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ - if (!ip_vs_app_pkt_out(cp, skb)) + if (!(ret = ip_vs_app_pkt_out(cp, skb))) return 0; + /* ret=2: csum update is needed after payload mangling */ + if (ret == 1) + oldlen = skb->len - tcphoff; + else + payload_csum = 1; } tcph = (void *)skb_network_header(skb) + tcphoff; @@ -151,12 +159,13 @@ tcp_snat_handler(struct sk_buff *skb, tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, htons(oldlen), htons(skb->len - tcphoff)); - } else if (!cp->app) { + } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = (cp->app && pp->csum_check) ? + CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; @@ -174,6 +183,7 @@ tcp_snat_handler(struct sk_buff *skb, skb->len - tcphoff, cp->protocol, skb->csum); + skb->ip_summed = CHECKSUM_UNNECESSARY; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, tcph->check, @@ -190,6 +200,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct tcphdr *tcph; unsigned int tcphoff; int oldlen; + int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -204,6 +215,8 @@ tcp_dnat_handler(struct sk_buff *skb, return 0; if (unlikely(cp->app != NULL)) { + int ret; + /* Some checks before mangling */ if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; @@ -212,8 +225,13 @@ tcp_dnat_handler(struct sk_buff *skb, * Attempt ip_vs_app call. * It will fix ip_vs_conn and iph ack_seq stuff */ - if (!ip_vs_app_pkt_in(cp, skb)) + if (!(ret = ip_vs_app_pkt_in(cp, skb))) return 0; + /* ret=2: csum update is needed after payload mangling */ + if (ret == 1) + oldlen = skb->len - tcphoff; + else + payload_csum = 1; } tcph = (void *)skb_network_header(skb) + tcphoff; @@ -226,12 +244,13 @@ tcp_dnat_handler(struct sk_buff *skb, tcp_partial_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - tcphoff)); - } else if (!cp->app) { + } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = (cp->app && pp->csum_check) ? + CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f929089..9c558c4 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -121,6 +121,7 @@ udp_snat_handler(struct sk_buff *skb, struct udphdr *udph; unsigned int udphoff; int oldlen; + int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -135,6 +136,8 @@ udp_snat_handler(struct sk_buff *skb, return 0; if (unlikely(cp->app != NULL)) { + int ret; + /* Some checks before mangling */ if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; @@ -142,8 +145,13 @@ udp_snat_handler(struct sk_buff *skb, /* * Call application helper if needed */ - if (!ip_vs_app_pkt_out(cp, skb)) + if (!(ret = ip_vs_app_pkt_out(cp, skb))) return 0; + /* ret=2: csum update is needed after payload mangling */ + if (ret == 1) + oldlen = skb->len - udphoff; + else + payload_csum = 1; } udph = (void *)skb_network_header(skb) + udphoff; @@ -156,12 +164,13 @@ udp_snat_handler(struct sk_buff *skb, udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, htons(oldlen), htons(skb->len - udphoff)); - } else if (!cp->app && (udph->check != 0)) { + } else if (!payload_csum && (udph->check != 0)) { /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = (cp->app && pp->csum_check) ? + CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ udph->check = 0; @@ -181,6 +190,7 @@ udp_snat_handler(struct sk_buff *skb, skb->csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; + skb->ip_summed = CHECKSUM_UNNECESSARY; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, udph->check, (char*)&(udph->check) - (char*)udph); @@ -196,6 +206,7 @@ udp_dnat_handler(struct sk_buff *skb, struct udphdr *udph; unsigned int udphoff; int oldlen; + int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -210,6 +221,8 @@ udp_dnat_handler(struct sk_buff *skb, return 0; if (unlikely(cp->app != NULL)) { + int ret; + /* Some checks before mangling */ if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) return 0; @@ -218,8 +231,13 @@ udp_dnat_handler(struct sk_buff *skb, * Attempt ip_vs_app call. * It will fix ip_vs_conn */ - if (!ip_vs_app_pkt_in(cp, skb)) + if (!(ret = ip_vs_app_pkt_in(cp, skb))) return 0; + /* ret=2: csum update is needed after payload mangling */ + if (ret == 1) + oldlen = skb->len - udphoff; + else + payload_csum = 1; } udph = (void *)skb_network_header(skb) + udphoff; @@ -232,12 +250,13 @@ udp_dnat_handler(struct sk_buff *skb, udp_partial_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - udphoff)); - } else if (!cp->app && (udph->check != 0)) { + } else if (!payload_csum && (udph->check != 0)) { /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = (cp->app && pp->csum_check) ? + CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ udph->check = 0; -- cgit v0.10.2 From cf356d69db0afef692cd640917bc70f708c27f14 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:21:07 +0300 Subject: ipvs: switch to notrack mode Change skb->ipvs_property semantic. This is preparation to support ip_vs_out processing in LOCAL_OUT. ipvs_property=1 will be used to avoid expensive lookups for traffic sent by transmitters. Now when conntrack support is not used we call ip_vs_notrack method to avoid problems in OUTPUT and POST_ROUTING hooks instead of exiting POST_ROUTING as before. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index adcdba9..0e46184 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,7 +25,7 @@ #include #include /* for struct ipv6hdr */ #include /* for ipv6_addr_copy */ -#ifdef CONFIG_IP_VS_NFCT +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include #endif @@ -1021,6 +1021,24 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +/* + * Forget current conntrack (unconfirmed) and attach notrack entry + */ +static inline void ip_vs_notrack(struct sk_buff *skb) +{ +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + + if (!ct || !nf_ct_is_untracked(ct)) { + nf_reset(skb); + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + } +#endif +} + #ifdef CONFIG_IP_VS_NFCT /* * Netfilter connection tracking diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e5fef7a..2224530 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -507,23 +507,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, return NF_DROP; } -/* - * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING - * chain and is used to avoid double NAT and confirmation when we do - * not want to keep the conntrack structure - */ -static unsigned int ip_vs_post_routing(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - if (!skb->ipvs_property) - return NF_ACCEPT; - /* The packet was sent from IPVS, exit this chain */ - return NF_STOP; -} - __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); @@ -682,8 +665,9 @@ static int handle_response_icmp(int af, struct sk_buff *skb, /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); + skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) - skb->ipvs_property = 1; + ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; @@ -929,8 +913,9 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) - skb->ipvs_property = 1; + ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); @@ -1496,14 +1481,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_FORWARD, .priority = 99, }, - /* Before the netfilter connection tracking, exit from POST_ROUTING */ - { - .hook = ip_vs_post_routing, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_NAT_SRC-1, - }, #ifdef CONFIG_IP_VS_IPV6 /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1532,14 +1509,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_FORWARD, .priority = 99, }, - /* Before the netfilter connection tracking, exit from POST_ROUTING */ - { - .hook = ip_vs_post_routing, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_NAT_SRC-1, - }, #endif }; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b0bd8af..94b53b4 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -217,6 +217,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) ({ \ int __ret = NF_ACCEPT; \ \ + (skb)->ipvs_property = 1; \ if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \ __ret = ip_vs_confirm_conntrack(skb, cp); \ if (__ret == NF_ACCEPT) { \ @@ -228,8 +229,9 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) #define IP_VS_XMIT_NAT(pf, skb, cp) \ do { \ + (skb)->ipvs_property = 1; \ if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ - (skb)->ipvs_property = 1; \ + ip_vs_notrack(skb); \ else \ ip_vs_update_conntrack(skb, cp, 1); \ skb_forward_csum(skb); \ @@ -239,8 +241,9 @@ do { \ #define IP_VS_XMIT(pf, skb, cp) \ do { \ + (skb)->ipvs_property = 1; \ if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ - (skb)->ipvs_property = 1; \ + ip_vs_notrack(skb); \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ skb_dst(skb)->dev, dst_output); \ -- cgit v0.10.2 From 190ecd27cd7294105e3b26ca71663c7d940acbbb Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:24:37 +0300 Subject: ipvs: do not schedule conns from real servers This patch is needed to avoid scheduling of packets from local real server when we add ip_vs_in in LOCAL_OUT hook to support local client. Currently, when ip_vs_in can not find existing connection it tries to create new one by calling ip_vs_schedule. The default indication from ip_vs_schedule was if connection was scheduled to real server. If real server is not available we try to use the bypass forwarding method or to send ICMP error. But in some cases we do not want to use the bypass feature. So, add flag 'ignored' to indicate if the scheduler ignores this packet. Make sure we do not create new connections from replies. We can hit this problem for persistent services and local real server when ip_vs_in is added to LOCAL_OUT hook to handle local clients. Also, make sure ip_vs_schedule ignores SYN packets for Active FTP DATA from local real server. The FTP DATA connection should be created on SYN+ACK from client to assign correct connection daddr. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0e46184..9d5c1b9 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -849,7 +849,8 @@ extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc); extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * -ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb); +ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, + struct ip_vs_protocol *pp, int *ignored); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_protocol *pp); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2224530..0090d6d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -342,7 +342,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * Protocols supported: TCP, UDP */ struct ip_vs_conn * -ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb) +ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, + struct ip_vs_protocol *pp, int *ignored) { struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; @@ -350,16 +351,43 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb) __be16 _ports[2], *pptr; unsigned int flags; + *ignored = 1; ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; /* + * FTPDATA needs this check when using local real server. + * Never schedule Active FTPDATA connections from real server. + * For LVS-NAT they must be already created. For other methods + * with persistence the connection is created on SYN+ACK. + */ + if (pptr[0] == FTPDATA) { + IP_VS_DBG_PKT(12, pp, skb, 0, "Not scheduling FTPDATA"); + return NULL; + } + + /* + * Do not schedule replies from local real server. It is risky + * for fwmark services but mostly for persistent services. + */ + if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && + (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) && + (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) { + IP_VS_DBG_PKT(12, pp, skb, 0, + "Not scheduling reply for existing connection"); + __ip_vs_conn_put(cp); + return NULL; + } + + /* * Persistent service */ - if (svc->flags & IP_VS_SVC_F_PERSISTENT) + if (svc->flags & IP_VS_SVC_F_PERSISTENT) { + *ignored = 0; return ip_vs_sched_persist(svc, skb, pptr); + } /* * Non-persistent service @@ -372,6 +400,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb) return NULL; } + *ignored = 0; + dest = svc->scheduler->schedule(svc, skb); if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 4c0855c..9ab5232 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -31,6 +31,8 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, if ((sch->type == SCTP_CID_INIT) && (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr, sh->dest))) { + int ignored; + if (ip_vs_todrop()) { /* * It seems that we are very loaded. @@ -44,8 +46,8 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb); - if (!*cpp) { + *cpp = ip_vs_schedule(svc, skb, pp, &ignored); + if (!*cpp && !ignored) { *verdict = ip_vs_leave(svc, skb, pp); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 64dc295..85d80a6 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -43,9 +43,12 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; } + /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (th->syn && (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr, th->dest))) { + int ignored; + if (ip_vs_todrop()) { /* * It seems that we are very loaded. @@ -60,8 +63,8 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb); - if (!*cpp) { + *cpp = ip_vs_schedule(svc, skb, pp, &ignored); + if (!*cpp && !ignored) { *verdict = ip_vs_leave(svc, skb, pp); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 9c558c4..5d21f08 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -46,6 +46,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr, uh->dest); if (svc) { + int ignored; + if (ip_vs_todrop()) { /* * It seems that we are very loaded. @@ -60,8 +62,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb); - if (!*cpp) { + *cpp = ip_vs_schedule(svc, skb, pp, &ignored); + if (!*cpp && !ignored) { *verdict = ip_vs_leave(svc, skb, pp); return 0; } -- cgit v0.10.2 From 489fdedaed5ddb437dd2840eb93df37a6dd8c7de Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:27:31 +0300 Subject: ipvs: stop ICMP from FORWARD to local Delivering locally ICMP from FORWARD hook is not supported. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0090d6d..27ecb25 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -48,6 +48,7 @@ #ifdef CONFIG_IP_VS_IPV6 #include #include +#include #endif #include @@ -1191,7 +1192,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset); - /* do not touch skb anymore */ + /* LOCALNODE from FORWARD hook is not supported */ + if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD && + skb_rtable(skb)->rt_flags & RTCF_LOCAL) { + IP_VS_DBG(1, "%s(): " + "local delivery to %pI4 but in FORWARD\n", + __func__, &skb_rtable(skb)->rt_dst); + verdict = NF_DROP; + } out: __ip_vs_conn_put(cp); @@ -1212,6 +1220,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_protocol *pp; unsigned int offset, verdict; union nf_inet_addr snet; + struct rt6_info *rt; *related = 1; @@ -1290,7 +1299,15 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) IPPROTO_SCTP == cih->nexthdr) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset); - /* do not touch skb anymore */ + /* LOCALNODE from FORWARD hook is not supported */ + if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD && + (rt = (struct rt6_info *) skb_dst(skb)) && + rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK) { + IP_VS_DBG(1, "%s(): " + "local delivery to %pI6 but in FORWARD\n", + __func__, &rt->rt6i_dst); + verdict = NF_DROP; + } __ip_vs_conn_put(cp); -- cgit v0.10.2 From 4256f1aaa662697c1faa0984b7a698c2c8c57735 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:29:40 +0300 Subject: ipvs: fix CHECKSUM_PARTIAL for TUN method The recent change in IP_VS_XMIT_TUNNEL to set CHECKSUM_NONE is not correct. After adding IPIP header skb->csum becomes invalid but the CHECKSUM_PARTIAL case must be supported. So, use skb_forward_csum() which is most suitable for us to allow local clients to send IPIP to remote real server. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 94b53b4..63cc0fe 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -222,7 +222,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) __ret = ip_vs_confirm_conntrack(skb, cp); \ if (__ret == NF_ACCEPT) { \ nf_reset(skb); \ - (skb)->ip_summed = CHECKSUM_NONE; \ + skb_forward_csum(skb); \ } \ __ret; \ }) -- cgit v0.10.2 From 1ca5bb5450aa2401fa272efeb741ebb260d0fbb0 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:32:29 +0300 Subject: ipvs: create ip_vs_defrag_user Create new function ip_vs_defrag_user to return correct IP_DEFRAG_xxx user depending on the hooknum. It will be needed when we add handlers in LOCAL_OUT. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 27ecb25..f7f5283 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -543,6 +543,15 @@ __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } +static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) +{ + if (NF_INET_LOCAL_IN == hooknum) + return IP_DEFRAG_VS_IN; + if (NF_INET_FORWARD == hooknum) + return IP_DEFRAG_VS_FWD; + return IP_DEFRAG_VS_OUT; +} + static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) { int err = ip_defrag(skb, user); @@ -714,7 +723,8 @@ out: * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ -static int ip_vs_out_icmp(struct sk_buff *skb, int *related) +static int ip_vs_out_icmp(struct sk_buff *skb, int *related, + unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; @@ -729,7 +739,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related) /* reassemble IP fragments */ if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { - if (ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT)) + if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -788,7 +798,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related) } #ifdef CONFIG_IP_VS_IPV6 -static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related) +static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, + unsigned int hooknum) { struct ipv6hdr *iph; struct icmp6hdr _icmph, *ic; @@ -804,7 +815,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related) /* reassemble IP fragments */ if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { - if (ip_vs_gather_frags_v6(skb, IP_DEFRAG_VS_OUT)) + if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -986,7 +997,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { - int related, verdict = ip_vs_out_icmp_v6(skb, &related); + int related; + int verdict = ip_vs_out_icmp_v6(skb, &related, + hooknum); if (related) { if (sysctl_ip_vs_snat_reroute && @@ -1000,7 +1013,8 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { - int related, verdict = ip_vs_out_icmp(skb, &related); + int related; + int verdict = ip_vs_out_icmp(skb, &related, hooknum); if (related) { if (sysctl_ip_vs_snat_reroute && @@ -1019,19 +1033,19 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { - int related, verdict = ip_vs_out_icmp_v6(skb, &related); - - if (related) - return verdict; - - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { + if (ip_vs_gather_frags_v6(skb, + ip_vs_defrag_user(hooknum))) + return NF_STOLEN; } + + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } else #endif if (unlikely(ip_hdr(skb)->frag_off & htons(IP_MF|IP_OFFSET) && !pp->dont_defrag)) { - if (ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT)) + if (ip_vs_gather_frags(skb, + ip_vs_defrag_user(hooknum))) return NF_STOLEN; ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); @@ -1114,8 +1128,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) /* reassemble IP fragments */ if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { - if (ip_vs_gather_frags(skb, hooknum == NF_INET_LOCAL_IN ? - IP_DEFRAG_VS_IN : IP_DEFRAG_VS_FWD)) + if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -1226,9 +1239,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) /* reassemble IP fragments */ if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { - if (ip_vs_gather_frags_v6(skb, hooknum == NF_INET_LOCAL_IN ? - IP_DEFRAG_VS_IN : - IP_DEFRAG_VS_FWD)) + if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -1349,7 +1360,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { - int related, verdict = ip_vs_in_icmp_v6(skb, &related, hooknum); + int related; + int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum); if (related) return verdict; @@ -1358,7 +1370,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { - int related, verdict = ip_vs_in_icmp(skb, &related, hooknum); + int related; + int verdict = ip_vs_in_icmp(skb, &related, hooknum); if (related) return verdict; -- cgit v0.10.2 From f5a41847acc535e2e2018e397b1876ba7577d9d9 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:35:46 +0300 Subject: ipvs: move ip_route_me_harder for ICMP Currently, ip_route_me_harder after ip_vs_out_icmp is called even if packet is not related to IPVS connection. Move it into handle_response_icmp. Also, force rerouting if sending to local client because IPv4 stack uses addresses from the route. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index f7f5283..c4f091d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -702,6 +702,17 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0) + goto out; + } else +#endif + if ((sysctl_ip_vs_snat_reroute || + skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + ip_route_me_harder(skb, RTN_LOCAL) != 0) + goto out; + /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); @@ -940,16 +951,16 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * if it came from this machine itself. So re-compute * the routing information. */ - if (sysctl_ip_vs_snat_reroute) { #ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (ip6_route_me_harder(skb) != 0) - goto drop; - } else + if (af == AF_INET6) { + if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0) + goto drop; + } else #endif - if (ip_route_me_harder(skb, RTN_LOCAL) != 0) - goto drop; - } + if ((sysctl_ip_vs_snat_reroute || + skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + ip_route_me_harder(skb, RTN_LOCAL) != 0) + goto drop; IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT"); @@ -1001,13 +1012,8 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int verdict = ip_vs_out_icmp_v6(skb, &related, hooknum); - if (related) { - if (sysctl_ip_vs_snat_reroute && - NF_ACCEPT == verdict && - ip6_route_me_harder(skb)) - verdict = NF_DROP; + if (related) return verdict; - } ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } } else @@ -1016,13 +1022,8 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int related; int verdict = ip_vs_out_icmp(skb, &related, hooknum); - if (related) { - if (sysctl_ip_vs_snat_reroute && - NF_ACCEPT == verdict && - ip_route_me_harder(skb, RTN_LOCAL)) - verdict = NF_DROP; + if (related) return verdict; - } ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } -- cgit v0.10.2 From fc604767613b6d2036cdc35b660bc39451040a47 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:38:15 +0300 Subject: ipvs: changes for local real server This patch deals with local real servers: - Add support for DNAT to local address (different real server port). It needs ip_vs_out hook in LOCAL_OUT for both families because skb->protocol is not set for locally generated packets and can not be used to set 'af'. - Skip packets in ip_vs_in marked with skb->ipvs_property because ip_vs_out processing can be executed in LOCAL_OUT but we still have the conn_out_get check in ip_vs_in. - Ignore packets with inet->nodefrag from local stack - Require skb_dst(skb) != NULL because we use it to get struct net - Add support for changing the route to local IPv4 stack after DNAT depending on the source address type. Local client sets output route and the remote client sets input route. It looks like IPv6 does not need such rerouting because the replies use addresses from initial incoming header, not from skb route. - All transmitters now have strict checks for the destination address type: redirect from non-local address to local real server requires NAT method, local address can not be used as source address when talking to remote real server. - Now LOCALNODE is not set explicitly as forwarding method in real server to allow the connections to provide correct forwarding method to the backup server. Not sure if this breaks tools that expect to see 'Local' real server type. If needed, this can be supported with new flag IP_VS_DEST_F_LOCAL. Now it should be possible connections in backup that lost their fwmark information during sync to be forwarded properly to their daddr, even if it is local address in the backup server. By this way backup could be used as real server for DR or TUN, for NAT there are some restrictions because tuple collisions in conntracks can create problems for the traffic. - Call ip_vs_dst_reset when destination is updated in case some real server IP type is changed between local and remote. [ horms@verge.net.au: removed trailing whitespace ] Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9d5c1b9..2f88d59 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -409,6 +409,7 @@ struct ip_vs_conn { /* packet transmitter for different forwarding methods. If it mangles the packet, it must return NF_DROP or better NF_STOLEN, otherwise this must be changed to a sk_buff **. + NF_ACCEPT can be returned when destination is local. */ int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index c4f091d..a6c8aff 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -984,26 +984,34 @@ drop: } /* - * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT. * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int -ip_vs_out(unsigned int hooknum, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_conn *cp; - int af; EnterFunction(11); - af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6; - + /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; + /* Bad... Do not break raw sockets */ + if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && + af == AF_INET)) { + struct sock *sk = skb->sk; + struct inet_sock *inet = inet_sk(skb->sk); + + if (inet && sk->sk_family == PF_INET && inet->nodefrag) + return NF_ACCEPT; + } + + if (unlikely(!skb_dst(skb))) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1106,6 +1114,69 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, return handle_response(af, skb, pp, cp, iph.len); } +/* + * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT. + * Check if packet is reply for established ip_vs_conn. + */ +static unsigned int +ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return ip_vs_out(hooknum, skb, AF_INET); +} + +/* + * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. + * Check if packet is reply for established ip_vs_conn. + */ +static unsigned int +ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int verdict; + + /* Disable BH in LOCAL_OUT until all places are fixed */ + local_bh_disable(); + verdict = ip_vs_out(hooknum, skb, AF_INET); + local_bh_enable(); + return verdict; +} + +#ifdef CONFIG_IP_VS_IPV6 + +/* + * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT. + * Check if packet is reply for established ip_vs_conn. + */ +static unsigned int +ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return ip_vs_out(hooknum, skb, AF_INET6); +} + +/* + * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. + * Check if packet is reply for established ip_vs_conn. + */ +static unsigned int +ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int verdict; + + /* Disable BH in LOCAL_OUT until all places are fixed */ + local_bh_disable(); + verdict = ip_vs_out(hooknum, skb, AF_INET6); + local_bh_enable(); + return verdict; +} + +#endif /* * Handle ICMP messages in the outside-to-inside direction (incoming). @@ -1342,6 +1413,10 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, struct ip_vs_conn *cp; int ret, restart, af, pkts; + /* Already marked as IPVS request or reply? */ + if (skb->ipvs_property) + return NF_ACCEPT; + af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6; ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); @@ -1525,13 +1600,13 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_LOCAL_IN, .priority = 100, }, - /* After packet filtering, change source only for VS/NAT */ + /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_out, + .hook = ip_vs_local_reply4, .owner = THIS_MODULE, .pf = PF_INET, - .hooknum = NF_INET_FORWARD, - .priority = 100, + .hooknum = NF_INET_LOCAL_OUT, + .priority = -99, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ @@ -1542,6 +1617,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_FORWARD, .priority = 99, }, + /* After packet filtering, change source only for VS/NAT */ + { + .hook = ip_vs_reply4, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_INET_FORWARD, + .priority = 100, + }, #ifdef CONFIG_IP_VS_IPV6 /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1553,13 +1636,13 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_LOCAL_IN, .priority = 100, }, - /* After packet filtering, change source only for VS/NAT */ + /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_out, + .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_INET_FORWARD, - .priority = 100, + .pf = PF_INET, + .hooknum = NF_INET_LOCAL_OUT, + .priority = -99, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ @@ -1570,6 +1653,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_FORWARD, .priority = 99, }, + /* After packet filtering, change source only for VS/NAT */ + { + .hook = ip_vs_reply6, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_FORWARD, + .priority = 100, + }, #endif }; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 0b884d3..5f5daa3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -777,20 +777,6 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; conn_flags |= IP_VS_CONN_F_INACTIVE; - /* check if local node and update the flags */ -#ifdef CONFIG_IP_VS_IPV6 - if (svc->af == AF_INET6) { - if (__ip_vs_addr_is_local_v6(&udest->addr.in6)) { - conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK) - | IP_VS_CONN_F_LOCALNODE; - } - } else -#endif - if (inet_addr_type(&init_net, udest->addr.ip) == RTN_LOCAL) { - conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK) - | IP_VS_CONN_F_LOCALNODE; - } - /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { conn_flags |= IP_VS_CONN_F_NOOUTPUT; @@ -824,6 +810,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, dest->u_threshold = udest->u_threshold; dest->l_threshold = udest->l_threshold; + spin_lock(&dest->dst_lock); + ip_vs_dst_reset(dest); + spin_unlock(&dest->dst_lock); + if (add) ip_vs_new_estimator(&dest->stats); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 63cc0fe..8608882 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -67,12 +67,19 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos) return dst; } +/* + * Get route to destination or remote server + * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest, + * &4=Allow redirect from remote daddr to local + */ static struct rtable * -__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_conn *cp, u32 rtos) +__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, + __be32 daddr, u32 rtos, int rt_mode) { - struct net *net = dev_net(skb->dev); + struct net *net = dev_net(skb_dst(skb)->dev); struct rtable *rt; /* Route to the other host */ - struct ip_vs_dest *dest = cp->dest; + struct rtable *ort; /* Original route */ + int local; if (dest) { spin_lock(&dest->dst_lock); @@ -104,23 +111,95 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_conn *cp, u32 rtos) .oif = 0, .nl_u = { .ip4_u = { - .daddr = cp->daddr.ip, + .daddr = daddr, .saddr = 0, .tos = rtos, } }, }; if (ip_route_output_key(net, &rt, &fl)) { IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", - &cp->daddr.ip); + &daddr); return NULL; } } + local = rt->rt_flags & RTCF_LOCAL; + if (!((local ? 1 : 2) & rt_mode)) { + IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n", + (rt->rt_flags & RTCF_LOCAL) ? + "local":"non-local", &rt->rt_dst); + ip_rt_put(rt); + return NULL; + } + if (local && !(rt_mode & 4) && !((ort = skb_rtable(skb)) && + ort->rt_flags & RTCF_LOCAL)) { + IP_VS_DBG_RL("Redirect from non-local address %pI4 to local " + "requires NAT method, dest: %pI4\n", + &ip_hdr(skb)->daddr, &rt->rt_dst); + ip_rt_put(rt); + return NULL; + } + if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) { + IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 " + "to non-local address, dest: %pI4\n", + &ip_hdr(skb)->saddr, &rt->rt_dst); + ip_rt_put(rt); + return NULL; + } + return rt; } +/* Reroute packet to local IPv4 stack after DNAT */ +static int +__ip_vs_reroute_locally(struct sk_buff *skb) +{ + struct rtable *rt = skb_rtable(skb); + struct net_device *dev = rt->dst.dev; + struct net *net = dev_net(dev); + struct iphdr *iph = ip_hdr(skb); + + if (rt->fl.iif) { + unsigned long orefdst = skb->_skb_refdst; + + if (ip_route_input(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) + return 0; + refdst_drop(orefdst); + } else { + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, + .tos = RT_TOS(iph->tos), + } + }, + .mark = skb->mark, + }; + struct rtable *rt; + + if (ip_route_output_key(net, &rt, &fl)) + return 0; + if (!(rt->rt_flags & RTCF_LOCAL)) { + ip_rt_put(rt); + return 0; + } + /* Drop old route. */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + } + return 1; +} + #ifdef CONFIG_IP_VS_IPV6 +static inline int __ip_vs_is_local_route6(struct rt6_info *rt) +{ + return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK; +} + static struct dst_entry * __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, struct in6_addr *ret_saddr, int do_xfrm) @@ -155,14 +234,21 @@ out_err: return NULL; } +/* + * Get route to destination or remote server + * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest, + * &4=Allow redirect from remote daddr to local + */ static struct rt6_info * -__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct in6_addr *ret_saddr, int do_xfrm) +__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, + struct in6_addr *daddr, struct in6_addr *ret_saddr, + int do_xfrm, int rt_mode) { - struct net *net = dev_net(skb->dev); + struct net *net = dev_net(skb_dst(skb)->dev); struct rt6_info *rt; /* Route to the other host */ - struct ip_vs_dest *dest = cp->dest; + struct rt6_info *ort; /* Original route */ struct dst_entry *dst; + int local; if (dest) { spin_lock(&dest->dst_lock); @@ -188,13 +274,38 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_conn *cp, ipv6_addr_copy(ret_saddr, &dest->dst_saddr); spin_unlock(&dest->dst_lock); } else { - dst = __ip_vs_route_output_v6(net, &cp->daddr.in6, ret_saddr, - do_xfrm); + dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); if (!dst) return NULL; rt = (struct rt6_info *) dst; } + local = __ip_vs_is_local_route6(rt); + if (!((local ? 1 : 2) & rt_mode)) { + IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n", + local ? "local":"non-local", daddr); + dst_release(&rt->dst); + return NULL; + } + if (local && !(rt_mode & 4) && + !((ort = (struct rt6_info *) skb_dst(skb)) && + __ip_vs_is_local_route6(ort))) { + IP_VS_DBG_RL("Redirect from non-local address %pI6 to local " + "requires NAT method, dest: %pI6\n", + &ipv6_hdr(skb)->daddr, daddr); + dst_release(&rt->dst); + return NULL; + } + if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) && + ipv6_addr_type(&ipv6_hdr(skb)->saddr) & + IPV6_ADDR_LOOPBACK)) { + IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 " + "to non-local address, dest: %pI6\n", + &ipv6_hdr(skb)->saddr, daddr); + dst_release(&rt->dst); + return NULL; + } + return rt; } #endif @@ -227,23 +338,27 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) __ret; \ }) -#define IP_VS_XMIT_NAT(pf, skb, cp) \ +#define IP_VS_XMIT_NAT(pf, skb, cp, local) \ do { \ (skb)->ipvs_property = 1; \ if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ ip_vs_notrack(skb); \ else \ ip_vs_update_conntrack(skb, cp, 1); \ + if (local) \ + return NF_ACCEPT; \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ skb_dst(skb)->dev, dst_output); \ } while (0) -#define IP_VS_XMIT(pf, skb, cp) \ +#define IP_VS_XMIT(pf, skb, cp, local) \ do { \ (skb)->ipvs_property = 1; \ if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ ip_vs_notrack(skb); \ + if (local) \ + return NF_ACCEPT; \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ skb_dst(skb)->dev, dst_output); \ @@ -258,7 +373,7 @@ ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { /* we do not touch skb and do not need pskb ptr */ - return NF_ACCEPT; + IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); } @@ -271,27 +386,15 @@ int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { - struct net *net = dev_net(skb->dev); struct rtable *rt; /* Route to the other host */ struct iphdr *iph = ip_hdr(skb); - u8 tos = iph->tos; int mtu; - struct flowi fl = { - .oif = 0, - .nl_u = { - .ip4_u = { - .daddr = iph->daddr, - .saddr = 0, - .tos = RT_TOS(tos), } }, - }; EnterFunction(10); - if (ip_route_output_key(net, &rt, &fl)) { - IP_VS_DBG_RL("%s(): ip_route_output error, dest: %pI4\n", - __func__, &iph->daddr); + if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, + RT_TOS(iph->tos), 2))) goto tx_error_icmp; - } /* MTU checking */ mtu = dst_mtu(&rt->dst); @@ -319,7 +422,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, cp); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0); LeaveFunction(10); return NF_STOLEN; @@ -337,18 +440,14 @@ int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { - struct net *net = dev_net(skb->dev); - struct dst_entry *dst; struct rt6_info *rt; /* Route to the other host */ struct ipv6hdr *iph = ipv6_hdr(skb); int mtu; EnterFunction(10); - dst = __ip_vs_route_output_v6(net, &iph->daddr, NULL, 0); - if (!dst) + if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, 2))) goto tx_error_icmp; - rt = (struct rt6_info *) dst; /* MTU checking */ mtu = dst_mtu(&rt->dst); @@ -376,7 +475,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, cp); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0); LeaveFunction(10); return NF_STOLEN; @@ -401,6 +500,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct rtable *rt; /* Route to the other host */ int mtu; struct iphdr *iph = ip_hdr(skb); + int local; EnterFunction(10); @@ -414,16 +514,40 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } - if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(iph->tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, + RT_TOS(iph->tos), 1|2|4))) goto tx_error_icmp; + local = rt->rt_flags & RTCF_LOCAL; + /* + * Avoid duplicate tuple in reply direction for NAT traffic + * to local address when connection is sync-ed + */ +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + if (cp->flags & IP_VS_CONN_F_SYNC && local) { + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + + if (ct && !nf_ct_is_untracked(ct)) { + IP_VS_DBG_RL_PKT(10, pp, skb, 0, "ip_vs_nat_xmit(): " + "stopping DNAT to local address"); + goto tx_error_put; + } + } +#endif + + /* From world but DNAT to loopback address? */ + if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { + IP_VS_DBG_RL_PKT(1, pp, skb, 0, "ip_vs_nat_xmit(): " + "stopping DNAT to loopback address"); + goto tx_error_put; + } /* MTU checking */ mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { - ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for"); - goto tx_error; + goto tx_error_put; } /* copy-on-write the packet before mangling it */ @@ -433,16 +557,27 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; - /* drop old route */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) - goto tx_error; + goto tx_error_put; ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); + if (!local) { + /* drop old route */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + } else { + ip_rt_put(rt); + /* + * Some IPv4 replies get local address from routes, + * not from iph, so while we DNAT after routing + * we need this second input/output route. + */ + if (!__ip_vs_reroute_locally(skb)) + goto tx_error; + } + IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length @@ -452,7 +587,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp); + IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local); LeaveFunction(10); return NF_STOLEN; @@ -475,6 +610,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, { struct rt6_info *rt; /* Route to the other host */ int mtu; + int local; EnterFunction(10); @@ -489,18 +625,44 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } - rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0); - if (!rt) + if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, + 0, 1|2|4))) goto tx_error_icmp; + local = __ip_vs_is_local_route6(rt); + /* + * Avoid duplicate tuple in reply direction for NAT traffic + * to local address when connection is sync-ed + */ +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + if (cp->flags & IP_VS_CONN_F_SYNC && local) { + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + + if (ct && !nf_ct_is_untracked(ct)) { + IP_VS_DBG_RL_PKT(10, pp, skb, 0, + "ip_vs_nat_xmit_v6(): " + "stopping DNAT to local address"); + goto tx_error_put; + } + } +#endif + + /* From world but DNAT to loopback address? */ + if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && + ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + IP_VS_DBG_RL_PKT(1, pp, skb, 0, + "ip_vs_nat_xmit_v6(): " + "stopping DNAT to loopback address"); + goto tx_error_put; + } /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { - dst_release(&rt->dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit_v6(): frag needed for"); - goto tx_error; + goto tx_error_put; } /* copy-on-write the packet before mangling it */ @@ -510,14 +672,19 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; - /* drop old route */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) goto tx_error; - ipv6_hdr(skb)->daddr = cp->daddr.in6; + ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6); + + if (!local || !skb->dev) { + /* drop the old route when skb is not shared */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + } else { + /* destined to loopback, do we need to change route? */ + dst_release(&rt->dst); + } IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); @@ -528,7 +695,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp); + IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local); LeaveFunction(10); return NF_STOLEN; @@ -588,16 +755,20 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } - if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, + RT_TOS(tos), 1|2))) goto tx_error_icmp; + if (rt->rt_flags & RTCF_LOCAL) { + ip_rt_put(rt); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); + } tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { - ip_rt_put(rt); IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); - goto tx_error; + goto tx_error_put; } if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); @@ -607,9 +778,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if ((old_iph->frag_off & htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); - ip_rt_put(rt); IP_VS_DBG_RL("%s(): frag needed\n", __func__); - goto tx_error; + goto tx_error_put; } /* @@ -678,6 +848,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; +tx_error_put: + ip_rt_put(rt); + goto tx_error; } #ifdef CONFIG_IP_VS_IPV6 @@ -703,27 +876,29 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } - rt = __ip_vs_get_out_rt_v6(skb, cp, &saddr, 1); - if (!rt) + if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, + &saddr, 1, 1|2))) goto tx_error_icmp; + if (__ip_vs_is_local_route6(rt)) { + dst_release(&rt->dst); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1); + } tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); if (mtu < IPV6_MIN_MTU) { - dst_release(&rt->dst); IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__, IPV6_MIN_MTU); - goto tx_error; + goto tx_error_put; } if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); - goto tx_error; + goto tx_error_put; } /* @@ -789,6 +964,9 @@ tx_error: kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; +tx_error_put: + dst_release(&rt->dst); + goto tx_error; } #endif @@ -807,8 +985,13 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(iph->tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, + RT_TOS(iph->tos), 1|2))) goto tx_error_icmp; + if (rt->rt_flags & RTCF_LOCAL) { + ip_rt_put(rt); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); + } /* MTU checking */ mtu = dst_mtu(&rt->dst); @@ -836,7 +1019,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, cp); + IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0); LeaveFunction(10); return NF_STOLEN; @@ -859,9 +1042,13 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0); - if (!rt) + if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, + 0, 1|2))) goto tx_error_icmp; + if (__ip_vs_is_local_route6(rt)) { + dst_release(&rt->dst); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1); + } /* MTU checking */ mtu = dst_mtu(&rt->dst); @@ -889,7 +1076,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, cp); + IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0); LeaveFunction(10); return NF_STOLEN; @@ -915,6 +1102,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct rtable *rt; /* Route to the other host */ int mtu; int rc; + int local; EnterFunction(10); @@ -935,16 +1123,43 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ - if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(ip_hdr(skb)->tos)))) + if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, + RT_TOS(ip_hdr(skb)->tos), 1|2|4))) goto tx_error_icmp; + local = rt->rt_flags & RTCF_LOCAL; + + /* + * Avoid duplicate tuple in reply direction for NAT traffic + * to local address when connection is sync-ed + */ +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + if (cp->flags & IP_VS_CONN_F_SYNC && local) { + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + + if (ct && !nf_ct_is_untracked(ct)) { + IP_VS_DBG(10, "%s(): " + "stopping DNAT to local address %pI4\n", + __func__, &cp->daddr.ip); + goto tx_error_put; + } + } +#endif + + /* From world but DNAT to loopback address? */ + if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { + IP_VS_DBG(1, "%s(): " + "stopping DNAT to loopback %pI4\n", + __func__, &cp->daddr.ip); + goto tx_error_put; + } /* MTU checking */ mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) { - ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); - goto tx_error; + goto tx_error_put; } /* copy-on-write the packet before mangling it */ @@ -954,16 +1169,27 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; - /* drop the old route when skb is not shared */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - ip_vs_nat_icmp(skb, pp, cp, 0); + if (!local) { + /* drop the old route when skb is not shared */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + } else { + ip_rt_put(rt); + /* + * Some IPv4 replies get local address from routes, + * not from iph, so while we DNAT after routing + * we need this second input/output route. + */ + if (!__ip_vs_reroute_locally(skb)) + goto tx_error; + } + /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV4, skb, cp); + IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local); rc = NF_STOLEN; goto out; @@ -989,6 +1215,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct rt6_info *rt; /* Route to the other host */ int mtu; int rc; + int local; EnterFunction(10); @@ -1009,17 +1236,44 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ - rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0); - if (!rt) + if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, + 0, 1|2|4))) goto tx_error_icmp; + local = __ip_vs_is_local_route6(rt); + /* + * Avoid duplicate tuple in reply direction for NAT traffic + * to local address when connection is sync-ed + */ +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + if (cp->flags & IP_VS_CONN_F_SYNC && local) { + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + + if (ct && !nf_ct_is_untracked(ct)) { + IP_VS_DBG(10, "%s(): " + "stopping DNAT to local address %pI6\n", + __func__, &cp->daddr.in6); + goto tx_error_put; + } + } +#endif + + /* From world but DNAT to loopback address? */ + if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && + ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + IP_VS_DBG(1, "%s(): " + "stopping DNAT to loopback %pI6\n", + __func__, &cp->daddr.in6); + goto tx_error_put; + } + /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { - dst_release(&rt->dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); - goto tx_error; + goto tx_error_put; } /* copy-on-write the packet before mangling it */ @@ -1029,16 +1283,21 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; - /* drop the old route when skb is not shared */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - ip_vs_nat_icmp_v6(skb, pp, cp, 0); + if (!local || !skb->dev) { + /* drop the old route when skb is not shared */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + } else { + /* destined to loopback, do we need to change route? */ + dst_release(&rt->dst); + } + /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; - IP_VS_XMIT(NFPROTO_IPV6, skb, cp); + IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local); rc = NF_STOLEN; goto out; -- cgit v0.10.2 From cb59155f21d4c0507d2034c2953f6a3f7806913d Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:40:51 +0300 Subject: ipvs: changes for local client This patch deals with local client processing. Prefer LOCAL_OUT hook for scheduling connections from local clients. LOCAL_IN is still supported if the packets are not marked as processed in LOCAL_OUT. The idea to process requests in LOCAL_OUT is to alter conntrack reply before it is confirmed at POST_ROUTING. If the local requests are processed in LOCAL_IN the conntrack can not be updated and matching by state is impossible. Add the following handlers: - ip_vs_reply[46] at LOCAL_IN:99 to process replies from remote real servers to local clients. Now when both replies from remote real servers (ip_vs_reply*) and local real servers (ip_vs_local_reply*) are handled it is safe to remove the conn_out_get call from ip_vs_in because it does not support related ICMP packets. - ip_vs_local_request[46] at LOCAL_OUT:-98 to process requests from local client Handling in LOCAL_OUT causes some changes: - as skb->dev, skb->protocol and skb->pkt_type are not defined in LOCAL_OUT make sure we set skb->dev before calling icmpv6_send, prefer skb_dst(skb) for struct net and remove the skb->protocol checks from TUN transmitters. [ horms@verge.net.au: removed trailing whitespace ] Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a6c8aff..5fbcf67 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -529,9 +529,14 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ #ifdef CONFIG_IP_VS_IPV6 - if (svc->af == AF_INET6) + if (svc->af == AF_INET6) { + if (!skb->dev) { + struct net *net = dev_net(skb_dst(skb)->dev); + + skb->dev = net->loopback_dev; + } icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); - else + } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -1065,57 +1070,61 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) */ cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0); - if (unlikely(!cp)) { - if (sysctl_ip_vs_nat_icmp_send && - (pp->protocol == IPPROTO_TCP || - pp->protocol == IPPROTO_UDP || - pp->protocol == IPPROTO_SCTP)) { - __be16 _ports[2], *pptr; - - pptr = skb_header_pointer(skb, iph.len, - sizeof(_ports), _ports); - if (pptr == NULL) - return NF_ACCEPT; /* Not for me */ - if (ip_vs_lookup_real_service(af, iph.protocol, - &iph.saddr, - pptr[0])) { - /* - * Notify the real server: there is no - * existing entry if it is not RST - * packet or not TCP packet. - */ - if ((iph.protocol != IPPROTO_TCP && - iph.protocol != IPPROTO_SCTP) - || ((iph.protocol == IPPROTO_TCP - && !is_tcp_reset(skb, iph.len)) - || (iph.protocol == IPPROTO_SCTP - && !is_sctp_abort(skb, - iph.len)))) { + if (likely(cp)) + return handle_response(af, skb, pp, cp, iph.len); + if (sysctl_ip_vs_nat_icmp_send && + (pp->protocol == IPPROTO_TCP || + pp->protocol == IPPROTO_UDP || + pp->protocol == IPPROTO_SCTP)) { + __be16 _ports[2], *pptr; + + pptr = skb_header_pointer(skb, iph.len, + sizeof(_ports), _ports); + if (pptr == NULL) + return NF_ACCEPT; /* Not for me */ + if (ip_vs_lookup_real_service(af, iph.protocol, + &iph.saddr, + pptr[0])) { + /* + * Notify the real server: there is no + * existing entry if it is not RST + * packet or not TCP packet. + */ + if ((iph.protocol != IPPROTO_TCP && + iph.protocol != IPPROTO_SCTP) + || ((iph.protocol == IPPROTO_TCP + && !is_tcp_reset(skb, iph.len)) + || (iph.protocol == IPPROTO_SCTP + && !is_sctp_abort(skb, + iph.len)))) { #ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) - icmpv6_send(skb, - ICMPV6_DEST_UNREACH, - ICMPV6_PORT_UNREACH, - 0); - else + if (af == AF_INET6) { + struct net *net = + dev_net(skb_dst(skb)->dev); + + if (!skb->dev) + skb->dev = net->loopback_dev; + icmpv6_send(skb, + ICMPV6_DEST_UNREACH, + ICMPV6_PORT_UNREACH, + 0); + } else #endif - icmp_send(skb, - ICMP_DEST_UNREACH, - ICMP_PORT_UNREACH, 0); - return NF_DROP; - } + icmp_send(skb, + ICMP_DEST_UNREACH, + ICMP_PORT_UNREACH, 0); + return NF_DROP; } } - IP_VS_DBG_PKT(12, pp, skb, 0, - "packet continues traversal as normal"); - return NF_ACCEPT; } - - return handle_response(af, skb, pp, cp, iph.len); + IP_VS_DBG_PKT(12, pp, skb, 0, + "ip_vs_out: packet continues traversal as normal"); + return NF_ACCEPT; } /* - * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT. + * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, + * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int @@ -1147,7 +1156,8 @@ ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 /* - * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT. + * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, + * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int @@ -1404,34 +1414,43 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) * and send it on its way... */ static unsigned int -ip_vs_in(unsigned int hooknum, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_conn *cp; - int ret, restart, af, pkts; + int ret, restart, pkts; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; - af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6; - - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - /* - * Big tappo: only PACKET_HOST, including loopback for local client - * Don't handle local packets on IPv6 for now + * Big tappo: + * - remote client: only PACKET_HOST + * - route: used for struct net when skb->dev is unset */ - if (unlikely(skb->pkt_type != PACKET_HOST)) { - IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s ignored\n", - skb->pkt_type, - iph.protocol, - IP_VS_DBG_ADDR(af, &iph.daddr)); + if (unlikely((skb->pkt_type != PACKET_HOST && + hooknum != NF_INET_LOCAL_OUT) || + !skb_dst(skb))) { + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" + " ignored in hook %u\n", + skb->pkt_type, iph.protocol, + IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + + /* Bad... Do not break raw sockets */ + if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && + af == AF_INET)) { + struct sock *sk = skb->sk; + struct inet_sock *inet = inet_sk(skb->sk); + + if (inet && sk->sk_family == PF_INET && inet->nodefrag) + return NF_ACCEPT; + } #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1467,11 +1486,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, if (unlikely(!cp)) { int v; - /* For local client packets, it could be a response */ - cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0); - if (cp) - return handle_response(af, skb, pp, cp, iph.len); - if (!pp->conn_schedule(af, skb, pp, &v, &cp)) return v; } @@ -1479,7 +1493,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, if (unlikely(!cp)) { /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, pp, skb, 0, - "packet continues traversal as normal"); + "ip_vs_in: packet continues traversal as normal"); return NF_ACCEPT; } @@ -1550,6 +1564,72 @@ out: return ret; } +/* + * AF_INET handler in NF_INET_LOCAL_IN chain + * Schedule and forward packets from remote clients + */ +static unsigned int +ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return ip_vs_in(hooknum, skb, AF_INET); +} + +/* + * AF_INET handler in NF_INET_LOCAL_OUT chain + * Schedule and forward packets from local clients + */ +static unsigned int +ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int verdict; + + /* Disable BH in LOCAL_OUT until all places are fixed */ + local_bh_disable(); + verdict = ip_vs_in(hooknum, skb, AF_INET); + local_bh_enable(); + return verdict; +} + +#ifdef CONFIG_IP_VS_IPV6 + +/* + * AF_INET6 handler in NF_INET_LOCAL_IN chain + * Schedule and forward packets from remote clients + */ +static unsigned int +ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return ip_vs_in(hooknum, skb, AF_INET6); +} + +/* + * AF_INET6 handler in NF_INET_LOCAL_OUT chain + * Schedule and forward packets from local clients + */ +static unsigned int +ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int verdict; + + /* Disable BH in LOCAL_OUT until all places are fixed */ + local_bh_disable(); + verdict = ip_vs_in(hooknum, skb, AF_INET6); + local_bh_enable(); + return verdict; +} + +#endif + /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP @@ -1590,15 +1670,23 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, static struct nf_hook_ops ip_vs_ops[] __read_mostly = { + /* After packet filtering, change source only for VS/NAT */ + { + .hook = ip_vs_reply4, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_INET_LOCAL_IN, + .priority = 99, + }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_in, + .hook = ip_vs_remote_request4, .owner = THIS_MODULE, .pf = PF_INET, - .hooknum = NF_INET_LOCAL_IN, - .priority = 100, + .hooknum = NF_INET_LOCAL_IN, + .priority = 101, }, /* Before ip_vs_in, change source only for VS/NAT */ { @@ -1608,14 +1696,22 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_LOCAL_OUT, .priority = -99, }, + /* After mangle, schedule and forward local requests */ + { + .hook = ip_vs_local_request4, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_INET_LOCAL_OUT, + .priority = -98, + }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .owner = THIS_MODULE, .pf = PF_INET, - .hooknum = NF_INET_FORWARD, - .priority = 99, + .hooknum = NF_INET_FORWARD, + .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { @@ -1626,15 +1722,23 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .priority = 100, }, #ifdef CONFIG_IP_VS_IPV6 + /* After packet filtering, change source only for VS/NAT */ + { + .hook = ip_vs_reply6, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_LOCAL_IN, + .priority = 99, + }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_in, + .hook = ip_vs_remote_request6, .owner = THIS_MODULE, .pf = PF_INET6, - .hooknum = NF_INET_LOCAL_IN, - .priority = 100, + .hooknum = NF_INET_LOCAL_IN, + .priority = 101, }, /* Before ip_vs_in, change source only for VS/NAT */ { @@ -1644,14 +1748,22 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .hooknum = NF_INET_LOCAL_OUT, .priority = -99, }, + /* After mangle, schedule and forward local requests */ + { + .hook = ip_vs_local_request6, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = -98, + }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp_v6, .owner = THIS_MODULE, .pf = PF_INET6, - .hooknum = NF_INET_FORWARD, - .priority = 99, + .hooknum = NF_INET_FORWARD, + .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 8608882..97b5361 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -11,6 +11,16 @@ * * Changes: * + * Description of forwarding methods: + * - all transmitters are called from LOCAL_IN (remote clients) and + * LOCAL_OUT (local clients) but for ICMP can be called from FORWARD + * - not all connections have destination server, for example, + * connections in backup server when fwmark is used + * - bypass connections use daddr from packet + * LOCAL_OUT rules: + * - skb->dev is NULL, skb->protocol is not set (both are set in POST_ROUTING) + * - skb->pkt_type is not set yet + * - the only place where we can see skb->sk != NULL */ #define KMSG_COMPONENT "IPVS" @@ -452,8 +462,13 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { - dst_release(&rt->dst); + if (!skb->dev) { + struct net *net = dev_net(skb_dst(skb)->dev); + + skb->dev = net->loopback_dev; + } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -659,6 +674,11 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { + if (!skb->dev) { + struct net *net = dev_net(skb_dst(skb)->dev); + + skb->dev = net->loopback_dev; + } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit_v6(): frag needed for"); @@ -748,13 +768,6 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (skb->protocol != htons(ETH_P_IP)) { - IP_VS_DBG_RL("%s(): protocol error, " - "ETH_P_IP: %d, skb protocol: %d\n", - __func__, htons(ETH_P_IP), skb->protocol); - goto tx_error; - } - if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(tos), 1|2))) goto tx_error_icmp; @@ -869,13 +882,6 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (skb->protocol != htons(ETH_P_IPV6)) { - IP_VS_DBG_RL("%s(): protocol error, " - "ETH_P_IPV6: %d, skb protocol: %d\n", - __func__, htons(ETH_P_IPV6), skb->protocol); - goto tx_error; - } - if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, &saddr, 1, 1|2))) goto tx_error_icmp; @@ -896,6 +902,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { + if (!skb->dev) { + struct net *net = dev_net(skb_dst(skb)->dev); + + skb->dev = net->loopback_dev; + } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; @@ -1053,6 +1064,11 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { + if (!skb->dev) { + struct net *net = dev_net(skb_dst(skb)->dev); + + skb->dev = net->loopback_dev; + } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); @@ -1271,6 +1287,11 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { + if (!skb->dev) { + struct net *net = dev_net(skb_dst(skb)->dev); + + skb->dev = net->loopback_dev; + } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; -- cgit v0.10.2 From 3233759be7eeca9998c514b8f49e8cf2b85e64d3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:43:36 +0300 Subject: ipvs: inherit forwarding method in backup Connections in backup server should inherit the forwarding method from real server. It is a way to fix a problem where the forwarding method in backup connection is damaged by logical OR operation with the real server's connection flags. And the change is needed for setups where the backup server uses different forwarding method for the same real servers. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 1d1a529..e9adecd 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -563,6 +563,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) conn_flags &= ~IP_VS_CONN_F_INACTIVE; + /* connections inherit forwarding method from dest */ + cp->flags &= ~IP_VS_CONN_F_FWD_MASK; } cp->flags |= conn_flags; cp->dest = dest; -- cgit v0.10.2 From 0d79641a96d612aaa6d57a4d4f521d7ed9c9ccdd Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 17 Oct 2010 16:46:17 +0300 Subject: ipvs: provide address family for debugging As skb->protocol is not valid in LOCAL_OUT add parameter for address family in packet debugging functions. Even if ports are not present in AH and ESP change them to use ip_vs_tcpudp_debug_packet to show at least valid addresses as before. This patch removes the last user of skb->protocol in IPVS. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2f88d59..b7bbd6c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -136,24 +136,24 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len, if (net_ratelimit()) \ printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__); \ } while (0) -#define IP_VS_DBG_PKT(level, pp, skb, ofs, msg) \ +#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg) \ do { \ if (level <= ip_vs_get_debug_level()) \ - pp->debug_packet(pp, skb, ofs, msg); \ + pp->debug_packet(af, pp, skb, ofs, msg); \ } while (0) -#define IP_VS_DBG_RL_PKT(level, pp, skb, ofs, msg) \ +#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg) \ do { \ if (level <= ip_vs_get_debug_level() && \ net_ratelimit()) \ - pp->debug_packet(pp, skb, ofs, msg); \ + pp->debug_packet(af, pp, skb, ofs, msg); \ } while (0) #else /* NO DEBUGGING at ALL */ #define IP_VS_DBG_BUF(level, msg...) do {} while (0) #define IP_VS_ERR_BUF(msg...) do {} while (0) #define IP_VS_DBG(level, msg...) do {} while (0) #define IP_VS_DBG_RL(msg...) do {} while (0) -#define IP_VS_DBG_PKT(level, pp, skb, ofs, msg) do {} while (0) -#define IP_VS_DBG_RL_PKT(level, pp, skb, ofs, msg) do {} while (0) +#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg) do {} while (0) +#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg) do {} while (0) #endif #define IP_VS_BUG() BUG() @@ -345,7 +345,7 @@ struct ip_vs_protocol { int (*app_conn_bind)(struct ip_vs_conn *cp); - void (*debug_packet)(struct ip_vs_protocol *pp, + void (*debug_packet)(int af, struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg); @@ -828,7 +828,8 @@ extern int ip_vs_set_state_timeout(int *table, int num, const char *const *names, const char *name, int to); extern void -ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, +ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, + const struct sk_buff *skb, int offset, const char *msg); extern struct ip_vs_protocol ip_vs_protocol_tcp; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5fbcf67..b4e51e9 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -365,7 +365,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * with persistence the connection is created on SYN+ACK. */ if (pptr[0] == FTPDATA) { - IP_VS_DBG_PKT(12, pp, skb, 0, "Not scheduling FTPDATA"); + IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, + "Not scheduling FTPDATA"); return NULL; } @@ -376,7 +377,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) && (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) { - IP_VS_DBG_PKT(12, pp, skb, 0, + IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, "Not scheduling reply for existing connection"); __ip_vs_conn_put(cp); return NULL; @@ -617,10 +618,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMP"); } @@ -662,11 +663,13 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, skb->ip_summed = CHECKSUM_PARTIAL; if (inout) - IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered outgoing ICMPv6"); + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, + (void *)ciph - (void *)iph, + "Forwarding altered outgoing ICMPv6"); else - IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered incoming ICMPv6"); + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, + (void *)ciph - (void *)iph, + "Forwarding altered incoming ICMPv6"); } #endif @@ -798,7 +801,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, pp->dont_defrag)) return NF_ACCEPT; - IP_VS_DBG_PKT(11, pp, skb, offset, "Checking outgoing ICMP for"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, + "Checking outgoing ICMP for"); offset += cih->ihl * 4; @@ -874,7 +878,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag)) return NF_ACCEPT; - IP_VS_DBG_PKT(11, pp, skb, offset, "Checking outgoing ICMPv6 for"); + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, + "Checking outgoing ICMPv6 for"); offset += sizeof(struct ipv6hdr); @@ -922,7 +927,7 @@ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int ihl) { - IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet"); + IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); if (!skb_make_writable(skb, ihl)) goto drop; @@ -967,7 +972,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_route_me_harder(skb, RTN_LOCAL) != 0) goto drop; - IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT"); + IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); @@ -1117,7 +1122,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) } } } - IP_VS_DBG_PKT(12, pp, skb, 0, + IP_VS_DBG_PKT(12, af, pp, skb, 0, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } @@ -1253,7 +1258,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) pp->dont_defrag)) return NF_ACCEPT; - IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMP for"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, + "Checking incoming ICMP for"); offset += cih->ihl * 4; @@ -1364,7 +1370,8 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag)) return NF_ACCEPT; - IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMPv6 for"); + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, + "Checking incoming ICMPv6 for"); offset += sizeof(struct ipv6hdr); @@ -1492,12 +1499,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely(!cp)) { /* sorry, all this trouble for a no-hit :) */ - IP_VS_DBG_PKT(12, pp, skb, 0, + IP_VS_DBG_PKT(12, af, pp, skb, 0, "ip_vs_in: packet continues traversal as normal"); return NF_ACCEPT; } - IP_VS_DBG_PKT(11, pp, skb, 0, "Incoming packet"); + IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 027f654..c539983 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -172,8 +172,8 @@ ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp, else if (ih->frag_off & htons(IP_OFFSET)) sprintf(buf, "%pI4->%pI4 frag", &ih->saddr, &ih->daddr); else { - __be16 _ports[2], *pptr -; + __be16 _ports[2], *pptr; + pptr = skb_header_pointer(skb, offset + ih->ihl*4, sizeof(_ports), _ports); if (pptr == NULL) @@ -223,13 +223,13 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, void -ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, +ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { #ifdef CONFIG_IP_VS_IPV6 - if (skb->protocol == htons(ETH_P_IPV6)) + if (af == AF_INET6) ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg); else #endif diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 8956ef3..3a04611 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -117,54 +117,6 @@ ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; } - -static void -ah_esp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb, - int offset, const char *msg) -{ - char buf[256]; - struct iphdr _iph, *ih; - - ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); - if (ih == NULL) - sprintf(buf, "TRUNCATED"); - else - sprintf(buf, "%pI4->%pI4", &ih->saddr, &ih->daddr); - - pr_debug("%s: %s %s\n", msg, pp->name, buf); -} - -#ifdef CONFIG_IP_VS_IPV6 -static void -ah_esp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb, - int offset, const char *msg) -{ - char buf[256]; - struct ipv6hdr _iph, *ih; - - ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); - if (ih == NULL) - sprintf(buf, "TRUNCATED"); - else - sprintf(buf, "%pI6->%pI6", &ih->saddr, &ih->daddr); - - pr_debug("%s: %s %s\n", msg, pp->name, buf); -} -#endif - -static void -ah_esp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb, - int offset, const char *msg) -{ -#ifdef CONFIG_IP_VS_IPV6 - if (skb->protocol == htons(ETH_P_IPV6)) - ah_esp_debug_packet_v6(pp, skb, offset, msg); - else -#endif - ah_esp_debug_packet_v4(pp, skb, offset, msg); -} - - static void ah_esp_init(struct ip_vs_protocol *pp) { /* nothing to do now */ @@ -195,7 +147,7 @@ struct ip_vs_protocol ip_vs_protocol_ah = { .register_app = NULL, .unregister_app = NULL, .app_conn_bind = NULL, - .debug_packet = ah_esp_debug_packet, + .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, /* ISAKMP */ .set_state_timeout = NULL, }; @@ -219,7 +171,7 @@ struct ip_vs_protocol ip_vs_protocol_esp = { .register_app = NULL, .unregister_app = NULL, .app_conn_bind = NULL, - .debug_packet = ah_esp_debug_packet, + .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, /* ISAKMP */ }; #endif diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 9ab5232..d254345 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -176,7 +176,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) if (val != cmp) { /* CRC failure, dump it. */ - IP_VS_DBG_RL_PKT(0, pp, skb, 0, + IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 85d80a6..f6c5200 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -300,7 +300,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) skb->len - tcphoff, ipv6_hdr(skb)->nexthdr, skb->csum)) { - IP_VS_DBG_RL_PKT(0, pp, skb, 0, + IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } @@ -311,7 +311,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) skb->len - tcphoff, ip_hdr(skb)->protocol, skb->csum)) { - IP_VS_DBG_RL_PKT(0, pp, skb, 0, + IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 5d21f08..9d106a0 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -314,7 +314,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) skb->len - udphoff, ipv6_hdr(skb)->nexthdr, skb->csum)) { - IP_VS_DBG_RL_PKT(0, pp, skb, 0, + IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } @@ -325,7 +325,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) skb->len - udphoff, ip_hdr(skb)->protocol, skb->csum)) { - IP_VS_DBG_RL_PKT(0, pp, skb, 0, + IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 97b5361..de04ea3 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -543,7 +543,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { - IP_VS_DBG_RL_PKT(10, pp, skb, 0, "ip_vs_nat_xmit(): " + IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0, + "ip_vs_nat_xmit(): " "stopping DNAT to local address"); goto tx_error_put; } @@ -552,7 +553,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { - IP_VS_DBG_RL_PKT(1, pp, skb, 0, "ip_vs_nat_xmit(): " + IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); goto tx_error_put; } @@ -561,7 +562,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); - IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for"); + IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0, + "ip_vs_nat_xmit(): frag needed for"); goto tx_error_put; } @@ -593,7 +595,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } - IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); + IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -654,7 +656,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { - IP_VS_DBG_RL_PKT(10, pp, skb, 0, + IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to local address"); goto tx_error_put; @@ -665,7 +667,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { - IP_VS_DBG_RL_PKT(1, pp, skb, 0, + IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); goto tx_error_put; @@ -680,7 +682,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->dev = net->loopback_dev; } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - IP_VS_DBG_RL_PKT(0, pp, skb, 0, + IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): frag needed for"); goto tx_error_put; } @@ -706,7 +708,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, dst_release(&rt->dst); } - IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); + IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still -- cgit v0.10.2 From 106e4c26b1529e559d1aae777f11b4f8f7bafc26 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 12:45:14 +0200 Subject: tproxy: kick out TIME_WAIT sockets in case a new connection comes in with the same tuple Without tproxy redirections an incoming SYN kicks out conflicting TIME_WAIT sockets, in order to handle clients that reuse ports within the TIME_WAIT period. The same mechanism didn't work in case TProxy is involved in finding the proper socket, as the time_wait processing code looked up the listening socket assuming that the listener addr/port matches those of the established connection. This is not the case with TProxy as the listener addr/port is possibly changed with the tproxy rule. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index 208b46f..b3a8942 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -8,12 +8,16 @@ #include #include +#define NFT_LOOKUP_ANY 0 +#define NFT_LOOKUP_LISTENER 1 +#define NFT_LOOKUP_ESTABLISHED 2 + /* look up and get a reference to a matching socket */ extern struct sock * nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, - const struct net_device *in, bool listening); + const struct net_device *in, int lookup_type); static inline void nf_tproxy_put_sock(struct sock *sk) diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index 5490fc3..8589e5e 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -22,21 +22,34 @@ struct sock * nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, - const struct net_device *in, bool listening_only) + const struct net_device *in, int lookup_type) { struct sock *sk; /* look up socket */ switch (protocol) { case IPPROTO_TCP: - if (listening_only) - sk = __inet_lookup_listener(net, &tcp_hashinfo, - daddr, ntohs(dport), - in->ifindex); - else + switch (lookup_type) { + case NFT_LOOKUP_ANY: sk = __inet_lookup(net, &tcp_hashinfo, saddr, sport, daddr, dport, in->ifindex); + break; + case NFT_LOOKUP_LISTENER: + sk = inet_lookup_listener(net, &tcp_hashinfo, + daddr, dport, + in->ifindex); + break; + case NFT_LOOKUP_ESTABLISHED: + sk = inet_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + default: + WARN_ON(1); + sk = NULL; + break; + } break; case IPPROTO_UDP: sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, @@ -47,8 +60,8 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, sk = NULL; } - pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, listener only: %d, sock %p\n", - protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), listening_only, sk); + pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", + protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); return sk; } diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 21bb2af..e0b6900 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -24,6 +24,57 @@ #include #include +/** + * tproxy_handle_time_wait() - handle TCP TIME_WAIT reopen redirections + * @skb: The skb being processed. + * @par: Iptables target parameters. + * @sk: The TIME_WAIT TCP socket found by the lookup. + * + * We have to handle SYN packets arriving to TIME_WAIT sockets + * differently: instead of reopening the connection we should rather + * redirect the new connection to the proxy if there's a listener + * socket present. + * + * tproxy_handle_time_wait() consumes the socket reference passed in. + * + * Returns the listener socket if there's one, the TIME_WAIT socket if + * no such listener is found, or NULL if the TCP header is incomplete. + */ +static struct sock * +tproxy_handle_time_wait(struct sk_buff *skb, const struct xt_action_param *par, struct sock *sk) +{ + const struct iphdr *iph = ip_hdr(skb); + const struct xt_tproxy_target_info *tgi = par->targinfo; + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); + if (hp == NULL) { + inet_twsk_put(inet_twsk(sk)); + return NULL; + } + + if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { + /* SYN to a TIME_WAIT socket, we'd rather redirect it + * to a listener socket if there's one */ + struct sock *sk2; + + sk2 = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, + iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr, + hp->source, tgi->lport ? tgi->lport : hp->dest, + par->in, NFT_LOOKUP_LISTENER); + if (sk2) { + /* yeah, there's one, let's kill the TIME_WAIT + * socket and redirect to the listener + */ + inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_put(inet_twsk(sk)); + sk = sk2; + } + } + + return sk; +} + static unsigned int tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par) { @@ -37,11 +88,18 @@ tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par) return NF_DROP; sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, - iph->saddr, - tgi->laddr ? tgi->laddr : iph->daddr, - hp->source, - tgi->lport ? tgi->lport : hp->dest, - par->in, true); + iph->saddr, iph->daddr, + hp->source, hp->dest, + par->in, NFT_LOOKUP_ESTABLISHED); + + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ + if (sk && sk->sk_state == TCP_TIME_WAIT) + sk = tproxy_handle_time_wait(skb, par, sk); + else if (!sk) + sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, + iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr, + hp->source, tgi->lport ? tgi->lport : hp->dest, + par->in, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ if (sk && nf_tproxy_assign_sock(skb, sk)) { diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 1ca8990..266faa0 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -142,7 +142,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, #endif sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, - saddr, daddr, sport, dport, par->in, false); + saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); if (sk != NULL) { bool wildcard; bool transparent = true; -- cgit v0.10.2 From 6006db84a91838813cdad8a6622a4e39efe9ea47 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 12:47:34 +0200 Subject: tproxy: add lookup type checks for UDP in nf_tproxy_get_sock_v4() Also, inline this function as the lookup_type is always a literal and inlining removes branches performed at runtime. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index b3a8942..1027d7f 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -13,11 +13,123 @@ #define NFT_LOOKUP_ESTABLISHED 2 /* look up and get a reference to a matching socket */ -extern struct sock * + + +/* This function is used by the 'TPROXY' target and the 'socket' + * match. The following lookups are supported: + * + * Explicit TProxy target rule + * =========================== + * + * This is used when the user wants to intercept a connection matching + * an explicit iptables rule. In this case the sockets are assumed + * matching in preference order: + * + * - match: if there's a fully established connection matching the + * _packet_ tuple, it is returned, assuming the redirection + * already took place and we process a packet belonging to an + * established connection + * + * - match: if there's a listening socket matching the redirection + * (e.g. on-port & on-ip of the connection), it is returned, + * regardless if it was bound to 0.0.0.0 or an explicit + * address. The reasoning is that if there's an explicit rule, it + * does not really matter if the listener is bound to an interface + * or to 0. The user already stated that he wants redirection + * (since he added the rule). + * + * "socket" match based redirection (no specific rule) + * =================================================== + * + * There are connections with dynamic endpoints (e.g. FTP data + * connection) that the user is unable to add explicit rules + * for. These are taken care of by a generic "socket" rule. It is + * assumed that the proxy application is trusted to open such + * connections without explicit iptables rule (except of course the + * generic 'socket' rule). In this case the following sockets are + * matched in preference order: + * + * - match: if there's a fully established connection matching the + * _packet_ tuple + * + * - match: if there's a non-zero bound listener (possibly with a + * non-local address) We don't accept zero-bound listeners, since + * then local services could intercept traffic going through the + * box. + * + * Please note that there's an overlap between what a TPROXY target + * and a socket match will match. Normally if you have both rules the + * "socket" match will be the first one, effectively all packets + * belonging to established connections going through that one. + */ +static inline struct sock * nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, - const struct net_device *in, int lookup_type); + const struct net_device *in, int lookup_type) +{ + struct sock *sk; + + /* look up socket */ + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NFT_LOOKUP_ANY: + sk = __inet_lookup(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + case NFT_LOOKUP_LISTENER: + sk = inet_lookup_listener(net, &tcp_hashinfo, + daddr, dport, + in->ifindex); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too */ + + break; + case NFT_LOOKUP_ESTABLISHED: + sk = inet_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + default: + WARN_ON(1); + sk = NULL; + break; + } + break; + case IPPROTO_UDP: + sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk && lookup_type != NFT_LOOKUP_ANY) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too */ + if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NFT_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", + protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); + + return sk; +} + static inline void nf_tproxy_put_sock(struct sock *sk) diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index 8589e5e..db65563 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -18,54 +18,6 @@ #include #include -struct sock * -nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, - const __be32 saddr, const __be32 daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, int lookup_type) -{ - struct sock *sk; - - /* look up socket */ - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_ANY: - sk = __inet_lookup(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - case NFT_LOOKUP_LISTENER: - sk = inet_lookup_listener(net, &tcp_hashinfo, - daddr, dport, - in->ifindex); - break; - case NFT_LOOKUP_ESTABLISHED: - sk = inet_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - default: - WARN_ON(1); - sk = NULL; - break; - } - break; - case IPPROTO_UDP: - sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", - protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); - - return sk; -} -EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v4); static void nf_tproxy_destructor(struct sk_buff *skb) -- cgit v0.10.2 From 093d282321daeb19c107e5f1f16d7f68484f3ade Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 13:06:43 +0200 Subject: tproxy: fix hash locking issue when using port redirection in __inet_inherit_port() When __inet_inherit_port() is called on a tproxy connection the wrong locks are held for the inet_bind_bucket it is added to. __inet_inherit_port() made an implicit assumption that the listener's port number (and thus its bind bucket). Unfortunately, if you're using the TPROXY target to redirect skbs to a transparent proxy that assumption is not true anymore and things break. This patch adds code to __inet_inherit_port() so that it can handle this case by looking up or creating a new bind bucket for the child socket and updates callers of __inet_inherit_port() to gracefully handle __inet_inherit_port() failing. Reported by and original patch from Stephen Buck . See http://marc.info/?t=128169268200001&r=1&w=2 for the original discussion. Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 74358d1..e9c2ed8 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -245,7 +245,7 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk) } /* Caller must disable local BH processing. */ -extern void __inet_inherit_port(struct sock *sk, struct sock *child); +extern int __inet_inherit_port(struct sock *sk, struct sock *child); extern void inet_put_port(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d4a166f..3f69ea1 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -392,7 +392,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto exit; + goto exit_nonewsk; sk_setup_caps(newsk, dst); @@ -409,16 +409,20 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, dccp_sync_mss(newsk, dst_mtu(dst)); + if (__inet_inherit_port(sk, newsk) < 0) { + sock_put(newsk); + goto exit; + } __inet_hash_nolisten(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; exit_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +exit_nonewsk: + dst_release(dst); exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - dst_release(dst); return NULL; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6e3f325..dca711d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -564,7 +564,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto out; + goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -632,18 +632,22 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (__inet_inherit_port(sk, newsk) < 0) { + sock_put(newsk); + goto out; + } __inet6_hash(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; out_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +out_nonewsk: + dst_release(dst); out: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); if (opt != NULL && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return NULL; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fb7ad5a..1b344f3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -101,19 +101,43 @@ void inet_put_port(struct sock *sk) } EXPORT_SYMBOL(inet_put_port); -void __inet_inherit_port(struct sock *sk, struct sock *child) +int __inet_inherit_port(struct sock *sk, struct sock *child) { struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->inet_num, + unsigned short port = inet_sk(child)->inet_num; + const int bhash = inet_bhashfn(sock_net(sk), port, table->bhash_size); struct inet_bind_hashbucket *head = &table->bhash[bhash]; struct inet_bind_bucket *tb; spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; + if (tb->port != port) { + /* NOTE: using tproxy and redirecting skbs to a proxy + * on a different listener port breaks the assumption + * that the listener socket's icsk_bind_hash is the same + * as that of the child socket. We have to look up or + * create a new bind bucket for the child here. */ + struct hlist_node *node; + inet_bind_bucket_for_each(tb, node, &head->chain) { + if (net_eq(ib_net(tb), sock_net(sk)) && + tb->port == port) + break; + } + if (!node) { + tb = inet_bind_bucket_create(table->bind_bucket_cachep, + sock_net(sk), head, port); + if (!tb) { + spin_unlock(&head->lock); + return -ENOMEM; + } + } + } sk_add_bind_node(child, &tb->owners); inet_csk(child)->icsk_bind_hash = tb; spin_unlock(&head->lock); + + return 0; } EXPORT_SYMBOL_GPL(__inet_inherit_port); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a0232f3..8f8527d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1422,7 +1422,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) - goto exit; + goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(newsk, dst); @@ -1469,16 +1469,20 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif + if (__inet_inherit_port(sk, newsk) < 0) { + sock_put(newsk); + goto exit; + } __inet_hash_nolisten(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; exit_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +exit_nonewsk: + dst_release(dst); exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - dst_release(dst); return NULL; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index fe6d404..ba5258ef 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1409,7 +1409,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = tcp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto out; + goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -1497,18 +1497,22 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif + if (__inet_inherit_port(sk, newsk) < 0) { + sock_put(newsk); + goto out; + } __inet6_hash(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; out_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); -out: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); +out_nonewsk: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); +out: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; } -- cgit v0.10.2 From b0aeef30433ea6854e985c2e9842fa19f51b95cc Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Mon, 11 Oct 2010 11:23:07 +0300 Subject: nf_nat: restrict ICMP translation for embedded header Skip ICMP translation of embedded protocol header if NAT bits are not set. Needed for IPVS to see the original embedded addresses because for IPVS traffic the IPS_SRC_NAT_BIT and IPS_DST_NAT_BIT bits are not set. It happens when IPVS performs DNAT for client packets after using nf_conntrack_alter_reply to expect replies from real server. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index e2e00c4..0047923 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -462,6 +462,18 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, return 0; } + if (manip == IP_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + pr_debug("icmp_reply_translation: translating error %p manip %u " "dir %s\n", skb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); @@ -496,20 +508,9 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, /* Change outer to look the reply to an incoming packet * (proto 0 means don't invert per-proto part). */ - if (manip == IP_NAT_MANIP_SRC) - statusbit = IPS_SRC_NAT; - else - statusbit = IPS_DST_NAT; - - /* Invert if this is reply dir. */ - if (dir == IP_CT_DIR_REPLY) - statusbit ^= IPS_NAT_MASK; - - if (ct->status & statusbit) { - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); - if (!manip_pkt(0, skb, 0, &target, manip)) - return 0; - } + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + if (!manip_pkt(0, skb, 0, &target, manip)) + return 0; return 1; } -- cgit v0.10.2 From e97c3e278e951501c2f385de70c3ceacdea78c4a Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:03:43 +0200 Subject: tproxy: split off ipv6 defragmentation to a separate module Like with IPv4, TProxy needs IPv6 defragmentation but does not require connection tracking. Since defragmentation was coupled with conntrack, I split off the two, creating an nf_defrag_ipv6 module, similar to the already existing nf_defrag_ipv4. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h new file mode 100644 index 0000000..94dd54d --- /dev/null +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -0,0 +1,6 @@ +#ifndef _NF_DEFRAG_IPV6_H +#define _NF_DEFRAG_IPV6_H + +extern void nf_defrag_ipv6_enable(void); + +#endif /* _NF_DEFRAG_IPV6_H */ diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index aafbba3..3f8e4a3 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -11,10 +11,11 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o # objects for l3 independent conntrack -nf_conntrack_ipv6-objs := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o nf_conntrack_reasm.o +nf_conntrack_ipv6-objs := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o +nf_defrag_ipv6-objs := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o # l3 independent conntrack -obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o +obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index ff43461..c8af58b 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -29,6 +28,7 @@ #include #include #include +#include #include static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, @@ -189,53 +189,6 @@ out: return nf_conntrack_confirm(skb); } -static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, - struct sk_buff *skb) -{ - u16 zone = NF_CT_DEFAULT_ZONE; - - if (skb->nfct) - zone = nf_ct_zone((struct nf_conn *)skb->nfct); - -#ifdef CONFIG_BRIDGE_NETFILTER - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; -#endif - if (hooknum == NF_INET_PRE_ROUTING) - return IP6_DEFRAG_CONNTRACK_IN + zone; - else - return IP6_DEFRAG_CONNTRACK_OUT + zone; - -} - -static unsigned int ipv6_defrag(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm; - - /* Previously seen (loopback)? */ - if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) - return NF_ACCEPT; - - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); - /* queued */ - if (reasm == NULL) - return NF_STOLEN; - - /* error occured or not fragmented */ - if (reasm == skb) - return NF_ACCEPT; - - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, - (struct net_device *)out, okfn); - - return NF_STOLEN; -} - static unsigned int __ipv6_conntrack_in(struct net *net, unsigned int hooknum, struct sk_buff *skb, @@ -288,13 +241,6 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { { - .hook = ipv6_defrag, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, - }, - { .hook = ipv6_conntrack_in, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -309,13 +255,6 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .priority = NF_IP6_PRI_CONNTRACK, }, { - .hook = ipv6_defrag, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, - }, - { .hook = ipv6_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -387,10 +326,6 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { .nlattr_to_tuple = ipv6_nlattr_to_tuple, .nla_policy = ipv6_nla_policy, #endif -#ifdef CONFIG_SYSCTL - .ctl_table_path = nf_net_netfilter_sysctl_path, - .ctl_table = nf_ct_ipv6_sysctl_table, -#endif .me = THIS_MODULE, }; @@ -403,16 +338,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) int ret = 0; need_conntrack(); + nf_defrag_ipv6_enable(); - ret = nf_ct_frag6_init(); - if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't initialize frag6.\n"); - return ret; - } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6); if (ret < 0) { pr_err("nf_conntrack_ipv6: can't register tcp.\n"); - goto cleanup_frag6; + return ret; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6); @@ -450,8 +381,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); cleanup_tcp: nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); - cleanup_frag6: - nf_ct_frag6_cleanup(); return ret; } @@ -463,7 +392,6 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); - nf_ct_frag6_cleanup(); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 138a8b3..489d71b 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -73,7 +73,7 @@ static struct inet_frags nf_frags; static struct netns_frags nf_init_frags; #ifdef CONFIG_SYSCTL -struct ctl_table nf_ct_ipv6_sysctl_table[] = { +struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .data = &nf_init_frags.timeout, @@ -97,6 +97,8 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { }, { } }; + +static struct ctl_table_header *nf_ct_frag6_sysctl_header; #endif static unsigned int nf_hashfn(struct inet_frag_queue *q) @@ -623,11 +625,21 @@ int nf_ct_frag6_init(void) inet_frags_init_net(&nf_init_frags); inet_frags_init(&nf_frags); + nf_ct_frag6_sysctl_header = register_sysctl_paths(nf_net_netfilter_sysctl_path, + nf_ct_frag6_sysctl_table); + if (!nf_ct_frag6_sysctl_header) { + inet_frags_fini(&nf_frags); + return -ENOMEM; + } + return 0; } void nf_ct_frag6_cleanup(void) { + unregister_sysctl_table(nf_ct_frag6_sysctl_header); + nf_ct_frag6_sysctl_header = NULL; + inet_frags_fini(&nf_frags); nf_init_frags.low_thresh = 0; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c new file mode 100644 index 0000000..99abfb5 --- /dev/null +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -0,0 +1,131 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ + u16 zone = NF_CT_DEFAULT_ZONE; + + if (skb->nfct) + zone = nf_ct_zone((struct nf_conn *)skb->nfct); + +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN + zone; + else + return IP6_DEFRAG_CONNTRACK_OUT + zone; + +} + +static unsigned int ipv6_defrag(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct sk_buff *reasm; + + /* Previously seen (loopback)? */ + if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) + return NF_ACCEPT; + + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); + /* queued */ + if (reasm == NULL) + return NF_STOLEN; + + /* error occured or not fragmented */ + if (reasm == skb) + return NF_ACCEPT; + + nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, + (struct net_device *)out, okfn); + + return NF_STOLEN; +} + +static struct nf_hook_ops ipv6_defrag_ops[] = { + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, +}; + +static int __init nf_defrag_init(void) +{ + int ret = 0; + + ret = nf_ct_frag6_init(); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't initialize frag6.\n"); + return ret; + } + ret = nf_register_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't register hooks\n"); + goto cleanup_frag6; + } + return ret; + +cleanup_frag6: + nf_ct_frag6_cleanup(); + return ret; + +} + +static void __exit nf_defrag_fini(void) +{ + nf_unregister_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); + nf_ct_frag6_cleanup(); +} + +void nf_defrag_ipv6_enable(void) +{ +} +EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); + +module_init(nf_defrag_init); +module_exit(nf_defrag_fini); + +MODULE_LICENSE("GPL"); -- cgit v0.10.2 From 88440ae70eda83d0cc94148d404f4990c9f1289c Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:04:33 +0200 Subject: tproxy: added const specifiers to udp lookup functions The parameters for various UDP lookup functions were non-const, even though they could be const. TProxy has some const references and instead of downcasting it, I added const specifiers along the path. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5acb356..33e3683 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -122,8 +122,8 @@ static void udp_v6_rehash(struct sock *sk) static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, - struct in6_addr *saddr, __be16 sport, - struct in6_addr *daddr, __be16 dport, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif) { int score = -1; @@ -239,8 +239,8 @@ exact_match: } static struct sock *__udp6_lib_lookup(struct net *net, - struct in6_addr *saddr, __be16 sport, - struct in6_addr *daddr, __be16 dport, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif, struct udp_table *udptable) { struct sock *sk, *result; -- cgit v0.10.2 From aa976fc011efa1f0e3290c6c9addf7c20757f885 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:05:41 +0200 Subject: tproxy: added udp6_lib_lookup function Just like with IPv4, we need access to the UDP hash table to look up local sockets, but instead of exporting the global udp_table, export a lookup function. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/net/udp.h b/include/net/udp.h index a184d34..200b828 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -183,6 +183,9 @@ extern int udp_lib_setsockopt(struct sock *sk, int level, int optname, extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); +extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif); /* * SNMP statistics for UDP and UDP-Lite diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 33e3683..c84dad4 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -320,6 +320,14 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, udptable); } +struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif) +{ + return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); +} +EXPORT_SYMBOL_GPL(udp6_lib_lookup); + + /* * This should be easy, if there is something there we * return it, otherwise we block. -- cgit v0.10.2 From 6c46862280c5f55eda7750391bc65cd7e08c7535 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:08:28 +0200 Subject: tproxy: added tproxy sockopt interface in the IPV6 layer Support for IPV6_RECVORIGDSTADDR sockopt for UDP sockets were contributed by Harry Mason. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/linux/in6.h b/include/linux/in6.h index c4bf46f..097a34b 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -268,6 +268,10 @@ struct in6_flowlabel_req { /* RFC5082: Generalized Ttl Security Mechanism */ #define IPV6_MINHOPCOUNT 73 +#define IPV6_ORIGDSTADDR 74 +#define IPV6_RECVORIGDSTADDR IPV6_ORIGDSTADDR +#define IPV6_TRANSPARENT 75 + /* * Multicast Routing: * see include/linux/mroute6.h. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e62683b..8e429d0 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -341,7 +341,9 @@ struct ipv6_pinfo { odstopts:1, rxflow:1, rxtclass:1, - rxpmtu:1; + rxpmtu:1, + rxorigdstaddr:1; + /* 2 bits hole */ } bits; __u16 all; } rxopt; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index ef371aa..320bdb8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -577,6 +577,25 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) u8 *ptr = nh + opt->dst1; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } + if (np->rxopt.bits.rxorigdstaddr) { + struct sockaddr_in6 sin6; + u16 *ports = (u16 *) skb_transport_header(skb); + + if (skb_transport_offset(skb) + 4 <= skb->len) { + /* All current transport protocols have the port numbers in the + * first four bytes of the transport header and this function is + * written with this assumption in mind. + */ + + sin6.sin6_family = AF_INET6; + ipv6_addr_copy(&sin6.sin6_addr, &ipv6_hdr(skb)->daddr); + sin6.sin6_port = ports[1]; + sin6.sin6_flowinfo = 0; + sin6.sin6_scope_id = 0; + + put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); + } + } return 0; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7f66bc..0553867 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -342,6 +342,21 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_TRANSPARENT: + if (optlen < sizeof(int)) + goto e_inval; + /* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */ + inet_sk(sk)->transparent = valbool; + retv = 0; + break; + + case IPV6_RECVORIGDSTADDR: + if (optlen < sizeof(int)) + goto e_inval; + np->rxopt.bits.rxorigdstaddr = valbool; + retv = 0; + break; + case IPV6_HOPOPTS: case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: @@ -1104,6 +1119,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; } + case IPV6_TRANSPARENT: + val = inet_sk(sk)->transparent; + break; + + case IPV6_RECVORIGDSTADDR: + val = np->rxopt.bits.rxorigdstaddr; + break; + case IPV6_UNICAST_HOPS: case IPV6_MULTICAST_HOPS: { -- cgit v0.10.2 From 0a513f6af962525ed4b3395f8c8d5daae8682aa9 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:10:03 +0200 Subject: tproxy: allow non-local binds of IPv6 sockets if IP_TRANSPARENT is enabled Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 56b9bf2..4869797 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -343,7 +343,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!ipv6_chk_addr(net, &addr->sin6_addr, + if (!inet->transparent && + !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; goto out_unlock; -- cgit v0.10.2 From 3b9afb29917f4ab08decf358ecfd354a72a91ac0 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:12:14 +0200 Subject: tproxy: added IPv6 socket lookup function to nf_tproxy_core Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index 1027d7f..cd85b3b 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -5,7 +5,8 @@ #include #include #include -#include +#include +#include #include #define NFT_LOOKUP_ANY 0 @@ -130,6 +131,75 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, return sk; } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static inline struct sock * +nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, int lookup_type) +{ + struct sock *sk; + + /* look up socket */ + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NFT_LOOKUP_ANY: + sk = inet6_lookup(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + case NFT_LOOKUP_LISTENER: + sk = inet6_lookup_listener(net, &tcp_hashinfo, + daddr, ntohs(dport), + in->ifindex); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too */ + + break; + case NFT_LOOKUP_ESTABLISHED: + sk = __inet6_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, ntohs(dport), + in->ifindex); + break; + default: + WARN_ON(1); + sk = NULL; + break; + } + break; + case IPPROTO_UDP: + sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk && lookup_type != NFT_LOOKUP_ANY) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too */ + if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NFT_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", + protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); + + return sk; +} +#endif static inline void nf_tproxy_put_sock(struct sock *sk) -- cgit v0.10.2 From 6ad7889327a5ee6ab4220bd34e4428c7d0de0f32 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:17:26 +0200 Subject: tproxy: added IPv6 support to the TPROXY target This requires a new revision as the old target structure was IPv4 specific. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h index 152e8f9..3f3d693 100644 --- a/include/linux/netfilter/xt_TPROXY.h +++ b/include/linux/netfilter/xt_TPROXY.h @@ -1,5 +1,5 @@ -#ifndef _XT_TPROXY_H_target -#define _XT_TPROXY_H_target +#ifndef _XT_TPROXY_H +#define _XT_TPROXY_H /* TPROXY target is capable of marking the packet to perform * redirection. We can get rid of that whenever we get support for @@ -11,4 +11,11 @@ struct xt_tproxy_target_info { __be16 lport; }; -#endif /* _XT_TPROXY_H_target */ +struct xt_tproxy_target_info_v1 { + u_int32_t mark_mask; + u_int32_t mark_value; + union nf_inet_addr laddr; + __be16 lport; +}; + +#endif /* _XT_TPROXY_H */ diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index e0b6900..d5f97e2 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -1,7 +1,7 @@ /* * Transparent proxy support for Linux/iptables * - * Copyright (c) 2006-2007 BalaBit IT Ltd. + * Copyright (c) 2006-2010 BalaBit IT Ltd. * Author: Balazs Scheidler, Krisztian Kovacs * * This program is free software; you can redistribute it and/or modify @@ -19,15 +19,18 @@ #include #include +#include #include #include +#include #include /** - * tproxy_handle_time_wait() - handle TCP TIME_WAIT reopen redirections + * tproxy_handle_time_wait4() - handle IPv4 TCP TIME_WAIT reopen redirections * @skb: The skb being processed. - * @par: Iptables target parameters. + * @laddr: IPv4 address to redirect to or zero. + * @lport: TCP port to redirect to or zero. * @sk: The TIME_WAIT TCP socket found by the lookup. * * We have to handle SYN packets arriving to TIME_WAIT sockets @@ -35,16 +38,16 @@ * redirect the new connection to the proxy if there's a listener * socket present. * - * tproxy_handle_time_wait() consumes the socket reference passed in. + * tproxy_handle_time_wait4() consumes the socket reference passed in. * * Returns the listener socket if there's one, the TIME_WAIT socket if * no such listener is found, or NULL if the TCP header is incomplete. */ static struct sock * -tproxy_handle_time_wait(struct sk_buff *skb, const struct xt_action_param *par, struct sock *sk) +tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, + struct sock *sk) { const struct iphdr *iph = ip_hdr(skb); - const struct xt_tproxy_target_info *tgi = par->targinfo; struct tcphdr _hdr, *hp; hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); @@ -59,13 +62,64 @@ tproxy_handle_time_wait(struct sk_buff *skb, const struct xt_action_param *par, struct sock *sk2; sk2 = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, - iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr, - hp->source, tgi->lport ? tgi->lport : hp->dest, - par->in, NFT_LOOKUP_LISTENER); + iph->saddr, laddr ? laddr : iph->daddr, + hp->source, lport ? lport : hp->dest, + skb->dev, NFT_LOOKUP_LISTENER); + if (sk2) { + inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_put(inet_twsk(sk)); + sk = sk2; + } + } + + return sk; +} + +/** + * tproxy_handle_time_wait6() - handle IPv6 TCP TIME_WAIT reopen redirections + * @skb: The skb being processed. + * @tproto: Transport protocol. + * @thoff: Transport protocol header offset. + * @par: Iptables target parameters. + * @sk: The TIME_WAIT TCP socket found by the lookup. + * + * We have to handle SYN packets arriving to TIME_WAIT sockets + * differently: instead of reopening the connection we should rather + * redirect the new connection to the proxy if there's a listener + * socket present. + * + * tproxy_handle_time_wait6() consumes the socket reference passed in. + * + * Returns the listener socket if there's one, the TIME_WAIT socket if + * no such listener is found, or NULL if the TCP header is incomplete. + */ +static struct sock * +tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, + const struct xt_action_param *par, + struct sock *sk) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr _hdr, *hp; + const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + inet_twsk_put(inet_twsk(sk)); + return NULL; + } + + if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { + /* SYN to a TIME_WAIT socket, we'd rather redirect it + * to a listener socket if there's one */ + struct sock *sk2; + + sk2 = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + &iph->saddr, + !ipv6_addr_any(&tgi->laddr.in6) ? &tgi->laddr.in6 : &iph->daddr, + hp->source, + tgi->lport ? tgi->lport : hp->dest, + skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - /* yeah, there's one, let's kill the TIME_WAIT - * socket and redirect to the listener - */ inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); inet_twsk_put(inet_twsk(sk)); sk = sk2; @@ -76,10 +130,10 @@ tproxy_handle_time_wait(struct sk_buff *skb, const struct xt_action_param *par, } static unsigned int -tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par) +tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, + u_int32_t mark_mask, u_int32_t mark_value) { const struct iphdr *iph = ip_hdr(skb); - const struct xt_tproxy_target_info *tgi = par->targinfo; struct udphdr _hdr, *hp; struct sock *sk; @@ -87,18 +141,105 @@ tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par) if (hp == NULL) return NF_DROP; + /* check if there's an ongoing connection on the packet + * addresses, this happens if the redirect already happened + * and the current packet belongs to an already established + * connection */ sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, - par->in, NFT_LOOKUP_ESTABLISHED); + skb->dev, NFT_LOOKUP_ESTABLISHED); /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) - sk = tproxy_handle_time_wait(skb, par, sk); + /* reopening a TIME_WAIT connection needs special handling */ + sk = tproxy_handle_time_wait4(skb, laddr, lport, sk); else if (!sk) + /* no, there's no established connection, check if + * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, - iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr, - hp->source, tgi->lport ? tgi->lport : hp->dest, + iph->saddr, laddr ? laddr : iph->daddr, + hp->source, lport ? lport : hp->dest, + skb->dev, NFT_LOOKUP_LISTENER); + + /* NOTE: assign_sock consumes our sk reference */ + if (sk && nf_tproxy_assign_sock(skb, sk)) { + /* This should be in a separate target, but we don't do multiple + targets on the same rule yet */ + skb->mark = (skb->mark & ~mark_mask) ^ mark_value; + + pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n", + iph->protocol, &iph->daddr, ntohs(hp->dest), + &laddr, ntohs(lport), skb->mark); + return NF_ACCEPT; + } + + pr_debug("no socket, dropping: proto %hhu %08x:%hu -> %08x:%hu, mark: %x\n", + iph->protocol, ntohl(iph->daddr), ntohs(hp->dest), + ntohl(laddr), ntohs(lport), skb->mark); + return NF_DROP; +} + +static unsigned int +tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_tproxy_target_info *tgi = par->targinfo; + + return tproxy_tg4(skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value); +} + +static unsigned int +tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; + + return tproxy_tg4(skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value); +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static unsigned int +tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; + struct udphdr _hdr, *hp; + struct sock *sk; + int thoff; + int tproto; + + tproto = ipv6_find_hdr(skb, &thoff, -1, NULL); + if (tproto < 0) { + pr_debug("unable to find transport header in IPv6 packet, dropping\n"); + return NF_DROP; + } + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + pr_debug("unable to grab transport header contents in IPv6 packet, dropping\n"); + return NF_DROP; + } + + /* check if there's an ongoing connection on the packet + * addresses, this happens if the redirect already happened + * and the current packet belongs to an already established + * connection */ + sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + &iph->saddr, &iph->daddr, + hp->source, hp->dest, + par->in, NFT_LOOKUP_ESTABLISHED); + + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ + if (sk && sk->sk_state == TCP_TIME_WAIT) + /* reopening a TIME_WAIT connection needs special handling */ + sk = tproxy_handle_time_wait6(skb, tproto, thoff, par, sk); + else if (!sk) + /* no there's no established connection, check if + * there's a listener on the redirected addr/port */ + sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + &iph->saddr, + !ipv6_addr_any(&tgi->laddr.in6) ? &tgi->laddr.in6 : &iph->daddr, + hp->source, + tgi->lport ? tgi->lport : hp->dest, par->in, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ @@ -107,19 +248,33 @@ tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par) targets on the same rule yet */ skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; - pr_debug("redirecting: proto %u %08x:%u -> %08x:%u, mark: %x\n", - iph->protocol, ntohl(iph->daddr), ntohs(hp->dest), - ntohl(tgi->laddr), ntohs(tgi->lport), skb->mark); + pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n", + tproto, &iph->saddr, ntohs(hp->dest), + &tgi->laddr.in6, ntohs(tgi->lport), skb->mark); return NF_ACCEPT; } - pr_debug("no socket, dropping: proto %u %08x:%u -> %08x:%u, mark: %x\n", - iph->protocol, ntohl(iph->daddr), ntohs(hp->dest), - ntohl(tgi->laddr), ntohs(tgi->lport), skb->mark); + pr_debug("no socket, dropping: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n", + tproto, &iph->saddr, ntohs(hp->dest), + &tgi->laddr.in6, ntohs(tgi->lport), skb->mark); return NF_DROP; } -static int tproxy_tg_check(const struct xt_tgchk_param *par) +static int tproxy_tg6_check(const struct xt_tgchk_param *par) +{ + const struct ip6t_ip6 *i = par->entryinfo; + + if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) + && !(i->flags & IP6T_INV_PROTO)) + return 0; + + pr_info("Can be used only in combination with " + "either -p tcp or -p udp\n"); + return -EINVAL; +} +#endif + +static int tproxy_tg4_check(const struct xt_tgchk_param *par) { const struct ipt_ip *i = par->entryinfo; @@ -132,31 +287,64 @@ static int tproxy_tg_check(const struct xt_tgchk_param *par) return -EINVAL; } -static struct xt_target tproxy_tg_reg __read_mostly = { - .name = "TPROXY", - .family = NFPROTO_IPV4, - .table = "mangle", - .target = tproxy_tg, - .targetsize = sizeof(struct xt_tproxy_target_info), - .checkentry = tproxy_tg_check, - .hooks = 1 << NF_INET_PRE_ROUTING, - .me = THIS_MODULE, +static struct xt_target tproxy_tg_reg[] __read_mostly = { + { + .name = "TPROXY", + .family = NFPROTO_IPV4, + .table = "mangle", + .target = tproxy_tg4_v0, + .revision = 0, + .targetsize = sizeof(struct xt_tproxy_target_info), + .checkentry = tproxy_tg4_check, + .hooks = 1 << NF_INET_PRE_ROUTING, + .me = THIS_MODULE, + }, + { + .name = "TPROXY", + .family = NFPROTO_IPV4, + .table = "mangle", + .target = tproxy_tg4_v1, + .revision = 1, + .targetsize = sizeof(struct xt_tproxy_target_info_v1), + .checkentry = tproxy_tg4_check, + .hooks = 1 << NF_INET_PRE_ROUTING, + .me = THIS_MODULE, + }, +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + { + .name = "TPROXY", + .family = NFPROTO_IPV6, + .table = "mangle", + .target = tproxy_tg6_v1, + .revision = 1, + .targetsize = sizeof(struct xt_tproxy_target_info_v1), + .checkentry = tproxy_tg6_check, + .hooks = 1 << NF_INET_PRE_ROUTING, + .me = THIS_MODULE, + }, +#endif + }; static int __init tproxy_tg_init(void) { nf_defrag_ipv4_enable(); - return xt_register_target(&tproxy_tg_reg); +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + nf_defrag_ipv6_enable(); +#endif + + return xt_register_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg)); } static void __exit tproxy_tg_exit(void) { - xt_unregister_target(&tproxy_tg_reg); + xt_unregister_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg)); } module_init(tproxy_tg_init); module_exit(tproxy_tg_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Krisztian Kovacs"); +MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs"); MODULE_DESCRIPTION("Netfilter transparent proxy (TPROXY) target module."); MODULE_ALIAS("ipt_TPROXY"); +MODULE_ALIAS("ip6t_TPROXY"); -- cgit v0.10.2 From b64c9256a9b76fc9f059f71bd08ba88fb0cbba2e Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:19:42 +0200 Subject: tproxy: added IPv6 support to the socket match The ICMP extraction bits were contributed by Harry Mason. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 266faa0..2dbd4c8 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -21,6 +22,7 @@ #include #include #include +#include #include @@ -30,7 +32,7 @@ #endif static int -extract_icmp_fields(const struct sk_buff *skb, +extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol, __be32 *raddr, __be32 *laddr, @@ -86,7 +88,6 @@ extract_icmp_fields(const struct sk_buff *skb, return 0; } - static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) @@ -115,7 +116,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, dport = hp->dest; } else if (iph->protocol == IPPROTO_ICMP) { - if (extract_icmp_fields(skb, &protocol, &saddr, &daddr, + if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, &sport, &dport)) return false; } else { @@ -165,32 +166,157 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, sk = NULL; } - pr_debug("proto %u %08x:%u -> %08x:%u (orig %08x:%u) sock %p\n", - protocol, ntohl(saddr), ntohs(sport), - ntohl(daddr), ntohs(dport), - ntohl(iph->daddr), hp ? ntohs(hp->dest) : 0, sk); + pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", + protocol, &saddr, ntohs(sport), + &daddr, ntohs(dport), + &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return (sk != NULL); } static bool -socket_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) +socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, NULL); } static bool -socket_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +socket_mt4_v1(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + +static int +extract_icmp6_fields(const struct sk_buff *skb, + unsigned int outside_hdrlen, + u8 *protocol, + struct in6_addr **raddr, + struct in6_addr **laddr, + __be16 *rport, + __be16 *lport) +{ + struct ipv6hdr *inside_iph, _inside_iph; + struct icmp6hdr *icmph, _icmph; + __be16 *ports, _ports[2]; + u8 inside_nexthdr; + int inside_hdrlen; + + icmph = skb_header_pointer(skb, outside_hdrlen, + sizeof(_icmph), &_icmph); + if (icmph == NULL) + return 1; + + if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK) + return 1; + + inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), sizeof(_inside_iph), &_inside_iph); + if (inside_iph == NULL) + return 1; + inside_nexthdr = inside_iph->nexthdr; + + inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph), &inside_nexthdr); + if (inside_hdrlen < 0) + return 1; /* hjm: Packet has no/incomplete transport layer headers. */ + + if (inside_nexthdr != IPPROTO_TCP && + inside_nexthdr != IPPROTO_UDP) + return 1; + + ports = skb_header_pointer(skb, inside_hdrlen, + sizeof(_ports), &_ports); + if (ports == NULL) + return 1; + + /* the inside IP packet is the one quoted from our side, thus + * its saddr is the local address */ + *protocol = inside_nexthdr; + *laddr = &inside_iph->saddr; + *lport = ports[0]; + *raddr = &inside_iph->daddr; + *rport = ports[1]; + + return 0; +} + +static bool +socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + struct udphdr _hdr, *hp = NULL; + struct sock *sk; + struct in6_addr *daddr, *saddr; + __be16 dport, sport; + int thoff; + u8 tproto; + const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; + + tproto = ipv6_find_hdr(skb, &thoff, -1, NULL); + if (tproto < 0) { + pr_debug("unable to find transport header in IPv6 packet, dropping\n"); + return NF_DROP; + } + + if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) { + hp = skb_header_pointer(skb, thoff, + sizeof(_hdr), &_hdr); + if (hp == NULL) + return false; + + saddr = &iph->saddr; + sport = hp->source; + daddr = &iph->daddr; + dport = hp->dest; + + } else if (tproto == IPPROTO_ICMPV6) { + if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, + &sport, &dport)) + return false; + } else { + return false; + } + + sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); + if (sk != NULL) { + bool wildcard; + bool transparent = true; + + /* Ignore sockets listening on INADDR_ANY */ + wildcard = (sk->sk_state != TCP_TIME_WAIT && + ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)); + + /* Ignore non-transparent sockets, + if XT_SOCKET_TRANSPARENT is used */ + if (info && info->flags & XT_SOCKET_TRANSPARENT) + transparent = ((sk->sk_state != TCP_TIME_WAIT && + inet_sk(sk)->transparent) || + (sk->sk_state == TCP_TIME_WAIT && + inet_twsk(sk)->tw_transparent)); + + nf_tproxy_put_sock(sk); + + if (wildcard || !transparent) + sk = NULL; + } + + pr_debug("proto %hhu %pI6:%hu -> %pI6:%hu " + "(orig %pI6:%hu) sock %p\n", + tproto, saddr, ntohs(sport), + daddr, ntohs(dport), + &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); + + return (sk != NULL); +} +#endif + static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", .revision = 0, .family = NFPROTO_IPV4, - .match = socket_mt_v0, + .match = socket_mt4_v0, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, @@ -199,17 +325,33 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, - .match = socket_mt_v1, + .match = socket_mt4_v1, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + { + .name = "socket", + .revision = 1, + .family = NFPROTO_IPV6, + .match = socket_mt6_v1, + .matchsize = sizeof(struct xt_socket_mtinfo1), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +#endif }; static int __init socket_mt_init(void) { nf_defrag_ipv4_enable(); +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + nf_defrag_ipv6_enable(); +#endif + return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } @@ -225,3 +367,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler"); MODULE_DESCRIPTION("x_tables socket match module"); MODULE_ALIAS("ipt_socket"); +MODULE_ALIAS("ip6t_socket"); -- cgit v0.10.2 From cc6eb433856983e91071469c4ce57accb6947ccb Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 21 Oct 2010 16:21:10 +0200 Subject: tproxy: use the interface primary IP address as a default value for --on-ip The REDIRECT target and the older TProxy versions used the primary address of the incoming interface as the default value of the --on-ip parameter. This was unintentionally changed during the initial TProxy submission and caused confusion among users. Since IPv6 has no notion of primary address, we just select the first address on the list: this way the socket lookup finds wildcard bound sockets properly and we cannot really do better without the user telling us the IPv6 address of the proxy. This is implemented for both IPv4 and IPv6. Signed-off-by: Balazs Scheidler Signed-off-by: KOVACS Krisztian Signed-off-by: Patrick McHardy diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index d5f97e2..19c482c 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -16,15 +16,41 @@ #include #include #include - +#include #include #include -#include -#include #include +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#include +#include +#include #include +#endif + #include +#include + +static inline __be32 +tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) +{ + struct in_device *indev; + __be32 laddr; + + if (user_laddr) + return user_laddr; + + laddr = 0; + rcu_read_lock(); + indev = __in_dev_get_rcu(skb->dev); + for_primary_ifa(indev) { + laddr = ifa->ifa_local; + break; + } endfor_ifa(indev); + rcu_read_unlock(); + + return laddr ? laddr : daddr; +} /** * tproxy_handle_time_wait4() - handle IPv4 TCP TIME_WAIT reopen redirections @@ -75,60 +101,6 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, return sk; } -/** - * tproxy_handle_time_wait6() - handle IPv6 TCP TIME_WAIT reopen redirections - * @skb: The skb being processed. - * @tproto: Transport protocol. - * @thoff: Transport protocol header offset. - * @par: Iptables target parameters. - * @sk: The TIME_WAIT TCP socket found by the lookup. - * - * We have to handle SYN packets arriving to TIME_WAIT sockets - * differently: instead of reopening the connection we should rather - * redirect the new connection to the proxy if there's a listener - * socket present. - * - * tproxy_handle_time_wait6() consumes the socket reference passed in. - * - * Returns the listener socket if there's one, the TIME_WAIT socket if - * no such listener is found, or NULL if the TCP header is incomplete. - */ -static struct sock * -tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, - const struct xt_action_param *par, - struct sock *sk) -{ - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct tcphdr _hdr, *hp; - const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; - - hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); - if (hp == NULL) { - inet_twsk_put(inet_twsk(sk)); - return NULL; - } - - if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { - /* SYN to a TIME_WAIT socket, we'd rather redirect it - * to a listener socket if there's one */ - struct sock *sk2; - - sk2 = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, - &iph->saddr, - !ipv6_addr_any(&tgi->laddr.in6) ? &tgi->laddr.in6 : &iph->daddr, - hp->source, - tgi->lport ? tgi->lport : hp->dest, - skb->dev, NFT_LOOKUP_LISTENER); - if (sk2) { - inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); - inet_twsk_put(inet_twsk(sk)); - sk = sk2; - } - } - - return sk; -} - static unsigned int tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) @@ -150,6 +122,10 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, hp->source, hp->dest, skb->dev, NFT_LOOKUP_ESTABLISHED); + laddr = tproxy_laddr4(skb, laddr, iph->daddr); + if (!lport) + lport = hp->dest; + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) /* reopening a TIME_WAIT connection needs special handling */ @@ -158,8 +134,8 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, - iph->saddr, laddr ? laddr : iph->daddr, - hp->source, lport ? lport : hp->dest, + iph->saddr, laddr, + hp->source, lport, skb->dev, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ @@ -174,9 +150,9 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, return NF_ACCEPT; } - pr_debug("no socket, dropping: proto %hhu %08x:%hu -> %08x:%hu, mark: %x\n", - iph->protocol, ntohl(iph->daddr), ntohs(hp->dest), - ntohl(laddr), ntohs(lport), skb->mark); + pr_debug("no socket, dropping: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n", + iph->protocol, &iph->saddr, ntohs(hp->source), + &iph->daddr, ntohs(hp->dest), skb->mark); return NF_DROP; } @@ -197,6 +173,88 @@ tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + +static inline const struct in6_addr * +tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, + const struct in6_addr *daddr) +{ + struct inet6_dev *indev; + struct inet6_ifaddr *ifa; + struct in6_addr *laddr; + + if (!ipv6_addr_any(user_laddr)) + return user_laddr; + laddr = NULL; + + rcu_read_lock(); + indev = __in6_dev_get(skb->dev); + if (indev) + list_for_each_entry(ifa, &indev->addr_list, if_list) { + if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED)) + continue; + + laddr = &ifa->addr; + break; + } + rcu_read_unlock(); + + return laddr ? laddr : daddr; +} + +/** + * tproxy_handle_time_wait6() - handle IPv6 TCP TIME_WAIT reopen redirections + * @skb: The skb being processed. + * @tproto: Transport protocol. + * @thoff: Transport protocol header offset. + * @par: Iptables target parameters. + * @sk: The TIME_WAIT TCP socket found by the lookup. + * + * We have to handle SYN packets arriving to TIME_WAIT sockets + * differently: instead of reopening the connection we should rather + * redirect the new connection to the proxy if there's a listener + * socket present. + * + * tproxy_handle_time_wait6() consumes the socket reference passed in. + * + * Returns the listener socket if there's one, the TIME_WAIT socket if + * no such listener is found, or NULL if the TCP header is incomplete. + */ +static struct sock * +tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, + const struct xt_action_param *par, + struct sock *sk) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr _hdr, *hp; + const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + inet_twsk_put(inet_twsk(sk)); + return NULL; + } + + if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { + /* SYN to a TIME_WAIT socket, we'd rather redirect it + * to a listener socket if there's one */ + struct sock *sk2; + + sk2 = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + &iph->saddr, + tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr), + hp->source, + tgi->lport ? tgi->lport : hp->dest, + skb->dev, NFT_LOOKUP_LISTENER); + if (sk2) { + inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_put(inet_twsk(sk)); + sk = sk2; + } + } + + return sk; +} + static unsigned int tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) { @@ -204,6 +262,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; struct udphdr _hdr, *hp; struct sock *sk; + const struct in6_addr *laddr; + __be16 lport; int thoff; int tproto; @@ -228,6 +288,9 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) hp->source, hp->dest, par->in, NFT_LOOKUP_ESTABLISHED); + laddr = tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr); + lport = tgi->lport ? tgi->lport : hp->dest; + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) /* reopening a TIME_WAIT connection needs special handling */ @@ -236,10 +299,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, - &iph->saddr, - !ipv6_addr_any(&tgi->laddr.in6) ? &tgi->laddr.in6 : &iph->daddr, - hp->source, - tgi->lport ? tgi->lport : hp->dest, + &iph->saddr, laddr, + hp->source, lport, par->in, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ @@ -249,14 +310,15 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n", - tproto, &iph->saddr, ntohs(hp->dest), - &tgi->laddr.in6, ntohs(tgi->lport), skb->mark); + tproto, &iph->saddr, ntohs(hp->source), + laddr, ntohs(lport), skb->mark); return NF_ACCEPT; } pr_debug("no socket, dropping: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n", - tproto, &iph->saddr, ntohs(hp->dest), - &tgi->laddr.in6, ntohs(tgi->lport), skb->mark); + tproto, &iph->saddr, ntohs(hp->source), + &iph->daddr, ntohs(hp->dest), skb->mark); + return NF_DROP; } -- cgit v0.10.2