[PATCH] ipvs: sloppy TCP and SCTP

From: Alexander Frolkin
Date: Wed Jun 12 2013 - 07:07:48 EST


This adds support for sloppy TCP and SCTP mode 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 <avf@xxxxxxxxxxxxxx>

---

The patch is against the latest ipvs-next tree.

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4405886..22bea5d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1002,6 +1002,8 @@ struct netns_ipvs {
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;
@@ -1044,6 +1046,8 @@ struct netns_ipvs {
#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
@@ -1080,6 +1084,16 @@ 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)
{
return ACCESS_ONCE(ipvs->sysctl_sync_ports);
@@ -1133,6 +1147,16 @@ 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)
{
return 1;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 7014649..04f8cbc 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1739,6 +1739,18 @@ static struct ctl_table vs_vars[] = {
.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,
@@ -3722,6 +3734,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
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;
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 8646488..fd8f587 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -15,6 +15,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
{
struct net *net;
struct ip_vs_service *svc;
+ struct netns_ipvs *ipvs;
sctp_chunkhdr_t _schunkh, *sch;
sctp_sctphdr_t *sh, _sctph;

@@ -27,13 +28,14 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
if (sch == NULL)
return 0;
net = skb_net(skb);
+ ipvs = net_ipvs(net);
rcu_read_lock();
- if ((sch->type == SCTP_CID_INIT) &&
+ if ((sysctl_sloppy_sctp(ipvs) || (sch->type == SCTP_CID_INIT)) &&
(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 :(
@@ -232,21 +234,21 @@ static struct ipvs_sctp_nextstate
* 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 */ },
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 50a1594..3fd23fa 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -39,6 +39,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
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) {
@@ -46,14 +47,15 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
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 ((sysctl_sloppy_tcp(ipvs) || th->syn) && !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 :(
@@ -401,7 +403,7 @@ static struct tcp_states_t tcp_states [] = {
/* 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 */
@@ -415,7 +417,7 @@ static struct tcp_states_t tcp_states [] = {
/* 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 }},
};

@@ -424,7 +426,7 @@ static struct tcp_states_t tcp_states_dos [] = {
/* 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 */
@@ -438,7 +440,7 @@ static struct tcp_states_t tcp_states_dos [] = {
/* 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 }},
};

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/