diff options
| author | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-02-13 00:34:17 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-02-13 00:34:17 +0100 |
| commit | 89697f1d715e20fff0361cca79efd5a371623af7 (patch) | |
| tree | d64d279f6805fd3d5fb53f059cbe7ea1ae348592 | |
| parent | don't use 'localversion*' files twice (diff) | |
| parent | [XFRM]: Fix OOPSes in xfrm_audit_log(). (diff) | |
| download | linux-89697f1d715e20fff0361cca79efd5a371623af7.tar.xz linux-89697f1d715e20fff0361cca79efd5a371623af7.zip | |
Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (25 commits)
[XFRM]: Fix OOPSes in xfrm_audit_log().
[TCP]: cleanup of htcp (resend)
[TCP]: Use read mostly for CUBIC parameters.
[NETFILTER]: nf_conntrack_tcp: make sysctl variables static
[NETFILTER]: ip6t_mh: drop piggyback payload packet on MH packets
[NETFILTER]: Fix whitespace errors
[NETFILTER]: Kconfig: improve dependency handling
[NETFILTER]: xt_mac/xt_CLASSIFY: use IPv6 hook names for IPv6 registration
[NETFILTER]: nf_conntrack: change nf_conntrack_l[34]proto_unregister to void
[NETFILTER]: nf_conntrack: properly use RCU for nf_conntrack_destroyed callback
[NETFILTER]: ip_conntrack: properly use RCU for ip_conntrack_destroyed callback
[NETFILTER]: nf_conntrack: fix invalid conntrack statistics RCU assumption
[NETFILTER]: ip_conntrack: fix invalid conntrack statistics RCU assumption
[NETFILTER]: nf_conntrack: properly use RCU API for nf_ct_protos/nf_ct_l3protos arrays
[NETFILTER]: ip_conntrack: properly use RCU API for ip_ct_protos array
[NETFILTER]: nf_nat: properly use RCU API for nf_nat_protos array
[NETFILTER]: ip_nat: properly use RCU API for ip_nat_protos array
[NETFILTER]: nf_log: minor cleanups
[NETFILTER]: nf_log: switch logger registration/unregistration to mutex
[NETFILTER]: nf_log: make nf_log_unregister_pf return void
...
71 files changed, 768 insertions, 709 deletions
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d4c4c5120bc0..70d3b4f1e48d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -172,8 +172,8 @@ struct nf_logger { /* Function to register/unregister log function. */ int nf_log_register(int pf, struct nf_logger *logger); -int nf_log_unregister_pf(int pf); -void nf_log_unregister_logger(struct nf_logger *logger); +void nf_log_unregister(struct nf_logger *logger); +void nf_log_unregister_pf(int pf); /* Calls the registered backend logging function */ void nf_log_packet(int pf, diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 33581c13d947..da9274e6bf12 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -301,6 +301,12 @@ extern unsigned int ip_conntrack_htable_size; extern int ip_conntrack_checksum; #define CONNTRACK_STAT_INC(count) (__get_cpu_var(ip_conntrack_stat).count++) +#define CONNTRACK_STAT_INC_ATOMIC(count) \ +do { \ + local_bh_disable(); \ + __get_cpu_var(ip_conntrack_stat).count++; \ + local_bh_enable(); \ +} while (0) #ifdef CONFIG_IP_NF_CONNTRACK_EVENTS #include <linux/notifier.h> diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 68ec27490c20..0e690e34c00b 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -257,6 +257,12 @@ extern int nf_conntrack_max; DECLARE_PER_CPU(struct ip_conntrack_stat, nf_conntrack_stat); #define NF_CT_STAT_INC(count) (__get_cpu_var(nf_conntrack_stat).count++) +#define NF_CT_STAT_INC_ATOMIC(count) \ +do { \ + local_bh_disable(); \ + __get_cpu_var(nf_conntrack_stat).count++; \ + local_bh_enable(); \ +} while (0) /* no helper, no nat */ #define NF_CT_F_BASIC 0 diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index 664ddcffe00d..eb575cbd4c95 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -89,7 +89,7 @@ extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; /* Protocol registration. */ extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); -extern int nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto); +extern void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto); extern struct nf_conntrack_l3proto * nf_ct_l3proto_find_get(u_int16_t l3proto); @@ -106,7 +106,7 @@ __nf_ct_l3proto_find(u_int16_t l3proto) { if (unlikely(l3proto >= AF_MAX)) return &nf_conntrack_l3proto_generic; - return nf_ct_l3protos[l3proto]; + return rcu_dereference(nf_ct_l3protos[l3proto]); } #endif /*_NF_CONNTRACK_L3PROTO_H*/ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index fc8af08ff542..8415182ec126 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -109,7 +109,7 @@ extern void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p); /* Protocol registration. */ extern int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *proto); -extern int nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *proto); +extern void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *proto); /* Generic netlink helpers */ extern int nf_ct_port_tuple_to_nfattr(struct sk_buff *skb, diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index f9a5ae9d5b6d..45712aec6a0e 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -208,7 +208,7 @@ static int __init ebt_log_init(void) static void __exit ebt_log_fini(void) { - nf_log_unregister_logger(&ebt_log_logger); + nf_log_unregister(&ebt_log_logger); ebt_unregister_watcher(&log); } diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 2e4cb24e191a..8e15cc47f6c0 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -323,7 +323,7 @@ static void __exit ebt_ulog_fini(void) ebt_ulog_buff_t *ub; int i; - nf_log_unregister_logger(&ebt_ulog_logger); + nf_log_unregister(&ebt_ulog_logger); ebt_unregister_watcher(&ulog); for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 9b08e7ad71bc..601808c796ec 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -226,7 +226,7 @@ config IP_NF_QUEUE config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" - depends on NETFILTER_XTABLES + select NETFILTER_XTABLES help iptables is a general, extensible packet identification framework. The packet filtering and full NAT (masquerading, port forwarding, @@ -606,7 +606,9 @@ config IP_NF_TARGET_TTL config IP_NF_TARGET_CLUSTERIP tristate "CLUSTERIP target support (EXPERIMENTAL)" depends on IP_NF_MANGLE && EXPERIMENTAL - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) + depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 + select IP_NF_CONNTRACK_MARK if IP_NF_CONNTRACK + select NF_CONNTRACK_MARK if NF_CONNTRACK_IPV4 help The CLUSTERIP target allows you to build load-balancing clusters of network servers without having a dedicated load-balancing @@ -629,7 +631,7 @@ config IP_NF_RAW # ARP tables config IP_NF_ARPTABLES tristate "ARP tables support" - depends on NETFILTER_XTABLES + select NETFILTER_XTABLES help arptables is a general, extensible packet identification framework. The ARP packet filtering and mangling (manipulation)subsystems diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c index 04e466d53c0b..07ba1dd136b5 100644 --- a/net/ipv4/netfilter/ip_conntrack_core.c +++ b/net/ipv4/netfilter/ip_conntrack_core.c @@ -303,6 +303,7 @@ destroy_conntrack(struct nf_conntrack *nfct) struct ip_conntrack *ct = (struct ip_conntrack *)nfct; struct ip_conntrack_protocol *proto; struct ip_conntrack_helper *helper; + typeof(ip_conntrack_destroyed) destroyed; DEBUGP("destroy_conntrack(%p)\n", ct); IP_NF_ASSERT(atomic_read(&nfct->use) == 0); @@ -318,12 +319,16 @@ destroy_conntrack(struct nf_conntrack *nfct) /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to ip_conntrack_lock!!! -HW */ + rcu_read_lock(); proto = __ip_conntrack_proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); if (proto && proto->destroy) proto->destroy(ct); - if (ip_conntrack_destroyed) - ip_conntrack_destroyed(ct); + destroyed = rcu_dereference(ip_conntrack_destroyed); + if (destroyed) + destroyed(ct); + + rcu_read_unlock(); write_lock_bh(&ip_conntrack_lock); /* Expectations will have been removed in clean_from_lists, @@ -536,7 +541,7 @@ static int early_drop(struct list_head *chain) if (del_timer(&ct->timeout)) { death_by_timeout((unsigned long)ct); dropped = 1; - CONNTRACK_STAT_INC(early_drop); + CONNTRACK_STAT_INC_ATOMIC(early_drop); } ip_conntrack_put(ct); return dropped; @@ -595,13 +600,13 @@ ip_conntrack_proto_find_get(u_int8_t protocol) { struct ip_conntrack_protocol *p; - preempt_disable(); + rcu_read_lock(); p = __ip_conntrack_proto_find(protocol); if (p) { if (!try_module_get(p->me)) p = &ip_conntrack_generic_protocol; } - preempt_enable(); + rcu_read_unlock(); return p; } @@ -802,7 +807,7 @@ unsigned int ip_conntrack_in(unsigned int hooknum, /* Previously seen (loopback or untracked)? Ignore. */ if ((*pskb)->nfct) { - CONNTRACK_STAT_INC(ignore); + CONNTRACK_STAT_INC_ATOMIC(ignore); return NF_ACCEPT; } @@ -830,6 +835,7 @@ unsigned int ip_conntrack_in(unsigned int hooknum, } #endif + /* rcu_read_lock()ed by nf_hook_slow */ proto = __ip_conntrack_proto_find((*pskb)->nh.iph->protocol); /* It may be an special packet, error, unclean... @@ -837,20 +843,20 @@ unsigned int ip_conntrack_in(unsigned int hooknum, * core what to do with the packet. */ if (proto->error != NULL && (ret = proto->error(*pskb, &ctinfo, hooknum)) <= 0) { - CONNTRACK_STAT_INC(error); - CONNTRACK_STAT_INC(invalid); + CONNTRACK_STAT_INC_ATOMIC(error); + CONNTRACK_STAT_INC_ATOMIC(invalid); return -ret; } if (!(ct = resolve_normal_ct(*pskb, proto,&set_reply,hooknum,&ctinfo))) { /* Not valid part of a connection */ - CONNTRACK_STAT_INC(invalid); + CONNTRACK_STAT_INC_ATOMIC(invalid); return NF_ACCEPT; } if (IS_ERR(ct)) { /* Too stressed to deal. */ - CONNTRACK_STAT_INC(drop); + CONNTRACK_STAT_INC_ATOMIC(drop); return NF_DROP; } @@ -862,7 +868,7 @@ unsigned int ip_conntrack_in(unsigned int hooknum, * the netfilter core what to do*/ nf_conntrack_put((*pskb)->nfct); (*pskb)->nfct = NULL; - CONNTRACK_STAT_INC(invalid); + CONNTRACK_STAT_INC_ATOMIC(invalid); return -ret; } @@ -875,8 +881,15 @@ unsigned int ip_conntrack_in(unsigned int hooknum, int invert_tuplepr(struct ip_conntrack_tuple *inverse, const struct ip_conntrack_tuple *orig) { - return ip_ct_invert_tuple(inverse, orig, - __ip_conntrack_proto_find(orig->dst.protonum)); + struct ip_conntrack_protocol *proto; + int ret; + + rcu_read_lock(); + proto = __ip_conntrack_proto_find(orig->dst.protonum); + ret = ip_ct_invert_tuple(inverse, orig, proto); + rcu_read_unlock(); + + return ret; } /* Would two expected things clash? */ @@ -1354,7 +1367,7 @@ static void free_conntrack_hash(struct list_head *hash, int vmalloced,int size) supposed to kill the mall. */ void ip_conntrack_cleanup(void) { - ip_ct_attach = NULL; + rcu_assign_pointer(ip_ct_attach, NULL); /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module @@ -1507,15 +1520,15 @@ int __init ip_conntrack_init(void) /* Don't NEED lock here, but good form anyway. */ write_lock_bh(&ip_conntrack_lock); for (i = 0; i < MAX_IP_CT_PROTO; i++) - ip_ct_protos[i] = &ip_conntrack_generic_protocol; + rcu_assign_pointer(ip_ct_protos[i], &ip_conntrack_generic_protocol); /* Sew in builtin protocols. */ - ip_ct_protos[IPPROTO_TCP] = &ip_conntrack_protocol_tcp; - ip_ct_protos[IPPROTO_UDP] = &ip_conntrack_protocol_udp; - ip_ct_protos[IPPROTO_ICMP] = &ip_conntrack_protocol_icmp; + rcu_assign_pointer(ip_ct_protos[IPPROTO_TCP], &ip_conntrack_protocol_tcp); + rcu_assign_pointer(ip_ct_protos[IPPROTO_UDP], &ip_conntrack_protocol_udp); + rcu_assign_pointer(ip_ct_protos[IPPROTO_ICMP], &ip_conntrack_protocol_icmp); write_unlock_bh(&ip_conntrack_lock); /* For use by ipt_REJECT */ - ip_ct_attach = ip_conntrack_attach; + rcu_assign_pointer(ip_ct_attach, ip_conntrack_attach); /* Set up fake conntrack: - to never be deleted, not in any hashes */ diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 300ccbbbdac9..c7c1ec61b0f5 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -796,7 +796,7 @@ int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto) ret = -EBUSY; goto out; } - ip_ct_protos[proto->proto] = proto; + rcu_assign_pointer(ip_ct_protos[proto->proto], proto); out: write_unlock_bh(&ip_conntrack_lock); return ret; @@ -805,11 +805,10 @@ int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto) void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto) { write_lock_bh(&ip_conntrack_lock); - ip_ct_protos[proto->proto] = &ip_conntrack_generic_protocol; + rcu_assign_pointer(ip_ct_protos[proto->proto], + &ip_conntrack_generic_protocol); write_unlock_bh(&ip_conntrack_lock); - - /* Somebody could be still looking at the proto in bh. */ - synchronize_net(); + synchronize_rcu(); /* Remove all contrack entries for this protocol */ ip_ct_iterate_cleanup(kill_proto, &proto->proto); diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c index 275a4d3faf0a..40737fdbe9a7 100644 --- a/net/ipv4/netfilter/ip_nat_core.c +++ b/net/ipv4/netfilter/ip_nat_core.c @@ -50,7 +50,7 @@ static struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO]; static inline struct ip_nat_protocol * __ip_nat_proto_find(u_int8_t protonum) { - return ip_nat_protos[protonum]; + return rcu_dereference(ip_nat_protos[protonum]); } struct ip_nat_protocol * @@ -58,13 +58,11 @@ ip_nat_proto_find_get(u_int8_t protonum) { struct ip_nat_protocol *p; - /* we need to disable preemption to make sure 'p' doesn't get - * removed until we've grabbed the reference */ - preempt_disable(); + rcu_read_lock(); p = __ip_nat_proto_find(protonum); if (!try_module_get(p->me)) p = &ip_nat_unknown_protocol; - preempt_enable(); + rcu_read_unlock(); return p; } @@ -120,8 +118,8 @@ static int in_range(const struct ip_conntrack_tuple *tuple, const struct ip_nat_range *range) { - struct ip_nat_protocol *proto = - __ip_nat_proto_find(tuple->dst.protonum); + struct ip_nat_protocol *proto; + int ret = 0; /* If we are supposed to map IPs, then we must be in the range specified, otherwise let this drag us onto a new src IP. */ @@ -131,12 +129,15 @@ in_range(const struct ip_conntrack_tuple *tuple, return 0; } + rcu_read_lock(); + proto = __ip_nat_proto_find(tuple->dst.protonum); if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, IP_NAT_MANIP_SRC, &range->min, &range->max)) - return 1; + ret = 1; + rcu_read_unlock(); - return 0; + return ret; } static inline int @@ -260,27 +261,25 @@ get_unique_tuple(struct ip_conntrack_tuple *tuple, /* 3) The per-protocol part of the manip is made to map into the range to make a unique tuple. */ - proto = ip_nat_proto_find_get(orig_tuple->dst.protonum); + rcu_read_lock(); + proto = __ip_nat_proto_find(orig_tuple->dst.protonum); /* Change protocol info to have some randomization */ if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) { proto->unique_tuple(tuple, range, maniptype, conntrack); - ip_nat_proto_put(proto); - return; + goto out; } /* Only bother mapping if it's not already in range and unique */ if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, maniptype, &range->min, &range->max)) - && !ip_nat_used_tuple(tuple, conntrack)) { - ip_nat_proto_put(proto); - return; - } + && !ip_nat_used_tuple(tuple, conntrack)) + goto out; /* Last change: get protocol to try to obtain unique tuple. */ proto->unique_tuple(tuple, range, maniptype, conntrack); - - ip_nat_proto_put(proto); +out: + rcu_read_unlock(); } unsigned int @@ -360,12 +359,11 @@ manip_pkt(u_int16_t proto, iph = (void *)(*pskb)->data + iphdroff; /* Manipulate protcol part. */ - p = ip_nat_proto_find_get(proto); - if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) { - ip_nat_proto_put(p); + + /* rcu_read_lock()ed by nf_hook_slow */ + p = __ip_nat_proto_find(proto); + if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) return 0; - } - ip_nat_proto_put(p); iph = (void *)(*pskb)->data + iphdroff; @@ -422,6 +420,7 @@ int ip_nat_icmp_reply_translation(struct ip_conntrack *ct, struct icmphdr icmp; struct iphdr ip; } *inside; + struct ip_conntrack_protocol *proto; struct ip_conntrack_tuple inner, target; int hdrlen = (*pskb)->nh.iph->ihl * 4; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -457,10 +456,11 @@ int ip_nat_icmp_reply_translation(struct ip_conntrack *ct, DEBUGP("icmp_reply_translation: translating error %p manp %u dir %s\n", *pskb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); + /* rcu_read_lock()ed by nf_hook_slow */ + proto = __ip_conntrack_proto_find(inside->ip.protocol); if (!ip_ct_get_tuple(&inside->ip, *pskb, (*pskb)->nh.iph->ihl*4 + sizeof(struct icmphdr) + inside->ip.ihl*4, - &inner, - __ip_conntrack_proto_find(inside->ip.protocol))) + &inner, proto)) return 0; /* Change inner back to look like incoming packet. We do the @@ -515,7 +515,7 @@ int ip_nat_protocol_register(struct ip_nat_protocol *proto) ret = -EBUSY; goto out; } - ip_nat_protos[proto->protonum] = proto; + rcu_assign_pointer(ip_nat_protos[proto->protonum], proto); out: write_unlock_bh(&ip_nat_lock); return ret; @@ -526,11 +526,10 @@ EXPORT_SYMBOL(ip_nat_protocol_register); void ip_nat_protocol_unregister(struct ip_nat_protocol *proto) { write_lock_bh(&ip_nat_lock); - ip_nat_protos[proto->protonum] = &ip_nat_unknown_protocol; + rcu_assign_pointer(ip_nat_protos[proto->protonum], + &ip_nat_unknown_protocol); write_unlock_bh(&ip_nat_lock); - - /* Someone could be still looking at the proto in a bh. */ - synchronize_net(); + synchronize_rcu(); } EXPORT_SYMBOL(ip_nat_protocol_unregister); @@ -594,10 +593,10 @@ static int __init ip_nat_init(void) /* Sew in builtin protocols. */ write_lock_bh(&ip_nat_lock); for (i = 0; i < MAX_IP_NAT_PROTO; i++) - ip_nat_protos[i] = &ip_nat_unknown_protocol; - ip_nat_protos[IPPROTO_TCP] = &ip_nat_protocol_tcp; - ip_nat_protos[IPPROTO_UDP] = &ip_nat_protocol_udp; - ip_nat_protos[IPPROTO_ICMP] = &ip_nat_protocol_icmp; + rcu_assign_pointer(ip_nat_protos[i], &ip_nat_unknown_protocol); + rcu_assign_pointer(ip_nat_protos[IPPROTO_TCP], &ip_nat_protocol_tcp); + rcu_assign_pointer(ip_nat_protos[IPPROTO_UDP], &ip_nat_protocol_udp); + rcu_assign_pointer(ip_nat_protos[IPPROTO_ICMP], &ip_nat_protocol_icmp); write_unlock_bh(&ip_nat_lock); for (i = 0; i < ip_nat_htable_size; i++) { @@ -605,8 +604,8 @@ static int __init ip_nat_init(void) } /* FIXME: Man, this is a hack. <SIGH> */ - IP_NF_ASSERT(ip_conntrack_destroyed == NULL); - ip_conntrack_destroyed = &ip_nat_cleanup_conntrack; + IP_NF_ASSERT(rcu_dereference(ip_conntrack_destroyed) == NULL); + rcu_assign_pointer(ip_conntrack_destroyed, ip_nat_cleanup_conntrack); /* Initialize fake conntrack so that NAT will skip it */ ip_conntrack_untracked.status |= IPS_NAT_DONE_MASK; @@ -624,7 +623,8 @@ static int clean_nat(struct ip_conntrack *i, void *data) static void __exit ip_nat_cleanup(void) { ip_ct_iterate_cleanup(&clean_nat, NULL); - ip_conntrack_destroyed = NULL; + rcu_assign_pointer(ip_conntrack_destroyed, NULL); + synchronize_rcu(); vfree(bysource); } diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index f4a62f2522ff..d9c37fd94228 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -489,7 +489,7 @@ static int __init ipt_log_init(void) static void __exit ipt_log_fini(void) { - nf_log_unregister_logger(&ipt_log_logger); + nf_log_unregister(&ipt_log_logger); xt_unregister_target(&ipt_log_reg); } diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 3a1eacc634b3..a26404dbe212 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -419,7 +419,7 @@ static void __exit ipt_ulog_fini(void) DEBUGP("ipt_ULOG: cleanup_module\n"); if (nflog) - nf_log_unregister_logger(&ipt_ulog_logger); + nf_log_unregister(&ipt_ulog_logger); xt_unregister_target(&ipt_ulog_reg); sock_release(nflognl->sk_socket); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 677b6c80c618..e5aa4d849b00 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -170,7 +170,9 @@ icmp_error_message(struct sk_buff *skb, return -NF_ACCEPT; } + /* rcu_read_lock()ed by nf_hook_slow */ innerproto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol); + dataoff = skb->nh.iph->ihl*4 + sizeof(inside->icmp); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuple(skb, dataoff, dataoff + inside->ip.ihl*4, PF_INET, diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index cf1010827be1..2c01378d3592 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -53,7 +53,7 @@ static struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]; static inline struct nf_nat_protocol * __nf_nat_proto_find(u_int8_t protonum) { - return nf_nat_protos[protonum]; + return rcu_dereference(nf_nat_protos[protonum]); } struct nf_nat_protocol * @@ -61,13 +61,11 @@ nf_nat_proto_find_get(u_int8_t protonum) { struct nf_nat_protocol *p; - /* we need to disable preemption to make sure 'p' doesn't get - * removed until we've grabbed the reference */ - preempt_disable(); + rcu_read_lock(); p = __nf_nat_proto_find(protonum); if (!try_module_get(p->me)) p = &nf_nat_unknown_protocol; - preempt_enable(); + rcu_read_unlock(); return p; } @@ -126,8 +124,8 @@ in_range(const struct nf_conntrack_tuple *tuple, const struct nf_nat_range *range) { struct nf_nat_protocol *proto; + int ret = 0; - proto = __nf_nat_proto_find(tuple->dst.protonum); /* If we are supposed to map IPs, then we must be in the range specified, otherwise let this drag us onto a new src IP. */ if (range->flags & IP_NAT_RANGE_MAP_IPS) { @@ -136,12 +134,15 @@ in_range(const struct nf_conntrack_tuple *tuple, return 0; } + rcu_read_lock(); + proto = __nf_nat_proto_find(tuple->dst.protonum); if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, IP_NAT_MANIP_SRC, &range->min, &range->max)) - return 1; + ret = 1; + rcu_read_unlock(); - return 0; + return ret; } static inline int @@ -268,27 +269,25 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, /* 3) The per-protocol part of the manip is made to map into the range to make a unique tuple. */ - proto = nf_nat_proto_find_get(orig_tuple->dst.protonum); + rcu_read_lock(); + proto = __nf_nat_proto_find(orig_tuple->dst.protonum); /* Change protocol info to have some randomization */ if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) { proto->unique_tuple(tuple, range, maniptype, ct); - nf_nat_proto_put(proto); - return; + goto out; } /* Only bother mapping if it's not already in range and unique */ if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, maniptype, &range->min, &range->max)) && - !nf_nat_used_tuple(tuple, ct)) { - nf_nat_proto_put(proto); - return; - } + !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); - - nf_nat_proto_put(proto); +out: + rcu_read_unlock(); } unsigned int @@ -369,12 +368,11 @@ manip_pkt(u_int16_t proto, iph = (void *)(*pskb)->data + iphdroff; /* Manipulate protcol part. */ - p = nf_nat_proto_find_get(proto); - if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) { - nf_nat_proto_put(p); + + /* rcu_read_lock()ed by nf_hook_slow */ + p = __nf_nat_proto_find(proto); + if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) return 0; - } - nf_nat_proto_put(p); iph = (void *)(*pskb)->data + iphdroff; @@ -431,6 +429,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, struct icmphdr icmp; struct iphdr ip; } *inside; + struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple inner, target; int hdrlen = (*pskb)->nh.iph->ihl * 4; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -466,16 +465,16 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, DEBUGP("icmp_reply_translation: translating error %p manp %u dir %s\n", *pskb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); + /* rcu_read_lock()ed by nf_hook_slow */ + l4proto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol); + if (!nf_ct_get_tuple(*pskb, (*pskb)->nh.iph->ihl*4 + sizeof(struct icmphdr), (*pskb)->nh.iph->ihl*4 + sizeof(struct icmphdr) + inside->ip.ihl*4, (u_int16_t)AF_INET, inside->ip.protocol, - &inner, - l3proto, - __nf_ct_l4proto_find((u_int16_t)PF_INET, - inside->ip.protocol))) + &inner, l3proto, l4proto)) return 0; /* Change inner back to look like incoming packet. We do the @@ -529,7 +528,7 @@ int nf_nat_protocol_register(struct nf_nat_protocol *proto) ret = -EBUSY; goto out; } - nf_nat_protos[proto->protonum] = proto; + rcu_assign_pointer(nf_nat_protos[proto->protonum], proto); out: write_unlock_bh(&nf_nat_lock); return ret; @@ -540,11 +539,10 @@ EXPORT_SYMBOL(nf_nat_protocol_register); void nf_nat_protocol_unregister(struct nf_nat_protocol *proto) { write_lock_bh(&nf_nat_lock); - nf_nat_protos[proto->protonum] = &nf_nat_unknown_protocol; + rcu_assign_pointer(nf_nat_protos[proto->protonum], + &nf_nat_unknown_protocol); write_unlock_bh(&nf_nat_lock); - - /* Someone could be still looking at the proto in a bh. */ - synchronize_net(); + synchronize_rcu(); } EXPORT_SYMBOL(nf_nat_protocol_unregister); @@ -608,10 +606,10 @@ static int __init nf_nat_init(void) /* Sew in builtin protocols. */ write_lock_bh(&nf_nat_lock); for (i = 0; i < MAX_IP_NAT_PROTO; i++) - nf_nat_protos[i] = &nf_nat_unknown_protocol; - nf_nat_protos[IPPROTO_TCP] = &nf_nat_protocol_tcp; - nf_nat_protos[IPPROTO_UDP] = &nf_nat_protocol_udp; - nf_nat_protos[IPPROTO_ICMP] = &nf_nat_protocol_icmp; + rcu_assign_pointer(nf_nat_protos[i], &nf_nat_unknown_protocol); + rcu_assign_pointer(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp); + rcu_assign_pointer(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp); + rcu_assign_pointer(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp); write_unlock_bh(&nf_nat_lock); for (i = 0; i < nf_nat_htable_size; i++) { @@ -619,8 +617,8 @@ static int __init nf_nat_init(void) } /* FIXME: Man, this is a hack. <SIGH> */ - NF_CT_ASSERT(nf_conntrack_destroyed == NULL); - nf_conntrack_destroyed = &nf_nat_cleanup_conntrack; + NF_CT_ASSERT(rcu_dereference(nf_conntrack_destroyed) == NULL); + rcu_assign_pointer(nf_conntrack_destroyed, nf_nat_cleanup_conntrack); /* Initialize fake conntrack so that NAT will skip it */ nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK; @@ -644,7 +642,8 @@ static int clean_nat(struct nf_conn *i, void *data) static void __exit nf_nat_cleanup(void) { nf_ct_iterate_cleanup(&clean_nat, NULL); - nf_conntrack_destroyed = NULL; + rcu_assign_pointer(nf_conntrack_destroyed, NULL); + synchronize_rcu(); vfree(bysource); nf_ct_l3proto_put(l3proto); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5ce6cd85680b..9a582fb4ef9f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -26,16 +26,16 @@ */ #define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ -static int fast_convergence = 1; -static int max_increment = 16; -static int beta = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */ -static int initial_ssthresh = 100; -static int bic_scale = 41; -static int tcp_friendliness = 1; - -static u32 cube_rtt_scale; -static u32 beta_scale; -static u64 cube_factor; +static int fast_convergence __read_mostly = 1; +static int max_increment __read_mostly = 16; +static int beta __read_mostly = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */ +static int initial_ssthresh __read_mostly = 100; +static int bic_scale __read_mostly = 41; +static int tcp_friendliness __read_mostly = 1; + +static u32 cube_rtt_scale __read_mostly; +static u32 beta_scale __read_mostly; +static u64 cube_factor __read_mostly; /* Note parameters that are used for precomputing scale factors are read-only */ module_param(fast_convergence, int, 0644); diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 63318b6e9d51..1020eb48d8d1 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -10,22 +10,23 @@ #include <linux/module.h> #include <net/tcp.h> -#define ALPHA_BASE (1<<7) /* 1.0 with shift << 7 */ -#define BETA_MIN (1<<6) /* 0.5 with shift << 7 */ +#define ALPHA_BASE (1<<7) /* 1.0 with shift << 7 */ +#define BETA_MIN (1<<6) /* 0.5 with shift << 7 */ #define BETA_MAX 102 /* 0.8 with shift << 7 */ -static int use_rtt_scaling = 1; +static int use_rtt_scaling __read_mostly = 1; module_param(use_rtt_scaling, int, 0644); MODULE_PARM_DESC(use_rtt_scaling, "turn on/off RTT scaling"); -static int use_bandwidth_switch = 1; +static int use_bandwidth_switch __read_mostly = 1; module_param(use_bandwidth_switch, int, 0644); MODULE_PARM_DESC(use_bandwidth_switch, "turn on/off bandwidth switcher"); struct htcp { u32 alpha; /* Fixed point arith, << 7 */ u8 beta; /* Fixed point arith, << 7 */ - u8 modeswitch; /* Delay modeswitch until we had at least one congestion event */ + u8 modeswitch; /* Delay modeswitch + until we had at least one congestion event */ u16 pkts_acked; u32 packetcount; u32 minRTT; @@ -44,14 +45,14 @@ struct htcp { u32 lasttime; }; -static inline u32 htcp_cong_time(struct htcp *ca) +static inline u32 htcp_cong_time(const struct htcp *ca) { return jiffies - ca->last_cong; } -static inline u32 htcp_ccount(struct htcp *ca) +static inline u32 htcp_ccount(const struct htcp *ca) { - return htcp_cong_time(ca)/ca->minRTT; + return htcp_cong_time(ca) / ca->minRTT; } static inline void htcp_reset(struct htcp *ca) @@ -67,10 +68,12 @@ static u32 htcp_cwnd_undo(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); + ca->last_cong = ca->undo_last_cong; ca->maxRTT = ca->undo_maxRTT; ca->old_maxB = ca->undo_old_maxB; - return max(tp->snd_cwnd, (tp->snd_ssthresh<<7)/ca->beta); + + return max(tp->snd_cwnd, (tp->snd_ssthresh << 7) / ca->beta); } static inline void measure_rtt(struct sock *sk) @@ -78,17 +81,19 @@ static inline void measure_rtt(struct sock *sk) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); - u32 srtt = tp->srtt>>3; + u32 srtt = tp->srtt >> 3; /* keep track of minimum RTT seen so far, minRTT is zero at first */ if (ca->minRTT > srtt || !ca->minRTT) ca->minRTT = srtt; /* max RTT */ - if (icsk->icsk_ca_state == TCP_CA_Open && tp->snd_ssthresh < 0xFFFF && htcp_ccount(ca) > 3) { + if (icsk->icsk_ca_state == TCP_CA_Open + && tp->snd_ssthresh < 0xFFFF && htcp_ccount(ca) > 3) { if (ca->maxRTT < ca->minRTT) ca->maxRTT = ca->minRTT; - if (ca->maxRTT < srtt && srtt <= ca->maxRTT+msecs_to_jiffies(20)) + if (ca->maxRTT < srtt + && srtt <= ca->maxRTT + msecs_to_jiffies(20)) ca->maxRTT = srtt; } } @@ -116,15 +121,16 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked) ca->packetcount += pkts_acked; - if (ca->packetcount >= tp->snd_cwnd - (ca->alpha>>7? : 1) - && now - ca->lasttime >= ca->minRTT - && ca->minRTT > 0) { - __u32 cur_Bi = ca->packetcount*HZ/(now - ca->lasttime); + if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) + && now - ca->lasttime >= ca->minRTT + && ca->minRTT > 0) { + __u32 cur_Bi = ca->packetcount * HZ / (now - ca->lasttime); + if (htcp_ccount(ca) <= 3) { /* just after backoff */ ca->minB = ca->maxB = ca->Bi = cur_Bi; } else { - ca->Bi = (3*ca->Bi + cur_Bi)/4; + ca->Bi = (3 * ca->Bi + cur_Bi) / 4; if (ca->Bi > ca->maxB) ca->maxB = ca->Bi; if (ca->minB > ca->maxB) @@ -142,7 +148,7 @@ static inline void htcp_beta_update(struct htcp *ca, u32 minRTT, u32 maxRTT) u32 old_maxB = ca->old_maxB; ca->old_maxB = ca->maxB; - if (!between(5*maxB, 4*old_maxB, 6*old_maxB)) { + if (!between(5 * maxB, 4 * old_maxB, 6 * old_maxB)) { ca->beta = BETA_MIN; ca->modeswitch = 0; return; @@ -150,7 +156,7 @@ static inline void htcp_beta_update(struct htcp *ca, u32 minRTT, u32 maxRTT) } if (ca->modeswitch && minRTT > msecs_to_jiffies(10) && maxRTT) { - ca->beta = (minRTT<<7)/maxRTT; + ca->beta = (minRTT << 7) / maxRTT; if (ca->beta < BETA_MIN) ca->beta = BETA_MIN; else if (ca->beta > BETA_MAX) @@ -169,23 +175,26 @@ static inline void htcp_alpha_update(struct htcp *ca) if (diff > HZ) { diff -= HZ; - factor = 1+ ( 10*diff + ((diff/2)*(diff/2)/HZ) )/HZ; + factor = 1 + (10 * diff + ((diff / 2) * (diff / 2) / HZ)) / HZ; } if (use_rtt_scaling && minRTT) { - u32 scale = (HZ<<3)/(10*minRTT); - scale = min(max(scale, 1U<<2), 10U<<3); /* clamping ratio to interval [0.5,10]<<3 */ - factor = (factor<<3)/scale; + u32 scale = (HZ << 3) / (10 * minRTT); + + /* clamping ratio to interval [0.5,10]<<3 */ + scale = min(max(scale, 1U << 2), 10U << 3); + factor = (factor << 3) / scale; if (!factor) factor = 1; } - ca->alpha = 2*factor*((1<<7)-ca->beta); + ca->alpha = 2 * factor * ((1 << 7) - ca->beta); if (!ca->alpha) ca->alpha = ALPHA_BASE; } -/* After we have the rtt data to calculate beta, we'd still prefer to wait one +/* + * After we have the rtt data to calculate beta, we'd still prefer to wait one * rtt before we adjust our beta to ensure we are working from a consistent * data. * @@ -202,15 +211,16 @@ static void htcp_param_update(struct sock *sk) htcp_beta_update(ca, minRTT, maxRTT); htcp_alpha_update(ca); - /* add slowly fading memory for maxRTT to accommodate routing changes etc */ + /* add slowly fading memory for maxRTT to accommodate routing changes */ if (minRTT > 0 && maxRTT > minRTT) - ca->maxRTT = minRTT + ((maxRTT-minRTT)*95)/100; + ca->maxRTT = minRTT + ((maxRTT - minRTT) * 95) / 100; } static u32 htcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct htcp *ca = inet_csk_ca(sk); + htcp_param_update(sk); return max((tp->snd_cwnd * ca->beta) >> 7, 2U); } @@ -227,7 +237,6 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, if (tp->snd_cwnd <= tp->snd_ssthresh) tcp_slow_start(tp); else { - measure_rtt(sk); /* In dangerous area, increase slowly. diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index cd549aea84f0..da07e9a88ee9 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -42,7 +42,8 @@ config IP6_NF_QUEUE config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" - depends on INET && IPV6 && EXPERIMENTAL && NETFILTER_XTABLES + depends on INET && IPV6 && EXPERIMENTAL + select NETFILTER_XTABLES help ip6tables is a general, extensible packet identification framework. Currently only the packet filtering and packet mangling subsystem diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index dc9ec9305778..afaa039d0b7b 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -501,7 +501,7 @@ static int __init ip6t_log_init(void) static void __exit ip6t_log_fini(void) { - nf_log_unregister_logger(&ip6t_logger); + nf_log_unregister(&ip6t_logger); xt_unregister_target(&ip6t_log_reg); } diff --git a/net/ipv6/netfilter/ip6t_mh.c b/net/ipv6/netfilter/ip6t_mh.c index 2c7efc6a506d..c2a909893a64 100644 --- a/net/ipv6/netfilter/ip6t_mh.c +++ b/net/ipv6/netfilter/ip6t_mh.c @@ -66,6 +66,13 @@ match(const struct sk_buff *skb, return 0; } + if (mh->ip6mh_proto != IPPROTO_NONE) { + duprintf("Dropping invalid MH Payload Proto: %u\n", + mh->ip6mh_proto); + *hotdrop = 1; + return 0; + } + return type_match(mhinfo->types[0], mhinfo->types[1], mh->ip6mh_type, !!(mhinfo->invflags & IP6T_MH_INV_TYPE)); } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index a2353edf4ebc..4b7be4bb4d03 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -154,8 +154,8 @@ ipv6_prepare(struct sk_buff **pskb, unsigned int hooknum, unsigned int *dataoff, */ if ((protoff < 0) || (protoff > (*pskb)->len)) { DEBUGP("ip6_conntrack_core: can't find proto in pkt\n"); - NF_CT_STAT_INC(error); - NF_CT_STAT_INC(invalid); + NF_CT_STAT_INC_ATOMIC(error); + NF_CT_STAT_INC_ATOMIC(invalid); return -NF_ACCEPT; } diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index b08622c992b2..19bdb7cb8ff3 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -182,6 +182,7 @@ icmpv6_error_message(struct sk_buff *skb, return -NF_ACCEPT; } + /* rcu_read_lock()ed by nf_hook_slow */ inproto = __nf_ct_l4proto_find(PF_INET6, inprotonum); /* Are they talking about one of our connections? */ diff --git a/net/key/af_key.c b/net/key/af_key.c index f3a026ff9b2c..1c58204d767e 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2297,16 +2297,17 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg &sel, tmp.security, 1); security_xfrm_policy_free(&tmp); - xfrm_audit_log(audit_get_loginuid(current->audit_context), 0, - AUDIT_MAC_IPSEC_DELSPD, (xp) ? 1 : 0, xp, NULL); - if (xp == NULL) return -ENOENT; - err = 0; + err = security_xfrm_policy_delete(xp); - if ((err = security_xfrm_policy_delete(xp))) + xfrm_audit_log(audit_get_loginuid(current->audit_context), 0, + AUDIT_MAC_IPSEC_DELSPD, err ? 0 : 1, xp, NULL); + + if (err) goto out; + c.seq = hdr->sadb_msg_seq; c.pid = hdr->sadb_msg_pid; c.event = XFRM_MSG_DELPOLICY; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 748f7f00909a..253fce3ad2d3 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -302,7 +302,9 @@ config NETFILTER_XT_TARGET_CONNMARK tristate '"CONNMARK" target support' depends on NETFILTER_XTABLES depends on IP_NF_MANGLE || IP6_NF_MANGLE - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK) + depends on IP_NF_CONNTRACK || NF_CONNTRACK + select IP_NF_CONNTRACK_MARK if IP_NF_CONNTRACK + select NF_CONNTRACK_MARK if NF_CONNTRACK help This option adds a `CONNMARK' target, which allows one to manipulate the connection mark value. Similar to the MARK target, but @@ -434,7 +436,9 @@ config NETFILTER_XT_MATCH_COMMENT config NETFILTER_XT_MATCH_CONNBYTES tristate '"connbytes" per-connection counter match support' depends on NETFILTER_XTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || (NF_CT_ACCT && NF_CONNTRACK) + depends on IP_NF_CONNTRACK || NF_CONNTRACK + select IP_NF_CT_ACCT if IP_NF_CONNTRACK + select NF_CT_ACCT if NF_CONNTRACK help This option adds a `connbytes' match, which allows you to match the number of bytes and/or packets for each direction within a connection. @@ -445,7 +449,9 @@ config NETFILTER_XT_MATCH_CONNBYTES config NETFILTER_XT_MATCH_CONNMARK tristate '"connmark" connection mark match support' depends on NETFILTER_XTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK) + depends on IP_NF_CONNTRACK || NF_CONNTRACK + select IP_NF_CONNTRACK_MARK if IP_NF_CONNTRACK + select NF_CONNTRACK_MARK if NF_CONNTRACK help This option adds a `connmark' match, which allows you to match the connection mark value previously set for the session by `CONNMARK'. diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 291b8c6862f1..c3ebdbd917e9 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -1,4 +1,4 @@ -/* netfilter.c: look after the filters for various protocols. +/* netfilter.c: look after the filters for various protocols. * Heavily influenced by the old firewall.c by David Bonn and Alan Cox. * * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any @@ -22,29 +22,34 @@ #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> +#include <linux/mutex.h> #include <net/sock.h> #include "nf_internals.h" -static DEFINE_SPINLOCK(afinfo_lock); +static DEFINE_MUTEX(afinfo_mutex); struct nf_afinfo *nf_afinfo[NPROTO] __read_mostly; EXPORT_SYMBOL(nf_afinfo); int nf_register_afinfo(struct nf_afinfo *afinfo) { - spin_lock(&afinfo_lock); + int err; + + err = mutex_lock_interruptible(&afinfo_mutex); + if (err < 0) + return err; rcu_assign_pointer(nf_afinfo[afinfo->family], afinfo); - spin_unlock(&afinfo_lock); + mutex_unlock(&afinfo_mutex); return 0; } EXPORT_SYMBOL_GPL(nf_register_afinfo); void nf_unregister_afinfo(struct nf_afinfo *afinfo) { - spin_lock(&afinfo_lock); + mutex_lock(&afinfo_mutex); rcu_assign_pointer(nf_afinfo[afinfo->family], NULL); - spin_unlock(&afinfo_lock); + mutex_unlock(&afinfo_mutex); synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_unregister_afinfo); @@ -56,30 +61,31 @@ EXPORT_SYMBOL_GPL(nf_unregister_afinfo); * packets come back: if the hook is gone, the packet is discarded. */ struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS] __read_mostly; EXPORT_SYMBOL(nf_hooks); -static DEFINE_SPINLOCK(nf_hook_lock); +static DEFINE_MUTEX(nf_hook_mutex); int nf_register_hook(struct nf_hook_ops *reg) { struct list_head *i; + int err; - spin_lock_bh(&nf_hook_lock); + err = mutex_lock_interruptible(&nf_hook_mutex); + if (err < 0) + return err; list_for_each(i, &nf_hooks[reg->pf][reg->hooknum]) { if (reg->priority < ((struct nf_hook_ops *)i)->priority) break; } list_add_rcu(®->list, i->prev); - spin_unlock_bh(&nf_hook_lock); - - synchronize_net(); + mutex_unlock(&nf_hook_mutex); return 0; } EXPORT_SYMBOL(nf_register_hook); void nf_unregister_hook(struct nf_hook_ops *reg) { - spin_lock_bh(&nf_hook_lock); + mutex_lock(&nf_hook_mutex); list_del_rcu(®->list); - spin_unlock_bh(&nf_hook_lock); + mutex_unlock(&nf_hook_mutex); synchronize_net(); } @@ -135,14 +141,14 @@ unsigned int nf_iterate(struct list_head *head, continue; /* Optimization: we don't need to hold module - reference here, since function can't sleep. --RR */ + reference here, since function can't sleep. --RR */ verdict = elem->hook(hook, skb, indev, outdev, okfn); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT)) { NFDEBUG("Evil return from %p(%u).\n", - elem->hook, hook); + elem->hook, hook); continue; } #endif @@ -248,9 +254,12 @@ void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) { void (*attach)(struct sk_buff *, struct sk_buff *); - if (skb->nfct && (attach = ip_ct_attach) != NULL) { - mb(); /* Just to be sure: must be read before executing this */ - attach(new, skb); + if (skb->nfct) { + rcu_read_lock(); + attach = rcu_dereference(ip_ct_attach); + if (attach) + attach(new, skb); + rcu_read_unlock(); } } EXPORT_SYMBOL(nf_ct_attach); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9b02ec4012fb..32891ebc9e68 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -318,6 +318,7 @@ destroy_conntrack(struct nf_conntrack *nfct) struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; + typeof(nf_conntrack_destroyed) destroyed; DEBUGP("destroy_conntrack(%p)\n", ct); NF_CT_ASSERT(atomic_read(&nfct->use) == 0); @@ -332,16 +333,21 @@ destroy_conntrack(struct nf_conntrack *nfct) /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to nf_conntrack_lock!!! -HW */ + rcu_read_lock(); l3proto = __nf_ct_l3proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num); if (l3proto && l3proto->destroy) l3proto->destroy(ct); - l4proto = __nf_ct_l4proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num, ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); + l4proto = __nf_ct_l4proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num, + ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); if (l4proto && l4proto->destroy) l4proto->destroy(ct); - if (nf_conntrack_destroyed) - nf_conntrack_destroyed(ct); + destroyed = rcu_dereference(nf_conntrack_destroyed); + if (destroyed) + destroyed(ct); + + rcu_read_unlock(); write_lock_bh(&nf_conntrack_lock); /* Expectations will have been removed in clean_from_lists, @@ -418,7 +424,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_find_get); static void __nf_conntrack_hash_insert(struct nf_conn *ct, unsigned int hash, - unsigned int repl_hash) + unsigned int repl_hash) { ct->id = ++nf_conntrack_next_id; list_add(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list, @@ -560,7 +566,7 @@ static int early_drop(struct list_head *chain) if (del_timer(&ct->timeout)) { death_by_timeout((unsigned long)ct); dropped = 1; - NF_CT_STAT_INC(early_drop); + NF_CT_STAT_INC_ATOMIC(early_drop); } nf_ct_put(ct); return dropped; @@ -647,9 +653,14 @@ struct nf_conn *nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl) { struct nf_conntrack_l3proto *l3proto; + struct nf_conn *ct; + rcu_read_lock(); l3proto = __nf_ct_l3proto_find(orig->src.l3num); - return __nf_conntrack_alloc(orig, repl, l3proto, 0); + ct = __nf_conntrack_alloc(orig, repl, l3proto, 0); + rcu_read_unlock(); + + return ct; } EXPORT_SYMBOL_GPL(nf_conntrack_alloc); @@ -813,11 +824,13 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb) /* Previously seen (loopback or untracked)? Ignore. */ if ((*pskb)->nfct) { - NF_CT_STAT_INC(ignore); + NF_CT_STAT_INC_ATOMIC(ignore); return NF_ACCEPT; } + /* rcu_read_lock()ed by nf_hook_slow */ l3proto = __nf_ct_l3proto_find((u_int16_t)pf); + if ((ret = l3proto->prepare(pskb, hooknum, &dataoff, &protonum)) <= 0) { DEBUGP("not prepared to track yet or error occured\n"); return -ret; @@ -830,8 +843,8 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb) * core what to do with the packet. */ if (l4proto->error != NULL && (ret = l4proto->error(*pskb, dataoff, &ctinfo, pf, hooknum)) <= 0) { - NF_CT_STAT_INC(error); - NF_CT_STAT_INC(invalid); + NF_CT_STAT_INC_ATOMIC(error); + NF_CT_STAT_INC_ATOMIC(invalid); return -ret; } @@ -839,13 +852,13 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb) &set_reply, &ctinfo); if (!ct) { /* Not valid part of a connection */ - NF_CT_STAT_INC(invalid); + NF_CT_STAT_INC_ATOMIC(invalid); return NF_ACCEPT; } if (IS_ERR(ct)) { /* Too stressed to deal. */ - NF_CT_STAT_INC(drop); + NF_CT_STAT_INC_ATOMIC(drop); return NF_DROP; } @@ -858,7 +871,7 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb) DEBUGP("nf_conntrack_in: Can't track with proto module\n"); nf_conntrack_put((*pskb)->nfct); (*pskb)->nfct = NULL; - NF_CT_STAT_INC(invalid); + NF_CT_STAT_INC_ATOMIC(invalid); return -ret; } @@ -872,10 +885,15 @@ EXPORT_SYMBOL_GPL(nf_conntrack_in); int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig) { - return nf_ct_invert_tuple(inverse, orig, - __nf_ct_l3proto_find(orig->src.l3num), - __nf_ct_l4proto_find(orig->src.l3num, - orig->dst.protonum)); + int ret; + + rcu_read_lock(); + ret = nf_ct_invert_tuple(inverse, orig, + __nf_ct_l3proto_find(orig->src.l3num), + __nf_ct_l4proto_find(orig->src.l3num, + orig->dst.protonum)); + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL_GPL(nf_ct_invert_tuplepr); @@ -1048,7 +1066,7 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), if (iter(ct, data)) goto found; } - } + } list_for_each_entry(h, &unconfirmed, list) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) @@ -1089,7 +1107,7 @@ static void free_conntrack_hash(struct list_head *hash, int vmalloced, int size) if (vmalloced) vfree(hash); else - free_pages((unsigned long)hash, + free_pages((unsigned long)hash, get_order(sizeof(struct list_head) * size)); } @@ -1105,7 +1123,7 @@ void nf_conntrack_cleanup(void) { int i; - ip_ct_attach = NULL; + rcu_assign_pointer(ip_ct_attach, NULL); /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module @@ -1150,18 +1168,18 @@ static struct list_head *alloc_hashtable(int size, int *vmalloced) struct list_head *hash; unsigned int i; - *vmalloced = 0; - hash = (void*)__get_free_pages(GFP_KERNEL, + *vmalloced = 0; + hash = (void*)__get_free_pages(GFP_KERNEL, get_order(sizeof(struct list_head) * size)); - if (!hash) { + if (!hash) { *vmalloced = 1; printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); hash = vmalloc(sizeof(struct list_head) * size); } if (hash) - for (i = 0; i < size; i++) + for (i = 0; i < size; i++) INIT_LIST_HEAD(&hash[i]); return hash; @@ -1268,12 +1286,12 @@ int __init nf_conntrack_init(void) /* Don't NEED lock here, but good form anyway. */ write_lock_bh(&nf_conntrack_lock); - for (i = 0; i < AF_MAX; i++) + for (i = 0; i < AF_MAX; i++) nf_ct_l3protos[i] = &nf_conntrack_l3proto_generic; - write_unlock_bh(&nf_conntrack_lock); + write_unlock_bh(&nf_conntrack_lock); /* For use by REJECT target */ - ip_ct_attach = __nf_conntrack_attach; + rcu_assign_pointer(ip_ct_attach, __nf_conntrack_attach); /* Set up fake conntrack: - to never be deleted, not in any hashes */ diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 5cdcd7f4e813..ce70a6fc6bda 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -130,7 +130,7 @@ void nf_ct_remove_expectations(struct nf_conn *ct) if (i->master == ct && del_timer(&i->timeout)) { nf_ct_unlink_expect(i); nf_conntrack_expect_put(i); - } + } } } EXPORT_SYMBOL_GPL(nf_ct_remove_expectations); diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 92a947168761..3089dfc40c88 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -126,7 +126,7 @@ get_ipv6_addr(const char *src, size_t dlen, struct in6_addr *dst, u_int8_t term) } static int try_number(const char *data, size_t dlen, u_int32_t array[], - int array_size, char sep, char term) + int array_size, char sep, char term) { u_int32_t i, len; @@ -413,8 +413,8 @@ static int help(struct sk_buff **pskb, goto out_update_nl; } - /* Initialize IP/IPv6 addr to expected address (it's not mentioned - in EPSV responses) */ + /* Initialize IP/IPv6 addr to expected address (it's not mentioned + in EPSV responses) */ cmd.l3num = ct->tuplehash[dir].tuple.src.l3num; memcpy(cmd.u3.all, &ct->tuplehash[dir].tuple.src.u3.all, sizeof(cmd.u3.all)); @@ -466,11 +466,11 @@ static int help(struct sk_buff **pskb, memcmp(&cmd.u3.all, &ct->tuplehash[dir].tuple.src.u3.all, sizeof(cmd.u3.all))) { /* Enrico Scholz's passive FTP to partially RNAT'd ftp - server: it really wants us to connect to a - different IP address. Simply don't record it for - NAT. */ + server: it really wants us to connect to a + different IP address. Simply don't record it for + NAT. */ if (cmd.l3num == PF_INET) { - DEBUGP("conntrack_ftp: NOT RECORDING: " NIPQUAD_FMT " != " NIPQUAD_FMT "\n", + DEBUGP("conntrack_ftp: NOT RECORDING: " NIPQUAD_FMT " != " NIPQUAD_FMT "\n", NIPQUAD(cmd.u3.ip), NIPQUAD(ct->tuplehash[dir].tuple.src.u3.ip)); } else { diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 6d8568959f82..b284db73ca7c 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -49,7 +49,7 @@ MODULE_PARM_DESC(gkrouted_only, "only accept calls from gatekeeper"); static int callforward_filter __read_mostly = 1; module_param(callforward_filter, bool, 0600); MODULE_PARM_DESC(callforward_filter, "only create call forwarding expectations " - "if both endpoints are on different sides " + "if both endpoints are on different sides " "(determined by routing information)"); /* Hooks for NAT */ @@ -300,7 +300,7 @@ static int expect_rtp_rtcp(struct sk_buff **pskb, struct nf_conn *ct, IPPROTO_UDP, NULL, &rtcp_port); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, - &ct->tuplehash[!dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.dst.u3, sizeof(ct->tuplehash[dir].tuple.src.u3)) && (nat_rtp_rtcp = rcu_dereference(nat_rtp_rtcp_hook)) && ct->status & IPS_NAT_MASK) { @@ -743,7 +743,7 @@ static int callforward_do_filter(union nf_conntrack_address *src, rt2 = (struct rt6_info *)ip6_route_output(NULL, &fl2); if (rt2) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, - sizeof(rt1->rt6i_gateway)) && + sizeof(rt1->rt6i_gateway)) && rt1->u.dst.dev == rt2->u.dst.dev) ret = 1; dst_release(&rt2->u.dst); @@ -780,7 +780,7 @@ static int expect_callforwarding(struct sk_buff **pskb, * we don't need to track the second call */ if (callforward_filter && callforward_do_filter(&addr, &ct->tuplehash[!dir].tuple.src.u3, - ct->tuplehash[!dir].tuple.src.l3num)) { + ct->tuplehash[!dir].tuple.src.l3num)) { DEBUGP("nf_ct_q931: Call Forwarding not tracked\n"); return 0; } @@ -840,7 +840,7 @@ static int process_setup(struct sk_buff **pskb, struct nf_conn *ct, if ((setup->options & eSetup_UUIE_destCallSignalAddress) && (set_h225_addr) && ct->status && IPS_NAT_MASK && get_h225_addr(ct, *data, &setup->destCallSignalAddress, - &addr, &port) && + &addr, &port) && memcmp(&addr, &ct->tuplehash[!dir].tuple.src.u3, sizeof(addr))) { DEBUGP("nf_ct_q931: set destCallSignalAddress " NIP6_FMT ":%hu->" NIP6_FMT ":%hu\n", @@ -858,7 +858,7 @@ static int process_setup(struct sk_buff **pskb, struct nf_conn *ct, if ((setup->options & eSetup_UUIE_sourceCallSignalAddress) && (set_h225_addr) && ct->status & IPS_NAT_MASK && get_h225_addr(ct, *data, &setup->sourceCallSignalAddress, - &addr, &port) && + &addr, &port) && memcmp(&addr, &ct->tuplehash[!dir].tuple.dst.u3, sizeof(addr))) { DEBUGP("nf_ct_q931: set sourceCallSignalAddress " NIP6_FMT ":%hu->" NIP6_FMT ":%hu\n", @@ -1282,7 +1282,7 @@ static int expect_q931(struct sk_buff **pskb, struct nf_conn *ct, for (i = 0; i < count; i++) { if (get_h225_addr(ct, *data, &taddr[i], &addr, &port) && memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, - sizeof(addr)) == 0 && port != 0) + sizeof(addr)) == 0 && port != 0) break; } @@ -1294,7 +1294,7 @@ static int expect_q931(struct sk_buff **pskb, struct nf_conn *ct, return -1; nf_conntrack_expect_init(exp, ct->tuplehash[!dir].tuple.src.l3num, gkrouted_only ? /* only accept calls from GK? */ - &ct->tuplehash[!dir].tuple.src.u3 : + &ct->tuplehash[!dir].tuple.src.u3 : NULL, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); @@ -1513,7 +1513,7 @@ static int process_arq(struct sk_buff **pskb, struct nf_conn *ct, set_h225_addr = rcu_dereference(set_h225_addr_hook); if ((arq->options & eAdmissionRequest_destCallSignalAddress) && get_h225_addr(ct, *data, &arq->destCallSignalAddress, - &addr, &port) && + &addr, &port) && !memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) && port == info->sig_port[dir] && set_h225_addr && ct->status & IPS_NAT_MASK) { @@ -1526,7 +1526,7 @@ static int process_arq(struct sk_buff **pskb, struct nf_conn *ct, if ((arq->options & eAdmissionRequest_srcCallSignalAddress) && get_h225_addr(ct, *data, &arq->srcCallSignalAddress, - &addr, &port) && + &addr, &port) && !memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) && set_h225_addr && ct->status & IPS_NAT_MASK) { /* Calling ARQ */ diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index ed01db634399..43ccd0e2e8ae 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -57,7 +57,7 @@ static const char *dccprotos[] = { #if 0 #define DEBUGP(format, args...) printk(KERN_DEBUG "%s:%s:" format, \ - __FILE__, __FUNCTION__ , ## args) + __FILE__, __FUNCTION__ , ## args) #else #define DEBUGP(format, args...) #endif diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c index a3d31c3ac8e6..cbd96f3c1b89 100644 --- a/net/netfilter/nf_conntrack_l3proto_generic.c +++ b/net/netfilter/nf_conntrack_l3proto_generic.c @@ -77,7 +77,7 @@ generic_prepare(struct sk_buff **pskb, unsigned int hooknum, static u_int32_t generic_get_features(const struct nf_conntrack_tuple *tuple) - + { return NF_CT_F_BASIC; } diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index 2a48efdf0d67..bb26a658cc1c 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -43,7 +43,7 @@ module_param(timeout, uint, 0400); MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds"); static int help(struct sk_buff **pskb, unsigned int protoff, - struct nf_conn *ct, enum ip_conntrack_info ctinfo) + struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct nf_conntrack_expect *exp; struct iphdr *iph = (*pskb)->nh.iph; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c64f029f7052..48f05314ebf7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -6,10 +6,10 @@ * (C) 2003 by Patrick Mchardy <kaber@trash.net> * (C) 2005-2006 by Pablo Neira Ayuso <pablo@eurodev.net> * - * I've reworked this stuff to use attributes instead of conntrack + * I've reworked this stuff to use attributes instead of conntrack * structures. 5.44 am. I need more tea. --pablo 05/07/11. * - * Initial connection tracking via netlink development funded and + * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) @@ -53,7 +53,7 @@ MODULE_LICENSE("GPL"); static char __initdata version[] = "0.93"; static inline int -ctnetlink_dump_tuples_proto(struct sk_buff *skb, +ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_l4proto *l4proto) { @@ -64,7 +64,7 @@ ctnetlink_dump_tuples_proto(struct sk_buff *skb, if (likely(l4proto->tuple_to_nfattr)) ret = l4proto->tuple_to_nfattr(skb, tuple); - + NFA_NEST_END(skb, nest_parms); return ret; @@ -135,7 +135,7 @@ ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct) timeout = 0; else timeout = htonl(timeout_l / HZ); - + NFA_PUT(skb, CTA_TIMEOUT, sizeof(timeout), &timeout); return 0; @@ -154,7 +154,7 @@ ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct nf_conn *ct) nf_ct_l4proto_put(l4proto); return 0; } - + nest_proto = NFA_NEST(skb, CTA_PROTOINFO); ret = l4proto->to_nfattr(skb, nest_proto, ct); @@ -178,7 +178,7 @@ ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) if (!help || !help->helper) return 0; - + nest_helper = NFA_NEST(skb, CTA_HELP); NFA_PUT(skb, CTA_HELP_NAME, strlen(help->helper->name), help->helper->name); @@ -250,7 +250,7 @@ static inline int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { __be32 use = htonl(atomic_read(&ct->ct_general.use)); - + NFA_PUT(skb, CTA_USE, sizeof(u_int32_t), &use); return 0; @@ -262,7 +262,7 @@ nfattr_failure: static int ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, - int event, int nowait, + int event, int nowait, const struct nf_conn *ct) { struct nlmsghdr *nlh; @@ -277,7 +277,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, nfmsg = NLMSG_DATA(nlh); nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; - nfmsg->nfgen_family = + nfmsg->nfgen_family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; @@ -286,7 +286,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nfattr_failure; NFA_NEST_END(skb, nest_parms); - + nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY); if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nfattr_failure; @@ -314,7 +314,7 @@ nfattr_failure: #ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_conntrack_event(struct notifier_block *this, - unsigned long events, void *ptr) + unsigned long events, void *ptr) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -364,7 +364,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nfattr_failure; NFA_NEST_END(skb, nest_parms); - + nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY); if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nfattr_failure; @@ -383,16 +383,16 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, if (events & IPCT_PROTOINFO && ctnetlink_dump_protoinfo(skb, ct) < 0) - goto nfattr_failure; + goto nfattr_failure; if ((events & IPCT_HELPER || nfct_help(ct)) && ctnetlink_dump_helpinfo(skb, ct) < 0) - goto nfattr_failure; + goto nfattr_failure; #ifdef CONFIG_NF_CONNTRACK_MARK if ((events & IPCT_MARK || ct->mark) && ctnetlink_dump_mark(skb, ct) < 0) - goto nfattr_failure; + goto nfattr_failure; #endif if (events & IPCT_COUNTER_FILLING && @@ -450,7 +450,7 @@ restart: cb->args[1] = 0; } if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_seq, IPCTNL_MSG_CT_NEW, 1, ct) < 0) { nf_conntrack_get(&ct->ct_general); @@ -500,7 +500,7 @@ static const size_t cta_min_proto[CTA_PROTO_MAX] = { }; static inline int -ctnetlink_parse_tuple_proto(struct nfattr *attr, +ctnetlink_parse_tuple_proto(struct nfattr *attr, struct nf_conntrack_tuple *tuple) { struct nfattr *tb[CTA_PROTO_MAX]; @@ -522,7 +522,7 @@ ctnetlink_parse_tuple_proto(struct nfattr *attr, ret = l4proto->nfattr_to_tuple(tb, tuple); nf_ct_l4proto_put(l4proto); - + return ret; } @@ -609,7 +609,7 @@ nfnetlink_parse_nat(struct nfattr *nat, int err; memset(range, 0, sizeof(*range)); - + nfattr_parse_nested(tb, CTA_NAT_MAX, nat); if (nfattr_bad_size(tb, CTA_NAT_MAX, cta_min_nat)) @@ -661,7 +661,7 @@ static const size_t cta_min[CTA_MAX] = { }; static int -ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, +ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) { struct nf_conntrack_tuple_hash *h; @@ -692,14 +692,14 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); - + if (cda[CTA_ID-1]) { u_int32_t id = ntohl(*(__be32 *)NFA_DATA(cda[CTA_ID-1])); if (ct->id != id) { nf_ct_put(ct); return -ENOENT; } - } + } if (del_timer(&ct->timeout)) ct->timeout.function((unsigned long)ct); @@ -709,7 +709,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, +ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) { struct nf_conntrack_tuple_hash *h; @@ -765,7 +765,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, return -ENOMEM; } - err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, + err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, IPCTNL_MSG_CT_NEW, 1, ct); nf_ct_put(ct); if (err <= 0) @@ -793,12 +793,12 @@ ctnetlink_change_status(struct nf_conn *ct, struct nfattr *cda[]) if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING)) /* unchangeable */ return -EINVAL; - + if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EINVAL; - + if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EINVAL; @@ -877,7 +877,7 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[]) memset(&help->help, 0, sizeof(help->help)); } } - + help->helper = helper; return 0; @@ -887,7 +887,7 @@ static inline int ctnetlink_change_timeout(struct nf_conn *ct, struct nfattr *cda[]) { u_int32_t timeout = ntohl(*(__be32 *)NFA_DATA(cda[CTA_TIMEOUT-1])); - + if (!del_timer(&ct->timeout)) return -ETIME; @@ -955,7 +955,7 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nfattr *cda[]) } static int -ctnetlink_create_conntrack(struct nfattr *cda[], +ctnetlink_create_conntrack(struct nfattr *cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple) { @@ -965,7 +965,7 @@ ctnetlink_create_conntrack(struct nfattr *cda[], ct = nf_conntrack_alloc(otuple, rtuple); if (ct == NULL || IS_ERR(ct)) - return -ENOMEM; + return -ENOMEM; if (!cda[CTA_TIMEOUT-1]) goto err; @@ -1003,13 +1003,13 @@ ctnetlink_create_conntrack(struct nfattr *cda[], return 0; -err: +err: nf_conntrack_free(ct); return err; } -static int -ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, +static int +ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) { struct nf_conntrack_tuple otuple, rtuple; @@ -1065,9 +1065,9 @@ out_unlock: return err; } -/*********************************************************************** - * EXPECT - ***********************************************************************/ +/*********************************************************************** + * EXPECT + ***********************************************************************/ static inline int ctnetlink_exp_dump_tuple(struct sk_buff *skb, @@ -1075,7 +1075,7 @@ ctnetlink_exp_dump_tuple(struct sk_buff *skb, enum ctattr_expect type) { struct nfattr *nest_parms = NFA_NEST(skb, type); - + if (ctnetlink_dump_tuples(skb, tuple) < 0) goto nfattr_failure; @@ -1085,7 +1085,7 @@ ctnetlink_exp_dump_tuple(struct sk_buff *skb, nfattr_failure: return -1; -} +} static inline int ctnetlink_exp_dump_mask(struct sk_buff *skb, @@ -1120,7 +1120,7 @@ nfattr_failure: static inline int ctnetlink_exp_dump_expect(struct sk_buff *skb, - const struct nf_conntrack_expect *exp) + const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; __be32 timeout = htonl((exp->timeout.expires - jiffies) / HZ); @@ -1134,20 +1134,20 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, CTA_EXPECT_MASTER) < 0) goto nfattr_failure; - + NFA_PUT(skb, CTA_EXPECT_TIMEOUT, sizeof(timeout), &timeout); NFA_PUT(skb, CTA_EXPECT_ID, sizeof(u_int32_t), &id); return 0; - + nfattr_failure: return -1; } static int ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq, - int event, - int nowait, + int event, + int nowait, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; @@ -1250,7 +1250,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) goto out; *id = exp->id; } -out: +out: read_unlock_bh(&nf_conntrack_lock); return skb->len; @@ -1262,7 +1262,7 @@ static const size_t cta_min_exp[CTA_EXPECT_MAX] = { }; static int -ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, +ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) { struct nf_conntrack_tuple tuple; @@ -1279,7 +1279,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, u32 rlen; if ((*errp = netlink_dump_start(ctnl, skb, nlh, - ctnetlink_exp_dump_table, + ctnetlink_exp_dump_table, ctnetlink_done)) != 0) return -EINVAL; rlen = NLMSG_ALIGN(nlh->nlmsg_len); @@ -1307,14 +1307,14 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, nf_conntrack_expect_put(exp); return -ENOENT; } - } + } err = -ENOMEM; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) goto out; - err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, + err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, 1, exp); if (err <= 0) @@ -1332,7 +1332,7 @@ out: } static int -ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, +ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) { struct nf_conntrack_expect *exp, *tmp; @@ -1366,7 +1366,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* after list removal, usage count == 1 */ nf_conntrack_unexpect_related(exp); - /* have to put what we 'get' above. + /* have to put what we 'get' above. * after this line usage count == 0 */ nf_conntrack_expect_put(exp); } else if (cda[CTA_EXPECT_HELP_NAME-1]) { @@ -1449,7 +1449,7 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3) err = -ENOMEM; goto out; } - + exp->expectfn = NULL; exp->flags = 0; exp->master = ct; @@ -1460,7 +1460,7 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3) err = nf_conntrack_expect_related(exp); nf_conntrack_expect_put(exp); -out: +out: nf_ct_put(nf_ct_tuplehash_to_ctrack(h)); return err; } diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index c59df3bc2bbd..115bcb5d5a7c 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -520,7 +520,7 @@ conntrack_pptp_help(struct sk_buff **pskb, unsigned int protoff, tcph = skb_header_pointer(*pskb, nexthdr_off, sizeof(_tcph), &_tcph); BUG_ON(!tcph); nexthdr_off += tcph->doff * 4; - datalen = tcplen - tcph->doff * 4; + datalen = tcplen - tcph->doff * 4; pptph = skb_header_pointer(*pskb, nexthdr_off, sizeof(_pptph), &_pptph); if (!pptph) { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 1a61b72712cd..456155f05c75 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -66,7 +66,7 @@ __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto) if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_l4proto_generic; - return nf_ct_protos[l3proto][l4proto]; + return rcu_dereference(nf_ct_protos[l3proto][l4proto]); } EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find); @@ -77,11 +77,11 @@ nf_ct_l4proto_find_get(u_int16_t l3proto, u_int8_t l4proto) { struct nf_conntrack_l4proto *p; - preempt_disable(); + rcu_read_lock(); p = __nf_ct_l4proto_find(l3proto, l4proto); if (!try_module_get(p->me)) p = &nf_conntrack_l4proto_generic; - preempt_enable(); + rcu_read_unlock(); return p; } @@ -98,11 +98,11 @@ nf_ct_l3proto_find_get(u_int16_t l3proto) { struct nf_conntrack_l3proto *p; - preempt_disable(); + rcu_read_lock(); p = __nf_ct_l3proto_find(l3proto); if (!try_module_get(p->me)) p = &nf_conntrack_l3proto_generic; - preempt_enable(); + rcu_read_unlock(); return p; } @@ -137,10 +137,8 @@ void nf_ct_l3proto_module_put(unsigned short l3proto) { struct nf_conntrack_l3proto *p; - preempt_disable(); + /* rcu_read_lock not necessary since the caller holds a reference */ p = __nf_ct_l3proto_find(l3proto); - preempt_enable(); - module_put(p->me); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put); @@ -202,7 +200,7 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) ret = -EBUSY; goto out_unlock; } - nf_ct_l3protos[proto->l3proto] = proto; + rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto); write_unlock_bh(&nf_conntrack_lock); ret = nf_ct_l3proto_register_sysctl(proto); @@ -217,35 +215,21 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_register); -int nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) +void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) { - int ret = 0; - - if (proto->l3proto >= AF_MAX) { - ret = -EBUSY; - goto out; - } + BUG_ON(proto->l3proto >= AF_MAX); write_lock_bh(&nf_conntrack_lock); - if (nf_ct_l3protos[proto->l3proto] != proto) { - write_unlock_bh(&nf_conntrack_lock); - ret = -EBUSY; - goto out; - } - - nf_ct_l3protos[proto->l3proto] = &nf_conntrack_l3proto_generic; + BUG_ON(nf_ct_l3protos[proto->l3proto] != proto); + rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], + &nf_conntrack_l3proto_generic); write_unlock_bh(&nf_conntrack_lock); + synchronize_rcu(); nf_ct_l3proto_unregister_sysctl(proto); - /* Somebody could be still looking at the proto in bh. */ - synchronize_net(); - /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(kill_l3proto, proto); - -out: - return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); @@ -356,7 +340,7 @@ retry: goto retry; } - nf_ct_protos[l4proto->l3proto][l4proto->l4proto] = l4proto; + rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], l4proto); write_unlock_bh(&nf_conntrack_lock); ret = nf_ct_l4proto_register_sysctl(l4proto); @@ -371,40 +355,25 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_register); -int nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) +void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) { - int ret = 0; - - if (l4proto->l3proto >= PF_MAX) { - ret = -EBUSY; - goto out; - } + BUG_ON(l4proto->l3proto >= PF_MAX); if (l4proto == &nf_conntrack_l4proto_generic) { nf_ct_l4proto_unregister_sysctl(l4proto); - goto out; + return; } write_lock_bh(&nf_conntrack_lock); - if (nf_ct_protos[l4proto->l3proto][l4proto->l4proto] - != l4proto) { - write_unlock_bh(&nf_conntrack_lock); - ret = -EBUSY; - goto out; - } - nf_ct_protos[l4proto->l3proto][l4proto->l4proto] - = &nf_conntrack_l4proto_generic; + BUG_ON(nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != l4proto); + rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], + &nf_conntrack_l4proto_generic); write_unlock_bh(&nf_conntrack_lock); + synchronize_rcu(); nf_ct_l4proto_unregister_sysctl(l4proto); - /* Somebody could be still looking at the proto in bh. */ - synchronize_net(); - /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(kill_l4proto, l4proto); - -out: - return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 76e263668222..0133afa2c7ef 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -1,9 +1,9 @@ /* * Connection tracking protocol helper module for SCTP. - * - * SCTP is defined in RFC 2960. References to various sections in this code + * + * SCTP is defined in RFC 2960. References to various sections in this code * are to this RFC. - * + * * 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. @@ -45,7 +45,7 @@ static DEFINE_RWLOCK(sctp_lock); /* FIXME: Examine ipfilter's timeouts and conntrack transitions more - closely. They're more complex. --RR + closely. They're more complex. --RR And so for me for SCTP :D -Kiran */ @@ -94,32 +94,32 @@ static unsigned int * sctp_timeouts[] #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sIV SCTP_CONNTRACK_MAX -/* +/* These are the descriptions of the states: -NOTE: These state names are tantalizingly similar to the states of an +NOTE: These state names are tantalizingly similar to the states of an SCTP endpoint. But the interpretation of the states is a little different, -considering that these are the states of the connection and not of an end +considering that these are the states of the connection and not of an end point. Please note the subtleties. -Kiran NONE - Nothing so far. -COOKIE WAIT - We have seen an INIT chunk in the original direction, or also - an INIT_ACK chunk in the reply direction. +COOKIE WAIT - We have seen an INIT chunk in the original direction, or also + an INIT_ACK chunk in the reply direction. COOKIE ECHOED - We have seen a COOKIE_ECHO chunk in the original direction. ESTABLISHED - We have seen a COOKIE_ACK in the reply direction. SHUTDOWN_SENT - We have seen a SHUTDOWN chunk in the original direction. SHUTDOWN_RECD - We have seen a SHUTDOWN chunk in the reply directoin. SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite - to that of the SHUTDOWN chunk. -CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of - the SHUTDOWN chunk. Connection is closed. + to that of the SHUTDOWN chunk. +CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of + the SHUTDOWN chunk. Connection is closed. */ /* TODO - - I have assumed that the first INIT is in the original direction. + - I have assumed that the first INIT is in the original direction. This messes things when an INIT comes in the reply direction in CLOSED state. - - Check the error type in the reply dir before transitioning from + - Check the error type in the reply dir before transitioning from cookie echoed to closed. - Sec 5.2.4 of RFC 2960 - Multi Homing support. @@ -237,7 +237,7 @@ static int do_basic_checks(struct nf_conn *conntrack, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { DEBUGP("Chunk Num: %d Type: %d\n", count, sch->type); - if (sch->type == SCTP_CID_INIT + if (sch->type == SCTP_CID_INIT || sch->type == SCTP_CID_INIT_ACK || sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { flag = 1; @@ -277,42 +277,42 @@ static int new_state(enum ip_conntrack_dir dir, DEBUGP("Chunk type: %d\n", chunk_type); switch (chunk_type) { - case SCTP_CID_INIT: + case SCTP_CID_INIT: DEBUGP("SCTP_CID_INIT\n"); i = 0; break; - case SCTP_CID_INIT_ACK: + case SCTP_CID_INIT_ACK: DEBUGP("SCTP_CID_INIT_ACK\n"); i = 1; break; - case SCTP_CID_ABORT: + case SCTP_CID_ABORT: DEBUGP("SCTP_CID_ABORT\n"); i = 2; break; - case SCTP_CID_SHUTDOWN: + case SCTP_CID_SHUTDOWN: DEBUGP("SCTP_CID_SHUTDOWN\n"); i = 3; break; - case SCTP_CID_SHUTDOWN_ACK: + case SCTP_CID_SHUTDOWN_ACK: DEBUGP("SCTP_CID_SHUTDOWN_ACK\n"); i = 4; break; - case SCTP_CID_ERROR: + case SCTP_CID_ERROR: DEBUGP("SCTP_CID_ERROR\n"); i = 5; break; - case SCTP_CID_COOKIE_ECHO: + case SCTP_CID_COOKIE_ECHO: DEBUGP("SCTP_CID_COOKIE_ECHO\n"); i = 6; break; - case SCTP_CID_COOKIE_ACK: + case SCTP_CID_COOKIE_ACK: DEBUGP("SCTP_CID_COOKIE_ACK\n"); i = 7; break; - case SCTP_CID_SHUTDOWN_COMPLETE: + case SCTP_CID_SHUTDOWN_COMPLETE: DEBUGP("SCTP_CID_SHUTDOWN_COMPLETE\n"); i = 8; break; default: /* Other chunks like DATA, SACK, HEARTBEAT and its ACK do not cause a change in state */ - DEBUGP("Unknown chunk type, Will stay in %s\n", + DEBUGP("Unknown chunk type, Will stay in %s\n", sctp_conntrack_names[cur_state]); return cur_state; } - DEBUGP("dir: %d cur_state: %s chunk_type: %d new_state: %s\n", + DEBUGP("dir: %d cur_state: %s chunk_type: %d new_state: %s\n", dir, sctp_conntrack_names[cur_state], chunk_type, sctp_conntrack_names[sctp_conntracks[dir][i][cur_state]]); @@ -377,7 +377,7 @@ static int sctp_packet(struct nf_conn *conntrack, /* Sec 8.5.1 (C) */ if (!(sh->vtag == conntrack->proto.sctp.vtag[CTINFO2DIR(ctinfo)]) && !(sh->vtag == conntrack->proto.sctp.vtag - [1 - CTINFO2DIR(ctinfo)] + [1 - CTINFO2DIR(ctinfo)] && (sch->flags & 1))) { write_unlock_bh(&sctp_lock); return -1; @@ -402,17 +402,17 @@ static int sctp_packet(struct nf_conn *conntrack, } /* If it is an INIT or an INIT ACK note down the vtag */ - if (sch->type == SCTP_CID_INIT + if (sch->type == SCTP_CID_INIT || sch->type == SCTP_CID_INIT_ACK) { sctp_inithdr_t _inithdr, *ih; ih = skb_header_pointer(skb, offset + sizeof(sctp_chunkhdr_t), - sizeof(_inithdr), &_inithdr); + sizeof(_inithdr), &_inithdr); if (ih == NULL) { write_unlock_bh(&sctp_lock); return -1; } - DEBUGP("Setting vtag %x for dir %d\n", + DEBUGP("Setting vtag %x for dir %d\n", ih->init_tag, !CTINFO2DIR(ctinfo)); conntrack->proto.sctp.vtag[!CTINFO2DIR(ctinfo)] = ih->init_tag; } @@ -466,7 +466,7 @@ static int sctp_new(struct nf_conn *conntrack, const struct sk_buff *skb, newconntrack = SCTP_CONNTRACK_MAX; for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Don't need lock here: this conntrack not in circulation yet */ - newconntrack = new_state(IP_CT_DIR_ORIGINAL, + newconntrack = new_state(IP_CT_DIR_ORIGINAL, SCTP_CONNTRACK_NONE, sch->type); /* Invalid: delete conntrack */ @@ -481,14 +481,14 @@ static int sctp_new(struct nf_conn *conntrack, const struct sk_buff *skb, sctp_inithdr_t _inithdr, *ih; ih = skb_header_pointer(skb, offset + sizeof(sctp_chunkhdr_t), - sizeof(_inithdr), &_inithdr); + sizeof(_inithdr), &_inithdr); if (ih == NULL) return 0; - DEBUGP("Setting vtag %x for new conn\n", + DEBUGP("Setting vtag %x for new conn\n", ih->init_tag); - conntrack->proto.sctp.vtag[IP_CT_DIR_REPLY] = + conntrack->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; } else { /* Sec 8.5.1 (A) */ @@ -498,7 +498,7 @@ static int sctp_new(struct nf_conn *conntrack, const struct sk_buff *skb, /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ else { - DEBUGP("Setting vtag %x for new conn OOTB\n", + DEBUGP("Setting vtag %x for new conn OOTB\n", sh->vtag); conntrack->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag; } @@ -698,7 +698,7 @@ int __init nf_conntrack_proto_sctp_init(void) cleanup_sctp4: nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp4); out: - DEBUGP("SCTP conntrack module loading %s\n", + DEBUGP("SCTP conntrack module loading %s\n", ret ? "failed": "succeeded"); return ret; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 6fccdcf43e08..aff65aad3c66 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -55,19 +55,19 @@ /* Protects conntrack->proto.tcp */ static DEFINE_RWLOCK(tcp_lock); -/* "Be conservative in what you do, - be liberal in what you accept from others." +/* "Be conservative in what you do, + be liberal in what you accept from others." If it's non-zero, we mark only out of window RST segments as INVALID. */ -int nf_ct_tcp_be_liberal __read_mostly = 0; +static int nf_ct_tcp_be_liberal __read_mostly = 0; /* If it is set to zero, we disable picking up already established connections. */ -int nf_ct_tcp_loose __read_mostly = 1; +static int nf_ct_tcp_loose __read_mostly = 1; -/* Max number of the retransmitted packets without receiving an (acceptable) - ACK from the destination. If this number is reached, a shorter timer +/* Max number of the retransmitted packets without receiving an (acceptable) + ACK from the destination. If this number is reached, a shorter timer will be started. */ -int nf_ct_tcp_max_retrans __read_mostly = 3; +static int nf_ct_tcp_max_retrans __read_mostly = 3; /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR */ @@ -84,7 +84,7 @@ static const char *tcp_conntrack_names[] = { "CLOSE", "LISTEN" }; - + #define SECS * HZ #define MINS * 60 SECS #define HOURS * 60 MINS @@ -100,10 +100,10 @@ static unsigned int nf_ct_tcp_timeout_time_wait __read_mostly = 2 MINS; static unsigned int nf_ct_tcp_timeout_close __read_mostly = 10 SECS; /* RFC1122 says the R2 limit should be at least 100 seconds. - Linux uses 15 packets as limit, which corresponds + Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS; - + static unsigned int * tcp_timeouts[] = { NULL, /* TCP_CONNTRACK_NONE */ &nf_ct_tcp_timeout_syn_sent, /* TCP_CONNTRACK_SYN_SENT, */ @@ -116,7 +116,7 @@ static unsigned int * tcp_timeouts[] = { &nf_ct_tcp_timeout_close, /* TCP_CONNTRACK_CLOSE, */ NULL, /* TCP_CONNTRACK_LISTEN */ }; - + #define sNO TCP_CONNTRACK_NONE #define sSS TCP_CONNTRACK_SYN_SENT #define sSR TCP_CONNTRACK_SYN_RECV @@ -139,13 +139,13 @@ enum tcp_bit_set { TCP_RST_SET, TCP_NONE_SET, }; - + /* * The TCP state transition table needs a few words... * * We are the man in the middle. All the packets go through us * but might get lost in transit to the destination. - * It is assumed that the destinations can't receive segments + * It is assumed that the destinations can't receive segments * we haven't seen. * * The checked segment is in window, but our windows are *not* @@ -155,11 +155,11 @@ enum tcp_bit_set { * The meaning of the states are: * * NONE: initial state - * SYN_SENT: SYN-only packet seen + * SYN_SENT: SYN-only packet seen * SYN_RECV: SYN-ACK packet seen * ESTABLISHED: ACK packet seen * FIN_WAIT: FIN packet seen - * CLOSE_WAIT: ACK seen (after FIN) + * CLOSE_WAIT: ACK seen (after FIN) * LAST_ACK: FIN seen (after FIN) * TIME_WAIT: last ACK seen * CLOSE: closed connection @@ -167,8 +167,8 @@ enum tcp_bit_set { * LISTEN state is not used. * * Packets marked as IGNORED (sIG): - * if they may be either invalid or valid - * and the receiver may send back a connection + * if they may be either invalid or valid + * and the receiver may send back a connection * closing RST or a SYN/ACK. * * Packets marked as INVALID (sIV): @@ -185,7 +185,7 @@ static enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sSS -> sSS Retransmitted SYN * sSR -> sIG Late retransmitted SYN? * sES -> sIG Error: SYNs in window outside the SYN_SENT state - * are errors. Receiver will reply with RST + * are errors. Receiver will reply with RST * and close the connection. * Or we are not in sync and hold a dead connection. * sFW -> sIG @@ -198,10 +198,10 @@ static enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { /*synack*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, /* * A SYN/ACK from the client is always invalid: - * - either it tries to set up a simultaneous open, which is + * - either it tries to set up a simultaneous open, which is * not supported; * - or the firewall has just been inserted between the two hosts - * during the session set-up. The SYN will be retransmitted + * during the session set-up. The SYN will be retransmitted * by the true client (or it'll time out). */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ @@ -213,7 +213,7 @@ static enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions, waiting for - * the last ACK. + * the last ACK. * Migth be a retransmitted FIN as well... * sCW -> sLA * sLA -> sLA Retransmitted FIN. Remain in the same state. @@ -291,7 +291,7 @@ static enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ /*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } - } + } }; static int tcp_pkt_to_tuple(const struct sk_buff *skb, @@ -352,21 +352,21 @@ static unsigned int get_conntrack_index(const struct tcphdr *tcph) /* TCP connection tracking based on 'Real Stateful TCP Packet Filtering in IP Filter' by Guido van Rooij. - + http://www.nluug.nl/events/sane2000/papers.html http://www.iae.nl/users/guido/papers/tcp_filtering.ps.gz - + The boundaries and the conditions are changed according to RFC793: the packet must intersect the window (i.e. segments may be after the right or before the left edge) and thus receivers may ACK segments after the right edge of the window. - td_maxend = max(sack + max(win,1)) seen in reply packets + td_maxend = max(sack + max(win,1)) seen in reply packets td_maxwin = max(max(win, 1)) + (sack - ack) seen in sent packets td_maxwin += seq + len - sender.td_maxend if seq + len > sender.td_maxend td_end = max(seq + len) seen in sent packets - + I. Upper bound for valid data: seq <= sender.td_maxend II. Lower bound for valid data: seq + len >= sender.td_end - receiver.td_maxwin III. Upper bound for valid ack: sack <= receiver.td_end @@ -374,8 +374,8 @@ static unsigned int get_conntrack_index(const struct tcphdr *tcph) where sack is the highest right edge of sack block found in the packet. - The upper bound limit for a valid ack is not ignored - - we doesn't have to deal with fragments. + The upper bound limit for a valid ack is not ignored - + we doesn't have to deal with fragments. */ static inline __u32 segment_seq_plus_len(__u32 seq, @@ -388,19 +388,19 @@ static inline __u32 segment_seq_plus_len(__u32 seq, return (seq + len - dataoff - tcph->doff*4 + (tcph->syn ? 1 : 0) + (tcph->fin ? 1 : 0)); } - + /* Fixme: what about big packets? */ #define MAXACKWINCONST 66000 #define MAXACKWINDOW(sender) \ ((sender)->td_maxwin > MAXACKWINCONST ? (sender)->td_maxwin \ : MAXACKWINCONST) - + /* * Simplified tcp_parse_options routine from tcp_input.c */ static void tcp_options(const struct sk_buff *skb, unsigned int dataoff, - struct tcphdr *tcph, + struct tcphdr *tcph, struct ip_ct_tcp_state *state) { unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; @@ -414,7 +414,7 @@ static void tcp_options(const struct sk_buff *skb, length, buff); BUG_ON(ptr == NULL); - state->td_scale = + state->td_scale = state->flags = 0; while (length > 0) { @@ -434,7 +434,7 @@ static void tcp_options(const struct sk_buff *skb, if (opsize > length) break; /* don't parse partial options */ - if (opcode == TCPOPT_SACK_PERM + if (opcode == TCPOPT_SACK_PERM && opsize == TCPOLEN_SACK_PERM) state->flags |= IP_CT_TCP_FLAG_SACK_PERM; else if (opcode == TCPOPT_WINDOW @@ -457,7 +457,7 @@ static void tcp_options(const struct sk_buff *skb, static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, struct tcphdr *tcph, __u32 *sack) { - unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; + unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; unsigned char *ptr; int length = (tcph->doff*4) - sizeof(struct tcphdr); __u32 tmp; @@ -472,10 +472,10 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, /* Fast path for timestamp-only option */ if (length == TCPOLEN_TSTAMP_ALIGNED*4 && *(__be32 *)ptr == - __constant_htonl((TCPOPT_NOP << 24) - | (TCPOPT_NOP << 16) - | (TCPOPT_TIMESTAMP << 8) - | TCPOLEN_TIMESTAMP)) + __constant_htonl((TCPOPT_NOP << 24) + | (TCPOPT_NOP << 16) + | (TCPOPT_TIMESTAMP << 8) + | TCPOLEN_TIMESTAMP)) return; while (length > 0) { @@ -495,15 +495,15 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, if (opsize > length) break; /* don't parse partial options */ - if (opcode == TCPOPT_SACK - && opsize >= (TCPOLEN_SACK_BASE - + TCPOLEN_SACK_PERBLOCK) - && !((opsize - TCPOLEN_SACK_BASE) - % TCPOLEN_SACK_PERBLOCK)) { - for (i = 0; - i < (opsize - TCPOLEN_SACK_BASE); - i += TCPOLEN_SACK_PERBLOCK) { - tmp = ntohl(*((__be32 *)(ptr+i)+1)); + if (opcode == TCPOPT_SACK + && opsize >= (TCPOLEN_SACK_BASE + + TCPOLEN_SACK_PERBLOCK) + && !((opsize - TCPOLEN_SACK_BASE) + % TCPOLEN_SACK_PERBLOCK)) { + for (i = 0; + i < (opsize - TCPOLEN_SACK_BASE); + i += TCPOLEN_SACK_PERBLOCK) { + tmp = ntohl(*((__be32 *)(ptr+i)+1)); if (after(tmp, *sack)) *sack = tmp; @@ -516,12 +516,12 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } -static int tcp_in_window(struct ip_ct_tcp *state, - enum ip_conntrack_dir dir, - unsigned int index, - const struct sk_buff *skb, +static int tcp_in_window(struct ip_ct_tcp *state, + enum ip_conntrack_dir dir, + unsigned int index, + const struct sk_buff *skb, unsigned int dataoff, - struct tcphdr *tcph, + struct tcphdr *tcph, int pf) { struct ip_ct_tcp_state *sender = &state->seen[dir]; @@ -543,14 +543,14 @@ static int tcp_in_window(struct ip_ct_tcp *state, DEBUGP("tcp_in_window: START\n"); DEBUGP("tcp_in_window: src=%u.%u.%u.%u:%hu dst=%u.%u.%u.%u:%hu " "seq=%u ack=%u sack=%u win=%u end=%u\n", - NIPQUAD(iph->saddr), ntohs(tcph->source), + NIPQUAD(iph->saddr), ntohs(tcph->source), NIPQUAD(iph->daddr), ntohs(tcph->dest), seq, ack, sack, win, end); DEBUGP("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, - sender->td_scale, - receiver->td_end, receiver->td_maxend, receiver->td_maxwin, + sender->td_scale, + receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); if (sender->td_end == 0) { @@ -561,26 +561,26 @@ static int tcp_in_window(struct ip_ct_tcp *state, /* * Outgoing SYN-ACK in reply to a SYN. */ - sender->td_end = + sender->td_end = sender->td_maxend = end; sender->td_maxwin = (win == 0 ? 1 : win); tcp_options(skb, dataoff, tcph, sender); - /* + /* * RFC 1323: * Both sides must send the Window Scale option * to enable window scaling in either direction. */ if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) - sender->td_scale = + sender->td_scale = receiver->td_scale = 0; } else { /* * We are in the middle of a connection, * its history is lost for us. * Let's try to use the data from the packet. - */ + */ sender->td_end = end; sender->td_maxwin = (win == 0 ? 1 : win); sender->td_maxend = end + sender->td_maxwin; @@ -592,7 +592,7 @@ static int tcp_in_window(struct ip_ct_tcp *state, && after(end, sender->td_end)) { /* * RFC 793: "if a TCP is reinitialized ... then it need - * not wait at all; it must only be sure to use sequence + * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." */ sender->td_end = @@ -607,8 +607,8 @@ static int tcp_in_window(struct ip_ct_tcp *state, * If there is no ACK, just pretend it was set and OK. */ ack = sack = receiver->td_end; - } else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) == - (TCP_FLAG_ACK|TCP_FLAG_RST)) + } else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) == + (TCP_FLAG_ACK|TCP_FLAG_RST)) && (ack == 0)) { /* * Broken TCP stacks, that set ACK in RST packets as well @@ -637,21 +637,21 @@ static int tcp_in_window(struct ip_ct_tcp *state, DEBUGP("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, - sender->td_scale, + sender->td_scale, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); DEBUGP("tcp_in_window: I=%i II=%i III=%i IV=%i\n", before(seq, sender->td_maxend + 1), after(end, sender->td_end - receiver->td_maxwin - 1), - before(sack, receiver->td_end + 1), - after(ack, receiver->td_end - MAXACKWINDOW(sender))); + before(sack, receiver->td_end + 1), + after(ack, receiver->td_end - MAXACKWINDOW(sender))); if (before(seq, sender->td_maxend + 1) && after(end, sender->td_end - receiver->td_maxwin - 1) && before(sack, receiver->td_end + 1) && after(ack, receiver->td_end - MAXACKWINDOW(sender))) { - /* + /* * Take into account window scaling (RFC 1323). */ if (!tcph->syn) @@ -676,7 +676,7 @@ static int tcp_in_window(struct ip_ct_tcp *state, receiver->td_maxend++; } - /* + /* * Check retransmissions. */ if (index == TCP_ACK_SET) { @@ -712,11 +712,11 @@ static int tcp_in_window(struct ip_ct_tcp *state, : "ACK is over the upper bound (ACKed data not seen yet)" : "SEQ is under the lower bound (already ACKed data retransmitted)" : "SEQ is over the upper bound (over the window of the receiver)"); - } - + } + DEBUGP("tcp_in_window: res=%i sender end=%u maxend=%u maxwin=%u " "receiver end=%u maxend=%u maxwin=%u\n", - res, sender->td_end, sender->td_maxend, sender->td_maxwin, + res, sender->td_end, sender->td_maxend, sender->td_maxwin, receiver->td_end, receiver->td_maxend, receiver->td_maxwin); return res; @@ -727,7 +727,7 @@ static int tcp_in_window(struct ip_ct_tcp *state, /* Caller must linearize skb at tcp header. */ void nf_conntrack_tcp_update(struct sk_buff *skb, unsigned int dataoff, - struct nf_conn *conntrack, + struct nf_conn *conntrack, int dir) { struct tcphdr *tcph = (void *)skb->data + dataoff; @@ -750,7 +750,7 @@ void nf_conntrack_tcp_update(struct sk_buff *skb, DEBUGP("tcp_update: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, - sender->td_scale, + sender->td_scale, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); } @@ -804,8 +804,8 @@ static int tcp_error(struct sk_buff *skb, nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: short packet "); return -NF_ACCEPT; - } - + } + /* Not whole TCP header or malformed packet */ if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) { if (LOG_INVALID(IPPROTO_TCP)) @@ -813,7 +813,7 @@ static int tcp_error(struct sk_buff *skb, "nf_ct_tcp: truncated/malformed packet "); return -NF_ACCEPT; } - + /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path * because the checksum is assumed to be correct. @@ -870,28 +870,28 @@ static int tcp_packet(struct nf_conn *conntrack, * * a) SYN in ORIGINAL * b) SYN/ACK in REPLY - * c) ACK in reply direction after initial SYN in original. + * c) ACK in reply direction after initial SYN in original. */ if (index == TCP_SYNACK_SET && conntrack->proto.tcp.last_index == TCP_SYN_SET && conntrack->proto.tcp.last_dir != dir && ntohl(th->ack_seq) == - conntrack->proto.tcp.last_end) { - /* This SYN/ACK acknowledges a SYN that we earlier + conntrack->proto.tcp.last_end) { + /* This SYN/ACK acknowledges a SYN that we earlier * ignored as invalid. This means that the client and * the server are both in sync, while the firewall is * not. We kill this session and block the SYN/ACK so - * that the client cannot but retransmit its SYN and + * that the client cannot but retransmit its SYN and * thus initiate a clean new session. */ - write_unlock_bh(&tcp_lock); + write_unlock_bh(&tcp_lock); if (LOG_INVALID(IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: killing out of sync session "); - if (del_timer(&conntrack->timeout)) - conntrack->timeout.function((unsigned long) - conntrack); - return -NF_DROP; + if (del_timer(&conntrack->timeout)) + conntrack->timeout.function((unsigned long) + conntrack); + return -NF_DROP; } conntrack->proto.tcp.last_index = index; conntrack->proto.tcp.last_dir = dir; @@ -921,13 +921,13 @@ static int tcp_packet(struct nf_conn *conntrack, IP_CT_TCP_FLAG_CLOSE_INIT) || after(ntohl(th->seq), conntrack->proto.tcp.seen[dir].td_end)) { - /* Attempt to reopen a closed connection. - * Delete this connection and look up again. */ - write_unlock_bh(&tcp_lock); - if (del_timer(&conntrack->timeout)) - conntrack->timeout.function((unsigned long) - conntrack); - return -NF_REPEAT; + /* Attempt to reopen a closed connection. + * Delete this connection and look up again. */ + write_unlock_bh(&tcp_lock); + if (del_timer(&conntrack->timeout)) + conntrack->timeout.function((unsigned long) + conntrack); + return -NF_REPEAT; } else { write_unlock_bh(&tcp_lock); if (LOG_INVALID(IPPROTO_TCP)) @@ -938,9 +938,9 @@ static int tcp_packet(struct nf_conn *conntrack, case TCP_CONNTRACK_CLOSE: if (index == TCP_RST_SET && ((test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status) - && conntrack->proto.tcp.last_index == TCP_SYN_SET) - || (!test_bit(IPS_ASSURED_BIT, &conntrack->status) - && conntrack->proto.tcp.last_index == TCP_ACK_SET)) + && conntrack->proto.tcp.last_index == TCP_SYN_SET) + || (!test_bit(IPS_ASSURED_BIT, &conntrack->status) + && conntrack->proto.tcp.last_index == TCP_ACK_SET)) && ntohl(th->ack_seq) == conntrack->proto.tcp.last_end) { /* RST sent to invalid SYN or ACK we had let through * at a) and c) above: @@ -1005,8 +1005,8 @@ static int tcp_packet(struct nf_conn *conntrack, && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) && new_state == TCP_CONNTRACK_ESTABLISHED) { - /* Set ASSURED if we see see valid ack in ESTABLISHED - after SYN_RECV or a valid answer for a picked up + /* Set ASSURED if we see see valid ack in ESTABLISHED + after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &conntrack->status); nf_conntrack_event_cache(IPCT_STATUS, skb); @@ -1015,7 +1015,7 @@ static int tcp_packet(struct nf_conn *conntrack, return NF_ACCEPT; } - + /* Called when a new connection for this protocol found. */ static int tcp_new(struct nf_conn *conntrack, const struct sk_buff *skb, @@ -1071,7 +1071,7 @@ static int tcp_new(struct nf_conn *conntrack, if (conntrack->proto.tcp.seen[0].td_maxwin == 0) conntrack->proto.tcp.seen[0].td_maxwin = 1; conntrack->proto.tcp.seen[0].td_maxend = - conntrack->proto.tcp.seen[0].td_end + + conntrack->proto.tcp.seen[0].td_end + conntrack->proto.tcp.seen[0].td_maxwin; conntrack->proto.tcp.seen[0].td_scale = 0; @@ -1081,20 +1081,20 @@ static int tcp_new(struct nf_conn *conntrack, conntrack->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM | IP_CT_TCP_FLAG_BE_LIBERAL; } - + conntrack->proto.tcp.seen[1].td_end = 0; conntrack->proto.tcp.seen[1].td_maxend = 0; conntrack->proto.tcp.seen[1].td_maxwin = 1; - conntrack->proto.tcp.seen[1].td_scale = 0; + conntrack->proto.tcp.seen[1].td_scale = 0; /* tcp_packet will set them */ conntrack->proto.tcp.state = TCP_CONNTRACK_NONE; conntrack->proto.tcp.last_index = TCP_NONE_SET; - + DEBUGP("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, - sender->td_scale, + sender->td_scale, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); return 1; @@ -1110,7 +1110,7 @@ static int tcp_to_nfattr(struct sk_buff *skb, struct nfattr *nfa, const struct nf_conn *ct) { struct nfattr *nest_parms; - + read_lock_bh(&tcp_lock); nest_parms = NFA_NEST(skb, CTA_PROTOINFO_TCP); NFA_PUT(skb, CTA_PROTOINFO_TCP_STATE, sizeof(u_int8_t), @@ -1140,7 +1140,7 @@ static int nfattr_to_tcp(struct nfattr *cda[], struct nf_conn *ct) if (!attr) return 0; - nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr); + nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr); if (nfattr_bad_size(tb, CTA_PROTOINFO_TCP_MAX, cta_min_tcp)) return -EINVAL; @@ -1149,7 +1149,7 @@ static int nfattr_to_tcp(struct nfattr *cda[], struct nf_conn *ct) return -EINVAL; write_lock_bh(&tcp_lock); - ct->proto.tcp.state = + ct->proto.tcp.state = *(u_int8_t *)NFA_DATA(tb[CTA_PROTOINFO_TCP_STATE-1]); write_unlock_bh(&tcp_lock); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 9dec11534678..7aaa8c91b293 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -341,7 +341,7 @@ int ct_sip_get_info(struct nf_conn *ct, continue; } aux = ct_sip_search(hnfo->ln_str, dptr, hnfo->ln_strlen, - ct_sip_lnlen(dptr, limit), + ct_sip_lnlen(dptr, limit), hnfo->case_sensitive); if (!aux) { DEBUGP("'%s' not found in '%s'.\n", hnfo->ln_str, @@ -451,12 +451,12 @@ static int sip_help(struct sk_buff **pskb, /* We'll drop only if there are parse problems. */ if (!parse_addr(ct, dptr + matchoff, NULL, &addr, - dptr + datalen)) { + dptr + datalen)) { ret = NF_DROP; goto out; } if (ct_sip_get_info(ct, dptr, datalen, &matchoff, &matchlen, - POS_MEDIA) > 0) { + POS_MEDIA) > 0) { port = simple_strtoul(dptr + matchoff, NULL, 10); if (port < 1024) { diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 04ac12431db7..a0bba481d70d 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -472,7 +472,7 @@ static int __init nf_conntrack_standalone_init(void) static void __exit nf_conntrack_standalone_fini(void) { #ifdef CONFIG_SYSCTL - unregister_sysctl_table(nf_ct_sysctl_header); + unregister_sysctl_table(nf_ct_sysctl_header); #endif #ifdef CONFIG_PROC_FS remove_proc_entry("nf_conntrack", proc_net_stat); diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index f5bffe24b0a5..37c4542e3112 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -31,7 +31,7 @@ MODULE_PARM_DESC(ports, "Port numbers of TFTP servers"); #if 0 #define DEBUGP(format, args...) printk("%s:%s:" format, \ - __FILE__, __FUNCTION__ , ## args) + __FILE__, __FUNCTION__ , ## args) #else #define DEBUGP(format, args...) #endif diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index a981971ce1d5..0df7fff196a7 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -24,7 +24,7 @@ extern unsigned int nf_iterate(struct list_head *head, /* nf_queue.c */ extern int nf_queue(struct sk_buff *skb, - struct list_head *elem, + struct list_head *elem, int pf, unsigned int hook, struct net_device *indev, struct net_device *outdev, diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 07e28e089616..91b220cf5a1f 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -14,62 +14,63 @@ #define NF_LOG_PREFIXLEN 128 -static struct nf_logger *nf_logging[NPROTO]; /* = NULL */ -static DEFINE_SPINLOCK(nf_log_lock); +static struct nf_logger *nf_loggers[NPROTO]; +static DEFINE_MUTEX(nf_log_mutex); /* return EBUSY if somebody else is registered, EEXIST if the same logger * is registred, 0 on success. */ int nf_log_register(int pf, struct nf_logger *logger) { - int ret = -EBUSY; + int ret; if (pf >= NPROTO) return -EINVAL; /* Any setup of logging members must be done before * substituting pointer. */ - spin_lock(&nf_log_lock); - if (!nf_logging[pf]) { - rcu_assign_pointer(nf_logging[pf], logger); - ret = 0; - } else if (nf_logging[pf] == logger) + ret = mutex_lock_interruptible(&nf_log_mutex); + if (ret < 0) + return ret; + + if (!nf_loggers[pf]) + rcu_assign_pointer(nf_loggers[pf], logger); + else if (nf_loggers[pf] == logger) ret = -EEXIST; + else + ret = -EBUSY; - spin_unlock(&nf_log_lock); + mutex_unlock(&nf_log_mutex); return ret; -} +} EXPORT_SYMBOL(nf_log_register); -int nf_log_unregister_pf(int pf) +void nf_log_unregister_pf(int pf) { if (pf >= NPROTO) - return -EINVAL; - - spin_lock(&nf_log_lock); - nf_logging[pf] = NULL; - spin_unlock(&nf_log_lock); + return; + mutex_lock(&nf_log_mutex); + rcu_assign_pointer(nf_loggers[pf], NULL); + mutex_unlock(&nf_log_mutex); /* Give time to concurrent readers. */ - synchronize_net(); - - return 0; + synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister_pf); -void nf_log_unregister_logger(struct nf_logger *logger) +void nf_log_unregister(struct nf_logger *logger) { int i; - spin_lock(&nf_log_lock); + mutex_lock(&nf_log_mutex); for (i = 0; i < NPROTO; i++) { - if (nf_logging[i] == logger) - nf_logging[i] = NULL; + if (nf_loggers[i] == logger) + rcu_assign_pointer(nf_loggers[i], NULL); } - spin_unlock(&nf_log_lock); + mutex_unlock(&nf_log_mutex); - synchronize_net(); + synchronize_rcu(); } -EXPORT_SYMBOL(nf_log_unregister_logger); +EXPORT_SYMBOL(nf_log_unregister); void nf_log_packet(int pf, unsigned int hooknum, @@ -82,9 +83,9 @@ void nf_log_packet(int pf, va_list args; char prefix[NF_LOG_PREFIXLEN]; struct nf_logger *logger; - + rcu_read_lock(); - logger = rcu_dereference(nf_logging[pf]); + logger = rcu_dereference(nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); @@ -131,11 +132,11 @@ static int seq_show(struct seq_file *s, void *v) loff_t *pos = v; const struct nf_logger *logger; - logger = rcu_dereference(nf_logging[*pos]); + logger = rcu_dereference(nf_loggers[*pos]); if (!logger) return seq_printf(s, "%2lld NONE\n", *pos); - + return seq_printf(s, "%2lld %s\n", *pos, logger->name); } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index e136fea1db22..b1f2ace96f6d 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -10,7 +10,7 @@ #include "nf_internals.h" -/* +/* * A queue handler may be registered for each protocol. Each is protected by * long term mutex. The handler must provide an an outfn() to accept packets * for queueing and must reinject all packets it receives, no matter what. @@ -22,7 +22,7 @@ static DEFINE_RWLOCK(queue_handler_lock); /* return EBUSY when somebody else is registered, return EEXIST if the * same handler is registered, return 0 in case of success. */ int nf_register_queue_handler(int pf, struct nf_queue_handler *qh) -{ +{ int ret; if (pf >= NPROTO) @@ -52,7 +52,7 @@ int nf_unregister_queue_handler(int pf) write_lock_bh(&queue_handler_lock); queue_handler[pf] = NULL; write_unlock_bh(&queue_handler_lock); - + return 0; } EXPORT_SYMBOL(nf_unregister_queue_handler); @@ -70,8 +70,8 @@ void nf_unregister_queue_handlers(struct nf_queue_handler *qh) } EXPORT_SYMBOL_GPL(nf_unregister_queue_handlers); -/* - * Any packet that leaves via this function must come back +/* + * Any packet that leaves via this function must come back * through nf_reinject(). */ static int __nf_queue(struct sk_buff *skb, @@ -115,7 +115,7 @@ static int __nf_queue(struct sk_buff *skb, return 1; } - *info = (struct nf_info) { + *info = (struct nf_info) { (struct nf_hook_ops *)elem, pf, hook, indev, outdev, okfn }; /* If it's going away, ignore hook. */ @@ -226,10 +226,10 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info, module_put(info->elem->owner); list_for_each_rcu(i, &nf_hooks[info->pf][info->hook]) { - if (i == elem) - break; - } - + if (i == elem) + break; + } + if (i == &nf_hooks[info->pf][info->hook]) { /* The module which sent it to userspace is gone. */ NFDEBUG("%s: module disappeared, dropping packet.\n", @@ -252,7 +252,7 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info, if (verdict == NF_ACCEPT) { next_hook: verdict = nf_iterate(&nf_hooks[info->pf][info->hook], - &skb, info->hook, + &skb, info->hook, info->indev, info->outdev, &elem, info->okfn, INT_MIN); } diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index c2e44e90e437..8b8ece750313 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -32,13 +32,13 @@ int nf_register_sockopt(struct nf_sockopt_ops *reg) list_for_each(i, &nf_sockopts) { struct nf_sockopt_ops *ops = (struct nf_sockopt_ops *)i; if (ops->pf == reg->pf - && (overlap(ops->set_optmin, ops->set_optmax, + && (overlap(ops->set_optmin, ops->set_optmax, reg->set_optmin, reg->set_optmax) - || overlap(ops->get_optmin, ops->get_optmax, + || overlap(ops->get_optmin, ops->get_optmax, reg->get_optmin, reg->get_optmax))) { NFDEBUG("nf_sock overlap: %u-%u/%u-%u v %u-%u/%u-%u\n", - ops->set_optmin, ops->set_optmax, - ops->get_optmin, ops->get_optmax, + ops->set_optmin, ops->set_optmax, + ops->get_optmin, ops->get_optmax, reg->set_optmin, reg->set_optmax, reg->get_optmin, reg->get_optmax); ret = -EBUSY; @@ -73,7 +73,7 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg) EXPORT_SYMBOL(nf_unregister_sockopt); /* Call get/setsockopt() */ -static int nf_sockopt(struct sock *sk, int pf, int val, +static int nf_sockopt(struct sock *sk, int pf, int val, char __user *opt, int *len, int get) { struct list_head *i; @@ -107,7 +107,7 @@ static int nf_sockopt(struct sock *sk, int pf, int val, } mutex_unlock(&nf_sockopt_mutex); return -ENOPROTOOPT; - + out: mutex_lock(&nf_sockopt_mutex); ops->use--; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 52fdfa2686c9..f42bb1366007 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -105,7 +105,7 @@ static inline struct nfnl_callback * nfnetlink_find_client(u_int16_t type, struct nfnetlink_subsystem *ss) { u_int8_t cb_id = NFNL_MSG_TYPE(type); - + if (cb_id >= ss->cb_count) { DEBUGP("msgtype %u >= %u, returning\n", type, ss->cb_count); return NULL; @@ -187,7 +187,7 @@ nfnetlink_check_attributes(struct nfnetlink_subsystem *subsys, /* implicit: if nlmsg_len == min_len, we return 0, and an empty * (zeroed) cda[] array. The message is valid, but empty. */ - return 0; + return 0; } int nfnetlink_has_listeners(unsigned int group) @@ -268,12 +268,12 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, } { - u_int16_t attr_count = + u_int16_t attr_count = ss->cb[NFNL_MSG_TYPE(nlh->nlmsg_type)].attr_count; struct nfattr *cda[attr_count]; memset(cda, 0, sizeof(struct nfattr *) * attr_count); - + err = nfnetlink_check_attributes(ss, nlh, cda); if (err < 0) goto err_inval; @@ -357,7 +357,7 @@ static int __init nfnetlink_init(void) printk("Netfilter messages via NETLINK v%s.\n", nfversion); nfnl = netlink_kernel_create(NETLINK_NETFILTER, NFNLGRP_MAX, - nfnetlink_rcv, THIS_MODULE); + nfnetlink_rcv, THIS_MODULE); if (!nfnl) { printk(KERN_ERR "cannot initialize nfnetlink!\n"); return -1; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index c47e7e2ba642..b8eab0dbc3dd 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -75,7 +75,7 @@ struct nfulnl_instance { u_int32_t seq; /* instance-local sequential counter */ u_int16_t group_num; /* number of this queue */ u_int16_t flags; - u_int8_t copy_mode; + u_int8_t copy_mode; }; static DEFINE_RWLOCK(instances_lock); @@ -146,7 +146,7 @@ instance_create(u_int16_t group_num, int pid) UDEBUG("entering (group_num=%u, pid=%d)\n", group_num, pid); - write_lock_bh(&instances_lock); + write_lock_bh(&instances_lock); if (__instance_lookup(group_num)) { inst = NULL; UDEBUG("aborting, instance already exists\n"); @@ -179,10 +179,10 @@ instance_create(u_int16_t group_num, int pid) if (!try_module_get(THIS_MODULE)) goto out_free; - hlist_add_head(&inst->hlist, + hlist_add_head(&inst->hlist, &instance_table[instance_hashfn(group_num)]); - UDEBUG("newly added node: %p, next=%p\n", &inst->hlist, + UDEBUG("newly added node: %p, next=%p\n", &inst->hlist, inst->hlist.next); write_unlock_bh(&instances_lock); @@ -251,14 +251,14 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, int status = 0; spin_lock_bh(&inst->lock); - + switch (mode) { case NFULNL_COPY_NONE: case NFULNL_COPY_META: inst->copy_mode = mode; inst->copy_range = 0; break; - + case NFULNL_COPY_PACKET: inst->copy_mode = mode; /* we're using struct nfattr which has 16bit nfa_len */ @@ -267,7 +267,7 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, else inst->copy_range = range; break; - + default: status = -EINVAL; break; @@ -327,7 +327,7 @@ nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags) return 0; } -static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, +static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; @@ -387,7 +387,7 @@ __nfulnl_send(struct nfulnl_instance *inst) static void nfulnl_timer(unsigned long data) { - struct nfulnl_instance *inst = (struct nfulnl_instance *)data; + struct nfulnl_instance *inst = (struct nfulnl_instance *)data; UDEBUG("timer function called, flushing buffer\n"); @@ -399,9 +399,9 @@ static void nfulnl_timer(unsigned long data) /* This is an inline function, we don't really care about a long * list of arguments */ -static inline int +static inline int __build_packet_message(struct nfulnl_instance *inst, - const struct sk_buff *skb, + const struct sk_buff *skb, unsigned int data_len, unsigned int pf, unsigned int hooknum, @@ -417,9 +417,9 @@ __build_packet_message(struct nfulnl_instance *inst, __be32 tmp_uint; UDEBUG("entered\n"); - + old_tail = inst->skb->tail; - nlh = NLMSG_PUT(inst->skb, 0, 0, + nlh = NLMSG_PUT(inst->skb, 0, 0, NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -457,7 +457,7 @@ __build_packet_message(struct nfulnl_instance *inst, NFA_PUT(inst->skb, NFULA_IFINDEX_INDEV, sizeof(tmp_uint), &tmp_uint); if (skb->nf_bridge && skb->nf_bridge->physindev) { - tmp_uint = + tmp_uint = htonl(skb->nf_bridge->physindev->ifindex); NFA_PUT(inst->skb, NFULA_IFINDEX_PHYSINDEV, sizeof(tmp_uint), &tmp_uint); @@ -488,7 +488,7 @@ __build_packet_message(struct nfulnl_instance *inst, NFA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV, sizeof(tmp_uint), &tmp_uint); if (skb->nf_bridge) { - tmp_uint = + tmp_uint = htonl(skb->nf_bridge->physoutdev->ifindex); NFA_PUT(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, sizeof(tmp_uint), &tmp_uint); @@ -558,7 +558,7 @@ __build_packet_message(struct nfulnl_instance *inst, if (skb_copy_bits(skb, 0, NFA_DATA(nfa), data_len)) BUG(); } - + nlh->nlmsg_len = inst->skb->tail - old_tail; return 0; @@ -599,7 +599,7 @@ nfulnl_log_packet(unsigned int pf, unsigned int nlbufsiz; unsigned int plen; - if (li_user && li_user->type == NF_LOG_TYPE_ULOG) + if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; else li = &default_loginfo; @@ -648,24 +648,24 @@ nfulnl_log_packet(unsigned int pf, /* per-rule qthreshold overrides per-instance */ if (qthreshold > li->u.ulog.qthreshold) qthreshold = li->u.ulog.qthreshold; - + switch (inst->copy_mode) { case NFULNL_COPY_META: case NFULNL_COPY_NONE: data_len = 0; break; - + case NFULNL_COPY_PACKET: - if (inst->copy_range == 0 + if (inst->copy_range == 0 || inst->copy_range > skb->len) data_len = skb->len; else data_len = inst->copy_range; - + size += NFA_SPACE(data_len); UDEBUG("copy_packet, therefore size now %u\n", size); break; - + default: spin_unlock_bh(&inst->lock); instance_put(inst); @@ -991,9 +991,9 @@ static int seq_show(struct seq_file *s, void *v) { const struct nfulnl_instance *inst = v; - return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", + return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", inst->group_num, - inst->peer_pid, inst->qlen, + inst->peer_pid, inst->qlen, inst->copy_mode, inst->copy_range, inst->flushtimeout, atomic_read(&inst->use)); } @@ -1041,10 +1041,10 @@ static int __init nfnetlink_log_init(void) #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_nful; #endif - + for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&instance_table[i]); - + /* it's not really all that important to have a random value, so * we can do this from the init function, even if there hasn't * been that much entropy yet */ @@ -1077,7 +1077,7 @@ cleanup_netlink_notifier: static void __exit nfnetlink_log_fini(void) { - nf_log_unregister_logger(&nfulnl_logger); + nf_log_unregister(&nfulnl_logger); #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", proc_net_netfilter); #endif diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 99e516eca41a..d9ce4a71d0f3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -129,7 +129,7 @@ instance_create(u_int16_t queue_num, int pid) QDEBUG("entering for queue_num=%u, pid=%d\n", queue_num, pid); - write_lock_bh(&instances_lock); + write_lock_bh(&instances_lock); if (__instance_lookup(queue_num)) { inst = NULL; QDEBUG("aborting, instance already exists\n"); @@ -154,7 +154,7 @@ instance_create(u_int16_t queue_num, int pid) if (!try_module_get(THIS_MODULE)) goto out_free; - hlist_add_head(&inst->hlist, + hlist_add_head(&inst->hlist, &instance_table[instance_hashfn(queue_num)]); write_unlock_bh(&instances_lock); @@ -239,14 +239,14 @@ __enqueue_entry(struct nfqnl_instance *queue, * entry if cmpfn is NULL. */ static inline struct nfqnl_queue_entry * -__find_entry(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, +__find_entry(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) { struct list_head *p; list_for_each_prev(p, &queue->queue_list) { struct nfqnl_queue_entry *entry = (struct nfqnl_queue_entry *)p; - + if (!cmpfn || cmpfn(entry, data)) return entry; } @@ -279,7 +279,7 @@ static inline void __nfqnl_flush(struct nfqnl_instance *queue, int verdict) { struct nfqnl_queue_entry *entry; - + while ((entry = __find_dequeue_entry(queue, NULL, 0))) issue_verdict(entry, verdict); } @@ -289,14 +289,14 @@ __nfqnl_set_mode(struct nfqnl_instance *queue, unsigned char mode, unsigned int range) { int status = 0; - + switch (mode) { case NFQNL_COPY_NONE: case NFQNL_COPY_META: queue->copy_mode = mode; queue->copy_range = 0; break; - + case NFQNL_COPY_PACKET: queue->copy_mode = mode; /* we're using struct nfattr which has 16bit nfa_len */ @@ -305,7 +305,7 @@ __nfqnl_set_mode(struct nfqnl_instance *queue, else queue->copy_range = range; break; - + default: status = -EINVAL; @@ -318,7 +318,7 @@ find_dequeue_entry(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) { struct nfqnl_queue_entry *entry; - + spin_lock_bh(&queue->lock); entry = __find_dequeue_entry(queue, cmpfn, data); spin_unlock_bh(&queue->lock); @@ -369,13 +369,13 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, outdev = entinf->outdev; spin_lock_bh(&queue->lock); - + switch (queue->copy_mode) { case NFQNL_COPY_META: case NFQNL_COPY_NONE: data_len = 0; break; - + case NFQNL_COPY_PACKET: if ((entskb->ip_summed == CHECKSUM_PARTIAL || entskb->ip_summed == CHECKSUM_COMPLETE) && @@ -383,15 +383,15 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, spin_unlock_bh(&queue->lock); return NULL; } - if (queue->copy_range == 0 + if (queue->copy_range == 0 || queue->copy_range > entskb->len) data_len = entskb->len; else data_len = queue->copy_range; - + size += NFA_SPACE(data_len); break; - + default: *errp = -EINVAL; spin_unlock_bh(&queue->lock); @@ -403,9 +403,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, skb = alloc_skb(size, GFP_ATOMIC); if (!skb) goto nlmsg_failure; - + old_tail= skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, + nlh = NLMSG_PUT(skb, 0, 0, NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -427,9 +427,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, #else if (entinf->pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to - * look for bridge group (when called from + * look for bridge group (when called from * netfilter_bridge) */ - NFA_PUT(skb, NFQA_IFINDEX_PHYSINDEV, sizeof(tmp_uint), + NFA_PUT(skb, NFQA_IFINDEX_PHYSINDEV, sizeof(tmp_uint), &tmp_uint); /* this is the bridge group "brX" */ tmp_uint = htonl(indev->br_port->br->dev->ifindex); @@ -457,7 +457,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, #else if (entinf->pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to - * look for bridge group (when called from + * look for bridge group (when called from * netfilter_bridge) */ NFA_PUT(skb, NFQA_IFINDEX_PHYSOUTDEV, sizeof(tmp_uint), &tmp_uint); @@ -490,7 +490,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct nfqnl_msg_packet_hw phw; int len = entskb->dev->hard_header_parse(entskb, - phw.hw_addr); + phw.hw_addr); phw.hw_addrlen = htons(len); NFA_PUT(skb, NFQA_HWADDR, sizeof(phw), &phw); } @@ -520,7 +520,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (skb_copy_bits(entskb, 0, NFA_DATA(nfa), data_len)) BUG(); } - + nlh->nlmsg_len = skb->tail - old_tail; return skb; @@ -535,7 +535,7 @@ nfattr_failure: } static int -nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, +nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, unsigned int queuenum, void *data) { int status = -EINVAL; @@ -560,7 +560,7 @@ nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) { if (net_ratelimit()) - printk(KERN_ERR + printk(KERN_ERR "nf_queue: OOM in nfqnl_enqueue_packet()\n"); status = -ENOMEM; goto err_out_put; @@ -573,18 +573,18 @@ nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, nskb = nfqnl_build_packet_message(queue, entry, &status); if (nskb == NULL) goto err_out_free; - + spin_lock_bh(&queue->lock); - + if (!queue->peer_pid) - goto err_out_free_nskb; + goto err_out_free_nskb; if (queue->queue_total >= queue->queue_maxlen) { - queue->queue_dropped++; + queue->queue_dropped++; status = -ENOSPC; if (net_ratelimit()) - printk(KERN_WARNING "nf_queue: full at %d entries, " - "dropping packets(s). Dropped: %d\n", + printk(KERN_WARNING "nf_queue: full at %d entries, " + "dropping packets(s). Dropped: %d\n", queue->queue_total, queue->queue_dropped); goto err_out_free_nskb; } @@ -592,7 +592,7 @@ nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, /* nfnetlink_unicast will either free the nskb or add it to a socket */ status = nfnetlink_unicast(nskb, queue->peer_pid, MSG_DONTWAIT); if (status < 0) { - queue->queue_user_dropped++; + queue->queue_user_dropped++; goto err_out_unlock; } @@ -603,8 +603,8 @@ nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, return status; err_out_free_nskb: - kfree_skb(nskb); - + kfree_skb(nskb); + err_out_unlock: spin_unlock_bh(&queue->lock); @@ -629,11 +629,11 @@ nfqnl_mangle(void *data, int data_len, struct nfqnl_queue_entry *e) return -EINVAL; if (diff > skb_tailroom(e->skb)) { struct sk_buff *newskb; - + newskb = skb_copy_expand(e->skb, - skb_headroom(e->skb), - diff, - GFP_ATOMIC); + skb_headroom(e->skb), + diff, + GFP_ATOMIC); if (newskb == NULL) { printk(KERN_WARNING "nf_queue: OOM " "in mangle, dropping packet\n"); @@ -676,7 +676,7 @@ static int dev_cmp(struct nfqnl_queue_entry *entry, unsigned long ifindex) { struct nf_info *entinf = entry->info; - + if (entinf->indev) if (entinf->indev->ifindex == ifindex) return 1; @@ -702,7 +702,7 @@ static void nfqnl_dev_drop(int ifindex) { int i; - + QDEBUG("entering for ifindex %u\n", ifindex); /* this only looks like we have to hold the readlock for a way too long @@ -717,7 +717,7 @@ nfqnl_dev_drop(int ifindex) hlist_for_each_entry(inst, tmp, head, hlist) { struct nfqnl_queue_entry *entry; - while ((entry = find_dequeue_entry(inst, dev_cmp, + while ((entry = find_dequeue_entry(inst, dev_cmp, ifindex)) != NULL) issue_verdict(entry, NF_DROP); } @@ -835,8 +835,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (nfqa[NFQA_MARK-1]) entry->skb->mark = ntohl(*(__be32 *) - NFA_DATA(nfqa[NFQA_MARK-1])); - + NFA_DATA(nfqa[NFQA_MARK-1])); + issue_verdict(entry, verdict); instance_put(queue); return 0; @@ -1093,7 +1093,7 @@ static int __init nfnetlink_queue_init(void) #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_nfqueue; #endif - + for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&instance_table[i]); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 134cc88f8c83..ec607a421a5a 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -305,7 +305,7 @@ int xt_find_revision(int af, const char *name, u8 revision, int target, EXPORT_SYMBOL_GPL(xt_find_revision); int xt_check_match(const struct xt_match *match, unsigned short family, - unsigned int size, const char *table, unsigned int hook_mask, + unsigned int size, const char *table, unsigned int hook_mask, unsigned short proto, int inv_proto) { if (XT_ALIGN(match->matchsize) != size) { @@ -377,7 +377,7 @@ int xt_compat_match_to_user(struct xt_entry_match *m, void __user **dstptr, if (copy_to_user(cm, m, sizeof(*cm)) || put_user(msize, &cm->u.user.match_size)) - return -EFAULT; + return -EFAULT; if (match->compat_to_user) { if (match->compat_to_user((void __user *)cm->data, m->data)) @@ -432,7 +432,7 @@ int xt_compat_target_offset(struct xt_target *target) EXPORT_SYMBOL_GPL(xt_compat_target_offset); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, - int *size) + int *size) { struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; @@ -467,7 +467,7 @@ int xt_compat_target_to_user(struct xt_entry_target *t, void __user **dstptr, if (copy_to_user(ct, t, sizeof(*ct)) || put_user(tsize, &ct->u.user.target_size)) - return -EFAULT; + return -EFAULT; if (target->compat_to_user) { if (target->compat_to_user((void __user *)ct->data, t->data)) @@ -710,7 +710,7 @@ static void *xt_tgt_seq_start(struct seq_file *seq, loff_t *pos) if (mutex_lock_interruptible(&xt[af].mutex) != 0) return NULL; - + return xt_get_idx(list, seq, *pos); } @@ -723,7 +723,7 @@ static void *xt_tgt_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (af >= NPROTO) return NULL; - + list = type2list(af, type); if (!list) return NULL; diff --git a/net/netfilter/xt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c index 195e92990da7..30884833e665 100644 --- a/net/netfilter/xt_CLASSIFY.c +++ b/net/netfilter/xt_CLASSIFY.c @@ -15,6 +15,8 @@ #include <linux/ip.h> #include <net/checksum.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CLASSIFY.h> @@ -46,7 +48,7 @@ static struct xt_target xt_classify_target[] = { .table = "mangle", .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING), + (1 << NF_IP_POST_ROUTING), .me = THIS_MODULE, }, { @@ -55,9 +57,9 @@ static struct xt_target xt_classify_target[] = { .target = target, .targetsize = sizeof(struct xt_classify_target_info), .table = "mangle", - .hooks = (1 << NF_IP_LOCAL_OUT) | - (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING), + .hooks = (1 << NF_IP6_LOCAL_OUT) | + (1 << NF_IP6_FORWARD) | + (1 << NF_IP6_POST_ROUTING), .me = THIS_MODULE, }, }; diff --git a/net/netfilter/xt_MARK.c b/net/netfilter/xt_MARK.c index cfc45af357d5..43817808d865 100644 --- a/net/netfilter/xt_MARK.c +++ b/net/netfilter/xt_MARK.c @@ -50,11 +50,11 @@ target_v1(struct sk_buff **pskb, case XT_MARK_SET: mark = markinfo->mark; break; - + case XT_MARK_AND: mark = (*pskb)->mark & markinfo->mark; break; - + case XT_MARK_OR: mark = (*pskb)->mark | markinfo->mark; break; diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 39e117502bd7..201155b316e0 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -3,9 +3,9 @@ * (C) 2005 by Harald Welte <laforge@netfilter.org> * * 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 + * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. - * + * */ #include <linux/module.h> diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c index 6d00dcaed238..b874a2008b2b 100644 --- a/net/netfilter/xt_NOTRACK.c +++ b/net/netfilter/xt_NOTRACK.c @@ -22,8 +22,8 @@ target(struct sk_buff **pskb, if ((*pskb)->nfct != NULL) return XT_CONTINUE; - /* Attach fake conntrack entry. - If there is a real ct entry correspondig to this packet, + /* Attach fake conntrack entry. + If there is a real ct entry correspondig to this packet, it'll hang aroun till timing out. We don't deal with it for performance reasons. JK */ nf_ct_untrack(*pskb); diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c index f1131c3a9db5..705f0e830a79 100644 --- a/net/netfilter/xt_SECMARK.c +++ b/net/netfilter/xt_SECMARK.c @@ -55,7 +55,7 @@ static int checkentry_selinux(struct xt_secmark_target_info *info) { int err; struct xt_secmark_target_selinux_info *sel = &info->u.sel; - + sel->selctx[SECMARK_SELCTX_MAX - 1] = '\0'; err = selinux_string_to_sid(sel->selctx, &sel->selsid); diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 3dc2357b8de8..2885c378288e 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -51,10 +51,10 @@ match(const struct sk_buff *skb, if (ct == &ip_conntrack_untracked) statebit = XT_CONNTRACK_STATE_UNTRACKED; else if (ct) - statebit = XT_CONNTRACK_STATE_BIT(ctinfo); - else - statebit = XT_CONNTRACK_STATE_INVALID; - + statebit = XT_CONNTRACK_STATE_BIT(ctinfo); + else + statebit = XT_CONNTRACK_STATE_INVALID; + if (sinfo->flags & XT_CONNTRACK_STATE) { if (ct) { if (test_bit(IPS_SRC_NAT_BIT, &ct->status)) @@ -77,7 +77,7 @@ match(const struct sk_buff *skb, FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, XT_CONNTRACK_PROTO)) - return 0; + return 0; if (sinfo->flags & XT_CONNTRACK_ORIGSRC && FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip & @@ -147,10 +147,10 @@ match(const struct sk_buff *skb, if (ct == &nf_conntrack_untracked) statebit = XT_CONNTRACK_STATE_UNTRACKED; else if (ct) - statebit = XT_CONNTRACK_STATE_BIT(ctinfo); - else - statebit = XT_CONNTRACK_STATE_INVALID; - + statebit = XT_CONNTRACK_STATE_BIT(ctinfo); + else + statebit = XT_CONNTRACK_STATE_INVALID; + if (sinfo->flags & XT_CONNTRACK_STATE) { if (ct) { if (test_bit(IPS_SRC_NAT_BIT, &ct->status)) @@ -171,41 +171,41 @@ match(const struct sk_buff *skb, if (sinfo->flags & XT_CONNTRACK_PROTO && FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != - sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, + sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, XT_CONNTRACK_PROTO)) - return 0; + return 0; if (sinfo->flags & XT_CONNTRACK_ORIGSRC && FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip & - sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != + sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, XT_CONNTRACK_ORIGSRC)) return 0; if (sinfo->flags & XT_CONNTRACK_ORIGDST && FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip & - sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != + sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, XT_CONNTRACK_ORIGDST)) return 0; if (sinfo->flags & XT_CONNTRACK_REPLSRC && FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip & - sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != + sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, XT_CONNTRACK_REPLSRC)) return 0; if (sinfo->flags & XT_CONNTRACK_REPLDST && FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip & - sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != + sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, XT_CONNTRACK_REPLDST)) return 0; if (sinfo->flags & XT_CONNTRACK_STATUS && FWINV((ct->status & sinfo->statusmask) == 0, - XT_CONNTRACK_STATUS)) + XT_CONNTRACK_STATUS)) return 0; if(sinfo->flags & XT_CONNTRACK_EXPIRES) { diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c index 3e6cf430e518..2c9c0dee8aaf 100644 --- a/net/netfilter/xt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -26,7 +26,7 @@ MODULE_DESCRIPTION("Match for DCCP protocol packets"); MODULE_ALIAS("ipt_dccp"); #define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ - || (!!((invflag) & (option)) ^ (cond))) + || (!!((invflag) & (option)) ^ (cond))) static unsigned char *dccp_optbuf; static DEFINE_SPINLOCK(dccp_buflock); @@ -67,9 +67,9 @@ dccp_find_option(u_int8_t option, return 1; } - if (op[i] < 2) + if (op[i] < 2) i++; - else + else i += op[i+1]?:1; } @@ -106,18 +106,18 @@ match(const struct sk_buff *skb, if (offset) return 0; - + dh = skb_header_pointer(skb, protoff, sizeof(_dh), &_dh); if (dh == NULL) { *hotdrop = 1; return 0; - } + } - return DCCHECK(((ntohs(dh->dccph_sport) >= info->spts[0]) - && (ntohs(dh->dccph_sport) <= info->spts[1])), - XT_DCCP_SRC_PORTS, info->flags, info->invflags) - && DCCHECK(((ntohs(dh->dccph_dport) >= info->dpts[0]) - && (ntohs(dh->dccph_dport) <= info->dpts[1])), + return DCCHECK(((ntohs(dh->dccph_sport) >= info->spts[0]) + && (ntohs(dh->dccph_sport) <= info->spts[1])), + XT_DCCP_SRC_PORTS, info->flags, info->invflags) + && DCCHECK(((ntohs(dh->dccph_dport) >= info->dpts[0]) + && (ntohs(dh->dccph_dport) <= info->dpts[1])), XT_DCCP_DEST_PORTS, info->flags, info->invflags) && DCCHECK(match_types(dh, info->typemask), XT_DCCP_TYPE, info->flags, info->invflags) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 269a1e793478..9f37d593ca38 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -208,7 +208,7 @@ static int htable_create(struct xt_hashlimit_info *minfo, int family) spin_lock_init(&hinfo->lock); hinfo->pde = create_proc_entry(minfo->name, 0, family == AF_INET ? hashlimit_procdir4 : - hashlimit_procdir6); + hashlimit_procdir6); if (!hinfo->pde) { vfree(hinfo); return -1; @@ -240,7 +240,7 @@ static int select_gc(struct xt_hashlimit_htable *ht, struct dsthash_ent *he) } static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, - int (*select)(struct xt_hashlimit_htable *ht, + int (*select)(struct xt_hashlimit_htable *ht, struct dsthash_ent *he)) { unsigned int i; @@ -279,7 +279,7 @@ static void htable_destroy(struct xt_hashlimit_htable *hinfo) /* remove proc entry */ remove_proc_entry(hinfo->pde->name, hinfo->family == AF_INET ? hashlimit_procdir4 : - hashlimit_procdir6); + hashlimit_procdir6); htable_selective_cleanup(hinfo, select_all); vfree(hinfo); } @@ -483,7 +483,7 @@ hashlimit_match(const struct sk_buff *skb, return 1; } - spin_unlock_bh(&hinfo->lock); + spin_unlock_bh(&hinfo->lock); /* default case: we're overlimit, thus don't match */ return 0; diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c index 04bc32ba7195..407d1d5da8a1 100644 --- a/net/netfilter/xt_helper.c +++ b/net/netfilter/xt_helper.c @@ -53,7 +53,7 @@ match(const struct sk_buff *skb, struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; int ret = info->invert; - + ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo); if (!ct) { DEBUGP("xt_helper: Eek! invalid conntrack?\n"); @@ -67,19 +67,19 @@ match(const struct sk_buff *skb, read_lock_bh(&ip_conntrack_lock); if (!ct->master->helper) { - DEBUGP("xt_helper: master ct %p has no helper\n", + DEBUGP("xt_helper: master ct %p has no helper\n", exp->expectant); goto out_unlock; } - DEBUGP("master's name = %s , info->name = %s\n", + DEBUGP("master's name = %s , info->name = %s\n", ct->master->helper->name, info->name); if (info->name[0] == '\0') ret ^= 1; else - ret ^= !strncmp(ct->master->helper->name, info->name, - strlen(ct->master->helper->name)); + ret ^= !strncmp(ct->master->helper->name, info->name, + strlen(ct->master->helper->name)); out_unlock: read_unlock_bh(&ip_conntrack_lock); return ret; @@ -102,7 +102,7 @@ match(const struct sk_buff *skb, struct nf_conn_help *master_help; enum ip_conntrack_info ctinfo; int ret = info->invert; - + ct = nf_ct_get((struct sk_buff *)skb, &ctinfo); if (!ct) { DEBUGP("xt_helper: Eek! invalid conntrack?\n"); @@ -117,19 +117,19 @@ match(const struct sk_buff *skb, read_lock_bh(&nf_conntrack_lock); master_help = nfct_help(ct->master); if (!master_help || !master_help->helper) { - DEBUGP("xt_helper: master ct %p has no helper\n", + DEBUGP("xt_helper: master ct %p has no helper\n", exp->expectant); goto out_unlock; } - DEBUGP("master's name = %s , info->name = %s\n", + DEBUGP("master's name = %s , info->name = %s\n", ct->master->helper->name, info->name); if (info->name[0] == '\0') ret ^= 1; else ret ^= !strncmp(master_help->helper->name, info->name, - strlen(master_help->helper->name)); + strlen(master_help->helper->name)); out_unlock: read_unlock_bh(&nf_conntrack_lock); return ret; diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index 67fd30d9f303..32fb998d9bac 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -32,7 +32,7 @@ match(const struct sk_buff *skb, { const struct xt_length_info *info = matchinfo; u_int16_t pktlen = ntohs(skb->nh.iph->tot_len); - + return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } @@ -48,7 +48,7 @@ match6(const struct sk_buff *skb, { const struct xt_length_info *info = matchinfo; u_int16_t pktlen = ntohs(skb->nh.ipv6h->payload_len) + sizeof(struct ipv6hdr); - + return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index fda7b7dec27d..6fd8347c0058 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -89,7 +89,7 @@ ipt_limit_match(const struct sk_buff *skb, return 1; } - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&limit_lock); return 0; } diff --git a/net/netfilter/xt_mac.c b/net/netfilter/xt_mac.c index 425fc21e31f5..d430d90d7b26 100644 --- a/net/netfilter/xt_mac.c +++ b/net/netfilter/xt_mac.c @@ -14,6 +14,7 @@ #include <linux/etherdevice.h> #include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> #include <linux/netfilter/xt_mac.h> #include <linux/netfilter/x_tables.h> @@ -59,9 +60,9 @@ static struct xt_match xt_mac_match[] = { .family = AF_INET6, .match = match, .matchsize = sizeof(struct xt_mac_info), - .hooks = (1 << NF_IP_PRE_ROUTING) | - (1 << NF_IP_LOCAL_IN) | - (1 << NF_IP_FORWARD), + .hooks = (1 << NF_IP6_PRE_ROUTING) | + (1 << NF_IP6_LOCAL_IN) | + (1 << NF_IP6_FORWARD), .me = THIS_MODULE, }, }; diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index dfa1ee6914c0..39911dddb011 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -36,10 +36,10 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const void *entry, + const void *entry, const struct xt_match *match, - void *matchinfo, - unsigned int hook_mask) + void *matchinfo, + unsigned int hook_mask) { const struct xt_mark_info *minfo = matchinfo; diff --git a/net/netfilter/xt_multiport.c b/net/netfilter/xt_multiport.c index 1602086c7fd6..4dce2a81702a 100644 --- a/net/netfilter/xt_multiport.c +++ b/net/netfilter/xt_multiport.c @@ -91,7 +91,7 @@ ports_match_v1(const struct xt_multiport_v1 *minfo, } } - return minfo->invert; + return minfo->invert; } static int diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index b9b3ffc5451d..35a0fe200c39 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -117,7 +117,7 @@ checkentry(const char *tablename, (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && hook_mask & ((1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING))) { + (1 << NF_IP_POST_ROUTING))) { printk(KERN_WARNING "physdev match: using --physdev-out in the " "OUTPUT, FORWARD and POSTROUTING chains for non-bridged " "traffic is not supported anymore.\n"); diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index 46bde2b1e1e0..15b45a95ec13 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -109,13 +109,13 @@ match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info, } static int match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct xt_match *match, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) + const struct net_device *in, + const struct net_device *out, + const struct xt_match *match, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) { const struct xt_policy_info *info = matchinfo; int ret; @@ -134,27 +134,27 @@ static int match(const struct sk_buff *skb, } static int checkentry(const char *tablename, const void *ip_void, - const struct xt_match *match, - void *matchinfo, unsigned int hook_mask) + const struct xt_match *match, + void *matchinfo, unsigned int hook_mask) { struct xt_policy_info *info = matchinfo; if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) { printk(KERN_ERR "xt_policy: neither incoming nor " - "outgoing policy selected\n"); + "outgoing policy selected\n"); return 0; } /* hook values are equal for IPv4 and IPv6 */ if (hook_mask & (1 << NF_IP_PRE_ROUTING | 1 << NF_IP_LOCAL_IN) && info->flags & XT_POLICY_MATCH_OUT) { printk(KERN_ERR "xt_policy: output policy not valid in " - "PRE_ROUTING and INPUT\n"); + "PRE_ROUTING and INPUT\n"); return 0; } if (hook_mask & (1 << NF_IP_POST_ROUTING | 1 << NF_IP_LOCAL_OUT) && info->flags & XT_POLICY_MATCH_IN) { printk(KERN_ERR "xt_policy: input policy not valid in " - "POST_ROUTING and OUTPUT\n"); + "POST_ROUTING and OUTPUT\n"); return 0; } if (info->len > XT_POLICY_MAX_ELEM) { diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c index b75fa2c70e66..bfdde06ca0b7 100644 --- a/net/netfilter/xt_quota.c +++ b/net/netfilter/xt_quota.c @@ -30,8 +30,8 @@ match(const struct sk_buff *skb, q->quota -= skb->len; ret ^= 1; } else { - /* we do not allow even small packets from now on */ - q->quota = 0; + /* we do not allow even small packets from now on */ + q->quota = 0; } spin_unlock_bh("a_lock); diff --git a/net/netfilter/xt_realm.c b/net/netfilter/xt_realm.c index a80b7d132b65..97ffc2fbc19d 100644 --- a/net/netfilter/xt_realm.c +++ b/net/netfilter/xt_realm.c @@ -35,7 +35,7 @@ match(const struct sk_buff *skb, { const struct xt_realm_info *info = matchinfo; struct dst_entry *dst = skb->dst; - + return (info->id == (dst->tclassid & info->mask)) ^ info->invert; } diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 71bf036f833c..f86d8d769d47 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -66,9 +66,9 @@ match_packet(const struct sk_buff *skb, duprintf("Dropping invalid SCTP packet.\n"); *hotdrop = 1; return 0; - } + } - duprintf("Chunk num: %d\toffset: %d\ttype: %d\tlength: %d\tflags: %x\n", + duprintf("Chunk num: %d\toffset: %d\ttype: %d\tlength: %d\tflags: %x\n", ++i, offset, sch->type, htons(sch->length), sch->flags); offset += (ntohs(sch->length) + 3) & ~3; @@ -78,21 +78,21 @@ match_packet(const struct sk_buff *skb, if (SCTP_CHUNKMAP_IS_SET(chunkmap, sch->type)) { switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ANY: - if (match_flags(flag_info, flag_count, + if (match_flags(flag_info, flag_count, sch->type, sch->flags)) { return 1; } break; case SCTP_CHUNK_MATCH_ALL: - if (match_flags(flag_info, flag_count, + if (match_flags(flag_info, flag_count, sch->type, sch->flags)) { SCTP_CHUNKMAP_CLEAR(chunkmapcopy, sch->type); } break; case SCTP_CHUNK_MATCH_ONLY: - if (!match_flags(flag_info, flag_count, + if (!match_flags(flag_info, flag_count, sch->type, sch->flags)) { return 0; } @@ -136,24 +136,24 @@ match(const struct sk_buff *skb, duprintf("Dropping non-first fragment.. FIXME\n"); return 0; } - + sh = skb_header_pointer(skb, protoff, sizeof(_sh), &_sh); if (sh == NULL) { duprintf("Dropping evil TCP offset=0 tinygram.\n"); *hotdrop = 1; return 0; - } + } duprintf("spt: %d\tdpt: %d\n", ntohs(sh->source), ntohs(sh->dest)); - return SCCHECK(((ntohs(sh->source) >= info->spts[0]) - && (ntohs(sh->source) <= info->spts[1])), - XT_SCTP_SRC_PORTS, info->flags, info->invflags) - && SCCHECK(((ntohs(sh->dest) >= info->dpts[0]) - && (ntohs(sh->dest) <= info->dpts[1])), + return SCCHECK(((ntohs(sh->source) >= info->spts[0]) + && (ntohs(sh->source) <= info->spts[1])), + XT_SCTP_SRC_PORTS, info->flags, info->invflags) + && SCCHECK(((ntohs(sh->dest) >= info->dpts[0]) + && (ntohs(sh->dest) <= info->dpts[1])), XT_SCTP_DEST_PORTS, info->flags, info->invflags) && SCCHECK(match_packet(skb, protoff + sizeof (sctp_sctphdr_t), info->chunkmap, info->chunk_match_type, - info->flag_info, info->flag_count, + info->flag_info, info->flag_count, hotdrop), XT_SCTP_CHUNK_TYPES, info->flags, info->invflags); } @@ -170,9 +170,9 @@ checkentry(const char *tablename, return !(info->flags & ~XT_SCTP_VALID_FLAGS) && !(info->invflags & ~XT_SCTP_VALID_FLAGS) && !(info->invflags & ~info->flags) - && ((!(info->flags & XT_SCTP_CHUNK_TYPES)) || + && ((!(info->flags & XT_SCTP_CHUNK_TYPES)) || (info->chunk_match_type & - (SCTP_CHUNK_MATCH_ALL + (SCTP_CHUNK_MATCH_ALL | SCTP_CHUNK_MATCH_ANY | SCTP_CHUNK_MATCH_ONLY))); } diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c index 4453252400aa..999a005dbd0c 100644 --- a/net/netfilter/xt_string.c +++ b/net/netfilter/xt_string.c @@ -1,5 +1,5 @@ /* String matching match for iptables - * + * * (C) 2005 Pablo Neira Ayuso <pablo@eurodev.net> * * This program is free software; you can redistribute it and/or modify @@ -35,8 +35,8 @@ static int match(const struct sk_buff *skb, memset(&state, 0, sizeof(struct ts_state)); - return (skb_find_text((struct sk_buff *)skb, conf->from_offset, - conf->to_offset, conf->config, &state) + return (skb_find_text((struct sk_buff *)skb, conf->from_offset, + conf->to_offset, conf->config, &state) != UINT_MAX) ^ conf->invert; } @@ -55,7 +55,7 @@ static int checkentry(const char *tablename, if (conf->from_offset > conf->to_offset) return 0; if (conf->algo[XT_STRING_MAX_ALGO_NAME_SIZE - 1] != '\0') - return 0; + return 0; if (conf->patlen > XT_STRING_MAX_PATTERN_SIZE) return 0; ts_conf = textsearch_prepare(conf->algo, conf->pattern, conf->patlen, diff --git a/net/netfilter/xt_tcpmss.c b/net/netfilter/xt_tcpmss.c index a3682fe2f192..80571d0749f7 100644 --- a/net/netfilter/xt_tcpmss.c +++ b/net/netfilter/xt_tcpmss.c @@ -64,9 +64,9 @@ match(const struct sk_buff *skb, u_int16_t mssval; mssval = (op[i+2] << 8) | op[i+3]; - + return (mssval >= info->mss_min && - mssval <= info->mss_max) ^ info->invert; + mssval <= info->mss_max) ^ info->invert; } if (op[i] < 2) i++; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index a24f38510719..c394b413f651 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1997,9 +1997,14 @@ void xfrm_audit_log(uid_t auid, u32 sid, int type, int result, if (audit_enabled == 0) return; + BUG_ON((type == AUDIT_MAC_IPSEC_ADDSA || + type == AUDIT_MAC_IPSEC_DELSA) && !x); + BUG_ON((type == AUDIT_MAC_IPSEC_ADDSPD || + type == AUDIT_MAC_IPSEC_DELSPD) && !xp); + audit_buf = audit_log_start(current->audit_context, GFP_ATOMIC, type); if (audit_buf == NULL) - return; + return; switch(type) { case AUDIT_MAC_IPSEC_ADDSA: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d55436d00e86..256745321611 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1273,10 +1273,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, xp = xfrm_policy_bysel_ctx(type, p->dir, &p->sel, tmp.security, delete); security_xfrm_policy_free(&tmp); } - if (delete) - xfrm_audit_log(NETLINK_CB(skb).loginuid, NETLINK_CB(skb).sid, - AUDIT_MAC_IPSEC_DELSPD, (xp) ? 1 : 0, xp, NULL); - if (xp == NULL) return -ENOENT; @@ -1292,8 +1288,14 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, MSG_DONTWAIT); } } else { - if ((err = security_xfrm_policy_delete(xp)) != 0) + err = security_xfrm_policy_delete(xp); + + xfrm_audit_log(NETLINK_CB(skb).loginuid, NETLINK_CB(skb).sid, + AUDIT_MAC_IPSEC_DELSPD, err ? 0 : 1, xp, NULL); + + if (err != 0) goto out; + c.data.byid = p->index; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; |