IPVS: sip persistence engine

Add the SIP callid as a key for persistence.

This allows multiple connections from the same IP address to be
differentiated on the basis of the callid.

When used in conjunction with the persistence mask, it allows connections
from different  IP addresses to be aggregated on the basis of the callid.

It is envisaged that a persistence mask of 0.0.0.0 will be a useful
setting.  That is, ignore the source IP address when checking for
persistence.

It is envisaged that this option will be used in conjunction with
one-packet scheduling.

This only works with UDP and cannot be made to work with TCP
within the current framework.

Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index af3c9f48f2d79a38ebdde88d5cb2a39429e88ff2..a22dac227055e7499bfd9d8dd509ee5fba3e1c9b 100644 (file)
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -256,4 +256,11 @@ config     IP_VS_NFCT
          connection state to be exported to the Netfilter framework
          for filtering purposes.
 
+config IP_VS_PE_SIP
+       tristate "SIP persistence engine"
+        depends on IP_VS_PROTO_UDP
+       depends on NF_CONNTRACK_SIP
+       ---help---
+         Allow persistence based on the SIP Call-ID
+
 endif # IP_VS

diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile
index 4a87bf3c6293d931b17fc891a521150baf6a4b98..34ee602ddb667d806691111c4f6cede4227a6872 100644 (file)
--- a/net/netfilter/ipvs/Makefile
+++ b/net/netfilter/ipvs/Makefile
@@ -35,3 +35,6 @@ obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o
 
 # IPVS application helpers
 obj-$(CONFIG_IP_VS_FTP) += ip_vs_ftp.o
+
+# IPVS connection template retrievers
+obj-$(CONFIG_IP_VS_PE_SIP) += ip_vs_pe_sip.o

diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
new file mode 100644 (file)
index 0000000..a0539f1
--- /dev/null
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -0,0 +1,167 @@
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <net/ip_vs.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <linux/netfilter/nf_conntrack_sip.h>
+
+static const char *ip_vs_dbg_callid(char *buf, size_t buf_len,
+                                   const char *callid, size_t callid_len,
+                                   int *idx)
+{
+       size_t len = min(min(callid_len, (size_t)64), buf_len - *idx - 1);
+       memcpy(buf + *idx, callid, len);
+       buf[*idx+len] = '\0';
+       *idx += len + 1;
+       return buf + *idx - len;
+}
+
+#define IP_VS_DEBUG_CALLID(callid, len)                                        \
+       ip_vs_dbg_callid(ip_vs_dbg_buf, sizeof(ip_vs_dbg_buf),          \
+                        callid, len, &ip_vs_dbg_idx)
+
+static int get_callid(const char *dptr, unsigned int dataoff,
+                     unsigned int datalen,
+                     unsigned int *matchoff, unsigned int *matchlen)
+{
+       /* Find callid */
+       while (1) {
+               int ret = ct_sip_get_header(NULL, dptr, dataoff, datalen,
+                                           SIP_HDR_CALL_ID, matchoff,
+                                           matchlen);
+               if (ret > 0)
+                       break;
+               if (!ret)
+                       return 0;
+               dataoff += *matchoff;
+       }
+
+       /* Empty callid is useless */
+       if (!*matchlen)
+               return -EINVAL;
+
+       /* Too large is useless */
+       if (*matchlen > IP_VS_PEDATA_MAXLEN)
+               return -EINVAL;
+
+       /* SIP headers are always followed by a line terminator */
+       if (*matchoff + *matchlen == datalen)
+               return -EINVAL;
+
+       /* RFC 2543 allows lines to be terminated with CR, LF or CRLF,
+        * RFC 3261 allows only CRLF, we support both. */
+       if (*(dptr + *matchoff + *matchlen) != '\r' &&
+           *(dptr + *matchoff + *matchlen) != '\n')
+               return -EINVAL;
+
+       IP_VS_DBG_BUF(9, "SIP callid %s (%d bytes)\n",
+                     IP_VS_DEBUG_CALLID(dptr + *matchoff, *matchlen),
+                     *matchlen);
+       return 0;
+}
+
+static int
+ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
+{
+       struct ip_vs_iphdr iph;
+       unsigned int dataoff, datalen, matchoff, matchlen;
+       const char *dptr;
+
+       ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph);
+
+       /* Only useful with UDP */
+       if (iph.protocol != IPPROTO_UDP)
+               return -EINVAL;
+
+       /* No Data ? */
+       dataoff = iph.len + sizeof(struct udphdr);
+       if (dataoff >= skb->len)
+               return -EINVAL;
+
+       dptr = skb->data + dataoff;
+       datalen = skb->len - dataoff;
+
+       if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
+               return -EINVAL;
+
+       p->pe_data = kmalloc(matchlen, GFP_ATOMIC);
+       if (!p->pe_data)
+               return -ENOMEM;
+
+       /* N.B: pe_data is only set on success,
+        * this allows fallback to the default persistence logic on failure
+        */
+       memcpy(p->pe_data, dptr + matchoff, matchlen);
+       p->pe_data_len = matchlen;
+
+       return 0;
+}
+
+static bool ip_vs_sip_ct_match(const struct ip_vs_conn_param *p,
+                                 struct ip_vs_conn *ct)
+
+{
+       bool ret = 0;
+
+       if (ct->af == p->af &&
+           ip_vs_addr_equal(p->af, p->caddr, &ct->caddr) &&
+           /* protocol should only be IPPROTO_IP if
+            * d_addr is a fwmark */
+           ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
+                            p->vaddr, &ct->vaddr) &&
+           ct->vport == p->vport &&
+           ct->flags & IP_VS_CONN_F_TEMPLATE &&
+           ct->protocol == p->protocol &&
+           ct->pe_data && ct->pe_data_len == p->pe_data_len &&
+           !memcmp(ct->pe_data, p->pe_data, p->pe_data_len))
+               ret = 1;
+
+       IP_VS_DBG_BUF(9, "SIP template match %s %s->%s:%d %s\n",
+                     ip_vs_proto_name(p->protocol),
+                     IP_VS_DEBUG_CALLID(p->pe_data, p->pe_data_len),
+                     IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport),
+                     ret ? "hit" : "not hit");
+
+       return ret;
+}
+
+static u32 ip_vs_sip_hashkey_raw(const struct ip_vs_conn_param *p,
+                                u32 initval, bool inverse)
+{
+       return jhash(p->pe_data, p->pe_data_len, initval);
+}
+
+static int ip_vs_sip_show_pe_data(const struct ip_vs_conn *cp, char *buf)
+{
+       memcpy(buf, cp->pe_data, cp->pe_data_len);
+       return cp->pe_data_len;
+}
+
+static struct ip_vs_pe ip_vs_sip_pe =
+{
+       .name =                 "sip",
+       .refcnt =               ATOMIC_INIT(0),
+       .module =               THIS_MODULE,
+       .n_list =               LIST_HEAD_INIT(ip_vs_sip_pe.n_list),
+       .fill_param =           ip_vs_sip_fill_param,
+       .ct_match =             ip_vs_sip_ct_match,
+       .hashkey_raw =          ip_vs_sip_hashkey_raw,
+       .show_pe_data =         ip_vs_sip_show_pe_data,
+};
+
+static int __init ip_vs_sip_init(void)
+{
+       return register_ip_vs_pe(&ip_vs_sip_pe);
+}
+
+static void __exit ip_vs_sip_cleanup(void)
+{
+       unregister_ip_vs_pe(&ip_vs_sip_pe);
+}
+
+module_init(ip_vs_sip_init);
+module_exit(ip_vs_sip_cleanup);
+MODULE_LICENSE("GPL");