ipvs: sloppy TCP and SCTP

This adds support for sloppy TCP and SCTP modes to IPVS.

When enabled (sysctls net.ipv4.vs.sloppy_tcp and
net.ipv4.vs.sloppy_sctp), allows IPVS to create connection state on any
packet, not just a TCP SYN (or SCTP INIT).

This allows connections to fail over from one IPVS director to another
mid-flight.

Signed-off-by: Alexander Frolkin <[e-mail]>
Signed-off-by: Julian Anastasov <[e-mail]>
Signed-off-by: Simon Horman <[e-mail]>

include/net/ip_vs.h

···
 	int			sysctl_sync_sock_size;
 	int			sysctl_cache_bypass;
 	int			sysctl_expire_nodest_conn;
+	int			sysctl_sloppy_tcp;
+	int			sysctl_sloppy_sctp;
 	int			sysctl_expire_quiescent_template;
 	int			sysctl_sync_threshold[2];
 	unsigned int		sysctl_sync_refresh_period;
···
 #define DEFAULT_SYNC_THRESHOLD	3
 #define DEFAULT_SYNC_PERIOD	50
 #define DEFAULT_SYNC_VER	1
+#define DEFAULT_SLOPPY_TCP	0
+#define DEFAULT_SLOPPY_SCTP	0
 #define DEFAULT_SYNC_REFRESH_PERIOD	(0U * HZ)
 #define DEFAULT_SYNC_RETRIES		0
 #define IPVS_SYNC_WAKEUP_RATE	8
···
 static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
 {
 	return ipvs->sysctl_sync_ver;
+}
+
+static inline int sysctl_sloppy_tcp(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sloppy_tcp;
+}
+
+static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sloppy_sctp;
 }
 
 static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
···
 static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
 {
 	return DEFAULT_SYNC_VER;
+}
+
+static inline int sysctl_sloppy_tcp(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SLOPPY_TCP;
+}
+
+static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SLOPPY_SCTP;
 }
 
 static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)

net/netfilter/ipvs/ip_vs_ctl.c

···
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "sloppy_tcp",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sloppy_sctp",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "expire_quiescent_template",
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
···
 	tbl[idx++].data = &ipvs->sysctl_sync_sock_size;
 	tbl[idx++].data = &ipvs->sysctl_cache_bypass;
 	tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
+	tbl[idx++].data = &ipvs->sysctl_sloppy_tcp;
+	tbl[idx++].data = &ipvs->sysctl_sloppy_sctp;
 	tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
 	ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
 	ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;

net/netfilter/ipvs/ip_vs_proto_sctp.c

···
 {
 	struct net *net;
 	struct ip_vs_service *svc;
+	struct netns_ipvs *ipvs;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
 
···
 	if (sch == NULL)
 		return 0;
 	net = skb_net(skb);
+	ipvs = net_ipvs(net);
 	rcu_read_lock();
-	if ((sch->type == SCTP_CID_INIT) &&
+	if ((sch->type == SCTP_CID_INIT || sysctl_sloppy_sctp(ipvs)) &&
 	    (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
 				      &iph->daddr, sh->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop(net_ipvs(net))) {
+		if (ip_vs_todrop(ipvs)) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
···
 	 * STATE : IP_VS_SCTP_S_NONE
 	 */
 	/*next state *//*event */
-	{{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
+	{{IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
 	 {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
 	 {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
-	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
+	 {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
-	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
+	 {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
-	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
+	 {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
-	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
+	 {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
-	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
+	 {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
 	 {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ },

net/netfilter/ipvs/ip_vs_proto_tcp.c

···
 	struct net *net;
 	struct ip_vs_service *svc;
 	struct tcphdr _tcph, *th;
+	struct netns_ipvs *ipvs;
 
 	th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
 	if (th == NULL) {
···
 		return 0;
 	}
 	net = skb_net(skb);
+	ipvs = net_ipvs(net);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
 	rcu_read_lock();
-	if (th->syn &&
+	if ((th->syn || sysctl_sloppy_tcp(ipvs)) && !th->rst &&
 	    (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
 				      &iph->daddr, th->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop(net_ipvs(net))) {
+		if (ip_vs_todrop(ipvs)) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
···
 /*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
 /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
 /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }},
-/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
+/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }},
 
 /*	OUTPUT */
···
 /*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
 /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
 /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }},
-/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
+/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
 };
 
···
 /*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
 /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }},
 /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }},
-/*ack*/ {{sCL, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }},
+/*ack*/ {{sES, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }},
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
 
 /*	OUTPUT */
···
 /*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
 /*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }},
 /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }},
-/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
+/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
 };