Merge branch 'for-patrick' of git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6

include/net/ip_vs.h

@@ -422,6 +422,7 @@ struct ip_vs_conn {
 	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
 	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
 
+	const struct ip_vs_pe	*pe;
 	char			*pe_data;
 	__u8			pe_data_len;
 };
@@ -814,8 +815,19 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
 void ip_vs_unbind_pe(struct ip_vs_service *svc);
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
-extern struct ip_vs_pe *ip_vs_pe_get(const char *name);
-extern void ip_vs_pe_put(struct ip_vs_pe *pe);
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
+
+static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		__module_get(pe->module);
+}
+
+static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		module_put(pe->module);
+}
 
 /*
  *	IPVS protocol functions (from ip_vs_proto.c)
@@ -904,7 +916,7 @@ extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(const struct ip_vs_conn *cp);
 
 
 /*

net/netfilter/ipvs/ip_vs_conn.c

@@ -48,18 +48,18 @@
 /*
  * Connection hash size. Default is what was selected at compile time.
 */
-int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
+static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
 module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444);
 MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size");
 
 /* size and mask values */
-int ip_vs_conn_tab_size;
-int ip_vs_conn_tab_mask;
+int ip_vs_conn_tab_size __read_mostly;
+static int ip_vs_conn_tab_mask __read_mostly;
 
 /*
  *  Connection hash table: for input and output packets lookups of IPVS
  */
-static struct list_head *ip_vs_conn_tab;
+static struct list_head *ip_vs_conn_tab __read_mostly;
 
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
@@ -71,7 +71,7 @@ static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);
 static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);
 
 /* random value for IPVS connection hash */
-static unsigned int ip_vs_conn_rnd;
+static unsigned int ip_vs_conn_rnd __read_mostly;
 
 /*
  *  Fine locking granularity for big connection hash table
@@ -176,8 +176,8 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 	ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
 			      NULL, 0, &p);
 
-	if (cp->dest && cp->dest->svc->pe) {
-		p.pe = cp->dest->svc->pe;
+	if (cp->pe) {
+		p.pe = cp->pe;
 		p.pe_data = cp->pe_data;
 		p.pe_data_len = cp->pe_data_len;
 	}
@@ -354,7 +354,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (p->pe_data && p->pe->ct_match) {
-			if (p->pe->ct_match(p, cp))
+			if (p->pe == cp->pe && p->pe->ct_match(p, cp))
 				goto out;
 			continue;
 		}
@@ -765,6 +765,7 @@ static void ip_vs_conn_expire(unsigned long data)
 		if (cp->flags & IP_VS_CONN_F_NFCT)
 			ip_vs_conn_drop_conntrack(cp);
 
+		ip_vs_pe_put(cp->pe);
 		kfree(cp->pe_data);
 		if (unlikely(cp->app != NULL))
 			ip_vs_unbind_app(cp);
@@ -826,7 +827,9 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 			&cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
-	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) {
+	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) {
+		ip_vs_pe_get(p->pe);
+		cp->pe = p->pe;
 		cp->pe_data = p->pe_data;
 		cp->pe_data_len = p->pe_data_len;
 	}
@@ -958,15 +961,13 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
 
-		if (cp->dest && cp->pe_data &&
-		    cp->dest->svc->pe->show_pe_data) {
+		if (cp->pe_data) {
 			pe_data[0] = ' ';
-			len = strlen(cp->dest->svc->pe->name);
-			memcpy(pe_data + 1, cp->dest->svc->pe->name, len);
+			len = strlen(cp->pe->name);
+			memcpy(pe_data + 1, cp->pe->name, len);
 			pe_data[len + 1] = ' ';
 			len += 2;
-			len += cp->dest->svc->pe->show_pe_data(cp,
-							       pe_data + len);
+			len += cp->pe->show_pe_data(cp, pe_data + len);
 		}
 		pe_data[len] = '\0';
 

net/netfilter/ipvs/ip_vs_ctl.c

@@ -1139,7 +1139,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u,
 	}
 
 	if (u->pe_name && *u->pe_name) {
-		pe = ip_vs_pe_get(u->pe_name);
+		pe = ip_vs_pe_getbyname(u->pe_name);
 		if (pe == NULL) {
 			pr_info("persistence engine module ip_vs_pe_%s "
 				"not found\n", u->pe_name);
@@ -1250,7 +1250,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	old_sched = sched;
 
 	if (u->pe_name && *u->pe_name) {
-		pe = ip_vs_pe_get(u->pe_name);
+		pe = ip_vs_pe_getbyname(u->pe_name);
 		if (pe == NULL) {
 			pr_info("persistence engine module ip_vs_pe_%s "
 				"not found\n", u->pe_name);

net/netfilter/ipvs/ip_vs_pe.c

@@ -30,7 +30,7 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc)
 
 /* Get pe in the pe list by name */
 static struct ip_vs_pe *
-ip_vs_pe_getbyname(const char *pe_name)
+__ip_vs_pe_getbyname(const char *pe_name)
 {
 	struct ip_vs_pe *pe;
 
@@ -60,28 +60,22 @@ ip_vs_pe_getbyname(const char *pe_name)
 }
 
 /* Lookup pe and try to load it if it doesn't exist */
-struct ip_vs_pe *ip_vs_pe_get(const char *name)
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name)
 {
 	struct ip_vs_pe *pe;
 
 	/* Search for the pe by name */
-	pe = ip_vs_pe_getbyname(name);
+	pe = __ip_vs_pe_getbyname(name);
 
 	/* If pe not found, load the module and search again */
 	if (!pe) {
 		request_module("ip_vs_pe_%s", name);
-		pe = ip_vs_pe_getbyname(name);
+		pe = __ip_vs_pe_getbyname(name);
 	}
 
 	return pe;
 }
 
-void ip_vs_pe_put(struct ip_vs_pe *pe)
-{
-	if (pe && pe->module)
-		module_put(pe->module);
-}
-
 /* Register a pe in the pe list */
 int register_ip_vs_pe(struct ip_vs_pe *pe)
 {

net/netfilter/ipvs/ip_vs_sync.c

@@ -236,7 +236,7 @@ get_curr_sync_buff(unsigned long time)
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
  */
-void ip_vs_sync_conn(struct ip_vs_conn *cp)
+void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_sync_mesg *m;
 	struct ip_vs_sync_conn *s;
@@ -303,7 +303,7 @@ ip_vs_conn_fill_param_sync(int af, int protocol,
  *      Process received multicast message and create the corresponding
  *      ip_vs_conn entries.
  */
-static void ip_vs_process_message(const char *buffer, const size_t buflen)
+static void ip_vs_process_message(char *buffer, const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
 	struct ip_vs_sync_conn *s;
@@ -381,20 +381,18 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
 			}
 		}
 
-		{
-			if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
-					      (union nf_inet_addr *)&s->caddr,
-					      s->cport,
-					      (union nf_inet_addr *)&s->vaddr,
-					      s->vport, &param)) {
-				pr_err("ip_vs_conn_fill_param_sync failed");
-				return;
-			}
-			if (!(flags & IP_VS_CONN_F_TEMPLATE))
-				cp = ip_vs_conn_in_get(&param);
-			else
-				cp = ip_vs_ct_in_get(&param);
+		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
+					       (union nf_inet_addr *)&s->caddr,
+					       s->cport,
+					       (union nf_inet_addr *)&s->vaddr,
+					       s->vport, &param)) {
+			pr_err("ip_vs_conn_fill_param_sync failed");
+			return;
 		}
+		if (!(flags & IP_VS_CONN_F_TEMPLATE))
+			cp = ip_vs_conn_in_get(&param);
+		else
+			cp = ip_vs_ct_in_get(&param);
 		if (!cp) {
 			/*
 			 * Find the appropriate destination for the connection.

net/netfilter/ipvs/ip_vs_xmit.c

@@ -188,7 +188,6 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 			},
 			.mark = skb->mark,
 		};
-		struct rtable *rt;
 
 		if (ip_route_output_key(net, &rt, &fl))
 			return 0;
@@ -408,7 +407,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
+	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
+	    !skb_is_gso(skb)) {
 		ip_rt_put(rt);
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -461,7 +461,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -561,7 +561,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
+	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
+	    !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
 				 "ip_vs_nat_xmit(): frag needed for");
@@ -676,7 +677,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -791,8 +792,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	df |= (old_iph->frag_off & htons(IP_DF));
 
-	if ((old_iph->frag_off & htons(IP_DF))
-	    && mtu < ntohs(old_iph->tot_len)) {
+	if ((old_iph->frag_off & htons(IP_DF) &&
+	    mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
@@ -904,7 +905,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (skb_dst(skb))
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
 
-	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) {
+	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
+	    !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -1009,7 +1011,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
+	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu &&
+	    !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		ip_rt_put(rt);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -1176,7 +1179,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) {
+	if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
+	    !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
@@ -1290,7 +1294,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);