Merge changes from linux-2.6 by hand

10 files changed, 117 insertions, 34 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 1b5a09d1b90..1b18ce66e7b 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -5,6 +5,7 @@
 #include <net/esp.h>
 #include <asm/scatterlist.h>
 #include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/pfkeyv2.h>
 #include <linux/random.h>
 #include <net/icmp.h>
@@ -42,10 +43,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	esp = x->data;
 	alen = esp->auth.icv_trunc_len;
 	tfm = esp->conf.tfm;
-	blksize = (crypto_tfm_alg_blocksize(tfm) + 3) & ~3;
-	clen = (clen + 2 + blksize-1)&~(blksize-1);
+	blksize = ALIGN(crypto_tfm_alg_blocksize(tfm), 4);
+	clen = ALIGN(clen + 2, blksize);
 	if (esp->conf.padlen)
-		clen = (clen + esp->conf.padlen-1)&~(esp->conf.padlen-1);
+		clen = ALIGN(clen, esp->conf.padlen);
 
 	if ((nfrags = skb_cow_data(skb, clen-skb->len+alen, &trailer)) < 0)
 		goto error;
@@ -143,7 +144,7 @@ static int esp_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc
 	struct ip_esp_hdr *esph;
 	struct esp_data *esp = x->data;
 	struct sk_buff *trailer;
-	int blksize = crypto_tfm_alg_blocksize(esp->conf.tfm);
+	int blksize = ALIGN(crypto_tfm_alg_blocksize(esp->conf.tfm), 4);
 	int alen = esp->auth.icv_trunc_len;
 	int elen = skb->len - sizeof(struct ip_esp_hdr) - esp->conf.ivlen - alen;
 	int nfrags;
@@ -304,16 +305,16 @@ static int esp_post_input(struct xfrm_state *x, struct xfrm_decap_state *decap,
 static u32 esp4_get_max_size(struct xfrm_state *x, int mtu)
 {
 	struct esp_data *esp = x->data;
-	u32 blksize = crypto_tfm_alg_blocksize(esp->conf.tfm);
+	u32 blksize = ALIGN(crypto_tfm_alg_blocksize(esp->conf.tfm), 4);
 
 	if (x->props.mode) {
-		mtu = (mtu + 2 + blksize-1)&~(blksize-1);
+		mtu = ALIGN(mtu + 2, blksize);
 	} else {
 		/* The worst case. */
-		mtu += 2 + blksize;
+		mtu = ALIGN(mtu + 2, 4) + blksize - 4;
 	}
 	if (esp->conf.padlen)
-		mtu = (mtu + esp->conf.padlen-1)&~(esp->conf.padlen-1);
+		mtu = ALIGN(mtu, esp->conf.padlen);
 
 	return mtu + x->props.header_len + esp->auth.icv_trunc_len;
 }
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index f9076ef3a1a..a010e9a6881 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -111,6 +111,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
 		tw->tw_prot	    = sk->sk_prot_creator;
 		atomic_set(&tw->tw_refcnt, 1);
 		inet_twsk_dead_node_init(tw);
+		__module_get(tw->tw_prot->owner);
 	}
 
 	return tw;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index a7659728e7a..7d917e4ce1d 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -139,6 +139,7 @@ config IP_NF_AMANDA
 
 config IP_NF_PPTP
 	tristate  'PPTP protocol support'
+	depends on IP_NF_CONNTRACK
 	help
 	  This module adds support for PPTP (Point to Point Tunnelling
 	  Protocol, RFC2637) connection tracking and NAT. 
@@ -498,9 +499,14 @@ config IP_NF_TARGET_LOG
 	  To compile it as a module, choose M here.  If unsure, say N.
 
 config IP_NF_TARGET_ULOG
-	tristate "ULOG target support"
+	tristate "ULOG target support (OBSOLETE)"
 	depends on IP_NF_IPTABLES
 	---help---
+
+	  This option enables the old IPv4-only "ipt_ULOG" implementation
+	  which has been obsoleted by the new "nfnetlink_log" code (see
+	  CONFIG_NETFILTER_NETLINK_LOG).
+
 	  This option adds a `ULOG' target, which allows you to create rules in
 	  any iptables table. The packet is passed to a userspace logging
 	  daemon using netlink multicast sockets; unlike the LOG target
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index fa163425668..a7969286e6e 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -716,8 +716,10 @@ static int translate_table(const char *name,
 	}
 
 	/* And one copy for every other CPU */
-	for (i = 1; i < num_possible_cpus(); i++) {
-		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size)*i,
+	for_each_cpu(i) {
+		if (i == 0)
+			continue;
+		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i,
 		       newinfo->entries,
 		       SMP_ALIGN(newinfo->size));
 	}
@@ -767,7 +769,7 @@ static void get_counters(const struct arpt_table_info *t,
 	unsigned int cpu;
 	unsigned int i;
 
-	for (cpu = 0; cpu < num_possible_cpus(); cpu++) {
+	for_each_cpu(cpu) {
 		i = 0;
 		ARPT_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
 				   t->size,
@@ -885,7 +887,8 @@ static int do_replace(void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	newinfo = vmalloc(sizeof(struct arpt_table_info)
-			  + SMP_ALIGN(tmp.size) * num_possible_cpus());
+			  + SMP_ALIGN(tmp.size) *
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 
@@ -1158,7 +1161,8 @@ int arpt_register_table(struct arpt_table *table,
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 
 	newinfo = vmalloc(sizeof(struct arpt_table_info)
-			  + SMP_ALIGN(repl->size) * num_possible_cpus());
+			  + SMP_ALIGN(repl->size) *
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo) {
 		ret = -ENOMEM;
 		return ret;
diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c
index ea65dd3e517..07a80b56e8d 100644
--- a/net/ipv4/netfilter/ip_conntrack_core.c
+++ b/net/ipv4/netfilter/ip_conntrack_core.c
@@ -1119,7 +1119,7 @@ void __ip_ct_refresh_acct(struct ip_conntrack *ct,
 			unsigned long extra_jiffies,
 			int do_acct)
 {
-	int do_event = 0;
+	int event = 0;
 
 	IP_NF_ASSERT(ct->timeout.data == (unsigned long)ct);
 	IP_NF_ASSERT(skb);
@@ -1129,13 +1129,13 @@ void __ip_ct_refresh_acct(struct ip_conntrack *ct,
 	/* If not in hash table, timer will not be active yet */
 	if (!is_confirmed(ct)) {
 		ct->timeout.expires = extra_jiffies;
-		do_event = 1;
+		event = IPCT_REFRESH;
 	} else {
 		/* Need del_timer for race avoidance (may already be dying). */
 		if (del_timer(&ct->timeout)) {
 			ct->timeout.expires = jiffies + extra_jiffies;
 			add_timer(&ct->timeout);
-			do_event = 1;
+			event = IPCT_REFRESH;
 		}
 	}
 
@@ -1144,14 +1144,17 @@ void __ip_ct_refresh_acct(struct ip_conntrack *ct,
 		ct->counters[CTINFO2DIR(ctinfo)].packets++;
 		ct->counters[CTINFO2DIR(ctinfo)].bytes += 
 						ntohs(skb->nh.iph->tot_len);
+		if ((ct->counters[CTINFO2DIR(ctinfo)].packets & 0x80000000)
+		    || (ct->counters[CTINFO2DIR(ctinfo)].bytes & 0x80000000))
+			event |= IPCT_COUNTER_FILLING;
 	}
 #endif
 
 	write_unlock_bh(&ip_conntrack_lock);
 
 	/* must be unlocked when calling event cache */
-	if (do_event)
-		ip_conntrack_event_cache(IPCT_REFRESH, skb);
+	if (event)
+		ip_conntrack_event_cache(event, skb);
 }
 
 #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \
diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c
index b08a432efcf..166e6069f12 100644
--- a/net/ipv4/netfilter/ip_conntrack_netlink.c
+++ b/net/ipv4/netfilter/ip_conntrack_netlink.c
@@ -177,11 +177,11 @@ ctnetlink_dump_counters(struct sk_buff *skb, const struct ip_conntrack *ct,
 	struct nfattr *nest_count = NFA_NEST(skb, type);
 	u_int64_t tmp;
 
-	tmp = cpu_to_be64(ct->counters[dir].packets);
-	NFA_PUT(skb, CTA_COUNTERS_PACKETS, sizeof(u_int64_t), &tmp);
+	tmp = htonl(ct->counters[dir].packets);
+	NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(u_int32_t), &tmp);
 
-	tmp = cpu_to_be64(ct->counters[dir].bytes);
-	NFA_PUT(skb, CTA_COUNTERS_BYTES, sizeof(u_int64_t), &tmp);
+	tmp = htonl(ct->counters[dir].bytes);
+	NFA_PUT(skb, CTA_COUNTERS32_BYTES, sizeof(u_int32_t), &tmp);
 
 	NFA_NEST_END(skb, nest_count);
 
@@ -833,7 +833,8 @@ out:
 static inline int
 ctnetlink_change_status(struct ip_conntrack *ct, struct nfattr *cda[])
 {
-	unsigned long d, status = *(u_int32_t *)NFA_DATA(cda[CTA_STATUS-1]);
+	unsigned long d;
+	unsigned status = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_STATUS-1]));
 	d = ct->status ^ status;
 
 	if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING))
@@ -948,6 +949,31 @@ ctnetlink_change_timeout(struct ip_conntrack *ct, struct nfattr *cda[])
 	return 0;
 }
 
+static inline int
+ctnetlink_change_protoinfo(struct ip_conntrack *ct, struct nfattr *cda[])
+{
+	struct nfattr *tb[CTA_PROTOINFO_MAX], *attr = cda[CTA_PROTOINFO-1];
+	struct ip_conntrack_protocol *proto;
+	u_int16_t npt = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
+	int err = 0;
+
+	if (nfattr_parse_nested(tb, CTA_PROTOINFO_MAX, attr) < 0)
+		goto nfattr_failure;
+
+	proto = ip_conntrack_proto_find_get(npt);
+	if (!proto)
+		return -EINVAL;
+
+	if (proto->from_nfattr)
+		err = proto->from_nfattr(tb, ct);
+	ip_conntrack_proto_put(proto); 
+
+	return err;
+
+nfattr_failure:
+	return -ENOMEM;
+}
+
 static int
 ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[])
 {
@@ -973,6 +999,12 @@ ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[])
 			return err;
 	}
 
+	if (cda[CTA_PROTOINFO-1]) {
+		err = ctnetlink_change_protoinfo(ct, cda);
+		if (err < 0)
+			return err;
+	}
+
 	DEBUGP("all done\n");
 	return 0;
 }
@@ -1002,6 +1034,12 @@ ctnetlink_create_conntrack(struct nfattr *cda[],
 	if (err < 0)
 		goto err;
 
+	if (cda[CTA_PROTOINFO-1]) {
+		err = ctnetlink_change_protoinfo(ct, cda);
+		if (err < 0)
+			return err;
+	}
+
 	ct->helper = ip_conntrack_helper_find_get(rtuple);
 
 	add_timer(&ct->timeout);
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c
index 838d1d69b36..98f0015dd25 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c
@@ -296,8 +296,7 @@ static int icmp_nfattr_to_tuple(struct nfattr *tb[],
 				struct ip_conntrack_tuple *tuple)
 {
 	if (!tb[CTA_PROTO_ICMP_TYPE-1]
-	    || !tb[CTA_PROTO_ICMP_CODE-1]
-	    || !tb[CTA_PROTO_ICMP_ID-1])
+	    || !tb[CTA_PROTO_ICMP_CODE-1])
 		return -1;
 
 	tuple->dst.u.icmp.type = 
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
index 121760d6cc5..d6701cafbcc 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
@@ -341,17 +341,43 @@ static int tcp_print_conntrack(struct seq_file *s,
 static int tcp_to_nfattr(struct sk_buff *skb, struct nfattr *nfa,
 			 const struct ip_conntrack *ct)
 {
+	struct nfattr *nest_parms = NFA_NEST(skb, CTA_PROTOINFO_TCP);
+	
 	read_lock_bh(&tcp_lock);
 	NFA_PUT(skb, CTA_PROTOINFO_TCP_STATE, sizeof(u_int8_t),
 		&ct->proto.tcp.state);
 	read_unlock_bh(&tcp_lock);
 
+	NFA_NEST_END(skb, nest_parms);
+
 	return 0;
 
 nfattr_failure:
 	read_unlock_bh(&tcp_lock);
 	return -1;
 }
+
+static int nfattr_to_tcp(struct nfattr *cda[], struct ip_conntrack *ct)
+{
+	struct nfattr *attr = cda[CTA_PROTOINFO_TCP-1];
+	struct nfattr *tb[CTA_PROTOINFO_TCP_MAX];
+
+        if (nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr) < 0)
+                goto nfattr_failure;
+
+	if (!tb[CTA_PROTOINFO_TCP_STATE-1])
+		return -EINVAL;
+
+	write_lock_bh(&tcp_lock);
+	ct->proto.tcp.state = 
+		*(u_int8_t *)NFA_DATA(tb[CTA_PROTOINFO_TCP_STATE-1]);
+	write_unlock_bh(&tcp_lock);
+
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
 #endif
 
 static unsigned int get_conntrack_index(const struct tcphdr *tcph)
@@ -1123,6 +1149,7 @@ struct ip_conntrack_protocol ip_conntrack_protocol_tcp =
 #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \
     defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE)
 	.to_nfattr		= tcp_to_nfattr,
+	.from_nfattr		= nfattr_to_tcp,
 	.tuple_to_nfattr	= ip_ct_port_tuple_to_nfattr,
 	.nfattr_to_tuple	= ip_ct_port_nfattr_to_tuple,
 #endif
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index eef99a1b5de..75c27e92f6a 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -27,6 +27,7 @@
 #include <asm/semaphore.h>
 #include <linux/proc_fs.h>
 #include <linux/err.h>
+#include <linux/cpumask.h>
 
 #include <linux/netfilter_ipv4/ip_tables.h>
 
@@ -921,8 +922,10 @@ translate_table(const char *name,
 	}
 
 	/* And one copy for every other CPU */
-	for (i = 1; i < num_possible_cpus(); i++) {
-		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size)*i,
+	for_each_cpu(i) {
+		if (i == 0)
+			continue;
+		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i,
 		       newinfo->entries,
 		       SMP_ALIGN(newinfo->size));
 	}
@@ -943,7 +946,7 @@ replace_table(struct ipt_table *table,
 		struct ipt_entry *table_base;
 		unsigned int i;
 
-		for (i = 0; i < num_possible_cpus(); i++) {
+		for_each_cpu(i) {
 			table_base =
 				(void *)newinfo->entries
 				+ TABLE_OFFSET(newinfo, i);
@@ -990,7 +993,7 @@ get_counters(const struct ipt_table_info *t,
 	unsigned int cpu;
 	unsigned int i;
 
-	for (cpu = 0; cpu < num_possible_cpus(); cpu++) {
+	for_each_cpu(cpu) {
 		i = 0;
 		IPT_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
 				  t->size,
@@ -1128,7 +1131,8 @@ do_replace(void __user *user, unsigned int len)
 		return -ENOMEM;
 
 	newinfo = vmalloc(sizeof(struct ipt_table_info)
-			  + SMP_ALIGN(tmp.size) * num_possible_cpus());
+			  + SMP_ALIGN(tmp.size) * 
+			  	(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 
@@ -1458,7 +1462,8 @@ int ipt_register_table(struct ipt_table *table, const struct ipt_replace *repl)
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 
 	newinfo = vmalloc(sizeof(struct ipt_table_info)
-			  + SMP_ALIGN(repl->size) * num_possible_cpus());
+			  + SMP_ALIGN(repl->size) * 
+			  		(highest_possible_processor_id()+1));
 	if (!newinfo)
 		return -ENOMEM;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8225e425725..b907456a79f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -435,8 +435,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
 	int nsize, old_factor;
 	u16 flags;
 
-	BUG_ON(len >= skb->len);
-
+	BUG_ON(len > skb->len);
 	nsize = skb_headlen(skb) - len;
 	if (nsize < 0)
 		nsize = 0;