Merge tag 'ipvs-for-v4.7' of https://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next

Simon Horman says:

====================
IPVS Updates for v4.7

please consider these enhancements to the IPVS. They allow SIP connections
originating from real-servers to be load balanced by the SIP psersitence
engine as is already implemented in the other direction. And for better one
packet scheduling (OPS) performance.
====================
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/net/ip_vs.h

@@ -731,6 +731,12 @@ struct ip_vs_pe {
 	u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval,
 			   bool inverse);
 	int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
+	/* create connections for real-server outgoing packets */
+	struct ip_vs_conn* (*conn_out)(struct ip_vs_service *svc,
+				       struct ip_vs_dest *dest,
+				       struct sk_buff *skb,
+				       const struct ip_vs_iphdr *iph,
+				       __be16 dport, __be16 cport);
 };
 
 /* The application module object (a.k.a. app incarnation) */
@@ -874,6 +880,7 @@ struct netns_ipvs {
 	/* Service counters */
 	atomic_t		ftpsvc_counter;
 	atomic_t		nullsvc_counter;
+	atomic_t		conn_out_counter;
 
 #ifdef CONFIG_SYSCTL
 	/* 1/rate drop and drop-entry variables */
@@ -1147,6 +1154,12 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs)
  */
 const char *ip_vs_proto_name(unsigned int proto);
 void ip_vs_init_hash_table(struct list_head *table, int rows);
+struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
+				      struct ip_vs_dest *dest,
+				      struct sk_buff *skb,
+				      const struct ip_vs_iphdr *iph,
+				      __be16 dport,
+				      __be16 cport);
 #define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table((t), ARRAY_SIZE((t)))
 
 #define IP_VS_APP_TYPE_FTP	1
@@ -1378,6 +1391,10 @@ ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol
 bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
 			    const union nf_inet_addr *daddr, __be16 dport);
 
+struct ip_vs_dest *
+ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
+			const union nf_inet_addr *daddr, __be16 dport);
+
 int ip_vs_use_count_inc(void);
 void ip_vs_use_count_dec(void);
 int ip_vs_register_nl_ioctl(void);

net/netfilter/ipvs/ip_vs_conn.c

@@ -104,6 +104,7 @@ static inline void ct_write_unlock_bh(unsigned int key)
 	spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
 }
 
+static void ip_vs_conn_expire(unsigned long data);
 
 /*
  *	Returns hash value for IPVS connection entry
@@ -453,10 +454,16 @@ ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
 }
 EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
 
+static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp)
+{
+	__ip_vs_conn_put(cp);
+	ip_vs_conn_expire((unsigned long)cp);
+}
+
 /*
  *      Put back the conn and restart its timer with its timeout
  */
-void ip_vs_conn_put(struct ip_vs_conn *cp)
+static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp)
 {
 	unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ?
 		0 : cp->timeout;
@@ -465,6 +472,16 @@ void ip_vs_conn_put(struct ip_vs_conn *cp)
 	__ip_vs_conn_put(cp);
 }
 
+void ip_vs_conn_put(struct ip_vs_conn *cp)
+{
+	if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) &&
+	    (atomic_read(&cp->refcnt) == 1) &&
+	    !timer_pending(&cp->timer))
+		/* expire connection immediately */
+		__ip_vs_conn_put_notimer(cp);
+	else
+		__ip_vs_conn_put_timer(cp);
+}
 
 /*
  *	Fill a no_client_port connection with a client port number
@@ -819,7 +836,8 @@ static void ip_vs_conn_expire(unsigned long data)
 		if (cp->control)
 			ip_vs_control_del(cp);
 
-		if (cp->flags & IP_VS_CONN_F_NFCT) {
+		if ((cp->flags & IP_VS_CONN_F_NFCT) &&
+		    !(cp->flags & IP_VS_CONN_F_ONE_PACKET)) {
 			/* Do not access conntracks during subsys cleanup
 			 * because nf_conntrack_find_get can not be used after
 			 * conntrack cleanup for the net.
@@ -834,6 +852,9 @@ static void ip_vs_conn_expire(unsigned long data)
 		ip_vs_unbind_dest(cp);
 		if (cp->flags & IP_VS_CONN_F_NO_CPORT)
 			atomic_dec(&ip_vs_conn_no_cport_cnt);
+		if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+			ip_vs_conn_rcu_free(&cp->rcu_head);
+		else
 			call_rcu(&cp->rcu_head, ip_vs_conn_rcu_free);
 		atomic_dec(&ipvs->conn_count);
 		return;
@@ -850,7 +871,7 @@ static void ip_vs_conn_expire(unsigned long data)
 	if (ipvs->sync_state & IP_VS_STATE_MASTER)
 		ip_vs_sync_conn(ipvs, cp, sysctl_sync_threshold(ipvs));
 
-	ip_vs_conn_put(cp);
+	__ip_vs_conn_put_timer(cp);
 }
 
 /* Modify timer, so that it expires as soon as possible.

net/netfilter/ipvs/ip_vs_core.c

@@ -68,6 +68,7 @@ EXPORT_SYMBOL(ip_vs_conn_put);
 #ifdef CONFIG_IP_VS_DEBUG
 EXPORT_SYMBOL(ip_vs_get_debug_level);
 #endif
+EXPORT_SYMBOL(ip_vs_new_conn_out);
 
 static int ip_vs_net_id __read_mostly;
 /* netns cnt used for uniqueness */
@@ -1100,6 +1101,143 @@ static inline bool is_new_conn_expected(const struct ip_vs_conn *cp,
 	}
 }
 
+/* Generic function to create new connections for outgoing RS packets
+ *
+ * Pre-requisites for successful connection creation:
+ * 1) Virtual Service is NOT fwmark based:
+ *    In fwmark-VS actual vaddr and vport are unknown to IPVS
+ * 2) Real Server and Virtual Service were NOT configured without port:
+ *    This is to allow match of different VS to the same RS ip-addr
+ */
+struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
+				      struct ip_vs_dest *dest,
+				      struct sk_buff *skb,
+				      const struct ip_vs_iphdr *iph,
+				      __be16 dport,
+				      __be16 cport)
+{
+	struct ip_vs_conn_param param;
+	struct ip_vs_conn *ct = NULL, *cp = NULL;
+	const union nf_inet_addr *vaddr, *daddr, *caddr;
+	union nf_inet_addr snet;
+	__be16 vport;
+	unsigned int flags;
+
+	EnterFunction(12);
+	vaddr = &svc->addr;
+	vport = svc->port;
+	daddr = &iph->saddr;
+	caddr = &iph->daddr;
+
+	/* check pre-requisites are satisfied */
+	if (svc->fwmark)
+		return NULL;
+	if (!vport || !dport)
+		return NULL;
+
+	/* for persistent service first create connection template */
+	if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
+		/* apply netmask the same way ingress-side does */
+#ifdef CONFIG_IP_VS_IPV6
+		if (svc->af == AF_INET6)
+			ipv6_addr_prefix(&snet.in6, &caddr->in6,
+					 (__force __u32)svc->netmask);
+		else
+#endif
+			snet.ip = caddr->ip & svc->netmask;
+		/* fill params and create template if not existent */
+		if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol,
+						  &snet, 0, vaddr,
+						  vport, &param) < 0)
+			return NULL;
+		ct = ip_vs_ct_in_get(&param);
+		if (!ct) {
+			ct = ip_vs_conn_new(&param, dest->af, daddr, dport,
+					    IP_VS_CONN_F_TEMPLATE, dest, 0);
+			if (!ct) {
+				kfree(param.pe_data);
+				return NULL;
+			}
+			ct->timeout = svc->timeout;
+		} else {
+			kfree(param.pe_data);
+		}
+	}
+
+	/* connection flags */
+	flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) &&
+		 iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0;
+	/* create connection */
+	ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
+			      caddr, cport, vaddr, vport, &param);
+	cp = ip_vs_conn_new(&param, dest->af, daddr, dport, flags, dest, 0);
+	if (!cp) {
+		if (ct)
+			ip_vs_conn_put(ct);
+		return NULL;
+	}
+	if (ct) {
+		ip_vs_control_add(cp, ct);
+		ip_vs_conn_put(ct);
+	}
+	ip_vs_conn_stats(cp, svc);
+
+	/* return connection (will be used to handle outgoing packet) */
+	IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u "
+		      "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
+		      ip_vs_fwd_tag(cp),
+		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
+		      cp->flags, atomic_read(&cp->refcnt));
+	LeaveFunction(12);
+	return cp;
+}
+
+/* Handle outgoing packets which are considered requests initiated by
+ * real servers, so that subsequent responses from external client can be
+ * routed to the right real server.
+ * Used also for outgoing responses in OPS mode.
+ *
+ * Connection management is handled by persistent-engine specific callback.
+ */
+static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum,
+					      struct netns_ipvs *ipvs,
+					      int af, struct sk_buff *skb,
+					      const struct ip_vs_iphdr *iph)
+{
+	struct ip_vs_dest *dest;
+	struct ip_vs_conn *cp = NULL;
+	__be16 _ports[2], *pptr;
+
+	if (hooknum == NF_INET_LOCAL_IN)
+		return NULL;
+
+	pptr = frag_safe_skb_hp(skb, iph->len,
+				sizeof(_ports), _ports, iph);
+	if (!pptr)
+		return NULL;
+
+	rcu_read_lock();
+	dest = ip_vs_find_real_service(ipvs, af, iph->protocol,
+				       &iph->saddr, pptr[0]);
+	if (dest) {
+		struct ip_vs_service *svc;
+		struct ip_vs_pe *pe;
+
+		svc = rcu_dereference(dest->svc);
+		if (svc) {
+			pe = rcu_dereference(svc->pe);
+			if (pe && pe->conn_out)
+				cp = pe->conn_out(svc, dest, skb, iph,
+						  pptr[0], pptr[1]);
+		}
+	}
+	rcu_read_unlock();
+
+	return cp;
+}
+
 /* Handle response packets: rewrite addresses and send away...
  */
 static unsigned int
@@ -1245,6 +1383,22 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 
 	if (likely(cp))
 		return handle_response(af, skb, pd, cp, &iph, hooknum);
+
+	/* Check for real-server-started requests */
+	if (atomic_read(&ipvs->conn_out_counter)) {
+		/* Currently only for UDP:
+		 * connection oriented protocols typically use
+		 * ephemeral ports for outgoing connections, so
+		 * related incoming responses would not match any VS
+		 */
+		if (pp->protocol == IPPROTO_UDP) {
+			cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph);
+			if (likely(cp))
+				return handle_response(af, skb, pd, cp, &iph,
+						       hooknum);
+		}
+	}
+
 	if (sysctl_nat_icmp_send(ipvs) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||

net/netfilter/ipvs/ip_vs_ctl.c

@@ -567,6 +567,36 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
 	return false;
 }
 
+/* Find real service record by <proto,addr,port>.
+ * In case of multiple records with the same <proto,addr,port>, only
+ * the first found record is returned.
+ *
+ * To be called under RCU lock.
+ */
+struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af,
+					   __u16 protocol,
+					   const union nf_inet_addr *daddr,
+					   __be16 dport)
+{
+	unsigned int hash;
+	struct ip_vs_dest *dest;
+
+	/* Check for "full" addressed entries */
+	hash = ip_vs_rs_hashkey(af, daddr, dport);
+
+	hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
+		if (dest->port == dport &&
+		    dest->af == af &&
+		    ip_vs_addr_equal(af, &dest->addr, daddr) &&
+			(dest->protocol == protocol || dest->vfwmark)) {
+			/* HIT */
+			return dest;
+		}
+	}
+
+	return NULL;
+}
+
 /* Lookup destination by {addr,port} in the given service
  * Called under RCU lock.
  */
@@ -1253,6 +1283,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 		atomic_inc(&ipvs->ftpsvc_counter);
 	else if (svc->port == 0)
 		atomic_inc(&ipvs->nullsvc_counter);
+	if (svc->pe && svc->pe->conn_out)
+		atomic_inc(&ipvs->conn_out_counter);
 
 	ip_vs_start_estimator(ipvs, &svc->stats);
 
@@ -1293,6 +1325,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	struct ip_vs_scheduler *sched = NULL, *old_sched;
 	struct ip_vs_pe *pe = NULL, *old_pe = NULL;
 	int ret = 0;
+	bool new_pe_conn_out, old_pe_conn_out;
 
 	/*
 	 * Lookup the scheduler, by 'u->sched_name'
@@ -1355,8 +1388,16 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	svc->netmask = u->netmask;
 
 	old_pe = rcu_dereference_protected(svc->pe, 1);
-	if (pe != old_pe)
+	if (pe != old_pe) {
 		rcu_assign_pointer(svc->pe, pe);
+		/* check for optional methods in new pe */
+		new_pe_conn_out = (pe && pe->conn_out) ? true : false;
+		old_pe_conn_out = (old_pe && old_pe->conn_out) ? true : false;
+		if (new_pe_conn_out && !old_pe_conn_out)
+			atomic_inc(&svc->ipvs->conn_out_counter);
+		if (old_pe_conn_out && !new_pe_conn_out)
+			atomic_dec(&svc->ipvs->conn_out_counter);
+	}
 
 out:
 	ip_vs_scheduler_put(old_sched);
@@ -1389,6 +1430,8 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
 
 	/* Unbind persistence engine, keep svc->pe */
 	old_pe = rcu_dereference_protected(svc->pe, 1);
+	if (old_pe && old_pe->conn_out)
+		atomic_dec(&ipvs->conn_out_counter);
 	ip_vs_pe_put(old_pe);
 
 	/*
@@ -3957,6 +4000,7 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 		    (unsigned long) ipvs);
 	atomic_set(&ipvs->ftpsvc_counter, 0);
 	atomic_set(&ipvs->nullsvc_counter, 0);
+	atomic_set(&ipvs->conn_out_counter, 0);
 
 	/* procfs stats */
 	ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);

net/netfilter/ipvs/ip_vs_nfct.c

@@ -93,6 +93,10 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
 		return;
 
+	/* Never alter conntrack for OPS conns (no reply is expected) */
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		return;
+
 	/* Alter reply only in original direction */
 	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
 		return;

net/netfilter/ipvs/ip_vs_pe_sip.c

@@ -143,6 +143,20 @@ static int ip_vs_sip_show_pe_data(const struct ip_vs_conn *cp, char *buf)
 	return cp->pe_data_len;
 }
 
+static struct ip_vs_conn *
+ip_vs_sip_conn_out(struct ip_vs_service *svc,
+		   struct ip_vs_dest *dest,
+		   struct sk_buff *skb,
+		   const struct ip_vs_iphdr *iph,
+		   __be16 dport,
+		   __be16 cport)
+{
+	if (likely(iph->protocol == IPPROTO_UDP))
+		return ip_vs_new_conn_out(svc, dest, skb, iph, dport, cport);
+	/* currently no need to handle other than UDP */
+	return NULL;
+}
+
 static struct ip_vs_pe ip_vs_sip_pe =
 {
 	.name =			"sip",
@@ -153,6 +167,7 @@ static struct ip_vs_pe ip_vs_sip_pe =
 	.ct_match =		ip_vs_sip_ct_match,
 	.hashkey_raw =		ip_vs_sip_hashkey_raw,
 	.show_pe_data =		ip_vs_sip_show_pe_data,
+	.conn_out =		ip_vs_sip_conn_out,
 };
 
 static int __init ip_vs_sip_init(void)