static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
{
struct ip6t_npt_tginfo *npt = par->targinfo;
__wsum src_sum = 0, dst_sum = 0;
struct in6_addr pfx;
unsigned int i;
if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
return -EINVAL;
/* Ensure that LSB of prefix is zero */
ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len);
if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6))
return -EINVAL;
ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len);
if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6))
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) {
src_sum = csum_add(src_sum,
(__force __wsum)npt->src_pfx.in6.s6_addr16[i]);
dst_sum = csum_add(dst_sum,
(__force __wsum)npt->dst_pfx.in6.s6_addr16[i]);
}
npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum));
return 0;
}
static struct dst_entry *
__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
{
struct dst_entry *dst;
/* Still not clear if we should set fl->fl6_{src,dst}... */
read_lock_bh(&policy->lock);
for (dst = policy->bundles; dst; dst = dst->next) {
struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
struct in6_addr fl_dst_prefix, fl_src_prefix;
ipv6_addr_prefix(&fl_dst_prefix,
&fl->fl6_dst,
xdst->u.rt6.rt6i_dst.plen);
ipv6_addr_prefix(&fl_src_prefix,
&fl->fl6_src,
xdst->u.rt6.rt6i_src.plen);
if (!ipv6_addr_cmp(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
!ipv6_addr_cmp(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
__xfrm6_bundle_ok(xdst, fl)) {
dst_clone(dst);
break;
}
}
read_unlock_bh(&policy->lock);
return dst;
}
static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
{
struct ip6t_npt_tginfo *npt = par->targinfo;
struct in6_addr pfx;
__wsum src_sum, dst_sum;
if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
return -EINVAL;
/* Ensure that LSB of prefix is zero */
ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len);
if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6))
return -EINVAL;
ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len);
if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6))
return -EINVAL;
src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0);
dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0);
npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum));
return 0;
}
static struct dst_entry *
__xfrm6_find_bundle(struct flowi *fl, struct rtable *rt, struct xfrm_policy *policy)
{
struct dst_entry *dst;
u32 ndisc_bit = 0;
if (fl->proto == IPPROTO_ICMPV6 &&
(fl->fl_icmp_type == NDISC_NEIGHBOUR_ADVERTISEMENT ||
fl->fl_icmp_type == NDISC_NEIGHBOUR_SOLICITATION ||
fl->fl_icmp_type == NDISC_ROUTER_SOLICITATION))
ndisc_bit = RTF_NDISC;
/* Still not clear if we should set fl->fl6_{src,dst}... */
read_lock_bh(&policy->lock);
for (dst = policy->bundles; dst; dst = dst->next) {
struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
struct in6_addr fl_dst_prefix, fl_src_prefix;
if ((xdst->u.rt6.rt6i_flags & RTF_NDISC) != ndisc_bit)
continue;
ipv6_addr_prefix(&fl_dst_prefix,
&fl->fl6_dst,
xdst->u.rt6.rt6i_dst.plen);
ipv6_addr_prefix(&fl_src_prefix,
&fl->fl6_src,
xdst->u.rt6.rt6i_src.plen);
if (!ipv6_addr_cmp(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
!ipv6_addr_cmp(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
__xfrm6_bundle_ok(xdst, fl)) {
dst_clone(dst);
break;
}
}
read_unlock_bh(&policy->lock);
return dst;
}
int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh)
{
int err;
struct rtmsg *r;
struct rt6_info *rt;
struct net_device *dev = NULL;
int addr_type;
if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128)
return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
if (rtmsg->rtmsg_src_len)
return -EINVAL;
#endif
if (rtmsg->rtmsg_metric == 0)
rtmsg->rtmsg_metric = IP6_RT_PRIO_USER;
rt = dst_alloc(&ip6_dst_ops);
if (rt == NULL)
return -ENOMEM;
rt->u.dst.obsolete = -1;
rt->rt6i_expires = rtmsg->rtmsg_info;
if (nlh && (r = NLMSG_DATA(nlh))) {
rt->rt6i_protocol = r->rtm_protocol;
} else {
rt->rt6i_protocol = RTPROT_BOOT;
}
addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst);
if (addr_type & IPV6_ADDR_MULTICAST)
rt->u.dst.input = ip6_mc_input;
else
rt->u.dst.input = ip6_forward;
rt->u.dst.output = ip6_output;
if (rtmsg->rtmsg_ifindex) {
dev = dev_get_by_index(rtmsg->rtmsg_ifindex);
err = -ENODEV;
if (dev == NULL)
goto out;
}
ipv6_addr_prefix(&rt->rt6i_dst.addr,
&rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len);
rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len;
if (rt->rt6i_dst.plen == 128)
rt->u.dst.flags = DST_HOST;
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr,
&rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
rt->rt6i_src.plen = rtmsg->rtmsg_src_len;
#endif
rt->rt6i_metric = rtmsg->rtmsg_metric;
/* We cannot add true routes via loopback here,
they would result in kernel looping; promote them to reject routes
*/
if ((rtmsg->rtmsg_flags&RTF_REJECT) ||
(dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
if (dev)
dev_put(dev);
dev = &loopback_dev;
dev_hold(dev);
rt->u.dst.output = ip6_pkt_discard;
rt->u.dst.input = ip6_pkt_discard;
rt->u.dst.error = -ENETUNREACH;
rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
goto install_route;
}
if (rtmsg->rtmsg_flags & RTF_GATEWAY) {
struct in6_addr *gw_addr;
int gwa_type;
gw_addr = &rtmsg->rtmsg_gateway;
ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway);
gwa_type = ipv6_addr_type(gw_addr);
if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
struct rt6_info *grt;
/* IPv6 strictly inhibits using not link-local
addresses as nexthop address.
Otherwise, router will not able to send redirects.
It is very good, but in some (rare!) curcumstances
(SIT, PtP, NBMA NOARP links) it is handy to allow
some exceptions. --ANK
*/
err = -EINVAL;
if (!(gwa_type&IPV6_ADDR_UNICAST))
goto out;
grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1);
err = -EHOSTUNREACH;
if (grt == NULL)
goto out;
if (dev) {
if (dev != grt->rt6i_dev) {
dst_release(&grt->u.dst);
goto out;
}
} else {
dev = grt->rt6i_dev;
dev_hold(dev);
}
if (!(grt->rt6i_flags&RTF_GATEWAY))
err = 0;
dst_release(&grt->u.dst);
if (err)
goto out;
}
err = -EINVAL;
if (dev == NULL || (dev->flags&IFF_LOOPBACK))
goto out;
}
err = -ENODEV;
if (dev == NULL)
goto out;
if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) {
rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
if (IS_ERR(rt->rt6i_nexthop)) {
err = PTR_ERR(rt->rt6i_nexthop);
rt->rt6i_nexthop = NULL;
goto out;
}
}
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr))
rt->rt6i_hoplimit = IPV6_DEFAULT_MCASTHOPS;
else
rt->rt6i_hoplimit = ipv6_get_hoplimit(dev);
rt->rt6i_flags = rtmsg->rtmsg_flags;
install_route:
rt->u.dst.pmtu = ipv6_get_mtu(dev);
rt->u.dst.advmss = max_t(unsigned int, rt->u.dst.pmtu - 60, ip6_rt_min_advmss);
/* Maximal non-jumbo IPv6 payload is 65535 and corresponding
MSS is 65535 - tcp_header_size. 65535 is also valid and
means: "any MSS, rely only on pmtu discovery"
*/
if (rt->u.dst.advmss > 65535-20)
rt->u.dst.advmss = 65535;
rt->u.dst.dev = dev;
return rt6_ins(rt, nlh);
out:
if (dev)
dev_put(dev);
dst_free((struct dst_entry *) rt);
return err;
}
/*
* IPVS persistent scheduling function
* It creates a connection entry according to its template if exists,
* or selects a server and creates a connection entry plus a template.
* Locking: we are svc user (svc->refcnt), so we hold all dests too
* Protocols supported: TCP, UDP
*/
static struct ip_vs_conn *
ip_vs_sched_persist(struct ip_vs_service *svc,
const struct sk_buff *skb,
__be16 ports[2])
{
struct ip_vs_conn *cp = NULL;
struct ip_vs_iphdr iph;
struct ip_vs_dest *dest;
struct ip_vs_conn *ct;
__be16 dport; /* destination port to forward */
union nf_inet_addr snet; /* source network of the client,
after masking */
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
/* Mask saddr with the netmask to adjust template granularity */
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6)
ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask);
else
#endif
snet.ip = iph.saddr.ip & svc->netmask;
IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
"mnet %s\n",
IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]),
IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]),
IP_VS_DBG_ADDR(svc->af, &snet));
/*
* As far as we know, FTP is a very complicated network protocol, and
* it uses control connection and data connections. For active FTP,
* FTP server initialize data connection to the client, its source port
* is often 20. For passive FTP, FTP server tells the clients the port
* that it passively listens to, and the client issues the data
* connection. In the tunneling or direct routing mode, the load
* balancer is on the client-to-server half of connection, the port
* number is unknown to the load balancer. So, a conn template like
* <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP
* service, and a template like <caddr, 0, vaddr, vport, daddr, dport>
* is created for other persistent services.
*/
if (ports[1] == svc->port) {
/* Check if a template already exists */
if (svc->port != FTPPORT)
ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
&iph.daddr, ports[1]);
else
ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
&iph.daddr, 0);
if (!ct || !ip_vs_check_template(ct)) {
/*
* No template found or the dest of the connection
* template is not available.
*/
dest = svc->scheduler->schedule(svc, skb);
if (dest == NULL) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
return NULL;
}
/*
* Create a template like <protocol,caddr,0,
* vaddr,vport,daddr,dport> for non-ftp service,
* and <protocol,caddr,0,vaddr,0,daddr,0>
* for ftp service.
*/
if (svc->port != FTPPORT)
ct = ip_vs_conn_new(svc->af, iph.protocol,
&snet, 0,
&iph.daddr,
ports[1],
&dest->addr, dest->port,
IP_VS_CONN_F_TEMPLATE,
dest);
else
ct = ip_vs_conn_new(svc->af, iph.protocol,
&snet, 0,
&iph.daddr, 0,
&dest->addr, 0,
IP_VS_CONN_F_TEMPLATE,
dest);
if (ct == NULL)
return NULL;
ct->timeout = svc->timeout;
} else {
/* set destination with the found template */
dest = ct->dest;
}
dport = dest->port;
} else {
/*
* Note: persistent fwmark-based services and persistent
* port zero service are handled here.
* fwmark template: <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
* port zero template: <protocol,caddr,0,vaddr,0,daddr,0>
*/
if (svc->fwmark) {
union nf_inet_addr fwmark = {
.ip = htonl(svc->fwmark)
};
ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0,
&fwmark, 0);
} else
ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
&iph.daddr, 0);
if (!ct || !ip_vs_check_template(ct)) {
/*
* If it is not persistent port zero, return NULL,
* otherwise create a connection template.
*/
if (svc->port)
return NULL;
dest = svc->scheduler->schedule(svc, skb);
if (dest == NULL) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
return NULL;
}
/*
* Create a template according to the service
*/
if (svc->fwmark) {
union nf_inet_addr fwmark = {
.ip = htonl(svc->fwmark)
};
ct = ip_vs_conn_new(svc->af, IPPROTO_IP,
&snet, 0,
&fwmark, 0,
&dest->addr, 0,
IP_VS_CONN_F_TEMPLATE,
dest);
} else
ct = ip_vs_conn_new(svc->af, iph.protocol,
&snet, 0,
&iph.daddr, 0,
&dest->addr, 0,
IP_VS_CONN_F_TEMPLATE,
dest);
if (ct == NULL)
return NULL;
ct->timeout = svc->timeout;
} else {
/* set destination with the found template */
dest = ct->dest;
}
dport = ports[1];
}
static struct ip_vs_conn *
ip_vs_sched_persist(struct ip_vs_service *svc,
struct sk_buff *skb,
__be16 src_port, __be16 dst_port, int *ignored)
{
struct ip_vs_conn *cp = NULL;
struct ip_vs_iphdr iph;
struct ip_vs_dest *dest;
struct ip_vs_conn *ct;
__be16 dport = 0;
unsigned int flags;
struct ip_vs_conn_param param;
const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
union nf_inet_addr snet;
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6)
ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask);
else
#endif
snet.ip = iph.saddr.ip & svc->netmask;
IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
"mnet %s\n",
IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port),
IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port),
IP_VS_DBG_ADDR(svc->af, &snet));
{
int protocol = iph.protocol;
const union nf_inet_addr *vaddr = &iph.daddr;
__be16 vport = 0;
if (dst_port == svc->port) {
if (svc->port != FTPPORT)
vport = dst_port;
} else {
if (svc->fwmark) {
protocol = IPPROTO_IP;
vaddr = &fwmark;
}
}
if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
vaddr, vport, ¶m) < 0) {
*ignored = -1;
return NULL;
}
}
ct = ip_vs_ct_in_get(¶m);
if (!ct || !ip_vs_check_template(ct)) {
dest = svc->scheduler->schedule(svc, skb);
if (!dest) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
kfree(param.pe_data);
*ignored = 0;
return NULL;
}
if (dst_port == svc->port && svc->port != FTPPORT)
dport = dest->port;
ct = ip_vs_conn_new(¶m, &dest->addr, dport,
IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
if (ct == NULL) {
kfree(param.pe_data);
*ignored = -1;
return NULL;
}
ct->timeout = svc->timeout;
} else {
dest = ct->dest;
kfree(param.pe_data);
}
dport = dst_port;
if (dport == svc->port && dest->port)
dport = dest->port;
flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
&& iph.protocol == IPPROTO_UDP)?
IP_VS_CONN_F_ONE_PACKET : 0;
ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
src_port, &iph.daddr, dst_port, ¶m);
cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest, skb->mark);
if (cp == NULL) {
ip_vs_conn_put(ct);
*ignored = -1;
return NULL;
}
ip_vs_control_add(cp, ct);
ip_vs_conn_put(ct);
ip_vs_conn_stats(cp, svc);
return cp;
}
struct ip_vs_conn *
ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_proto_data *pd, int *ignored)
{
struct ip_vs_protocol *pp = pd->pp;
struct ip_vs_conn *cp = NULL;
struct ip_vs_iphdr iph;
struct ip_vs_dest *dest;
__be16 _ports[2], *pptr;
unsigned int flags;
*ignored = 1;
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
if (pptr == NULL)
return NULL;
if (pptr[0] == FTPDATA) {
IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
"Not scheduling FTPDATA");
return NULL;
}
if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
(cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) {
IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
"Not scheduling reply for existing connection");
__ip_vs_conn_put(cp);
return NULL;
}
if (svc->flags & IP_VS_SVC_F_PERSISTENT)
return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored);
*ignored = 0;
if (!svc->fwmark && pptr[1] != svc->port) {
if (!svc->port)
pr_err("Schedule: port zero only supported "
"in persistent services, "
"check your ipvs configuration\n");
return NULL;
}
dest = svc->scheduler->schedule(svc, skb);
if (dest == NULL) {
IP_VS_DBG(1, "Schedule: no dest found.\n");
return NULL;
}
flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
&& iph.protocol == IPPROTO_UDP)?
IP_VS_CONN_F_ONE_PACKET : 0;
{
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
&iph.saddr, pptr[0], &iph.daddr, pptr[1],
&p);
cp = ip_vs_conn_new(&p, &dest->addr,
dest->port ? dest->port : pptr[1],
flags, dest, skb->mark);
if (!cp) {
*ignored = -1;
return NULL;
}
}
IP_VS_DBG_BUF(6, "Schedule fwd:%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(svc->af, &cp->caddr), ntohs(cp->cport),
IP_VS_DBG_ADDR(svc->af, &cp->vaddr), ntohs(cp->vport),
IP_VS_DBG_ADDR(svc->af, &cp->daddr), ntohs(cp->dport),
cp->flags, atomic_read(&cp->refcnt));
ip_vs_conn_stats(cp, svc);
return cp;
}
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_proto_data *pd)
{
__be16 _ports[2], *pptr;
struct ip_vs_iphdr iph;
#ifdef CONFIG_SYSCTL
struct net *net;
struct netns_ipvs *ipvs;
int unicast;
#endif
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
if (pptr == NULL) {
ip_vs_service_put(svc);
return NF_DROP;
}
#ifdef CONFIG_SYSCTL
net = skb_net(skb);
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6)
unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST;
else
#endif
unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST);
ipvs = net_ipvs(net);
if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
int ret;
struct ip_vs_conn *cp;
unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
iph.protocol == IPPROTO_UDP)?
IP_VS_CONN_F_ONE_PACKET : 0;
union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } };
ip_vs_service_put(svc);
IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
{
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
&iph.saddr, pptr[0],
&iph.daddr, pptr[1], &p);
cp = ip_vs_conn_new(&p, &daddr, 0,
IP_VS_CONN_F_BYPASS | flags,
NULL, skb->mark);
if (!cp)
return NF_DROP;
}
ip_vs_in_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
ret = cp->packet_xmit(skb, cp, pd->pp);
atomic_inc(&cp->in_pkts);
ip_vs_conn_put(cp);
return ret;
}
/*
* IPVS persistent scheduling function
* It creates a connection entry according to its template if exists,
* or selects a server and creates a connection entry plus a template.
* Locking: we are svc user (svc->refcnt), so we hold all dests too
* Protocols supported: TCP, UDP
*/
static struct ip_vs_conn *
ip_vs_sched_persist(struct ip_vs_service *svc,
struct sk_buff *skb, __be16 src_port, __be16 dst_port,
int *ignored, struct ip_vs_iphdr *iph)
{
struct ip_vs_conn *cp = NULL;
struct ip_vs_dest *dest;
struct ip_vs_conn *ct;
__be16 dport = 0; /* destination port to forward */
unsigned int flags;
struct ip_vs_conn_param param;
const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
union nf_inet_addr snet; /* source network of the client,
after masking */
/* Mask saddr with the netmask to adjust template granularity */
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6)
ipv6_addr_prefix(&snet.in6, &iph->saddr.in6,
(__force __u32) svc->netmask);
else
#endif
snet.ip = iph->saddr.ip & svc->netmask;
IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
"mnet %s\n",
IP_VS_DBG_ADDR(svc->af, &iph->saddr), ntohs(src_port),
IP_VS_DBG_ADDR(svc->af, &iph->daddr), ntohs(dst_port),
IP_VS_DBG_ADDR(svc->af, &snet));
/*
* As far as we know, FTP is a very complicated network protocol, and
* it uses control connection and data connections. For active FTP,
* FTP server initialize data connection to the client, its source port
* is often 20. For passive FTP, FTP server tells the clients the port
* that it passively listens to, and the client issues the data
* connection. In the tunneling or direct routing mode, the load
* balancer is on the client-to-server half of connection, the port
* number is unknown to the load balancer. So, a conn template like
* <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP
* service, and a template like <caddr, 0, vaddr, vport, daddr, dport>
* is created for other persistent services.
*/
{
int protocol = iph->protocol;
const union nf_inet_addr *vaddr = &iph->daddr;
__be16 vport = 0;
if (dst_port == svc->port) {
/* non-FTP template:
* <protocol, caddr, 0, vaddr, vport, daddr, dport>
* FTP template:
* <protocol, caddr, 0, vaddr, 0, daddr, 0>
*/
if (svc->port != FTPPORT)
vport = dst_port;
} else {
/* Note: persistent fwmark-based services and
* persistent port zero service are handled here.
* fwmark template:
* <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
* port zero template:
* <protocol,caddr,0,vaddr,0,daddr,0>
*/
if (svc->fwmark) {
protocol = IPPROTO_IP;
vaddr = &fwmark;
}
}
/* return *ignored = -1 so NF_DROP can be used */
if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
vaddr, vport, ¶m) < 0) {
*ignored = -1;
return NULL;
}
}
/* Check if a template already exists */
ct = ip_vs_ct_in_get(¶m);
if (!ct || !ip_vs_check_template(ct)) {
struct ip_vs_scheduler *sched;
/*
* No template found or the dest of the connection
* template is not available.
* return *ignored=0 i.e. ICMP and NF_DROP
*/
sched = rcu_dereference(svc->scheduler);
if (sched) {
/* read svc->sched_data after svc->scheduler */
smp_rmb();
dest = sched->schedule(svc, skb, iph);
} else {
dest = NULL;
}
if (!dest) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
kfree(param.pe_data);
*ignored = 0;
return NULL;
}
if (dst_port == svc->port && svc->port != FTPPORT)
dport = dest->port;
/* Create a template
* This adds param.pe_data to the template,
* and thus param.pe_data will be destroyed
* when the template expires */
ct = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport,
IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
if (ct == NULL) {
kfree(param.pe_data);
*ignored = -1;
return NULL;
}
ct->timeout = svc->timeout;
} else {
/* set destination with the found template */
dest = ct->dest;
kfree(param.pe_data);
}
dport = dst_port;
if (dport == svc->port && dest->port)
dport = dest->port;
flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
&& iph->protocol == IPPROTO_UDP) ?
IP_VS_CONN_F_ONE_PACKET : 0;
/*
* Create a new connection according to the template
*/
ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr,
src_port, &iph->daddr, dst_port, ¶m);
cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest,
skb->mark);
if (cp == NULL) {
ip_vs_conn_put(ct);
*ignored = -1;
return NULL;
}
/*
* Add its control
*/
ip_vs_control_add(cp, ct);
ip_vs_conn_put(ct);
ip_vs_conn_stats(cp, svc);
return cp;
}
/*
* IPVS main scheduling function
* It selects a server according to the virtual service, and
* creates a connection entry.
* Protocols supported: TCP, UDP
*
* Usage of *ignored
*
* 1 : protocol tried to schedule (eg. on SYN), found svc but the
* svc/scheduler decides that this packet should be accepted with
* NF_ACCEPT because it must not be scheduled.
*
* 0 : scheduler can not find destination, so try bypass or
* return ICMP and then NF_DROP (ip_vs_leave).
*
* -1 : scheduler tried to schedule but fatal error occurred, eg.
* ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param
* failure such as missing Call-ID, ENOMEM on skb_linearize
* or pe_data. In this case we should return NF_DROP without
* any attempts to send ICMP with ip_vs_leave.
*/
struct ip_vs_conn *
ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_proto_data *pd, int *ignored,
struct ip_vs_iphdr *iph)
{
struct ip_vs_protocol *pp = pd->pp;
struct ip_vs_conn *cp = NULL;
struct ip_vs_scheduler *sched;
struct ip_vs_dest *dest;
__be16 _ports[2], *pptr;
unsigned int flags;
*ignored = 1;
/*
* IPv6 frags, only the first hit here.
*/
pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
if (pptr == NULL)
return NULL;
/*
* FTPDATA needs this check when using local real server.
* Never schedule Active FTPDATA connections from real server.
* For LVS-NAT they must be already created. For other methods
* with persistence the connection is created on SYN+ACK.
*/
if (pptr[0] == FTPDATA) {
IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
"Not scheduling FTPDATA");
return NULL;
}
/*
* Do not schedule replies from local real server.
*/
if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
(cp = pp->conn_in_get(svc->af, skb, iph, 1))) {
IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
"Not scheduling reply for existing connection");
__ip_vs_conn_put(cp);
return NULL;
}
/*
* Persistent service
*/
if (svc->flags & IP_VS_SVC_F_PERSISTENT)
return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored,
iph);
*ignored = 0;
/*
* Non-persistent service
*/
if (!svc->fwmark && pptr[1] != svc->port) {
if (!svc->port)
pr_err("Schedule: port zero only supported "
"in persistent services, "
"check your ipvs configuration\n");
return NULL;
}
sched = rcu_dereference(svc->scheduler);
if (sched) {
/* read svc->sched_data after svc->scheduler */
smp_rmb();
dest = sched->schedule(svc, skb, iph);
} else {
dest = NULL;
}
if (dest == NULL) {
IP_VS_DBG(1, "Schedule: no dest found.\n");
return NULL;
}
flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
&& iph->protocol == IPPROTO_UDP) ?
IP_VS_CONN_F_ONE_PACKET : 0;
/*
* Create a connection entry.
*/
{
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
&iph->saddr, pptr[0], &iph->daddr,
pptr[1], &p);
cp = ip_vs_conn_new(&p, dest->af, &dest->addr,
dest->port ? dest->port : pptr[1],
flags, dest, skb->mark);
if (!cp) {
*ignored = -1;
return NULL;
}
}
IP_VS_DBG_BUF(6, "Schedule fwd:%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->daf, &cp->daddr), ntohs(cp->dport),
cp->flags, atomic_read(&cp->refcnt));
ip_vs_conn_stats(cp, svc);
return cp;
}
/*
* Pass or drop the packet.
* Called by ip_vs_in, when the virtual service is available but
* no destination is available for a new connection.
*/
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph)
{
__be16 _ports[2], *pptr;
#ifdef CONFIG_SYSCTL
struct net *net;
struct netns_ipvs *ipvs;
int unicast;
#endif
pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
if (pptr == NULL) {
return NF_DROP;
}
#ifdef CONFIG_SYSCTL
net = skb_net(skb);
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6)
unicast = ipv6_addr_type(&iph->daddr.in6) & IPV6_ADDR_UNICAST;
else
#endif
unicast = (inet_addr_type(net, iph->daddr.ip) == RTN_UNICAST);
/* if it is fwmark-based service, the cache_bypass sysctl is up
and the destination is a non-local unicast, then create
a cache_bypass connection entry */
ipvs = net_ipvs(net);
if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
int ret;
struct ip_vs_conn *cp;
unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
iph->protocol == IPPROTO_UDP) ?
IP_VS_CONN_F_ONE_PACKET : 0;
union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } };
/* create a new connection entry */
IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
{
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
&iph->saddr, pptr[0],
&iph->daddr, pptr[1], &p);
cp = ip_vs_conn_new(&p, svc->af, &daddr, 0,
IP_VS_CONN_F_BYPASS | flags,
NULL, skb->mark);
if (!cp)
return NF_DROP;
}
/* statistics */
ip_vs_in_stats(cp, skb);
/* set state */
ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
/* transmit the first SYN packet */
ret = cp->packet_xmit(skb, cp, pd->pp, iph);
/* do not touch skb anymore */
atomic_inc(&cp->in_pkts);
ip_vs_conn_put(cp);
return ret;
}
