Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6

include/linux/netfilter/Kbuild

@@ -3,6 +3,7 @@ header-y += nf_conntrack_tuple_common.h
 header-y += nfnetlink_conntrack.h
 header-y += nfnetlink_log.h
 header-y += nfnetlink_queue.h
+header-y += xt_CHECKSUM.h
 header-y += xt_CLASSIFY.h
 header-y += xt_CONNMARK.h
 header-y += xt_CONNSECMARK.h
@@ -19,17 +20,19 @@ header-y += xt_TCPMSS.h
 header-y += xt_TCPOPTSTRIP.h
 header-y += xt_TEE.h
 header-y += xt_TPROXY.h
+header-y += xt_cluster.h
 header-y += xt_comment.h
 header-y += xt_connbytes.h
 header-y += xt_connlimit.h
 header-y += xt_connmark.h
 header-y += xt_conntrack.h
-header-y += xt_cluster.h
+header-y += xt_cpu.h
 header-y += xt_dccp.h
 header-y += xt_dscp.h
 header-y += xt_esp.h
 header-y += xt_hashlimit.h
 header-y += xt_iprange.h
+header-y += xt_ipvs.h
 header-y += xt_helper.h
 header-y += xt_length.h
 header-y += xt_limit.h

include/linux/netfilter/nfnetlink_log.h

@@ -89,7 +89,7 @@ enum nfulnl_attr_config {
 #define NFULNL_COPY_NONE	0x00
 #define NFULNL_COPY_META	0x01
 #define NFULNL_COPY_PACKET	0x02
-#define NFULNL_COPY_DISABLED	0x03
+/* 0xff is reserved, don't use it for new copy modes. */
 
 #define NFULNL_CFG_F_SEQ	0x0001
 #define NFULNL_CFG_F_SEQ_GLOBAL	0x0002

include/linux/netfilter/xt_CHECKSUM.h

@@ -0,0 +1,20 @@
+/* Header file for iptables ipt_CHECKSUM target
+ *
+ * (C) 2002 by Harald Welte <laforge@gnumonks.org>
+ * (C) 2010 Red Hat Inc
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This software is distributed under GNU GPL v2, 1991
+*/
+#ifndef _XT_CHECKSUM_TARGET_H
+#define _XT_CHECKSUM_TARGET_H
+
+#include <linux/types.h>
+
+#define XT_CHECKSUM_OP_FILL	0x01	/* fill in checksum in IP header */
+
+struct xt_CHECKSUM_info {
+	__u8 operation;	/* bitset of operations */
+};
+
+#endif /* _XT_CHECKSUM_TARGET_H */

include/linux/netfilter/xt_cpu.h

@@ -0,0 +1,11 @@
+#ifndef _XT_CPU_H
+#define _XT_CPU_H
+
+#include <linux/types.h>
+
+struct xt_cpu_info {
+	__u32	cpu;
+	__u32	invert;
+};
+
+#endif /*_XT_CPU_H*/

include/linux/netfilter/xt_ipvs.h

@@ -0,0 +1,27 @@
+#ifndef _XT_IPVS_H
+#define _XT_IPVS_H
+
+enum {
+	XT_IPVS_IPVS_PROPERTY =	1 << 0, /* all other options imply this one */
+	XT_IPVS_PROTO =		1 << 1,
+	XT_IPVS_VADDR =		1 << 2,
+	XT_IPVS_VPORT =		1 << 3,
+	XT_IPVS_DIR =		1 << 4,
+	XT_IPVS_METHOD =	1 << 5,
+	XT_IPVS_VPORTCTL =	1 << 6,
+	XT_IPVS_MASK =		(1 << 7) - 1,
+	XT_IPVS_ONCE_MASK =	XT_IPVS_MASK & ~XT_IPVS_IPVS_PROPERTY
+};
+
+struct xt_ipvs_mtinfo {
+	union nf_inet_addr	vaddr, vmask;
+	__be16			vport;
+	__u8			l4proto;
+	__u8			fwd_method;
+	__be16			vportctl;
+
+	__u8			invert;
+	__u8			bitmask;
+};
+
+#endif /* _XT_IPVS_H */

include/linux/netfilter/xt_quota.h

@@ -11,9 +11,9 @@ struct xt_quota_priv;
 struct xt_quota_info {
 	u_int32_t		flags;
 	u_int32_t		pad;
+	aligned_u64		quota;
 
 	/* Used internally by the kernel */
-	aligned_u64		quota;
 	struct xt_quota_priv	*master;
 };
 

include/net/ip_vs.h

@@ -632,10 +632,22 @@ extern struct ip_vs_conn *ip_vs_ct_in_get
 (int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
  const union nf_inet_addr *d_addr, __be16 d_port);
 
+struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
+					    struct ip_vs_protocol *pp,
+					    const struct ip_vs_iphdr *iph,
+					    unsigned int proto_off,
+					    int inverse);
+
 extern struct ip_vs_conn *ip_vs_conn_out_get
 (int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
  const union nf_inet_addr *d_addr, __be16 d_port);
 
+struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
+					     struct ip_vs_protocol *pp,
+					     const struct ip_vs_iphdr *iph,
+					     unsigned int proto_off,
+					     int inverse);
+
 /* put back the conn without restarting its timer */
 static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 {
@@ -736,8 +748,6 @@ extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
 
 extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
 extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
-extern int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
-			     char *o_buf, int o_len, char *n_buf, int n_len);
 extern int ip_vs_app_init(void);
 extern void ip_vs_app_cleanup(void);
 

include/net/netfilter/nf_conntrack_extend.h

@@ -28,9 +28,14 @@ struct nf_ct_ext {
 	char data[0];
 };
 
-static inline int nf_ct_ext_exist(const struct nf_conn *ct, u8 id)
+static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id)
 {
-	return (ct->ext && ct->ext->offset[id]);
+	return !!ext->offset[id];
+}
+
+static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id)
+{
+	return (ct->ext && __nf_ct_ext_exist(ct->ext, id));
 }
 
 static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)

include/net/netfilter/nf_nat_protocol.h

@@ -27,9 +27,9 @@ struct nf_nat_protocol {
 
 	/* Alter the per-proto part of the tuple (depending on
 	   maniptype), to give a unique tuple in the given range if
-	   possible; return false if not.  Per-protocol part of tuple
-	   is initialized to the incoming packet. */
-	bool (*unique_tuple)(struct nf_conntrack_tuple *tuple,
+	   possible.  Per-protocol part of tuple is initialized to the
+	   incoming packet. */
+	void (*unique_tuple)(struct nf_conntrack_tuple *tuple,
 			     const struct nf_nat_range *range,
 			     enum nf_nat_manip_type maniptype,
 			     const struct nf_conn *ct);
@@ -63,7 +63,7 @@ extern bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
 				  const union nf_conntrack_man_proto *min,
 				  const union nf_conntrack_man_proto *max);
 
-extern bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
+extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 				      const struct nf_nat_range *range,
 				      enum nf_nat_manip_type maniptype,
 				      const struct nf_conn *ct,

include/net/netfilter/nfnetlink_log.h

@@ -10,5 +10,7 @@ nfulnl_log_packet(u_int8_t pf,
 		  const struct nf_loginfo *li_user,
 		  const char *prefix);
 
+#define NFULNL_COPY_DISABLED    0xff
+
 #endif /* _KER_NFNETLINK_LOG_H */
 

net/ipv4/netfilter/arp_tables.c

@@ -283,16 +283,13 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	arp = arp_hdr(skb);
 	do {
 		const struct arpt_entry_target *t;
-		int hdr_len;
 
 		if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
 			e = arpt_next_entry(e);
 			continue;
 		}
 
-		hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
-			(2 * skb->dev->addr_len);
-		ADD_COUNTER(e->counters, hdr_len, 1);
+		ADD_COUNTER(e->counters, arp_hdr_len(skb->dev), 1);
 
 		t = arpt_get_target_c(e);
 
@@ -713,7 +710,7 @@ static void get_counters(const struct xt_table_info *t,
 	struct arpt_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu;
+	unsigned int curcpu = get_cpu();
 
 	/* Instead of clearing (by a previous call to memset())
 	 * the counters and using adds, we set the counters
@@ -723,14 +720,16 @@ static void get_counters(const struct xt_table_info *t,
 	 * if new softirq were to run and call ipt_do_table
 	 */
 	local_bh_disable();
-	curcpu = smp_processor_id();
-
 	i = 0;
 	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
 		SET_COUNTER(counters[i], iter->counters.bcnt,
 			    iter->counters.pcnt);
 		++i;
 	}
+	local_bh_enable();
+	/* Processing counters from other cpus, we can let bottom half enabled,
+	 * (preemption is disabled)
+	 */
 
 	for_each_possible_cpu(cpu) {
 		if (cpu == curcpu)
@@ -744,7 +743,7 @@ static void get_counters(const struct xt_table_info *t,
 		}
 		xt_info_wrunlock(cpu);
 	}
-	local_bh_enable();
+	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)

net/ipv4/netfilter/ip_tables.c

@@ -364,7 +364,7 @@ ipt_do_table(struct sk_buff *skb,
 				goto no_match;
 		}
 
-		ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
+		ADD_COUNTER(e->counters, skb->len, 1);
 
 		t = ipt_get_target(e);
 		IP_NF_ASSERT(t->u.kernel.target);
@@ -884,7 +884,7 @@ get_counters(const struct xt_table_info *t,
 	struct ipt_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu;
+	unsigned int curcpu = get_cpu();
 
 	/* Instead of clearing (by a previous call to memset())
 	 * the counters and using adds, we set the counters
@@ -894,14 +894,16 @@ get_counters(const struct xt_table_info *t,
 	 * if new softirq were to run and call ipt_do_table
 	 */
 	local_bh_disable();
-	curcpu = smp_processor_id();
-
 	i = 0;
 	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
 		SET_COUNTER(counters[i], iter->counters.bcnt,
 			    iter->counters.pcnt);
 		++i;
 	}
+	local_bh_enable();
+	/* Processing counters from other cpus, we can let bottom half enabled,
+	 * (preemption is disabled)
+	 */
 
 	for_each_possible_cpu(cpu) {
 		if (cpu == curcpu)
@@ -915,7 +917,7 @@ get_counters(const struct xt_table_info *t,
 		}
 		xt_info_wrunlock(cpu);
 	}
-	local_bh_enable();
+	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)

net/ipv4/netfilter/ipt_REJECT.c

@@ -95,10 +95,11 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 	}
 
 	tcph->rst	= 1;
-	tcph->check	= tcp_v4_check(sizeof(struct tcphdr),
-				       niph->saddr, niph->daddr,
-				       csum_partial(tcph,
-						    sizeof(struct tcphdr), 0));
+	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
+				    niph->daddr, 0);
+	nskb->ip_summed = CHECKSUM_PARTIAL;
+	nskb->csum_start = (unsigned char *)tcph - nskb->head;
+	nskb->csum_offset = offsetof(struct tcphdr, check);
 
 	addr_type = RTN_UNSPEC;
 	if (hook != NF_INET_FORWARD
@@ -115,7 +116,6 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 		goto free_nskb;
 
 	niph->ttl	= dst_metric(skb_dst(nskb), RTAX_HOPLIMIT);
-	nskb->ip_summed = CHECKSUM_NONE;
 
 	/* "Never happens" */
 	if (nskb->len > dst_mtu(skb_dst(nskb)))

net/ipv4/netfilter/nf_nat_core.c

@@ -261,14 +261,9 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	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);
-		goto out;
-	}
-
 	/* Only bother mapping if it's not already in range and unique */
-	if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
+	if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM) &&
+	    (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
 	     proto->in_range(tuple, maniptype, &range->min, &range->max)) &&
 	    !nf_nat_used_tuple(tuple, ct))
 		goto out;
@@ -440,7 +435,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
 	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
 		return 0;
 
-	inside = (void *)skb->data + ip_hdrlen(skb);
+	inside = (void *)skb->data + hdrlen;
 
 	/* We're actually going to mangle it beyond trivial checksum
 	   adjustment, so make sure the current checksum is correct. */
@@ -470,12 +465,10 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
 	/* rcu_read_lock()ed by nf_hook_slow */
 	l4proto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol);
 
-	if (!nf_ct_get_tuple(skb,
-			     ip_hdrlen(skb) + sizeof(struct icmphdr),
-			     (ip_hdrlen(skb) +
+	if (!nf_ct_get_tuple(skb, hdrlen + sizeof(struct icmphdr),
+			     (hdrlen +
 			      sizeof(struct icmphdr) + inside->ip.ihl * 4),
-			     (u_int16_t)AF_INET,
-			     inside->ip.protocol,
+			     (u_int16_t)AF_INET, inside->ip.protocol,
 			     &inner, l3proto, l4proto))
 		return 0;
 
@@ -484,15 +477,13 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
 	   pass all hooks (locally-generated ICMP).  Consider incoming
 	   packet: PREROUTING (DST manip), routing produces ICMP, goes
 	   through POSTROUTING (which must correct the DST manip). */
-	if (!manip_pkt(inside->ip.protocol, skb,
-		       ip_hdrlen(skb) + sizeof(inside->icmp),
-		       &ct->tuplehash[!dir].tuple,
-		       !manip))
+	if (!manip_pkt(inside->ip.protocol, skb, hdrlen + sizeof(inside->icmp),
+		       &ct->tuplehash[!dir].tuple, !manip))
 		return 0;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
 		/* Reloading "inside" here since manip_pkt inner. */
-		inside = (void *)skb->data + ip_hdrlen(skb);
+		inside = (void *)skb->data + hdrlen;
 		inside->icmp.checksum = 0;
 		inside->icmp.checksum =
 			csum_fold(skb_checksum(skb, hdrlen,

net/ipv4/netfilter/nf_nat_proto_common.c

@@ -34,7 +34,7 @@ bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
 }
 EXPORT_SYMBOL_GPL(nf_nat_proto_in_range);
 
-bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
+void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 			       const struct nf_nat_range *range,
 			       enum nf_nat_manip_type maniptype,
 			       const struct nf_conn *ct,
@@ -53,7 +53,7 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 	if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) {
 		/* If it's dst rewrite, can't change port */
 		if (maniptype == IP_NAT_MANIP_DST)
-			return false;
+			return;
 
 		if (ntohs(*portptr) < 1024) {
 			/* Loose convention: >> 512 is credential passing */
@@ -81,15 +81,15 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 	else
 		off = *rover;
 
-	for (i = 0; i < range_size; i++, off++) {
+	for (i = 0; ; ++off) {
 		*portptr = htons(min + off % range_size);
-		if (nf_nat_used_tuple(tuple, ct))
+		if (++i != range_size && nf_nat_used_tuple(tuple, ct))
 			continue;
 		if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM))
 			*rover = off;
-		return true;
+		return;
 	}
-	return false;
+	return;
 }
 EXPORT_SYMBOL_GPL(nf_nat_proto_unique_tuple);
 

net/ipv4/netfilter/nf_nat_proto_dccp.c

@@ -22,14 +22,14 @@
 
 static u_int16_t dccp_port_rover;
 
-static bool
+static void
 dccp_unique_tuple(struct nf_conntrack_tuple *tuple,
 		  const struct nf_nat_range *range,
 		  enum nf_nat_manip_type maniptype,
 		  const struct nf_conn *ct)
 {
-	return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
-					 &dccp_port_rover);
+	nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
+				  &dccp_port_rover);
 }
 
 static bool

net/ipv4/netfilter/nf_nat_proto_gre.c

@@ -37,7 +37,7 @@ MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
 MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
 
 /* generate unique tuple ... */
-static bool
+static void
 gre_unique_tuple(struct nf_conntrack_tuple *tuple,
 		 const struct nf_nat_range *range,
 		 enum nf_nat_manip_type maniptype,
@@ -50,7 +50,7 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
 	/* If there is no master conntrack we are not PPTP,
 	   do not change tuples */
 	if (!ct->master)
-		return false;
+		return;
 
 	if (maniptype == IP_NAT_MANIP_SRC)
 		keyptr = &tuple->src.u.gre.key;
@@ -68,14 +68,14 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
 
 	pr_debug("min = %u, range_size = %u\n", min, range_size);
 
-	for (i = 0; i < range_size; i++, key++) {
+	for (i = 0; ; ++key) {
 		*keyptr = htons(min + key % range_size);
-		if (!nf_nat_used_tuple(tuple, ct))
-			return true;
+		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
+			return;
 	}
 
 	pr_debug("%p: no NAT mapping\n", ct);
-	return false;
+	return;
 }
 
 /* manipulate a GRE packet according to maniptype */

net/ipv4/netfilter/nf_nat_proto_icmp.c

@@ -27,7 +27,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple,
 	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
 }
 
-static bool
+static void
 icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
 		  const struct nf_nat_range *range,
 		  enum nf_nat_manip_type maniptype,
@@ -42,13 +42,13 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
 	if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED))
 		range_size = 0xFFFF;
 
-	for (i = 0; i < range_size; i++, id++) {
+	for (i = 0; ; ++id) {
 		tuple->src.u.icmp.id = htons(ntohs(range->min.icmp.id) +
 					     (id % range_size));
-		if (!nf_nat_used_tuple(tuple, ct))
-			return true;
+		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
+			return;
 	}
-	return false;
+	return;
 }
 
 static bool

net/ipv4/netfilter/nf_nat_proto_sctp.c

@@ -16,14 +16,14 @@
 
 static u_int16_t nf_sctp_port_rover;
 
-static bool
+static void
 sctp_unique_tuple(struct nf_conntrack_tuple *tuple,
 		  const struct nf_nat_range *range,
 		  enum nf_nat_manip_type maniptype,
 		  const struct nf_conn *ct)
 {
-	return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
-					 &nf_sctp_port_rover);
+	nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
+				  &nf_sctp_port_rover);
 }
 
 static bool

net/ipv4/netfilter/nf_nat_proto_tcp.c

@@ -20,14 +20,13 @@
 
 static u_int16_t tcp_port_rover;
 
-static bool
+static void
 tcp_unique_tuple(struct nf_conntrack_tuple *tuple,
 		 const struct nf_nat_range *range,
 		 enum nf_nat_manip_type maniptype,
 		 const struct nf_conn *ct)
 {
-	return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
-					 &tcp_port_rover);
+	nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, &tcp_port_rover);
 }
 
 static bool