/*
* It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn,
* rewrite addresses of the packet and send it on its way...
*/
static unsigned int
ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *pskb;
struct iphdr *iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
int ihl;
EnterFunction(11);
if (skb->ipvs_property)
return NF_ACCEPT;
iph = ip_hdr(skb);
if (unlikely(iph->protocol == IPPROTO_ICMP)) {
int related, verdict = ip_vs_out_icmp(pskb, &related);
if (related)
return verdict;
skb = *pskb;
iph = ip_hdr(skb);
}
pp = ip_vs_proto_get(iph->protocol);
if (unlikely(!pp))
return NF_ACCEPT;
/* reassemble IP fragments */
if (unlikely(iph->frag_off & htons(IP_MF|IP_OFFSET) &&
!pp->dont_defrag)) {
skb = ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT);
if (!skb)
return NF_STOLEN;
iph = ip_hdr(skb);
*pskb = skb;
}
ihl = iph->ihl << 2;
/*
* Check if the packet belongs to an existing entry
*/
cp = pp->conn_out_get(skb, pp, iph, ihl, 0);
if (unlikely(!cp)) {
if (sysctl_ip_vs_nat_icmp_send &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP)) {
__be16 _ports[2], *pptr;
pptr = skb_header_pointer(skb, ihl,
sizeof(_ports), _ports);
if (pptr == NULL)
return NF_ACCEPT; /* Not for me */
if (ip_vs_lookup_real_service(iph->protocol,
iph->saddr, pptr[0])) {
/*
* Notify the real server: there is no
* existing entry if it is not RST
* packet or not TCP packet.
*/
if (iph->protocol != IPPROTO_TCP
|| !is_tcp_reset(skb)) {
icmp_send(skb,ICMP_DEST_UNREACH,
ICMP_PORT_UNREACH, 0);
return NF_DROP;
}
}
}
IP_VS_DBG_PKT(12, pp, skb, 0,
"packet continues traversal as normal");
return NF_ACCEPT;
}
IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet");
if (!ip_vs_make_skb_writable(pskb, ihl))
goto drop;
/* mangle the packet */
if (pp->snat_handler && !pp->snat_handler(pskb, pp, cp))
goto drop;
skb = *pskb;
ip_hdr(skb)->saddr = cp->vaddr;
ip_send_check(ip_hdr(skb));
/* For policy routing, packets originating from this
* machine itself may be routed differently to packets
* passing through. We want this packet to be routed as
* if it came from this machine itself. So re-compute
* the routing information.
*/
if (ip_route_me_harder(pskb, RTN_LOCAL) != 0)
goto drop;
skb = *pskb;
IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT");
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
ip_vs_conn_put(cp);
skb->ipvs_property = 1;
LeaveFunction(11);
return NF_ACCEPT;
drop:
ip_vs_conn_put(cp);
kfree_skb(*pskb);
return NF_STOLEN;
}
/*
* Check if it's for virtual services, look it up,
* and send it on its way...
*/
static unsigned int
ip_vs_in(unsigned int hooknum, struct sk_buff **pskb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *pskb;
struct iphdr *iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
int ret, restart;
int ihl;
/*
* Big tappo: only PACKET_HOST (neither loopback nor mcasts)
* ... don't know why 1st test DOES NOT include 2nd (?)
*/
if (unlikely(skb->pkt_type != PACKET_HOST
|| skb->dev == &loopback_dev || skb->sk)) {
IP_VS_DBG(12, "packet type=%d proto=%d daddr=%d.%d.%d.%d ignored\n",
skb->pkt_type,
ip_hdr(skb)->protocol,
NIPQUAD(ip_hdr(skb)->daddr));
return NF_ACCEPT;
}
iph = ip_hdr(skb);
if (unlikely(iph->protocol == IPPROTO_ICMP)) {
int related, verdict = ip_vs_in_icmp(pskb, &related, hooknum);
if (related)
return verdict;
skb = *pskb;
iph = ip_hdr(skb);
}
/* Protocol supported? */
pp = ip_vs_proto_get(iph->protocol);
if (unlikely(!pp))
return NF_ACCEPT;
ihl = iph->ihl << 2;
/*
* Check if the packet belongs to an existing connection entry
*/
cp = pp->conn_in_get(skb, pp, iph, ihl, 0);
if (unlikely(!cp)) {
int v;
if (!pp->conn_schedule(skb, pp, &v, &cp))
return v;
}
if (unlikely(!cp)) {
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG_PKT(12, pp, skb, 0,
"packet continues traversal as normal");
return NF_ACCEPT;
}
IP_VS_DBG_PKT(11, pp, skb, 0, "Incoming packet");
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
if (sysctl_ip_vs_expire_nodest_conn) {
/* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
}
/* don't restart its timer, and silently
drop the packet. */
__ip_vs_conn_put(cp);
return NF_DROP;
}
ip_vs_in_stats(cp, skb);
restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
if (cp->packet_xmit)
ret = cp->packet_xmit(skb, cp, pp);
/* do not touch skb anymore */
else {
IP_VS_DBG_RL("warning: packet_xmit is null");
ret = NF_ACCEPT;
}
/* increase its packet counter and check if it is needed
to be synchronized */
atomic_inc(&cp->in_pkts);
if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
(cp->protocol != IPPROTO_TCP ||
cp->state == IP_VS_TCP_S_ESTABLISHED) &&
(atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
== sysctl_ip_vs_sync_threshold[0]))
ip_vs_sync_conn(cp);
ip_vs_conn_put(cp);
return ret;
}
/*
* It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn,
* rewrite addresses of the packet and send it on its way...
*/
static unsigned int ip_vs_out(unsigned int hooknum,
struct sk_buff **skb_p,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *skb_p;
struct iphdr *iph;
union ip_vs_tphdr h;
struct ip_vs_conn *cp;
int size;
int ihl;
EnterFunction(11);
if (skb->nfcache & NFC_IPVS_PROPERTY)
return NF_ACCEPT;
iph = skb->nh.iph;
if (iph->protocol == IPPROTO_ICMP)
return ip_vs_out_icmp(skb_p);
/* let it go if other IP protocols */
if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
return NF_ACCEPT;
/* reassemble IP fragments */
if (iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) {
skb = ip_defrag(skb, IP_DEFRAG_VS_OUT);
if (!skb)
return NF_STOLEN;
iph = skb->nh.iph;
*skb_p = skb;
}
/* make sure that protocol header available in skb data area,
note that skb data area may be reallocated. */
ihl = iph->ihl << 2;
if (ip_vs_header_check(skb, iph->protocol, ihl) == -1)
return NF_DROP;
iph = skb->nh.iph;
h.raw = (char*) iph + ihl;
/*
* Check if the packet belongs to an old entry
*/
cp = ip_vs_conn_out_get(iph->protocol, iph->saddr, h.portp[0],
iph->daddr, h.portp[1]);
if (!cp) {
if (sysctl_ip_vs_nat_icmp_send &&
ip_vs_lookup_real_service(iph->protocol,
iph->saddr, h.portp[0])) {
/*
* Notify the real server: there is no existing
* entry if it is not RST packet or not TCP packet.
*/
if (!h.th->rst || iph->protocol != IPPROTO_TCP) {
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PORT_UNREACH, 0);
kfree_skb(skb);
return NF_STOLEN;
}
}
IP_VS_DBG(12, "packet for %s %d.%d.%d.%d:%d "
"continue traversal as normal.\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->daddr),
ntohs(h.portp[1]));
if (skb_is_nonlinear(skb))
ip_send_check(iph);
return NF_ACCEPT;
}
/*
* If it has ip_vs_app helper, the helper may change the payload,
* so it needs full checksum checking and checksum calculation.
* If not, only the header (addr/port) is changed, so it is fast
* to do incremental checksum update, and let the destination host
* do final checksum checking.
*/
if (cp->app && skb_is_nonlinear(skb)) {
if (skb_linearize(skb, GFP_ATOMIC) != 0) {
ip_vs_conn_put(cp);
return NF_DROP;
}
iph = skb->nh.iph;
h.raw = (char*) iph + ihl;
}
size = skb->len - ihl;
IP_VS_DBG(11, "O-pkt: %s size=%d\n",
ip_vs_proto_name(iph->protocol), size);
/* do TCP/UDP checksum checking if it has application helper */
if (cp->app && (iph->protocol != IPPROTO_UDP || h.uh->check != 0)) {
switch (skb->ip_summed) {
case CHECKSUM_NONE:
skb->csum = csum_partial(h.raw, size, 0);
case CHECKSUM_HW:
if (csum_tcpudp_magic(iph->saddr, iph->daddr, size,
iph->protocol, skb->csum)) {
ip_vs_conn_put(cp);
IP_VS_DBG_RL("Outgoing failed %s checksum "
"from %d.%d.%d.%d (size=%d)!\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->saddr),
size);
return NF_DROP;
}
break;
default:
/* CHECKSUM_UNNECESSARY */
break;
}
}
IP_VS_DBG(11, "Outgoing %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->saddr), ntohs(h.portp[0]),
NIPQUAD(iph->daddr), ntohs(h.portp[1]));
/* mangle the packet */
iph->saddr = cp->vaddr;
h.portp[0] = cp->vport;
/*
* Call application helper if needed
*/
if (ip_vs_app_pkt_out(cp, skb) != 0) {
/* skb data has probably changed, update pointers */
iph = skb->nh.iph;
h.raw = (char*)iph + ihl;
size = skb->len - ihl;
}
/*
* Adjust TCP/UDP checksums
*/
if (!cp->app && (iph->protocol != IPPROTO_UDP || h.uh->check != 0)) {
/* Only port and addr are changed, do fast csum update */
ip_vs_fast_check_update(&h, cp->daddr, cp->vaddr,
cp->dport, cp->vport, iph->protocol);
if (skb->ip_summed == CHECKSUM_HW)
skb->ip_summed = CHECKSUM_NONE;
} else {
/* full checksum calculation */
switch (iph->protocol) {
case IPPROTO_TCP:
h.th->check = 0;
skb->csum = csum_partial(h.raw, size, 0);
h.th->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
size, iph->protocol,
skb->csum);
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%d)\n",
ip_vs_proto_name(iph->protocol), h.th->check,
(char*)&(h.th->check) - (char*)h.raw);
break;
case IPPROTO_UDP:
h.uh->check = 0;
skb->csum = csum_partial(h.raw, size, 0);
h.uh->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
size, iph->protocol,
skb->csum);
if (h.uh->check == 0)
h.uh->check = 0xFFFF;
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%d)\n",
ip_vs_proto_name(iph->protocol), h.uh->check,
(char*)&(h.uh->check) - (char*)h.raw);
break;
}
}
ip_send_check(iph);
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, VS_STATE_OUTPUT, iph, h.portp);
ip_vs_conn_put(cp);
skb->nfcache |= NFC_IPVS_PROPERTY;
LeaveFunction(11);
return NF_ACCEPT;
}
/*
* 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_protocol *pp)
{
__be16 _ports[2], *pptr;
struct iphdr *iph = ip_hdr(skb);
pptr = skb_header_pointer(skb, iph->ihl*4,
sizeof(_ports), _ports);
if (pptr == NULL) {
ip_vs_service_put(svc);
return NF_DROP;
}
/* if it is fwmark-based service, the cache_bypass sysctl is up
and the destination is RTN_UNICAST (and not local), then create
a cache_bypass connection entry */
if (sysctl_ip_vs_cache_bypass && svc->fwmark
&& (inet_addr_type(iph->daddr) == RTN_UNICAST)) {
int ret, cs;
struct ip_vs_conn *cp;
ip_vs_service_put(svc);
/* create a new connection entry */
IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n");
cp = ip_vs_conn_new(iph->protocol,
iph->saddr, pptr[0],
iph->daddr, pptr[1],
0, 0,
IP_VS_CONN_F_BYPASS,
NULL);
if (cp == NULL)
return NF_DROP;
/* statistics */
ip_vs_in_stats(cp, skb);
/* set state */
cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
/* transmit the first SYN packet */
ret = cp->packet_xmit(skb, cp, pp);
/* do not touch skb anymore */
atomic_inc(&cp->in_pkts);
ip_vs_conn_put(cp);
return ret;
}
/*
* When the virtual ftp service is presented, packets destined
* for other services on the VIP may get here (except services
* listed in the ipvs table), pass the packets, because it is
* not ipvs job to decide to drop the packets.
*/
if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) {
ip_vs_service_put(svc);
return NF_ACCEPT;
}
ip_vs_service_put(svc);
/*
* Notify the client that the destination is unreachable, and
* release the socket buffer.
* Since it is in IP layer, the TCP socket is not actually
* created, the TCP RST packet cannot be sent, instead that
* ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
return NF_DROP;
}
/*
* 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.
*/
static int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb)
{
struct iphdr *iph = skb->nh.iph;
__u16 *portp = (__u16 *)&(((char *)iph)[iph->ihl*4]);
/* if it is fwmark-based service, the cache_bypass sysctl is up
and the destination is RTN_UNICAST (and not local), then create
a cache_bypass connection entry */
if (sysctl_ip_vs_cache_bypass && svc->fwmark
&& (inet_addr_type(iph->daddr) == RTN_UNICAST)) {
int ret;
struct ip_vs_conn *cp;
ip_vs_service_put(svc);
/* create a new connection entry */
IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n");
cp = ip_vs_conn_new(iph->protocol,
iph->saddr, portp[0],
iph->daddr, portp[1],
0, 0,
IP_VS_CONN_F_BYPASS,
NULL);
if (cp == NULL) {
kfree_skb(skb);
return NF_STOLEN;
}
/* statistics */
ip_vs_in_stats(cp, skb);
/* set state */
ip_vs_set_state(cp, VS_STATE_INPUT, iph, portp);
/* transmit the first SYN packet */
ret = cp->packet_xmit(skb, cp);
atomic_inc(&cp->in_pkts);
ip_vs_conn_put(cp);
return ret;
}
/*
* When the virtual ftp service is presented, packets destined
* for other services on the VIP may get here (except services
* listed in the ipvs table), pass the packets, because it is
* not ipvs job to decide to drop the packets.
*/
if ((svc->port == FTPPORT) && (portp[1] != FTPPORT)) {
ip_vs_service_put(svc);
return NF_ACCEPT;
}
ip_vs_service_put(svc);
/*
* Notify the client that the destination is unreachable, and
* release the socket buffer.
* Since it is in IP layer, the TCP socket is not actually
* created, the TCP RST packet cannot be sent, instead that
* ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
kfree_skb(skb);
return NF_STOLEN;
}
/*
* Check if it's for virtual services, look it up,
* and send it on its way...
*/
static unsigned int ip_vs_in(unsigned int hooknum,
struct sk_buff **skb_p,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *skb_p;
struct iphdr *iph = skb->nh.iph;
union ip_vs_tphdr h;
struct ip_vs_conn *cp;
struct ip_vs_service *svc;
int ihl;
int ret;
/*
* Big tappo: only PACKET_HOST (nor loopback neither mcasts)
* ... don't know why 1st test DOES NOT include 2nd (?)
*/
if (skb->pkt_type != PACKET_HOST || skb->dev == &loopback_dev) {
IP_VS_DBG(12, "packet type=%d proto=%d daddr=%d.%d.%d.%d ignored\n",
skb->pkt_type,
iph->protocol,
NIPQUAD(iph->daddr));
return NF_ACCEPT;
}
if (iph->protocol == IPPROTO_ICMP)
return ip_vs_in_icmp(skb_p);
/* let it go if other IP protocols */
if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
return NF_ACCEPT;
/* make sure that protocol header available in skb data area,
note that skb data area may be reallocated. */
ihl = iph->ihl << 2;
if (ip_vs_header_check(skb, iph->protocol, ihl) == -1)
return NF_DROP;
iph = skb->nh.iph;
h.raw = (char*) iph + ihl;
/*
* Check if the packet belongs to an existing connection entry
*/
cp = ip_vs_conn_in_get(iph->protocol, iph->saddr, h.portp[0],
iph->daddr, h.portp[1]);
if (!cp &&
(h.th->syn || (iph->protocol!=IPPROTO_TCP)) &&
(svc = ip_vs_service_get(skb->nfmark, iph->protocol,
iph->daddr, h.portp[1]))) {
if (ip_vs_todrop()) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
*/
ip_vs_service_put(svc);
return NF_DROP;
}
/*
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
cp = ip_vs_schedule(svc, iph);
if (!cp)
return ip_vs_leave(svc, skb);
ip_vs_conn_stats(cp, svc);
ip_vs_service_put(svc);
}
if (!cp) {
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG(12, "packet for %s %d.%d.%d.%d:%d continue "
"traversal as normal.\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->daddr),
ntohs(h.portp[1]));
return NF_ACCEPT;
}
IP_VS_DBG(11, "Incoming %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->saddr), ntohs(h.portp[0]),
NIPQUAD(iph->daddr), ntohs(h.portp[1]));
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
if (sysctl_ip_vs_expire_nodest_conn) {
/* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
} else {
/* don't restart its timer, and silently
drop the packet. */
__ip_vs_conn_put(cp);
}
return NF_DROP;
}
ip_vs_in_stats(cp, skb);
ip_vs_set_state(cp, VS_STATE_INPUT, iph, h.portp);
if (cp->packet_xmit)
ret = cp->packet_xmit(skb, cp);
else {
IP_VS_DBG_RL("warning: packet_xmit is null");
ret = NF_ACCEPT;
}
/* increase its packet counter and check if it is needed
to be synchronized */
atomic_inc(&cp->in_pkts);
if (ip_vs_sync_state & IP_VS_STATE_MASTER &&
(cp->protocol != IPPROTO_TCP ||
cp->state == IP_VS_S_ESTABLISHED) &&
(atomic_read(&cp->in_pkts) % 50 == sysctl_ip_vs_sync_threshold))
ip_vs_sync_conn(cp);
ip_vs_conn_put(cp);
return ret;
}
/*
* It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn,
* rewrite addresses of the packet and send it on its way...
*/
static unsigned int
ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *pskb;
struct iphdr *iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
int ihl;
EnterFunction(11);
if (skb->nfcache & NFC_IPVS_PROPERTY)
return NF_ACCEPT;
if (skb->ip_summed == CHECKSUM_HW) {
if (skb_checksum_help(pskb, (out == NULL)))
return NF_DROP;
if (skb != *pskb)
skb = *pskb;
}
iph = skb->nh.iph;
if (unlikely(iph->protocol == IPPROTO_ICMP)) {
int related, verdict = ip_vs_out_icmp(pskb, &related);
if (related)
return verdict;
skb = *pskb;
iph = skb->nh.iph;
}
pp = ip_vs_proto_get(iph->protocol);
if (unlikely(!pp))
return NF_ACCEPT;
/* reassemble IP fragments */
if (unlikely(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET) &&
!pp->dont_defrag)) {
skb = ip_vs_gather_frags(skb);
if (!skb)
return NF_STOLEN;
iph = skb->nh.iph;
*pskb = skb;
}
ihl = iph->ihl << 2;
/*
* Check if the packet belongs to an existing entry
*/
cp = pp->conn_out_get(skb, pp, iph, ihl, 0);
if (unlikely(!cp)) {
if (sysctl_ip_vs_nat_icmp_send &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP)) {
__u16 ports[2];
if (skb_copy_bits(skb, ihl, ports, sizeof(ports)) < 0)
return NF_ACCEPT; /* Not for me */
if (ip_vs_lookup_real_service(iph->protocol,
iph->saddr, ports[0])) {
/*
* Notify the real server: there is no
* existing entry if it is not RST
* packet or not TCP packet.
*/
if (iph->protocol != IPPROTO_TCP
|| !is_tcp_reset(skb)) {
icmp_send(skb,ICMP_DEST_UNREACH,
ICMP_PORT_UNREACH, 0);
return NF_DROP;
}
}
}
IP_VS_DBG_PKT(12, pp, skb, 0,
"packet continues traversal as normal");
return NF_ACCEPT;
}
IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet");
if (!ip_vs_make_skb_writable(pskb, ihl))
goto drop;
/* mangle the packet */
if (pp->snat_handler && !pp->snat_handler(pskb, pp, cp))
goto drop;
skb = *pskb;
skb->nh.iph->saddr = cp->vaddr;
ip_send_check(skb->nh.iph);
IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT");
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
ip_vs_conn_put(cp);
skb->nfcache |= NFC_IPVS_PROPERTY;
LeaveFunction(11);
return NF_ACCEPT;
drop:
ip_vs_conn_put(cp);
kfree_skb(*pskb);
return NF_STOLEN;
}
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;
}
