static inline void
ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
struct ip_vs_dest *dest = cp->dest;
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
s = this_cpu_ptr(dest->stats.cpustats);
s->ustats.outpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
s = this_cpu_ptr(dest->svc->stats.cpustats);
s->ustats.outpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
s = this_cpu_ptr(ipvs->tot_stats.cpustats);
s->ustats.outpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
}
}
static struct ip_vs_conn *
ah_esp_conn_in_get(int af, const struct sk_buff *skb,
const struct ip_vs_iphdr *iph, unsigned int proto_off,
int inverse)
{
struct ip_vs_conn *cp;
struct ip_vs_conn_param p;
struct net *net = skb_net(skb);
ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
cp = ip_vs_conn_in_get(&p);
if (!cp) {
/*
* We are not sure if the packet is from our
* service, so our conn_schedule hook should return NF_ACCEPT
*/
IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet "
"%s%s %s->%s\n",
inverse ? "ICMP+" : "",
ip_vs_proto_get(iph->protocol)->name,
IP_VS_DBG_ADDR(af, &iph->saddr),
IP_VS_DBG_ADDR(af, &iph->daddr));
}
return cp;
}
static inline void
ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
struct ip_vs_dest *dest = cp->dest;
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.outpkts++;
s->cnt.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
rcu_read_lock();
svc = rcu_dereference(dest->svc);
s = this_cpu_ptr(svc->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.outpkts++;
s->cnt.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
rcu_read_unlock();
s = this_cpu_ptr(ipvs->tot_stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.outpkts++;
s->cnt.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
}
}
static int
sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
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;
struct ip_vs_iphdr iph;
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
sh = skb_header_pointer(skb, iph.len, sizeof(_sctph), &_sctph);
if (sh == NULL)
return 0;
sch = skb_header_pointer(skb, iph.len + sizeof(sctp_sctphdr_t),
sizeof(_schunkh), &_schunkh);
if (sch == NULL)
return 0;
net = skb_net(skb);
if ((sch->type == SCTP_CID_INIT) &&
(svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
&iph.daddr, sh->dest))) {
int ignored;
if (ip_vs_todrop(net_ipvs(net))) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
*/
ip_vs_service_put(svc);
*verdict = NF_DROP;
return 0;
}
/*
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
if (!*cpp && ignored <= 0) {
if (!ignored)
*verdict = ip_vs_leave(svc, skb, pd);
else {
ip_vs_service_put(svc);
*verdict = NF_DROP;
}
return 0;
}
ip_vs_service_put(svc);
}
/* NF_ACCEPT */
return 1;
}
static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
struct ip_vs_iphdr *ipvsh,
struct sk_buff *skb, int mtu)
{
#ifdef CONFIG_IP_VS_IPV6
if (skb_af == AF_INET6) {
struct net *net = dev_net(skb_dst(skb)->dev);
if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
if (!skb->dev)
skb->dev = net->loopback_dev;
/* only send ICMP too big on first fragment */
if (!ipvsh->fragoffs)
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG(1, "frag needed for %pI6c\n",
&ipv6_hdr(skb)->saddr);
return false;
}
} else
#endif
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
/* If we're going to tunnel the packet and pmtu discovery
* is disabled, we'll just fragment it anyway
*/
if ((rt_mode & IP_VS_RT_MODE_TUNNEL) && !sysctl_pmtu_disc(ipvs))
return true;
if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) &&
skb->len > mtu && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
IP_VS_DBG(1, "frag needed for %pI4\n",
&ip_hdr(skb)->saddr);
return false;
}
}
return true;
}
static struct ip_vs_conn *
ah_esp_conn_out_get(int af, const struct sk_buff *skb,
const struct ip_vs_iphdr *iph,
unsigned int proto_off,
int inverse)
{
struct ip_vs_conn *cp;
struct ip_vs_conn_param p;
struct net *net = skb_net(skb);
ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
cp = ip_vs_conn_out_get(&p);
if (!cp) {
IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
"%s%s %s->%s\n",
inverse ? "ICMP+" : "",
ip_vs_proto_get(iph->protocol)->name,
IP_VS_DBG_ADDR(af, &iph->saddr),
IP_VS_DBG_ADDR(af, &iph->daddr));
}
return cp;
}
/*
* Look at outgoing ftp packets to catch the response to a PASV command
* from the server (inside-to-outside).
* When we see one, we build a connection entry with the client address,
* client port 0 (unknown at the moment), the server address and the
* server port. Mark the current connection entry as a control channel
* of the new entry. All this work is just to make the data connection
* can be scheduled to the right server later.
*
* The outgoing packet should be something like
* "227 Entering Passive Mode (xxx,xxx,xxx,xxx,ppp,ppp)".
* xxx,xxx,xxx,xxx is the server address, ppp,ppp is the server port number.
*/
static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
struct sk_buff *skb, int *diff)
{
struct iphdr *iph;
struct tcphdr *th;
char *data, *data_limit;
char *start, *end;
union nf_inet_addr from;
__be16 port;
struct ip_vs_conn *n_cp;
char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */
unsigned buf_len;
int ret = 0;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct net *net;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
* so turn this into a no-op for IPv6 packets
*/
if (cp->af == AF_INET6)
return 1;
#endif
*diff = 0;
/* Only useful for established sessions */
if (cp->state != IP_VS_TCP_S_ESTABLISHED)
return 1;
/* Linear packets are much easier to deal with. */
if (!skb_make_writable(skb, skb->len))
return 0;
if (cp->app_data == &ip_vs_ftp_pasv) {
iph = ip_hdr(skb);
th = (struct tcphdr *)&(((char *)iph)[iph->ihl*4]);
data = (char *)th + (th->doff << 2);
data_limit = skb_tail_pointer(skb);
if (ip_vs_ftp_get_addrport(data, data_limit,
SERVER_STRING,
sizeof(SERVER_STRING)-1,
'(', ')',
&from.ip, &port,
&start, &end) != 1)
return 1;
IP_VS_DBG(7, "PASV response (%pI4:%d) -> %pI4:%d detected\n",
&from.ip, ntohs(port), &cp->caddr.ip, 0);
/*
* Now update or create an connection entry for it
*/
{
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
iph->protocol, &from, port,
&cp->caddr, 0, &p);
n_cp = ip_vs_conn_out_get(&p);
}
if (!n_cp) {
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(ip_vs_conn_net(cp),
AF_INET, IPPROTO_TCP, &cp->caddr,
0, &cp->vaddr, port, &p);
n_cp = ip_vs_conn_new(&p, &from, port,
IP_VS_CONN_F_NO_CPORT |
IP_VS_CONN_F_NFCT,
cp->dest, skb->mark);
if (!n_cp)
return 0;
/* add its controller */
ip_vs_control_add(n_cp, cp);
}
/*
* Replace the old passive address with the new one
*/
from.ip = n_cp->vaddr.ip;
port = n_cp->vport;
snprintf(buf, sizeof(buf), "%u,%u,%u,%u,%u,%u",
((unsigned char *)&from.ip)[0],
((unsigned char *)&from.ip)[1],
((unsigned char *)&from.ip)[2],
((unsigned char *)&from.ip)[3],
ntohs(port) >> 8,
ntohs(port) & 0xFF);
buf_len = strlen(buf);
ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct) && nfct_nat(ct)) {
/* If mangling fails this function will return 0
* which will cause the packet to be dropped.
* Mangling can only fail under memory pressure,
* hopefully it will succeed on the retransmitted
* packet.
*/
ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
start-data, end-start,
buf, buf_len);
if (ret) {
ip_vs_nfct_expect_related(skb, ct, n_cp,
IPPROTO_TCP, 0, 0);
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_UNNECESSARY;
/* csum is updated */
ret = 1;
}
}
/*
* Not setting 'diff' is intentional, otherwise the sequence
* would be adjusted twice.
*/
net = skb_net(skb);
cp->app_data = NULL;
ip_vs_tcp_conn_listen(net, n_cp);
ip_vs_conn_put(n_cp);
return ret;
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT |
IP_VS_RT_MODE_TUNNEL, &saddr);
if (local < 0)
goto tx_error;
if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
rt = skb_rtable(skb);
tdev = rt->dst.dev;
/* Copy DF, reset fragment offset and MF */
df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
goto tx_error;
consume_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb->transport_header = skb->network_header;
/* fix old IP header checksum */
ip_send_check(old_iph);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
ip_select_ident(skb, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
tx_error:
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct net *net = skb_net(skb);
struct netns_ipvs *ipvs = net_ipvs(net);
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
__u8 next_protocol = 0;
__u8 dsfield = 0;
__u8 ttl = 0;
__be16 df = 0;
__be16 *dfp = NULL;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT |
IP_VS_RT_MODE_TUNNEL, &saddr, ipvsh);
if (local < 0)
goto tx_error;
if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
rt = skb_rtable(skb);
tdev = rt->dst.dev;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
&next_protocol, NULL, &dsfield,
&ttl, dfp);
if (IS_ERR(skb))
goto tx_error;
skb = iptunnel_handle_offloads(
skb, false, __tun_gso_type_mask(AF_INET, cp->af));
if (IS_ERR(skb))
goto tx_error;
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = next_protocol;
iph->tos = dsfield;
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = ttl;
ip_select_ident(net, skb, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->ignore_df = 1;
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
tx_error:
if (!IS_ERR(skb))
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
int ret;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT,
&saddr)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
if (rt_is_output_route(skb_rtable(skb)))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
/* Copy DF, reset fragment offset and MF */
df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom
|| skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
consume_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb->transport_header = skb->network_header;
/* fix old IP header checksum */
ip_send_check(old_iph);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
ip_select_ident(iph, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
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;
}