diff options
author | David S. Miller <davem@davemloft.net> | 2011-03-15 13:03:27 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2011-03-15 13:03:27 -0700 |
commit | 31111c26d976ca0f298312f08e44cdb078005b03 (patch) | |
tree | ca08ef55b2ea91f9e69f8a78bb8b4363a1759b54 /net/netfilter | |
parent | 0c0217b016ba8a970a6f6ab62ad0d858f39881ca (diff) | |
parent | 2f5dc63123905a89d4260ab8ee08d19ec104db04 (diff) |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6
Conflicts:
Documentation/feature-removal-schedule.txt
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/Kconfig | 11 | ||||
-rw-r--r-- | net/netfilter/Makefile | 1 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_core.c | 2 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_conn.c | 13 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_core.c | 104 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_ctl.c | 256 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_est.c | 63 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_lblc.c | 31 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_lblcr.c | 35 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_pe_sip.c | 9 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_sync.c | 11 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 1 | ||||
-rw-r--r-- | net/netfilter/x_tables.c | 26 | ||||
-rw-r--r-- | net/netfilter/xt_addrtype.c | 229 | ||||
-rw-r--r-- | net/netfilter/xt_connlimit.c | 59 |
15 files changed, 602 insertions, 249 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 82a6e0d80f05..c3f988aa1152 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -649,6 +649,17 @@ config NETFILTER_XT_TARGET_TCPOPTSTRIP comment "Xtables matches" +config NETFILTER_XT_MATCH_ADDRTYPE + tristate '"addrtype" address type match support' + depends on NETFILTER_ADVANCED + depends on (IPV6 || IPV6=n) + ---help--- + This option allows you to match what routing thinks of an address, + eg. UNICAST, LOCAL, BROADCAST, ... + + If you want to compile it as a module, say M here and read + <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. + config NETFILTER_XT_MATCH_CLUSTER tristate '"cluster" match support' depends on NF_CONNTRACK diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index d57a890eaee5..1a02853df863 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -70,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o # matches +obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 8b1a54c1e400..618a615acc9d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -612,7 +612,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[]) { - struct ip_set *set, *clash; + struct ip_set *set, *clash = NULL; ip_set_id_t index = IPSET_INVALID_ID; struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {}; const char *name, *typename; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 9c2a517b69c8..f289306cbf12 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -680,6 +680,16 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) atomic_dec(&dest->refcnt); } +static int expire_quiescent_template(struct netns_ipvs *ipvs, + struct ip_vs_dest *dest) +{ +#ifdef CONFIG_SYSCTL + return ipvs->sysctl_expire_quiescent_template && + (atomic_read(&dest->weight) == 0); +#else + return 0; +#endif +} /* * Checking if the destination of a connection template is available. @@ -696,8 +706,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) */ if ((dest == NULL) || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || - (ipvs->sysctl_expire_quiescent_template && - (atomic_read(&dest->weight) == 0))) { + expire_quiescent_template(ipvs, dest)) { IP_VS_DBG_BUF(9, "check_template: dest not available for " "protocol %s s:%s:%d v:%s:%d " "-> d:%s:%d\n", diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2d1f932add46..07accf6b2401 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -132,7 +132,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(ipvs->cpustats); + s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); s->ustats.inbytes += skb->len; @@ -162,7 +162,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(ipvs->cpustats); + s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); s->ustats.outbytes += skb->len; @@ -183,7 +183,7 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) s = this_cpu_ptr(svc->stats.cpustats); s->ustats.conns++; - s = this_cpu_ptr(ipvs->cpustats); + s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.conns++; } @@ -499,11 +499,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd) { - struct net *net; - struct netns_ipvs *ipvs; __be16 _ports[2], *pptr; struct ip_vs_iphdr iph; +#ifdef CONFIG_SYSCTL + struct net *net; + struct netns_ipvs *ipvs; int unicast; +#endif ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); @@ -512,6 +514,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_service_put(svc); return NF_DROP; } + +#ifdef CONFIG_SYSCTL net = skb_net(skb); #ifdef CONFIG_IP_VS_IPV6 @@ -563,6 +567,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_conn_put(cp); return ret; } +#endif /* * When the virtual ftp service is presented, packets destined @@ -599,6 +604,33 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, return NF_DROP; } +#ifdef CONFIG_SYSCTL + +static int sysctl_snat_reroute(struct sk_buff *skb) +{ + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + return ipvs->sysctl_snat_reroute; +} + +static int sysctl_nat_icmp_send(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + return ipvs->sysctl_nat_icmp_send; +} + +static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_expire_nodest_conn; +} + +#else + +static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; } +static int sysctl_nat_icmp_send(struct net *net) { return 0; } +static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; } + +#endif + __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); @@ -631,6 +663,22 @@ static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user) } #endif +static int ip_vs_route_me_harder(int af, struct sk_buff *skb) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0) + return 1; + } else +#endif + if ((sysctl_snat_reroute(skb) || + skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + ip_route_me_harder(skb, RTN_LOCAL) != 0) + return 1; + + return 0; +} + /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in @@ -737,7 +785,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl) { - struct netns_ipvs *ipvs; unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != 0) { @@ -759,8 +806,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb, if (!skb_make_writable(skb, offset)) goto out; - ipvs = net_ipvs(skb_net(skb)); - #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); @@ -768,16 +813,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0) - goto out; - } else -#endif - if ((ipvs->sysctl_snat_reroute || - skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(skb, RTN_LOCAL) != 0) - goto out; + if (ip_vs_route_me_harder(af, skb)) + goto out; /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); @@ -985,7 +1022,6 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int ihl) { struct ip_vs_protocol *pp = pd->pp; - struct netns_ipvs *ipvs; IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); @@ -1021,18 +1057,8 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * if it came from this machine itself. So re-compute * the routing information. */ - ipvs = net_ipvs(skb_net(skb)); - -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0) - goto drop; - } else -#endif - if ((ipvs->sysctl_snat_reroute || - skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(skb, RTN_LOCAL) != 0) - goto drop; + if (ip_vs_route_me_harder(af, skb)) + goto drop; IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); @@ -1066,7 +1092,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; - struct netns_ipvs *ipvs; EnterFunction(11); @@ -1141,11 +1166,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) * Check if the packet belongs to an existing entry */ cp = pp->conn_out_get(af, skb, &iph, iph.len, 0); - ipvs = net_ipvs(net); if (likely(cp)) return handle_response(af, skb, pd, cp, iph.len); - if (ipvs->sysctl_nat_icmp_send && + if (sysctl_nat_icmp_send(net) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { @@ -1570,7 +1594,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ - if (ipvs->sysctl_expire_nodest_conn) { + if (sysctl_expire_nodest_conn(ipvs)) { /* try to expire the connection immediately */ ip_vs_conn_expire_now(cp); } @@ -1600,15 +1624,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) - pkts = ipvs->sysctl_sync_threshold[0]; + pkts = sysctl_sync_threshold(ipvs); else pkts = atomic_add_return(1, &cp->in_pkts); if ((ipvs->sync_state & IP_VS_STATE_MASTER) && cp->protocol == IPPROTO_SCTP) { if ((cp->state == IP_VS_SCTP_S_ESTABLISHED && - (pkts % ipvs->sysctl_sync_threshold[1] - == ipvs->sysctl_sync_threshold[0])) || + (pkts % sysctl_sync_period(ipvs) + == sysctl_sync_threshold(ipvs))) || (cp->old_state != cp->state && ((cp->state == IP_VS_SCTP_S_CLOSED) || (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) || @@ -1622,8 +1646,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) else if ((ipvs->sync_state & IP_VS_STATE_MASTER) && (((cp->protocol != IPPROTO_TCP || cp->state == IP_VS_TCP_S_ESTABLISHED) && - (pkts % ipvs->sysctl_sync_threshold[1] - == ipvs->sysctl_sync_threshold[0])) || + (pkts % sysctl_sync_period(ipvs) + == sysctl_sync_threshold(ipvs))) || ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && ((cp->state == IP_VS_TCP_S_FIN_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index a60b20fa142e..b799cea31f95 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -86,6 +86,8 @@ static int __ip_vs_addr_is_local_v6(struct net *net, return 0; } #endif + +#ifdef CONFIG_SYSCTL /* * update_defense_level is called from keventd and from sysctl, * so it needs to protect itself from softirqs @@ -227,6 +229,7 @@ static void defense_work_handler(struct work_struct *work) ip_vs_random_dropentry(ipvs->net); schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); } +#endif int ip_vs_use_count_inc(void) @@ -409,9 +412,11 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, /* * Check the table hashed by fwmark first */ - svc = __ip_vs_svc_fwm_find(net, af, fwmark); - if (fwmark && svc) - goto out; + if (fwmark) { + svc = __ip_vs_svc_fwm_find(net, af, fwmark); + if (svc) + goto out; + } /* * Check the table hashed by <protocol,addr,port> @@ -707,13 +712,39 @@ static void ip_vs_trash_cleanup(struct net *net) } } +static void +ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src) +{ +#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c + + spin_lock_bh(&src->lock); + + IP_VS_SHOW_STATS_COUNTER(conns); + IP_VS_SHOW_STATS_COUNTER(inpkts); + IP_VS_SHOW_STATS_COUNTER(outpkts); + IP_VS_SHOW_STATS_COUNTER(inbytes); + IP_VS_SHOW_STATS_COUNTER(outbytes); + + ip_vs_read_estimator(dst, src); + + spin_unlock_bh(&src->lock); +} static void ip_vs_zero_stats(struct ip_vs_stats *stats) { spin_lock_bh(&stats->lock); - memset(&stats->ustats, 0, sizeof(stats->ustats)); + /* get current counters as zero point, rates are zeroed */ + +#define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c + + IP_VS_ZERO_STATS_COUNTER(conns); + IP_VS_ZERO_STATS_COUNTER(inpkts); + IP_VS_ZERO_STATS_COUNTER(outpkts); + IP_VS_ZERO_STATS_COUNTER(inbytes); + IP_VS_ZERO_STATS_COUNTER(outbytes); + ip_vs_zero_estimator(stats); spin_unlock_bh(&stats->lock); @@ -772,7 +803,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock_bh(&dest->dst_lock); if (add) - ip_vs_new_estimator(svc->net, &dest->stats); + ip_vs_start_estimator(svc->net, &dest->stats); write_lock_bh(&__ip_vs_svc_lock); @@ -978,7 +1009,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest) { struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_kill_estimator(net, &dest->stats); + ip_vs_stop_estimator(net, &dest->stats); /* * Remove it from the d-linked list with the real services. @@ -1171,7 +1202,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, else if (svc->port == 0) atomic_inc(&ipvs->nullsvc_counter); - ip_vs_new_estimator(net, &svc->stats); + ip_vs_start_estimator(net, &svc->stats); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) @@ -1323,7 +1354,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) if (svc->af == AF_INET) ipvs->num_services--; - ip_vs_kill_estimator(svc->net, &svc->stats); + ip_vs_stop_estimator(svc->net, &svc->stats); /* Unbind scheduler */ old_sched = svc->scheduler; @@ -1477,11 +1508,11 @@ static int ip_vs_zero_all(struct net *net) } } - ip_vs_zero_stats(net_ipvs(net)->tot_stats); + ip_vs_zero_stats(&net_ipvs(net)->tot_stats); return 0; } - +#ifdef CONFIG_SYSCTL static int proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -1503,7 +1534,6 @@ proc_do_defense_mode(ctl_table *table, int write, return rc; } - static int proc_do_sync_threshold(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -1737,6 +1767,7 @@ const struct ctl_path net_vs_ctl_path[] = { { } }; EXPORT_SYMBOL_GPL(net_vs_ctl_path); +#endif #ifdef CONFIG_PROC_FS @@ -1959,7 +1990,7 @@ static const struct file_operations ip_vs_info_fops = { static int ip_vs_stats_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); - struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats; + struct ip_vs_stats_user show; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, @@ -1967,22 +1998,18 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) seq_printf(seq, " Conns Packets Packets Bytes Bytes\n"); - spin_lock_bh(&tot_stats->lock); - seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns, - tot_stats->ustats.inpkts, tot_stats->ustats.outpkts, - (unsigned long long) tot_stats->ustats.inbytes, - (unsigned long long) tot_stats->ustats.outbytes); + ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats); + seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", show.conns, + show.inpkts, show.outpkts, + (unsigned long long) show.inbytes, + (unsigned long long) show.outbytes); /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); - seq_printf(seq,"%8X %8X %8X %16X %16X\n", - tot_stats->ustats.cps, - tot_stats->ustats.inpps, - tot_stats->ustats.outpps, - tot_stats->ustats.inbps, - tot_stats->ustats.outbps); - spin_unlock_bh(&tot_stats->lock); + seq_printf(seq, "%8X %8X %8X %16X %16X\n", + show.cps, show.inpps, show.outpps, + show.inbps, show.outbps); return 0; } @@ -2003,7 +2030,9 @@ static const struct file_operations ip_vs_stats_fops = { static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); - struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats; + struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats; + struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats; + struct ip_vs_stats_user rates; int i; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ @@ -2013,30 +2042,43 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) "CPU Conns Packets Packets Bytes Bytes\n"); for_each_possible_cpu(i) { - struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i); + struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i); + unsigned int start; + __u64 inbytes, outbytes; + + do { + start = u64_stats_fetch_begin_bh(&u->syncp); + inbytes = u->ustats.inbytes; + outbytes = u->ustats.outbytes; + } while (u64_stats_fetch_retry_bh(&u->syncp, start)); + seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n", - i, u->ustats.conns, u->ustats.inpkts, - u->ustats.outpkts, (__u64)u->ustats.inbytes, - (__u64)u->ustats.outbytes); + i, u->ustats.conns, u->ustats.inpkts, + u->ustats.outpkts, (__u64)inbytes, + (__u64)outbytes); } spin_lock_bh(&tot_stats->lock); + seq_printf(seq, " ~ %8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns, tot_stats->ustats.inpkts, tot_stats->ustats.outpkts, (unsigned long long) tot_stats->ustats.inbytes, (unsigned long long) tot_stats->ustats.outbytes); + ip_vs_read_estimator(&rates, tot_stats); + + spin_unlock_bh(&tot_stats->lock); + /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); seq_printf(seq, " %8X %8X %8X %16X %16X\n", - tot_stats->ustats.cps, - tot_stats->ustats.inpps, - tot_stats->ustats.outpps, - tot_stats->ustats.inbps, - tot_stats->ustats.outbps); - spin_unlock_bh(&tot_stats->lock); + rates.cps, + rates.inpps, + rates.outpps, + rates.inbps, + rates.outbps); return 0; } @@ -2284,14 +2326,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) static void -ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src) -{ - spin_lock_bh(&src->lock); - memcpy(dst, &src->ustats, sizeof(*dst)); - spin_unlock_bh(&src->lock); -} - -static void ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { dst->protocol = src->protocol; @@ -2677,31 +2711,29 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, struct ip_vs_stats *stats) { + struct ip_vs_stats_user ustats; struct nlattr *nl_stats = nla_nest_start(skb, container_type); if (!nl_stats) return -EMSGSIZE; - spin_lock_bh(&stats->lock); - - NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, stats->ustats.conns); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, stats->ustats.inpkts); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, stats->ustats.outpkts); - NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, stats->ustats.inbytes); - NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, stats->ustats.outbytes); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, stats->ustats.cps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, stats->ustats.inpps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, stats->ustats.outpps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, stats->ustats.inbps); - NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, stats->ustats.outbps); + ip_vs_copy_stats(&ustats, stats); - spin_unlock_bh(&stats->lock); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts); + NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes); + NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, ustats.cps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps); + NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps); nla_nest_end(skb, nl_stats); return 0; nla_put_failure: - spin_unlock_bh(&stats->lock); nla_nest_cancel(skb, nl_stats); return -EMSGSIZE; } @@ -3480,7 +3512,8 @@ static void ip_vs_genl_unregister(void) /* * per netns intit/exit func. */ -int __net_init __ip_vs_control_init(struct net *net) +#ifdef CONFIG_SYSCTL +int __net_init __ip_vs_control_init_sysctl(struct net *net) { int idx; struct netns_ipvs *ipvs = net_ipvs(net); @@ -3490,38 +3523,11 @@ int __net_init __ip_vs_control_init(struct net *net) spin_lock_init(&ipvs->dropentry_lock); spin_lock_init(&ipvs->droppacket_lock); spin_lock_init(&ipvs->securetcp_lock); - ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock); - - /* Initialize rs_table */ - for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) - INIT_LIST_HEAD(&ipvs->rs_table[idx]); - - INIT_LIST_HEAD(&ipvs->dest_trash); - atomic_set(&ipvs->ftpsvc_counter, 0); - atomic_set(&ipvs->nullsvc_counter, 0); - - /* procfs stats */ - ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL); - if (ipvs->tot_stats == NULL) { - pr_err("%s(): no memory.\n", __func__); - return -ENOMEM; - } - ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!ipvs->cpustats) { - pr_err("%s() alloc_percpu failed\n", __func__); - goto err_alloc; - } - spin_lock_init(&ipvs->tot_stats->lock); - - proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); - proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops); - proc_net_fops_create(net, "ip_vs_stats_percpu", 0, - &ip_vs_stats_percpu_fops); if (!net_eq(net, &init_net)) { tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); if (tbl == NULL) - goto err_dup; + return -ENOMEM; } else tbl = vs_vars; /* Initialize sysctl defaults */ @@ -3543,52 +3549,94 @@ int __net_init __ip_vs_control_init(struct net *net) tbl[idx++].data = &ipvs->sysctl_cache_bypass; tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template; - ipvs->sysctl_sync_threshold[0] = 3; - ipvs->sysctl_sync_threshold[1] = 50; + ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; + ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; -#ifdef CONFIG_SYSCTL ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path, tbl); if (ipvs->sysctl_hdr == NULL) { if (!net_eq(net, &init_net)) kfree(tbl); - goto err_dup; + return -ENOMEM; } -#endif - ip_vs_new_estimator(net, ipvs->tot_stats); + ip_vs_start_estimator(net, &ipvs->tot_stats); ipvs->sysctl_tbl = tbl; /* Schedule defense work */ INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); - return 0; -err_dup: - free_percpu(ipvs->cpustats); -err_alloc: - kfree(ipvs->tot_stats); - return -ENOMEM; + return 0; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_trash_cleanup(net); - ip_vs_kill_estimator(net, ipvs->tot_stats); cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); -#ifdef CONFIG_SYSCTL unregister_net_sysctl_table(ipvs->sysctl_hdr); +} + +#else + +int __net_init __ip_vs_control_init_sysctl(struct net *net) { return 0; } +void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } + #endif + +int __net_init __ip_vs_control_init(struct net *net) +{ + int idx; + struct netns_ipvs *ipvs = net_ipvs(net); + + ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock); + + /* Initialize rs_table */ + for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) + INIT_LIST_HEAD(&ipvs->rs_table[idx]); + + INIT_LIST_HEAD(&ipvs->dest_trash); + atomic_set(&ipvs->ftpsvc_counter, 0); + atomic_set(&ipvs->nullsvc_counter, 0); + + /* procfs stats */ + ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (ipvs->tot_stats.cpustats) { + pr_err("%s(): alloc_percpu.\n", __func__); + return -ENOMEM; + } + spin_lock_init(&ipvs->tot_stats.lock); + + proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); + proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops); + proc_net_fops_create(net, "ip_vs_stats_percpu", 0, + &ip_vs_stats_percpu_fops); + + if (__ip_vs_control_init_sysctl(net)) + goto err; + + return 0; + +err: + free_percpu(ipvs->tot_stats.cpustats); + return -ENOMEM; +} + +static void __net_exit __ip_vs_control_cleanup(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_trash_cleanup(net); + ip_vs_stop_estimator(net, &ipvs->tot_stats); + __ip_vs_control_cleanup_sysctl(net); proc_net_remove(net, "ip_vs_stats_percpu"); proc_net_remove(net, "ip_vs_stats"); proc_net_remove(net, "ip_vs"); - free_percpu(ipvs->cpustats); - kfree(ipvs->tot_stats); + free_percpu(ipvs->tot_stats.cpustats); } static struct pernet_operations ipvs_control_ops = { diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f560a05c965a..8c8766ca56ad 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -69,10 +69,10 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, sum->inpkts += s->ustats.inpkts; sum->outpkts += s->ustats.outpkts; do { - start = u64_stats_fetch_begin_bh(&s->syncp); + start = u64_stats_fetch_begin(&s->syncp); inbytes = s->ustats.inbytes; outbytes = s->ustats.outbytes; - } while (u64_stats_fetch_retry_bh(&s->syncp, start)); + } while (u64_stats_fetch_retry(&s->syncp, start)); sum->inbytes += inbytes; sum->outbytes += outbytes; } else { @@ -80,10 +80,10 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, sum->inpkts = s->ustats.inpkts; sum->outpkts = s->ustats.outpkts; do { - start = u64_stats_fetch_begin_bh(&s->syncp); + start = u64_stats_fetch_begin(&s->syncp); sum->inbytes = s->ustats.inbytes; sum->outbytes = s->ustats.outbytes; - } while (u64_stats_fetch_retry_bh(&s->syncp, start)); + } while (u64_stats_fetch_retry(&s->syncp, start)); } } } @@ -101,13 +101,12 @@ static void estimation_timer(unsigned long arg) struct netns_ipvs *ipvs; ipvs = net_ipvs(net); - ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats); spin_lock(&ipvs->est_lock); list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); - ip_vs_read_cpu_stats(&s->ustats, s->cpustats); spin_lock(&s->lock); + ip_vs_read_cpu_stats(&s->ustats, s->cpustats); n_conns = s->ustats.conns; n_inpkts = s->ustats.inpkts; n_outpkts = s->ustats.outpkts; @@ -118,61 +117,41 @@ static void estimation_timer(unsigned long arg) rate = (n_conns - e->last_conns) << 9; e->last_conns = n_conns; e->cps += ((long)rate - (long)e->cps) >> 2; - s->ustats.cps = (e->cps + 0x1FF) >> 10; rate = (n_inpkts - e->last_inpkts) << 9; e->last_inpkts = n_inpkts; e->inpps += ((long)rate - (long)e->inpps) >> 2; - s->ustats.inpps = (e->inpps + 0x1FF) >> 10; rate = (n_outpkts - e->last_outpkts) << 9; e->last_outpkts = n_outpkts; e->outpps += ((long)rate - (long)e->outpps) >> 2; - s->ustats.outpps = (e->outpps + 0x1FF) >> 10; rate = (n_inbytes - e->last_inbytes) << 4; e->last_inbytes = n_inbytes; e->inbps += ((long)rate - (long)e->inbps) >> 2; - s->ustats.inbps = (e->inbps + 0xF) >> 5; rate = (n_outbytes - e->last_outbytes) << 4; e->last_outbytes = n_outbytes; e->outbps += ((long)rate - (long)e->outbps) >> 2; - s->ustats.outbps = (e->outbps + 0xF) >> 5; spin_unlock(&s->lock); } spin_unlock(&ipvs->est_lock); mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } -void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats) +void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; INIT_LIST_HEAD(&est->list); - est->last_conns = stats->ustats.conns; - est->cps = stats->ustats.cps<<10; - - est->last_inpkts = stats->ustats.inpkts; - est->inpps = stats->ustats.inpps<<10; - - est->last_outpkts = stats->ustats.outpkts; - est->outpps = stats->ustats.outpps<<10; - - est->last_inbytes = stats->ustats.inbytes; - est->inbps = stats->ustats.inbps<<5; - - est->last_outbytes = stats->ustats.outbytes; - est->outbps = stats->ustats.outbps<<5; - spin_lock_bh(&ipvs->est_lock); list_add(&est->list, &ipvs->est_list); spin_unlock_bh(&ipvs->est_lock); } -void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats) +void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; @@ -185,13 +164,14 @@ void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats) void ip_vs_zero_estimator(struct ip_vs_stats *stats) { struct ip_vs_estimator *est = &stats->est; - - /* set counters zero, caller must hold the stats->lock lock */ - est->last_inbytes = 0; - est->last_outbytes = 0; - est->last_conns = 0; - est->last_inpkts = 0; - est->last_outpkts = 0; + struct ip_vs_stats_user *u = &stats->ustats; + + /* reset counters, caller must hold the stats->lock lock */ + est->last_inbytes = u->inbytes; + est->last_outbytes = u->outbytes; + est->last_conns = u->conns; + est->last_inpkts = u->inpkts; + est->last_outpkts = u->outpkts; est->cps = 0; est->inpps = 0; est->outpps = 0; @@ -199,6 +179,19 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats) est->outbps = 0; } +/* Get decoded rates */ +void ip_vs_read_estimator(struct ip_vs_stats_user *dst, + struct ip_vs_stats *stats) +{ + struct ip_vs_estimator *e = &stats->est; + + dst->cps = (e->cps + 0x1FF) >> 10; + dst->inpps = (e->inpps + 0x1FF) >> 10; + dst->outpps = (e->outpps + 0x1FF) >> 10; + dst->inbps = (e->inbps + 0xF) >> 5; + dst->outbps = (e->outbps + 0xF) >> 5; +} + static int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 6bf7a807649c..f276df9896b3 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -63,6 +63,8 @@ #define CHECK_EXPIRE_INTERVAL (60*HZ) #define ENTRY_TIMEOUT (6*60*HZ) +#define DEFAULT_EXPIRATION (24*60*60*HZ) + /* * It is for full expiration check. * When there is no partial expiration check (garbage collection) @@ -112,7 +114,7 @@ struct ip_vs_lblc_table { /* * IPVS LBLC sysctl table */ - +#ifdef CONFIG_SYSCTL static ctl_table vs_vars_table[] = { { .procname = "lblc_expiration", @@ -123,6 +125,7 @@ static ctl_table vs_vars_table[] = { }, { } }; +#endif static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) { @@ -238,6 +241,15 @@ static void ip_vs_lblc_flush(struct ip_vs_lblc_table *tbl) } } +static int sysctl_lblc_expiration(struct ip_vs_service *svc) +{ +#ifdef CONFIG_SYSCTL + struct netns_ipvs *ipvs = net_ipvs(svc->net); + return ipvs->sysctl_lblc_expiration; +#else + return DEFAULT_EXPIRATION; +#endif +} static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) { @@ -245,7 +257,6 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) struct ip_vs_lblc_entry *en, *nxt; unsigned long now = jiffies; int i, j; - struct netns_ipvs *ipvs = net_ipvs(svc->net); for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; @@ -254,7 +265,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_before(now, en->lastuse + - ipvs->sysctl_lblc_expiration)) + sysctl_lblc_expiration(svc))) continue; ip_vs_lblc_free(en); @@ -538,6 +549,7 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = /* * per netns init. */ +#ifdef CONFIG_SYSCTL static int __net_init __ip_vs_lblc_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -550,10 +562,9 @@ static int __net_init __ip_vs_lblc_init(struct net *net) return -ENOMEM; } else ipvs->lblc_ctl_table = vs_vars_table; - ipvs->sysctl_lblc_expiration = 24*60*60*HZ; + ipvs->sysctl_lblc_expiration = DEFAULT_EXPIRATION; ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration; -#ifdef CONFIG_SYSCTL ipvs->lblc_ctl_header = register_net_sysctl_table(net, net_vs_ctl_path, ipvs->lblc_ctl_table); @@ -562,7 +573,6 @@ static int __net_init __ip_vs_lblc_init(struct net *net) kfree(ipvs->lblc_ctl_table); return -ENOMEM; } -#endif return 0; } @@ -571,14 +581,19 @@ static void __net_exit __ip_vs_lblc_exit(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); -#ifdef CONFIG_SYSCTL unregister_net_sysctl_table(ipvs->lblc_ctl_header); -#endif if (!net_eq(net, &init_net)) kfree(ipvs->lblc_ctl_table); } +#else + +static int __net_init __ip_vs_lblc_init(struct net *net) { return 0; } +static void __net_exit __ip_vs_lblc_exit(struct net *net) { } + +#endif + static struct pernet_operations ip_vs_lblc_ops = { .init = __ip_vs_lblc_init, .exit = __ip_vs_lblc_exit, diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 00631765b92a..cb1c9913d38b 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -63,6 +63,8 @@ #define CHECK_EXPIRE_INTERVAL (60*HZ) #define ENTRY_TIMEOUT (6*60*HZ) +#define DEFAULT_EXPIRATION (24*60*60*HZ) + /* * It is for full expiration check. * When there is no partial expiration check (garbage collection) @@ -283,6 +285,7 @@ struct ip_vs_lblcr_table { }; +#ifdef CONFIG_SYSCTL /* * IPVS LBLCR sysctl table */ @@ -297,6 +300,7 @@ static ctl_table vs_vars_table[] = { }, { } }; +#endif static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) { @@ -410,6 +414,15 @@ static void ip_vs_lblcr_flush(struct ip_vs_lblcr_table *tbl) } } +static int sysctl_lblcr_expiration(struct ip_vs_service *svc) +{ +#ifdef CONFIG_SYSCTL + struct netns_ipvs *ipvs = net_ipvs(svc->net); + return ipvs->sysctl_lblcr_expiration; +#else + return DEFAULT_EXPIRATION; +#endif +} static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) { @@ -417,15 +430,14 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) unsigned long now = jiffies; int i, j; struct ip_vs_lblcr_entry *en, *nxt; - struct netns_ipvs *ipvs = net_ipvs(svc->net); for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { - if (time_after(en->lastuse - + ipvs->sysctl_lblcr_expiration, now)) + if (time_after(en->lastuse + + sysctl_lblcr_expiration(svc), now)) continue; ip_vs_lblcr_free(en); @@ -650,7 +662,6 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) read_lock(&svc->sched_lock); en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr); if (en) { - struct netns_ipvs *ipvs = net_ipvs(svc->net); /* We only hold a read lock, but this is atomic */ en->lastuse = jiffies; @@ -662,7 +673,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* More than one destination + enough time passed by, cleanup */ if (atomic_read(&en->set.size) > 1 && time_after(jiffies, en->set.lastmod + - ipvs->sysctl_lblcr_expiration)) { + sysctl_lblcr_expiration(svc))) { struct ip_vs_dest *m; write_lock(&en->set.lock); @@ -734,6 +745,7 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = /* * per netns init. */ +#ifdef CONFIG_SYSCTL static int __net_init __ip_vs_lblcr_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -746,10 +758,9 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) return -ENOMEM; } else ipvs->lblcr_ctl_table = vs_vars_table; - ipvs->sysctl_lblcr_expiration = 24*60*60*HZ; + ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION; ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration; -#ifdef CONFIG_SYSCTL ipvs->lblcr_ctl_header = register_net_sysctl_table(net, net_vs_ctl_path, ipvs->lblcr_ctl_table); @@ -758,7 +769,6 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) kfree(ipvs->lblcr_ctl_table); return -ENOMEM; } -#endif return 0; } @@ -767,14 +777,19 @@ static void __net_exit __ip_vs_lblcr_exit(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); -#ifdef CONFIG_SYSCTL unregister_net_sysctl_table(ipvs->lblcr_ctl_header); -#endif if (!net_eq(net, &init_net)) kfree(ipvs->lblcr_ctl_table); } +#else + +static int __net_init __ip_vs_lblcr_init(struct net *net) { return 0; } +static void __net_exit __ip_vs_lblcr_exit(struct net *net) { } + +#endif + static struct pernet_operations ip_vs_lblcr_ops = { .init = __ip_vs_lblcr_init, .exit = __ip_vs_lblcr_exit, diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 0d83bc01fed4..13d607ae9c52 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -92,14 +92,13 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen)) return -EINVAL; - p->pe_data = kmalloc(matchlen, GFP_ATOMIC); - if (!p->pe_data) - return -ENOMEM; - /* N.B: pe_data is only set on success, * this allows fallback to the default persistence logic on failure */ - memcpy(p->pe_data, dptr + matchoff, matchlen); + p->pe_data = kmemdup(dptr + matchoff, matchlen, GFP_ATOMIC); + if (!p->pe_data) + return -ENOMEM; + p->pe_data_len = matchlen; return 0; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index fecf24de4af3..3e7961e85e9c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -394,7 +394,7 @@ void ip_vs_sync_switch_mode(struct net *net, int mode) if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) return; - if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff) + if (mode == sysctl_sync_ver(ipvs) || !ipvs->sync_buff) return; spin_lock_bh(&ipvs->sync_buff_lock); @@ -521,7 +521,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp) unsigned int len, pe_name_len, pad; /* Handle old version of the protocol */ - if (ipvs->sysctl_sync_ver == 0) { + if (sysctl_sync_ver(ipvs) == 0) { ip_vs_sync_conn_v0(net, cp); return; } @@ -650,7 +650,7 @@ control: if (cp->flags & IP_VS_CONN_F_TEMPLATE) { int pkts = atomic_add_return(1, &cp->in_pkts); - if (pkts % ipvs->sysctl_sync_threshold[1] != 1) + if (pkts % sysctl_sync_period(ipvs) != 1) return; } goto sloop; @@ -697,13 +697,12 @@ ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc, return 1; } - p->pe_data = kmalloc(pe_data_len, GFP_ATOMIC); + p->pe_data = kmemdup(pe_data, pe_data_len, GFP_ATOMIC); if (!p->pe_data) { if (p->pe->module) module_put(p->pe->module); return -ENOMEM; } - memcpy(p->pe_data, pe_data, pe_data_len); p->pe_data_len = pe_data_len; } return 0; @@ -795,7 +794,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, if (opt) memcpy(&cp->in_seq, opt, sizeof(*opt)); - atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]); + atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs)); cp->state = state; cp->old_state = cp->state; /* diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2f454efa1a8b..941286ca911d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1301,6 +1301,7 @@ static void nf_conntrack_cleanup_net(struct net *net) nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); nf_conntrack_ecache_fini(net); + nf_conntrack_tstamp_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); kmem_cache_destroy(net->ct.nf_conntrack_cachep); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 0a77d2ff2154..a9adf4c6b299 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -183,14 +183,14 @@ EXPORT_SYMBOL(xt_unregister_matches); /* * These are weird, but module loading must not be done with mutex * held (since they will register), and we have to have a single - * function to use try_then_request_module(). + * function to use. */ /* Find match, grabs ref. Returns ERR_PTR() on error. */ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) { struct xt_match *m; - int err = 0; + int err = -ENOENT; if (mutex_lock_interruptible(&xt[af].mutex) != 0) return ERR_PTR(-EINTR); @@ -221,9 +221,13 @@ xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) { struct xt_match *match; - match = try_then_request_module(xt_find_match(nfproto, name, revision), - "%st_%s", xt_prefix[nfproto], name); - return (match != NULL) ? match : ERR_PTR(-ENOENT); + match = xt_find_match(nfproto, name, revision); + if (IS_ERR(match)) { + request_module("%st_%s", xt_prefix[nfproto], name); + match = xt_find_match(nfproto, name, revision); + } + + return match; } EXPORT_SYMBOL_GPL(xt_request_find_match); @@ -231,7 +235,7 @@ EXPORT_SYMBOL_GPL(xt_request_find_match); struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; - int err = 0; + int err = -ENOENT; if (mutex_lock_interruptible(&xt[af].mutex) != 0) return ERR_PTR(-EINTR); @@ -261,9 +265,13 @@ struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { struct xt_target *target; - target = try_then_request_module(xt_find_target(af, name, revision), - "%st_%s", xt_prefix[af], name); - return (target != NULL) ? target : ERR_PTR(-ENOENT); + target = xt_find_target(af, name, revision); + if (IS_ERR(target)) { + request_module("%st_%s", xt_prefix[af], name); + target = xt_find_target(af, name, revision); + } + + return target; } EXPORT_SYMBOL_GPL(xt_request_find_target); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c new file mode 100644 index 000000000000..2220b85e9519 --- /dev/null +++ b/net/netfilter/xt_addrtype.c @@ -0,0 +1,229 @@ +/* + * iptables module to match inet_addr_type() of an ip. + * + * Copyright (c) 2004 Patrick McHardy <kaber@trash.net> + * (C) 2007 Laszlo Attila Toth <panther@balabit.hu> + * + * 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. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/ip.h> +#include <net/route.h> + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/ip6_fib.h> +#endif + +#include <linux/netfilter/xt_addrtype.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Xtables: address type match"); +MODULE_ALIAS("ipt_addrtype"); +MODULE_ALIAS("ip6t_addrtype"); + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) +{ + u32 ret; + + if (!rt) + return XT_ADDRTYPE_UNREACHABLE; + + if (rt->rt6i_flags & RTF_REJECT) + ret = XT_ADDRTYPE_UNREACHABLE; + else + ret = 0; + + if (rt->rt6i_flags & RTF_LOCAL) + ret |= XT_ADDRTYPE_LOCAL; + if (rt->rt6i_flags & RTF_ANYCAST) + ret |= XT_ADDRTYPE_ANYCAST; + return ret; +} + +static bool match_type6(struct net *net, const struct net_device *dev, + const struct in6_addr *addr, u16 mask) +{ + int addr_type = ipv6_addr_type(addr); + + if ((mask & XT_ADDRTYPE_MULTICAST) && + !(addr_type & IPV6_ADDR_MULTICAST)) + return false; + if ((mask & XT_ADDRTYPE_UNICAST) && !(addr_type & IPV6_ADDR_UNICAST)) + return false; + if ((mask & XT_ADDRTYPE_UNSPEC) && addr_type != IPV6_ADDR_ANY) + return false; + + if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST | + XT_ADDRTYPE_UNREACHABLE) & mask) { + struct rt6_info *rt; + u32 type; + int ifindex = dev ? dev->ifindex : 0; + + rt = rt6_lookup(net, addr, NULL, ifindex, !!dev); + + type = xt_addrtype_rt6_to_type(rt); + + dst_release(&rt->dst); + return !!(mask & type); + } + return true; +} + +static bool +addrtype_mt6(struct net *net, const struct net_device *dev, + const struct sk_buff *skb, const struct xt_addrtype_info_v1 *info) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + bool ret = true; + + if (info->source) + ret &= match_type6(net, dev, &iph->saddr, info->source) ^ + (info->flags & XT_ADDRTYPE_INVERT_SOURCE); + if (ret && info->dest) + ret &= match_type6(net, dev, &iph->daddr, info->dest) ^ + !!(info->flags & XT_ADDRTYPE_INVERT_DEST); + return ret; +} +#endif + +static inline bool match_type(struct net *net, const struct net_device *dev, + __be32 addr, u_int16_t mask) +{ + return !!(mask & (1 << inet_dev_addr_type(net, dev, addr))); +} + +static bool +addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct net *net = dev_net(par->in ? par->in : par->out); + const struct xt_addrtype_info *info = par->matchinfo; + const struct iphdr *iph = ip_hdr(skb); + bool ret = true; + + if (info->source) + ret &= match_type(net, NULL, iph->saddr, info->source) ^ + info->invert_source; + if (info->dest) + ret &= match_type(net, NULL, iph->daddr, info->dest) ^ + info->invert_dest; + + return ret; +} + +static bool +addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct net *net = dev_net(par->in ? par->in : par->out); + const struct xt_addrtype_info_v1 *info = par->matchinfo; + const struct iphdr *iph; + const struct net_device *dev = NULL; + bool ret = true; + + if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN) + dev = par->in; + else if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) + dev = par->out; + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) + if (par->family == NFPROTO_IPV6) + return addrtype_mt6(net, dev, skb, info); +#endif + iph = ip_hdr(skb); + if (info->source) + ret &= match_type(net, dev, iph->saddr, info->source) ^ + (info->flags & XT_ADDRTYPE_INVERT_SOURCE); + if (ret && info->dest) + ret &= match_type(net, dev, iph->daddr, info->dest) ^ + !!(info->flags & XT_ADDRTYPE_INVERT_DEST); + return ret; +} + +static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) +{ + struct xt_addrtype_info_v1 *info = par->matchinfo; + + if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN && + info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) { + pr_info("both incoming and outgoing " + "interface limitation cannot be selected\n"); + return -EINVAL; + } + + if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN)) && + info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) { + pr_info("output interface limitation " + "not valid in PREROUTING and INPUT\n"); + return -EINVAL; + } + + if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT)) && + info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN) { + pr_info("input interface limitation " + "not valid in POSTROUTING and OUTPUT\n"); + return -EINVAL; + } + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) + if (par->family == NFPROTO_IPV6) { + if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) { + pr_err("ipv6 BLACKHOLE matching not supported\n"); + return -EINVAL; + } + if ((info->source | info->dest) >= XT_ADDRTYPE_PROHIBIT) { + pr_err("ipv6 PROHIBT (THROW, NAT ..) matching not supported\n"); + return -EINVAL; + } + if ((info->source | info->dest) & XT_ADDRTYPE_BROADCAST) { + pr_err("ipv6 does not support BROADCAST matching\n"); + return -EINVAL; + } + } +#endif + return 0; +} + +static struct xt_match addrtype_mt_reg[] __read_mostly = { + { + .name = "addrtype", + .family = NFPROTO_IPV4, + .match = addrtype_mt_v0, + .matchsize = sizeof(struct xt_addrtype_info), + .me = THIS_MODULE + }, + { + .name = "addrtype", + .family = NFPROTO_UNSPEC, + .revision = 1, + .match = addrtype_mt_v1, + .checkentry = addrtype_mt_checkentry_v1, + .matchsize = sizeof(struct xt_addrtype_info_v1), + .me = THIS_MODULE + } +}; + +static int __init addrtype_mt_init(void) +{ + return xt_register_matches(addrtype_mt_reg, + ARRAY_SIZE(addrtype_mt_reg)); +} + +static void __exit addrtype_mt_exit(void) +{ + xt_unregister_matches(addrtype_mt_reg, ARRAY_SIZE(addrtype_mt_reg)); +} + +module_init(addrtype_mt_init); +module_exit(addrtype_mt_exit); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index e029c4807404..c6d5a83450c9 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -33,17 +33,17 @@ /* we will save the tuples of all connections we care about */ struct xt_connlimit_conn { - struct list_head list; - struct nf_conntrack_tuple tuple; + struct hlist_node node; + struct nf_conntrack_tuple tuple; + union nf_inet_addr addr; }; struct xt_connlimit_data { - struct list_head iphash[256]; - spinlock_t lock; + struct hlist_head iphash[256]; + spinlock_t lock; }; static u_int32_t connlimit_rnd __read_mostly; -static bool connlimit_rnd_inited __read_mostly; static inline unsigned int connlimit_iphash(__be32 addr) { @@ -101,9 +101,9 @@ static int count_them(struct net *net, { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; - struct xt_connlimit_conn *tmp; + struct hlist_node *pos, *n; struct nf_conn *found_ct; - struct list_head *hash; + struct hlist_head *hash; bool addit = true; int matches = 0; @@ -115,7 +115,7 @@ static int count_them(struct net *net, rcu_read_lock(); /* check the saved connections */ - list_for_each_entry_safe(conn, tmp, hash, list) { + hlist_for_each_entry_safe(conn, pos, n, hash, node) { found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE, &conn->tuple); found_ct = NULL; @@ -135,7 +135,7 @@ static int count_them(struct net *net, if (found == NULL) { /* this one is gone */ - list_del(&conn->list); + hlist_del(&conn->node); kfree(conn); continue; } @@ -146,12 +146,12 @@ static int count_them(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - list_del(&conn->list); + hlist_del(&conn->node); kfree(conn); continue; } - if (same_source_net(addr, mask, &conn->tuple.src.u3, family)) + if (same_source_net(addr, mask, &conn->addr, family)) /* same source network -> be counted! */ ++matches; nf_ct_put(found_ct); @@ -161,11 +161,12 @@ static int count_them(struct net *net, if (addit) { /* save the new connection in our list */ - conn = kzalloc(sizeof(*conn), GFP_ATOMIC); + conn = kmalloc(sizeof(*conn), GFP_ATOMIC); if (conn == NULL) return -ENOMEM; conn->tuple = *tuple; - list_add(&conn->list, hash); + conn->addr = *addr; + hlist_add_head(&conn->node, hash); ++matches; } @@ -185,15 +186,11 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) int connections; ct = nf_ct_get(skb, &ctinfo); - if (ct != NULL) { - if (info->flags & XT_CONNLIMIT_DADDR) - tuple_ptr = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - else - tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - } else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - par->family, &tuple)) { + if (ct != NULL) + tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + par->family, &tuple)) goto hotdrop; - } if (par->family == NFPROTO_IPV6) { const struct ipv6hdr *iph = ipv6_hdr(skb); @@ -228,9 +225,13 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) unsigned int i; int ret; - if (unlikely(!connlimit_rnd_inited)) { - get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd)); - connlimit_rnd_inited = true; + if (unlikely(!connlimit_rnd)) { + u_int32_t rand; + + do { + get_random_bytes(&rand, sizeof(rand)); + } while (!rand); + cmpxchg(&connlimit_rnd, 0, rand); } ret = nf_ct_l3proto_try_module_get(par->family); if (ret < 0) { @@ -248,7 +249,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) spin_lock_init(&info->data->lock); for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) - INIT_LIST_HEAD(&info->data->iphash[i]); + INIT_HLIST_HEAD(&info->data->iphash[i]); return 0; } @@ -257,15 +258,15 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_connlimit_info *info = par->matchinfo; struct xt_connlimit_conn *conn; - struct xt_connlimit_conn *tmp; - struct list_head *hash = info->data->iphash; + struct hlist_node *pos, *n; + struct hlist_head *hash = info->data->iphash; unsigned int i; nf_ct_l3proto_module_put(par->family); for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) { - list_for_each_entry_safe(conn, tmp, &hash[i], list) { - list_del(&conn->list); + hlist_for_each_entry_safe(conn, pos, n, &hash[i], node) { + hlist_del(&conn->node); kfree(conn); } } |