IPVS: netns to services part 1

Services hash tables got netns ptr a hash arg,
While Real Servers (rs) has been moved to ipvs struct.
Two new inline functions added to get net ptr from skb.

Since ip_vs is called from different contexts there is two
places to dig for the net ptr skb->dev or skb->sk
this is handled in skb_net() and skb_sknet()

Global functions, ip_vs_service_get() ip_vs_lookup_real_service()
etc have got  struct net *net as first param.
If possible get net ptr skb etc,
 - if not &init_net is used at this early stage of patching.

ip_vs_ctl.c  procfs not ready for netns yet.

*v3
 Comments by Julian
- __ip_vs_service_find and __ip_vs_svc_fwm_find are fast path,
  net_eq(svc->net, net) so the check is at the end now.
- net = skb_net(skb) in ip_vs_out moved after check for skb_dst.
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

include/net/ip_vs.h

@@ -37,6 +37,59 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
 {
 	return net->ipvs;
 }
+/*
+ * Get net ptr from skb in traffic cases
+ * use skb_sknet when call is from userland (ioctl or netlink)
+ */
+static inline struct net *skb_net(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/*
+	 * This is used for debug only.
+	 * Start with the most likely hit
+	 * End with BUG
+	 */
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	if (skb_dst(skb)->dev)
+		return dev_net(skb_dst(skb)->dev);
+	WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
+		      __func__, __LINE__);
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return dev_net(skb->dev ? : skb_dst(skb)->dev);
+#endif
+#else
+	return &init_net;
+#endif
+}
+
+static inline struct net *skb_sknet(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/* Start with the most likely hit */
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n",
+		       __func__, __LINE__);
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return sock_net(skb->sk);
+#endif
+#else
+	return &init_net;
+#endif
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -496,6 +549,7 @@ struct ip_vs_service {
 	unsigned		flags;	  /* service status flags */
 	unsigned		timeout;  /* persistent timeout in ticks */
 	__be32			netmask;  /* grouping granularity */
+	struct net		*net;
 
 	struct list_head	destinations;  /* real server d-linked list */
 	__u32			num_dests;     /* number of servers */
@@ -896,7 +950,7 @@ extern int sysctl_ip_vs_sync_ver;
 
 extern void ip_vs_sync_switch_mode(int mode);
 extern struct ip_vs_service *
-ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
 
 static inline void ip_vs_service_put(struct ip_vs_service *svc)
@@ -905,7 +959,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc)
 }
 
 extern struct ip_vs_dest *
-ip_vs_lookup_real_service(int af, __u16 protocol,
+ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 			  const union nf_inet_addr *daddr, __be16 dport);
 
 extern int ip_vs_use_count_inc(void);
@@ -913,9 +967,9 @@ extern void ip_vs_use_count_dec(void);
 extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
 extern struct ip_vs_dest *
-ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
-		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol,
-		__u32 fwmark);
+ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
+		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
+		__u16 protocol, __u32 fwmark);
 extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 

include/net/netns/ip_vs.h

@@ -20,6 +20,14 @@ struct ctl_table_header;
 
 struct netns_ipvs {
 	int			gen;		/* Generation */
+	/*
+	 *	Hash table: for real service lookups
+	 */
+	#define IP_VS_RTAB_BITS 4
+	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
+	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
+
+	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 };
 
 #endif /* IP_VS_H_ */

net/netfilter/ipvs/ip_vs_conn.c

@@ -611,7 +611,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	if ((cp) && (!cp->dest)) {
-		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
+		dest = ip_vs_find_dest(&init_net, cp->af, &cp->daddr, cp->dport,
 				       &cp->vaddr, cp->vport,
 				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);

net/netfilter/ipvs/ip_vs_core.c

@@ -1031,6 +1031,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 static unsigned int
 ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_conn *cp;
@@ -1054,6 +1055,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (unlikely(!skb_dst(skb)))
 		return NF_ACCEPT;
 
+	net = skb_net(skb);
 	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
@@ -1119,7 +1121,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 					  sizeof(_ports), _ports);
 		if (pptr == NULL)
 			return NF_ACCEPT;	/* Not for me */
-		if (ip_vs_lookup_real_service(af, iph.protocol,
+		if (ip_vs_lookup_real_service(net, af, iph.protocol,
 					      &iph.saddr,
 					      pptr[0])) {
 			/*

net/netfilter/ipvs/ip_vs_proto_sctp.c

@@ -12,6 +12,7 @@ static int
 sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		   int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
@@ -27,9 +28,9 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 				 sizeof(_schunkh), &_schunkh);
 	if (sch == NULL)
 		return 0;
-
+	net = skb_net(skb);
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				     &iph.daddr, sh->dest))) {
 		int ignored;
 

net/netfilter/ipvs/ip_vs_proto_tcp.c

@@ -31,6 +31,7 @@ static int
 tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	struct tcphdr _tcph, *th;
 	struct ip_vs_iphdr iph;
@@ -42,11 +43,11 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		*verdict = NF_DROP;
 		return 0;
 	}
-
+	net = skb_net(skb);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
 	if (th->syn &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr,
-				     th->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
+				     &iph.daddr, th->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop()) {

net/netfilter/ipvs/ip_vs_proto_udp.c

@@ -31,6 +31,7 @@ static int
 udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	struct udphdr _udph, *uh;
 	struct ip_vs_iphdr iph;
@@ -42,8 +43,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		*verdict = NF_DROP;
 		return 0;
 	}
-
-	svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	net = skb_net(skb);
+	svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				&iph.daddr, uh->dest);
 	if (svc) {
 		int ignored;

net/netfilter/ipvs/ip_vs_sync.c

@@ -749,7 +749,7 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
 		 * If it is not found the connection will remain unbound
 		 * but still handled.
 		 */
-		dest = ip_vs_find_dest(type, daddr, dport, param->vaddr,
+		dest = ip_vs_find_dest(&init_net, type, daddr, dport, param->vaddr,
 				       param->vport, protocol, fwmark);
 
 		/*  Set the approprite ativity flag */