summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPatrick McHardy <kaber@trash.net>2010-10-21 16:25:51 +0200
committerPatrick McHardy <kaber@trash.net>2010-10-21 16:25:51 +0200
commit3b1a1ce6f418cb7ab35eb55c8a6575987a524e30 (patch)
treea3ebee69d6370631746a348f5852eeb955df5bd3
parentcc6eb433856983e91071469c4ce57accb6947ccb (diff)
parentb0aeef30433ea6854e985c2e9842fa19f51b95cc (diff)
Merge branch 'for-patrick' of git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6
-rw-r--r--include/net/ip_vs.h53
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c29
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c586
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c18
-rw-r--r--net/netfilter/ipvs/ip_vs_ftp.c7
-rw-r--r--net/netfilter/ipvs/ip_vs_proto.c8
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_ah_esp.c52
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_sctp.c8
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_tcp.c52
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_udp.c51
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c503
12 files changed, 959 insertions, 410 deletions
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 6e8a6192e574..b7bbd6c28cfa 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -25,7 +25,7 @@
#include <linux/ip.h>
#include <linux/ipv6.h> /* for struct ipv6hdr */
#include <net/ipv6.h> /* for ipv6_addr_copy */
-#ifdef CONFIG_IP_VS_NFCT
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netfilter/nf_conntrack.h>
#endif
@@ -136,24 +136,24 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
if (net_ratelimit()) \
printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__); \
} while (0)
-#define IP_VS_DBG_PKT(level, pp, skb, ofs, msg) \
+#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg) \
do { \
if (level <= ip_vs_get_debug_level()) \
- pp->debug_packet(pp, skb, ofs, msg); \
+ pp->debug_packet(af, pp, skb, ofs, msg); \
} while (0)
-#define IP_VS_DBG_RL_PKT(level, pp, skb, ofs, msg) \
+#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg) \
do { \
if (level <= ip_vs_get_debug_level() && \
net_ratelimit()) \
- pp->debug_packet(pp, skb, ofs, msg); \
+ pp->debug_packet(af, pp, skb, ofs, msg); \
} while (0)
#else /* NO DEBUGGING at ALL */
#define IP_VS_DBG_BUF(level, msg...) do {} while (0)
#define IP_VS_ERR_BUF(msg...) do {} while (0)
#define IP_VS_DBG(level, msg...) do {} while (0)
#define IP_VS_DBG_RL(msg...) do {} while (0)
-#define IP_VS_DBG_PKT(level, pp, skb, ofs, msg) do {} while (0)
-#define IP_VS_DBG_RL_PKT(level, pp, skb, ofs, msg) do {} while (0)
+#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg) do {} while (0)
+#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg) do {} while (0)
#endif
#define IP_VS_BUG() BUG()
@@ -345,7 +345,7 @@ struct ip_vs_protocol {
int (*app_conn_bind)(struct ip_vs_conn *cp);
- void (*debug_packet)(struct ip_vs_protocol *pp,
+ void (*debug_packet)(int af, struct ip_vs_protocol *pp,
const struct sk_buff *skb,
int offset,
const char *msg);
@@ -409,6 +409,7 @@ struct ip_vs_conn {
/* packet transmitter for different forwarding methods. If it
mangles the packet, it must return NF_DROP or better NF_STOLEN,
otherwise this must be changed to a sk_buff **.
+ NF_ACCEPT can be returned when destination is local.
*/
int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp);
@@ -597,11 +598,19 @@ struct ip_vs_app {
__be16 port; /* port number in net order */
atomic_t usecnt; /* usage counter */
- /* output hook: return false if can't linearize. diff set for TCP. */
+ /*
+ * output hook: Process packet in inout direction, diff set for TCP.
+ * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
+ * 2=Mangled but checksum was not updated
+ */
int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *,
struct sk_buff *, int *diff);
- /* input hook: return false if can't linearize. diff set for TCP. */
+ /*
+ * input hook: Process packet in outin direction, diff set for TCP.
+ * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
+ * 2=Mangled but checksum was not updated
+ */
int (*pkt_in)(struct ip_vs_app *, struct ip_vs_conn *,
struct sk_buff *, int *diff);
@@ -819,7 +828,8 @@ extern int
ip_vs_set_state_timeout(int *table, int num, const char *const *names,
const char *name, int to);
extern void
-ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb,
+ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
+ const struct sk_buff *skb,
int offset, const char *msg);
extern struct ip_vs_protocol ip_vs_protocol_tcp;
@@ -841,7 +851,8 @@ extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc);
extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
extern struct ip_vs_conn *
-ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb);
+ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
+ struct ip_vs_protocol *pp, int *ignored);
extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_protocol *pp);
@@ -1013,6 +1024,24 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
return csum_partial(diff, sizeof(diff), oldsum);
}
+/*
+ * Forget current conntrack (unconfirmed) and attach notrack entry
+ */
+static inline void ip_vs_notrack(struct sk_buff *skb)
+{
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+
+ if (!ct || !nf_ct_is_untracked(ct)) {
+ nf_reset(skb);
+ skb->nfct = &nf_ct_untracked_get()->ct_general;
+ skb->nfctinfo = IP_CT_NEW;
+ nf_conntrack_get(skb->nfct);
+ }
+#endif
+}
+
#ifdef CONFIG_IP_VS_NFCT
/*
* Netfilter connection tracking
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index e2e00c4da883..0047923c1f22 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -462,6 +462,18 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
return 0;
}
+ if (manip == IP_NAT_MANIP_SRC)
+ statusbit = IPS_SRC_NAT;
+ else
+ statusbit = IPS_DST_NAT;
+
+ /* Invert if this is reply dir. */
+ if (dir == IP_CT_DIR_REPLY)
+ statusbit ^= IPS_NAT_MASK;
+
+ if (!(ct->status & statusbit))
+ return 1;
+
pr_debug("icmp_reply_translation: translating error %p manip %u "
"dir %s\n", skb, manip,
dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY");
@@ -496,20 +508,9 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
/* Change outer to look the reply to an incoming packet
* (proto 0 means don't invert per-proto part). */
- if (manip == IP_NAT_MANIP_SRC)
- statusbit = IPS_SRC_NAT;
- else
- statusbit = IPS_DST_NAT;
-
- /* Invert if this is reply dir. */
- if (dir == IP_CT_DIR_REPLY)
- statusbit ^= IPS_NAT_MASK;
-
- if (ct->status & statusbit) {
- nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
- if (!manip_pkt(0, skb, 0, &target, manip))
- return 0;
- }
+ nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+ if (!manip_pkt(0, skb, 0, &target, manip))
+ return 0;
return 1;
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 1d1a529dbe24..e9adecdc8ca4 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -563,6 +563,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
*/
if (!(cp->flags & IP_VS_CONN_F_TEMPLATE))
conn_flags &= ~IP_VS_CONN_F_INACTIVE;
+ /* connections inherit forwarding method from dest */
+ cp->flags &= ~IP_VS_CONN_F_FWD_MASK;
}
cp->flags |= conn_flags;
cp->dest = dest;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e5fef7aef0d4..b4e51e9c5a04 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -48,6 +48,7 @@
#ifdef CONFIG_IP_VS_IPV6
#include <net/ipv6.h>
#include <linux/netfilter_ipv6.h>
+#include <net/ip6_route.h>
#endif
#include <net/ip_vs.h>
@@ -342,7 +343,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
* Protocols supported: TCP, UDP
*/
struct ip_vs_conn *
-ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb)
+ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
+ struct ip_vs_protocol *pp, int *ignored)
{
struct ip_vs_conn *cp = NULL;
struct ip_vs_iphdr iph;
@@ -350,16 +352,44 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb)
__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;
/*
+ * 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. It is risky
+ * for fwmark services but mostly for persistent services.
+ */
+ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
+ (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) &&
+ (cp = pp->conn_in_get(svc->af, skb, pp, &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;
+ }
+
+ /*
* Persistent service
*/
- if (svc->flags & IP_VS_SVC_F_PERSISTENT)
+ if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
+ *ignored = 0;
return ip_vs_sched_persist(svc, skb, pptr);
+ }
/*
* Non-persistent service
@@ -372,6 +402,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb)
return NULL;
}
+ *ignored = 0;
+
dest = svc->scheduler->schedule(svc, skb);
if (dest == NULL) {
IP_VS_DBG(1, "Schedule: no dest found.\n");
@@ -498,35 +530,32 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
* ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
*/
#ifdef CONFIG_IP_VS_IPV6
- if (svc->af == AF_INET6)
+ if (svc->af == AF_INET6) {
+ if (!skb->dev) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ skb->dev = net->loopback_dev;
+ }
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
- else
+ } else
#endif
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
return NF_DROP;
}
-/*
- * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING
- * chain and is used to avoid double NAT and confirmation when we do
- * not want to keep the conntrack structure
- */
-static unsigned int ip_vs_post_routing(unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
- if (!skb->ipvs_property)
- return NF_ACCEPT;
- /* The packet was sent from IPVS, exit this chain */
- return NF_STOP;
+ return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
}
-__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
+static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum)
{
- return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
+ if (NF_INET_LOCAL_IN == hooknum)
+ return IP_DEFRAG_VS_IN;
+ if (NF_INET_FORWARD == hooknum)
+ return IP_DEFRAG_VS_FWD;
+ return IP_DEFRAG_VS_OUT;
}
static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
@@ -589,10 +618,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (inout)
- IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph,
+ IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
"Forwarding altered outgoing ICMP");
else
- IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph,
+ IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
"Forwarding altered incoming ICMP");
}
@@ -634,11 +663,13 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
skb->ip_summed = CHECKSUM_PARTIAL;
if (inout)
- IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph,
- "Forwarding altered outgoing ICMPv6");
+ IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
+ (void *)ciph - (void *)iph,
+ "Forwarding altered outgoing ICMPv6");
else
- IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph,
- "Forwarding altered incoming ICMPv6");
+ IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
+ (void *)ciph - (void *)iph,
+ "Forwarding altered incoming ICMPv6");
}
#endif
@@ -679,11 +710,23 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
#endif
ip_vs_nat_icmp(skb, pp, cp, 1);
+#ifdef CONFIG_IP_VS_IPV6
+ if (af == AF_INET6) {
+ if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+ goto out;
+ } else
+#endif
+ if ((sysctl_ip_vs_snat_reroute ||
+ skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+ ip_route_me_harder(skb, RTN_LOCAL) != 0)
+ goto out;
+
/* do the statistics and put it back */
ip_vs_out_stats(cp, skb);
+ skb->ipvs_property = 1;
if (!(cp->flags & IP_VS_CONN_F_NFCT))
- skb->ipvs_property = 1;
+ ip_vs_notrack(skb);
else
ip_vs_update_conntrack(skb, cp, 0);
verdict = NF_ACCEPT;
@@ -699,7 +742,8 @@ out:
* Find any that might be relevant, check against existing connections.
* Currently handles error types - unreachable, quench, ttl exceeded.
*/
-static int ip_vs_out_icmp(struct sk_buff *skb, int *related)
+static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
+ unsigned int hooknum)
{
struct iphdr *iph;
struct icmphdr _icmph, *ic;
@@ -714,7 +758,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related)
/* reassemble IP fragments */
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
- if (ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT))
+ if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
}
@@ -757,7 +801,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related)
pp->dont_defrag))
return NF_ACCEPT;
- IP_VS_DBG_PKT(11, pp, skb, offset, "Checking outgoing ICMP for");
+ IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
+ "Checking outgoing ICMP for");
offset += cih->ihl * 4;
@@ -773,7 +818,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related)
}
#ifdef CONFIG_IP_VS_IPV6
-static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related)
+static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
+ unsigned int hooknum)
{
struct ipv6hdr *iph;
struct icmp6hdr _icmph, *ic;
@@ -789,7 +835,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related)
/* reassemble IP fragments */
if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
- if (ip_vs_gather_frags_v6(skb, IP_DEFRAG_VS_OUT))
+ if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
}
@@ -832,7 +878,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related)
if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag))
return NF_ACCEPT;
- IP_VS_DBG_PKT(11, pp, skb, offset, "Checking outgoing ICMPv6 for");
+ IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
+ "Checking outgoing ICMPv6 for");
offset += sizeof(struct ipv6hdr);
@@ -880,7 +927,7 @@ static unsigned int
handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
struct ip_vs_conn *cp, int ihl)
{
- IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet");
+ IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
if (!skb_make_writable(skb, ihl))
goto drop;
@@ -914,23 +961,24 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
* if it came from this machine itself. So re-compute
* the routing information.
*/
- if (sysctl_ip_vs_snat_reroute) {
#ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6) {
- if (ip6_route_me_harder(skb) != 0)
- goto drop;
- } else
+ if (af == AF_INET6) {
+ if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+ goto drop;
+ } else
#endif
- if (ip_route_me_harder(skb, RTN_LOCAL) != 0)
- goto drop;
- }
+ if ((sysctl_ip_vs_snat_reroute ||
+ skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+ ip_route_me_harder(skb, RTN_LOCAL) != 0)
+ goto drop;
- IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT");
+ IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
+ skb->ipvs_property = 1;
if (!(cp->flags & IP_VS_CONN_F_NFCT))
- skb->ipvs_property = 1;
+ ip_vs_notrack(skb);
else
ip_vs_update_conntrack(skb, cp, 0);
ip_vs_conn_put(cp);
@@ -946,53 +994,54 @@ drop:
}
/*
- * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn.
*/
static unsigned int
-ip_vs_out(unsigned int hooknum, struct sk_buff *skb,
- const struct net_device *in, const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
{
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
- int af;
EnterFunction(11);
- af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6;
-
+ /* Already marked as IPVS request or reply? */
if (skb->ipvs_property)
return NF_ACCEPT;
+ /* Bad... Do not break raw sockets */
+ if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT &&
+ af == AF_INET)) {
+ struct sock *sk = skb->sk;
+ struct inet_sock *inet = inet_sk(skb->sk);
+
+ if (inet && sk->sk_family == PF_INET && inet->nodefrag)
+ return NF_ACCEPT;
+ }
+
+ if (unlikely(!skb_dst(skb)))
+ return NF_ACCEPT;
+
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
- int related, verdict = ip_vs_out_icmp_v6(skb, &related);
+ int related;
+ int verdict = ip_vs_out_icmp_v6(skb, &related,
+ hooknum);
- if (related) {
- if (sysctl_ip_vs_snat_reroute &&
- NF_ACCEPT == verdict &&
- ip6_route_me_harder(skb))
- verdict = NF_DROP;
+ if (related)
return verdict;
- }
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
}
} else
#endif
if (unlikely(iph.protocol == IPPROTO_ICMP)) {
- int related, verdict = ip_vs_out_icmp(skb, &related);
+ int related;
+ int verdict = ip_vs_out_icmp(skb, &related, hooknum);
- if (related) {
- if (sysctl_ip_vs_snat_reroute &&
- NF_ACCEPT == verdict &&
- ip_route_me_harder(skb, RTN_LOCAL))
- verdict = NF_DROP;
+ if (related)
return verdict;
- }
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
}
@@ -1003,19 +1052,19 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb,
/* reassemble IP fragments */
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
- int related, verdict = ip_vs_out_icmp_v6(skb, &related);
-
- if (related)
- return verdict;
-
- ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+ if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
+ if (ip_vs_gather_frags_v6(skb,
+ ip_vs_defrag_user(hooknum)))
+ return NF_STOLEN;
}
+
+ ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
} else
#endif
if (unlikely(ip_hdr(skb)->frag_off & htons(IP_MF|IP_OFFSET) &&
!pp->dont_defrag)) {
- if (ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT))
+ if (ip_vs_gather_frags(skb,
+ ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
@@ -1026,55 +1075,123 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb,
*/
cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0);
- if (unlikely(!cp)) {
- if (sysctl_ip_vs_nat_icmp_send &&
- (pp->protocol == IPPROTO_TCP ||
- pp->protocol == IPPROTO_UDP ||
- pp->protocol == IPPROTO_SCTP)) {
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, iph.len,
- sizeof(_ports), _ports);
- if (pptr == NULL)
- return NF_ACCEPT; /* Not for me */
- if (ip_vs_lookup_real_service(af, 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 &&
- iph.protocol != IPPROTO_SCTP)
- || ((iph.protocol == IPPROTO_TCP
- && !is_tcp_reset(skb, iph.len))
- || (iph.protocol == IPPROTO_SCTP
- && !is_sctp_abort(skb,
- iph.len)))) {
+ if (likely(cp))
+ return handle_response(af, skb, pp, cp, iph.len);
+ if (sysctl_ip_vs_nat_icmp_send &&
+ (pp->protocol == IPPROTO_TCP ||
+ pp->protocol == IPPROTO_UDP ||
+ pp->protocol == IPPROTO_SCTP)) {
+ __be16 _ports[2], *pptr;
+
+ pptr = skb_header_pointer(skb, iph.len,
+ sizeof(_ports), _ports);
+ if (pptr == NULL)
+ return NF_ACCEPT; /* Not for me */
+ if (ip_vs_lookup_real_service(af, 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 &&
+ iph.protocol != IPPROTO_SCTP)
+ || ((iph.protocol == IPPROTO_TCP
+ && !is_tcp_reset(skb, iph.len))
+ || (iph.protocol == IPPROTO_SCTP
+ && !is_sctp_abort(skb,
+ iph.len)))) {
#ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6)
- icmpv6_send(skb,
- ICMPV6_DEST_UNREACH,
- ICMPV6_PORT_UNREACH,
- 0);
- else
+ if (af == AF_INET6) {
+ struct net *net =
+ dev_net(skb_dst(skb)->dev);
+
+ if (!skb->dev)
+ skb->dev = net->loopback_dev;
+ icmpv6_send(skb,
+ ICMPV6_DEST_UNREACH,
+ ICMPV6_PORT_UNREACH,
+ 0);
+ } else
#endif
- icmp_send(skb,
- ICMP_DEST_UNREACH,
- ICMP_PORT_UNREACH, 0);
- return NF_DROP;
- }
+ 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(12, af, pp, skb, 0,
+ "ip_vs_out: packet continues traversal as normal");
+ return NF_ACCEPT;
+}
+
+/*
+ * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
+ * used only for VS/NAT.
+ * Check if packet is reply for established ip_vs_conn.
+ */
+static unsigned int
+ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ return ip_vs_out(hooknum, skb, AF_INET);
+}
+
+/*
+ * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
+ * Check if packet is reply for established ip_vs_conn.
+ */
+static unsigned int
+ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ unsigned int verdict;
- return handle_response(af, skb, pp, cp, iph.len);
+ /* Disable BH in LOCAL_OUT until all places are fixed */
+ local_bh_disable();
+ verdict = ip_vs_out(hooknum, skb, AF_INET);
+ local_bh_enable();
+ return verdict;
}
+#ifdef CONFIG_IP_VS_IPV6
+
+/*
+ * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
+ * used only for VS/NAT.
+ * Check if packet is reply for established ip_vs_conn.
+ */
+static unsigned int
+ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ return ip_vs_out(hooknum, skb, AF_INET6);
+}
+
+/*
+ * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
+ * Check if packet is reply for established ip_vs_conn.
+ */
+static unsigned int
+ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ unsigned int verdict;
+
+ /* Disable BH in LOCAL_OUT until all places are fixed */
+ local_bh_disable();
+ verdict = ip_vs_out(hooknum, skb, AF_INET6);
+ local_bh_enable();
+ return verdict;
+}
+
+#endif
/*
* Handle ICMP messages in the outside-to-inside direction (incoming).
@@ -1098,8 +1215,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
/* reassemble IP fragments */
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
- if (ip_vs_gather_frags(skb, hooknum == NF_INET_LOCAL_IN ?
- IP_DEFRAG_VS_IN : IP_DEFRAG_VS_FWD))
+ if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
}
@@ -1142,7 +1258,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
pp->dont_defrag))
return NF_ACCEPT;
- IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMP for");
+ IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
+ "Checking incoming ICMP for");
offset += cih->ihl * 4;
@@ -1176,7 +1293,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
offset += 2 * sizeof(__u16);
verdict = ip_vs_icmp_xmit(skb, cp, pp, offset);
- /* do not touch skb anymore */
+ /* LOCALNODE from FORWARD hook is not supported */
+ if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD &&
+ skb_rtable(skb)->rt_flags & RTCF_LOCAL) {
+ IP_VS_DBG(1, "%s(): "
+ "local delivery to %pI4 but in FORWARD\n",
+ __func__, &skb_rtable(skb)->rt_dst);
+ verdict = NF_DROP;
+ }
out:
__ip_vs_conn_put(cp);
@@ -1197,14 +1321,13 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
struct ip_vs_protocol *pp;
unsigned int offset, verdict;
union nf_inet_addr snet;
+ struct rt6_info *rt;
*related = 1;
/* reassemble IP fragments */
if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
- if (ip_vs_gather_frags_v6(skb, hooknum == NF_INET_LOCAL_IN ?
- IP_DEFRAG_VS_IN :
- IP_DEFRAG_VS_FWD))
+ if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
}
@@ -1247,7 +1370,8 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag))
return NF_ACCEPT;
- IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMPv6 for");
+ IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
+ "Checking incoming ICMPv6 for");
offset += sizeof(struct ipv6hdr);
@@ -1275,7 +1399,15 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
IPPROTO_SCTP == cih->nexthdr)
offset += 2 * sizeof(__u16);
verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset);
- /* do not touch skb anymore */
+ /* LOCALNODE from FORWARD hook is not supported */
+ if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD &&
+ (rt = (struct rt6_info *) skb_dst(skb)) &&
+ rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK) {
+ IP_VS_DBG(1, "%s(): "
+ "local delivery to %pI6 but in FORWARD\n",
+ __func__, &rt->rt6i_dst);
+ verdict = NF_DROP;
+ }
__ip_vs_conn_put(cp);
@@ -1289,35 +1421,49 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
* and send it on its way...
*/
static unsigned int
-ip_vs_in(unsigned int hooknum, struct sk_buff *skb,
- const struct net_device *in, const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
{
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
- int ret, restart, af, pkts;
-
- af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6;
+ int ret, restart, pkts;
- ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+ /* Already marked as IPVS request or reply? */
+ if (skb->ipvs_property)
+ return NF_ACCEPT;
/*
- * Big tappo: only PACKET_HOST, including loopback for local client
- * Don't handle local packets on IPv6 for now
+ * Big tappo:
+ * - remote client: only PACKET_HOST
+ * - route: used for struct net when skb->dev is unset
*/
- if (unlikely(skb->pkt_type != PACKET_HOST)) {
- IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s ignored\n",
- skb->pkt_type,
- iph.protocol,
- IP_VS_DBG_ADDR(af, &iph.daddr));
+ if (unlikely((skb->pkt_type != PACKET_HOST &&
+ hooknum != NF_INET_LOCAL_OUT) ||
+ !skb_dst(skb))) {
+ ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+ IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s"
+ " ignored in hook %u\n",
+ skb->pkt_type, iph.protocol,
+ IP_VS_DBG_ADDR(af, &iph.daddr), hooknum);
return NF_ACCEPT;
}
+ ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+
+ /* Bad... Do not break raw sockets */
+ if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT &&
+ af == AF_INET)) {
+ struct sock *sk = skb->sk;
+ struct inet_sock *inet = inet_sk(skb->sk);
+
+ if (inet && sk->sk_family == PF_INET && inet->nodefrag)
+ return NF_ACCEPT;
+ }
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
- int related, verdict = ip_vs_in_icmp_v6(skb, &related, hooknum);
+ int related;
+ int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum);
if (related)
return verdict;
@@ -1326,7 +1472,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb,
} else
#endif
if (unlikely(iph.protocol == IPPROTO_ICMP)) {
- int related, verdict = ip_vs_in_icmp(skb, &related, hooknum);
+ int related;
+ int verdict = ip_vs_in_icmp(skb, &related, hooknum);
if (related)
return verdict;
@@ -1346,23 +1493,18 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb,
if (unlikely(!cp)) {
int v;
- /* For local client packets, it could be a response */
- cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0);
- if (cp)
- return handle_response(af, skb, pp, cp, iph.len);
-
if (!pp->conn_schedule(af, 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");
+ IP_VS_DBG_PKT(12, af, pp, skb, 0,
+ "ip_vs_in: packet continues traversal as normal");
return NF_ACCEPT;
}
- IP_VS_DBG_PKT(11, pp, skb, 0, "Incoming packet");
+ IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
@@ -1429,6 +1571,72 @@ out:
return ret;
}
+/*
+ * AF_INET handler in NF_INET_LOCAL_IN chain
+ * Schedule and forward packets from remote clients
+ */
+static unsigned int
+ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ return ip_vs_in(hooknum, skb, AF_INET);
+}
+
+/*
+ * AF_INET handler in NF_INET_LOCAL_OUT chain
+ * Schedule and forward packets from local clients
+ */
+static unsigned int
+ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ unsigned int verdict;
+
+ /* Disable BH in LOCAL_OUT until all places are fixed */
+ local_bh_disable();
+ verdict = ip_vs_in(hooknum, skb, AF_INET);
+ local_bh_enable();
+ return verdict;
+}
+
+#ifdef CONFIG_IP_VS_IPV6
+
+/*
+ * AF_INET6 handler in NF_INET_LOCAL_IN chain
+ * Schedule and forward packets from remote clients
+ */
+static unsigned int
+ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ return ip_vs_in(hooknum, skb, AF_INET6);
+}
+
+/*
+ * AF_INET6 handler in NF_INET_LOCAL_OUT chain
+ * Schedule and forward packets from local clients
+ */
+static unsigned int
+ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ unsigned int verdict;
+
+ /* Disable BH in LOCAL_OUT until all places are fixed */
+ local_bh_disable();
+ verdict = ip_vs_in(hooknum, skb, AF_INET6);
+ local_bh_enable();
+ return verdict;
+}
+
+#endif
+
/*
* It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP
@@ -1469,23 +1677,39 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
+ /* After packet filtering, change source only for VS/NAT */
+ {
+ .hook = ip_vs_reply4,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = 99,
+ },
/* After packet filtering, forward packet through VS/DR, VS/TUN,
* or VS/NAT(change destination), so that filtering rules can be
* applied to IPVS. */
{
- .hook = ip_vs_in,
+ .hook = ip_vs_remote_request4,
.owner = THIS_MODULE,
.pf = PF_INET,
- .hooknum = NF_INET_LOCAL_IN,
- .priority = 100,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = 101,
},
- /* After packet filtering, change source only for VS/NAT */
+ /* Before ip_vs_in, change source only for VS/NAT */
+ {
+ .hook = ip_vs_local_reply4,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = -99,
+ },
+ /* After mangle, schedule and forward local requests */
{
- .hook = ip_vs_out,
+ .hook = ip_vs_local_request4,
.owner = THIS_MODULE,
.pf = PF_INET,
- .hooknum = NF_INET_FORWARD,
- .priority = 100,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = -98,
},
/* After packet filtering (but before ip_vs_out_icmp), catch icmp
* destined for 0.0.0.0/0, which is for incoming IPVS connections */
@@ -1493,35 +1717,51 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
.hook = ip_vs_forward_icmp,
.owner = THIS_MODULE,
.pf = PF_INET,
- .hooknum = NF_INET_FORWARD,
- .priority = 99,
+ .hooknum = NF_INET_FORWARD,
+ .priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
+ /* After packet filtering, change source only for VS/NAT */
{
- .hook = ip_vs_post_routing,
+ .hook = ip_vs_reply4,
.owner = THIS_MODULE,
.pf = PF_INET,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP_PRI_NAT_SRC-1,
+ .hooknum = NF_INET_FORWARD,
+ .priority = 100,
},
#ifdef CONFIG_IP_VS_IPV6
+ /* After packet filtering, change source only for VS/NAT */
+ {
+ .hook = ip_vs_reply6,
+ .owner = THIS_MODULE,
+ .pf = PF_INET6,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = 99,
+ },
/* After packet filtering, forward packet through VS/DR, VS/TUN,
* or VS/NAT(change destination), so that filtering rules can be
* applied to IPVS. */
{
- .hook = ip_vs_in,
+ .hook = ip_vs_remote_request6,
.owner = THIS_MODULE,
.pf = PF_INET6,
- .hooknum = NF_INET_LOCAL_IN,
- .priority = 100,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = 101,
},
- /* After packet filtering, change source only for VS/NAT */
+ /* Before ip_vs_in, change source only for VS/NAT */
{
- .hook = ip_vs_out,
+ .hook = ip_vs_local_reply6,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = -99,
+ },
+ /* After mangle, schedule and forward local requests */
+ {
+ .hook = ip_vs_local_request6,
.owner = THIS_MODULE,
.pf = PF_INET6,
- .hooknum = NF_INET_FORWARD,
- .priority = 100,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = -98,
},
/* After packet filtering (but before ip_vs_out_icmp), catch icmp
* destined for 0.0.0.0/0, which is for incoming IPVS connections */
@@ -1529,16 +1769,16 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
.hook = ip_vs_forward_icmp_v6,
.owner = THIS_MODULE,
.pf = PF_INET6,
- .hooknum = NF_INET_FORWARD,
- .priority = 99,
+ .hooknum = NF_INET_FORWARD,
+ .priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
+ /* After packet filtering, change source only for VS/NAT */
{
- .hook = ip_vs_post_routing,
+ .hook = ip_vs_reply6,
.owner = THIS_MODULE,
.pf = PF_INET6,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP6_PRI_NAT_SRC-1,
+ .hooknum = NF_INET_FORWARD,
+ .priority = 100,
},
#endif
};
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 0b884d3e192f..5f5daa30b0af 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -777,20 +777,6 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
conn_flags |= IP_VS_CONN_F_INACTIVE;
- /* check if local node and update the flags */
-#ifdef CONFIG_IP_VS_IPV6
- if (svc->af == AF_INET6) {
- if (__ip_vs_addr_is_local_v6(&udest->addr.in6)) {
- conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK)
- | IP_VS_CONN_F_LOCALNODE;
- }
- } else
-#endif
- if (inet_addr_type(&init_net, udest->addr.ip) == RTN_LOCAL) {
- conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK)
- | IP_VS_CONN_F_LOCALNODE;
- }
-
/* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) {
conn_flags |= IP_VS_CONN_F_NOOUTPUT;
@@ -824,6 +810,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
dest->u_threshold = udest->u_threshold;
dest->l_threshold = udest->l_threshold;
+ spin_lock(&dest->dst_lock);
+ ip_vs_dst_reset(dest);
+ spin_unlock(&dest->dst_lock);
+
if (add)
ip_vs_new_estimator(&dest->stats);
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 090889a3b3af..75455000ad1c 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -242,9 +242,14 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
start-data, end-start,
buf, buf_len);
- if (ret)
+ 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;
+ }
}
/*
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 027f654799fe..c53998390877 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -172,8 +172,8 @@ ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp,
else if (ih->frag_off & htons(IP_OFFSET))
sprintf(buf, "%pI4->%pI4 frag", &ih->saddr, &ih->daddr);
else {
- __be16 _ports[2], *pptr
-;
+ __be16 _ports[2], *pptr;
+
pptr = skb_header_pointer(skb, offset + ih->ihl*4,
sizeof(_ports), _ports);
if (pptr == NULL)
@@ -223,13 +223,13 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp,
void
-ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp,
+ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
const struct sk_buff *skb,
int offset,
const char *msg)
{
#ifdef CONFIG_IP_VS_IPV6
- if (skb->protocol == htons(ETH_P_IPV6))
+ if (af == AF_INET6)
ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg);
else
#endif
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index 8956ef33ea6c..3a0461117d3f 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -117,54 +117,6 @@ ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
return 0;
}
-
-static void
-ah_esp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb,
- int offset, const char *msg)
-{
- char buf[256];
- struct iphdr _iph, *ih;
-
- ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
- if (ih == NULL)
- sprintf(buf, "TRUNCATED");
- else
- sprintf(buf, "%pI4->%pI4", &ih->saddr, &ih->daddr);
-
- pr_debug("%s: %s %s\n", msg, pp->name, buf);
-}
-
-#ifdef CONFIG_IP_VS_IPV6
-static void
-ah_esp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb,
- int offset, const char *msg)
-{
- char buf[256];
- struct ipv6hdr _iph, *ih;
-
- ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
- if (ih == NULL)
- sprintf(buf, "TRUNCATED");
- else
- sprintf(buf, "%pI6->%pI6", &ih->saddr, &ih->daddr);
-
- pr_debug("%s: %s %s\n", msg, pp->name, buf);
-}
-#endif
-
-static void
-ah_esp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb,
- int offset, const char *msg)
-{
-#ifdef CONFIG_IP_VS_IPV6
- if (skb->protocol == htons(ETH_P_IPV6))
- ah_esp_debug_packet_v6(pp, skb, offset, msg);
- else
-#endif
- ah_esp_debug_packet_v4(pp, skb, offset, msg);
-}
-
-
static void ah_esp_init(struct ip_vs_protocol *pp)
{
/* nothing to do now */
@@ -195,7 +147,7 @@ struct ip_vs_protocol ip_vs_protocol_ah = {
.register_app = NULL,
.unregister_app = NULL,
.app_conn_bind = NULL,
- .debug_packet = ah_esp_debug_packet,
+ .debug_packet = ip_vs_tcpudp_debug_packet,
.timeout_change = NULL, /* ISAKMP */
.set_state_timeout = NULL,
};
@@ -219,7 +171,7 @@ struct ip_vs_protocol ip_vs_protocol_esp = {
.register_app = NULL,
.unregister_app = NULL,
.app_conn_bind = NULL,
- .debug_packet = ah_esp_debug_packet,
+ .debug_packet = ip_vs_tcpudp_debug_packet,
.timeout_change = NULL, /* ISAKMP */
};
#endif
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 4c0855cb006e..d254345bfda7 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -31,6 +31,8 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
if ((sch->type == SCTP_CID_INIT) &&
(svc = ip_vs_service_get(af, skb->mark, iph.protocol,
&iph.daddr, sh->dest))) {
+ int ignored;
+
if (ip_vs_todrop()) {
/*
* It seems that we are very loaded.
@@ -44,8 +46,8 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
- *cpp = ip_vs_schedule(svc, skb);
- if (!*cpp) {
+ *cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+ if (!*cpp && !ignored) {
*verdict = ip_vs_leave(svc, skb, pp);
return 0;
}
@@ -174,7 +176,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
if (val != cmp) {
/* CRC failure, dump it. */
- IP_VS_DBG_RL_PKT(0, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
"Failed checksum for");
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 282d24de8592..f6c5200e2146 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -43,9 +43,12 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
return 0;
}
+ /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
if (th->syn &&
(svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr,
th->dest))) {
+ int ignored;
+
if (ip_vs_todrop()) {
/*
* It seems that we are very loaded.
@@ -60,8 +63,8 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
- *cpp = ip_vs_schedule(svc, skb);
- if (!*cpp) {
+ *cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+ if (!*cpp && !ignored) {
*verdict = ip_vs_leave(svc, skb, pp);
return 0;
}
@@ -101,15 +104,15 @@ tcp_partial_csum_update(int af, struct tcphdr *tcph,
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
tcph->check =
- csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
+ ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
ip_vs_check_diff2(oldlen, newlen,
- ~csum_unfold(tcph->check))));
+ csum_unfold(tcph->check))));
else
#endif
tcph->check =
- csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
+ ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
ip_vs_check_diff2(oldlen, newlen,
- ~csum_unfold(tcph->check))));
+ csum_unfold(tcph->check))));
}
@@ -120,6 +123,7 @@ tcp_snat_handler(struct sk_buff *skb,
struct tcphdr *tcph;
unsigned int tcphoff;
int oldlen;
+ int payload_csum = 0;
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
@@ -134,13 +138,20 @@ tcp_snat_handler(struct sk_buff *skb,
return 0;
if (unlikely(cp->app != NULL)) {
+ int ret;
+
/* Some checks before mangling */
if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
return 0;
/* Call application helper if needed */
- if (!ip_vs_app_pkt_out(cp, skb))
+ if (!(ret = ip_vs_app_pkt_out(cp, skb)))
return 0;
+ /* ret=2: csum update is needed after payload mangling */
+ if (ret == 1)
+ oldlen = skb->len - tcphoff;
+ else
+ payload_csum = 1;
}
tcph = (void *)skb_network_header(skb) + tcphoff;
@@ -151,12 +162,13 @@ tcp_snat_handler(struct sk_buff *skb,
tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
htons(oldlen),
htons(skb->len - tcphoff));
- } else if (!cp->app) {
+ } else if (!payload_csum) {
/* Only port and addr are changed, do fast csum update */
tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
cp->dport, cp->vport);
if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = (cp->app && pp->csum_check) ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
} else {
/* full checksum calculation */
tcph->check = 0;
@@ -174,6 +186,7 @@ tcp_snat_handler(struct sk_buff *skb,
skb->len - tcphoff,
cp->protocol,
skb->csum);
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
pp->name, tcph->check,
@@ -190,6 +203,7 @@ tcp_dnat_handler(struct sk_buff *skb,
struct tcphdr *tcph;
unsigned int tcphoff;
int oldlen;
+ int payload_csum = 0;
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
@@ -204,6 +218,8 @@ tcp_dnat_handler(struct sk_buff *skb,
return 0;
if (unlikely(cp->app != NULL)) {
+ int ret;
+
/* Some checks before mangling */
if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
return 0;
@@ -212,8 +228,13 @@ tcp_dnat_handler(struct sk_buff *skb,
* Attempt ip_vs_app call.
* It will fix ip_vs_conn and iph ack_seq stuff
*/
- if (!ip_vs_app_pkt_in(cp, skb))
+ if (!(ret = ip_vs_app_pkt_in(cp, skb)))
return 0;
+ /* ret=2: csum update is needed after payload mangling */
+ if (ret == 1)
+ oldlen = skb->len - tcphoff;
+ else
+ payload_csum = 1;
}
tcph = (void *)skb_network_header(skb) + tcphoff;
@@ -223,15 +244,16 @@ tcp_dnat_handler(struct sk_buff *skb,
* Adjust TCP checksums
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
+ tcp_partial_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr,
htons(oldlen),
htons(skb->len - tcphoff));
- } else if (!cp->app) {
+ } else if (!payload_csum) {
/* Only port and addr are changed, do fast csum update */
tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr,
cp->vport, cp->dport);
if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = (cp->app && pp->csum_check) ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
} else {
/* full checksum calculation */
tcph->check = 0;
@@ -278,7 +300,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
skb->len - tcphoff,
ipv6_hdr(skb)->nexthdr,
skb->csum)) {
- IP_VS_DBG_RL_PKT(0, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
"Failed checksum for");
return 0;
}
@@ -289,7 +311,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
skb->len - tcphoff,
ip_hdr(skb)->protocol,
skb->csum)) {
- IP_VS_DBG_RL_PKT(0, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
"Failed checksum for");
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 8553231b5d41..9d106a06bb0a 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -46,6 +46,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
svc = ip_vs_service_get(af, skb->mark, iph.protocol,
&iph.daddr, uh->dest);
if (svc) {
+ int ignored;
+
if (ip_vs_todrop()) {
/*
* It seems that we are very loaded.
@@ -60,8 +62,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
- *cpp = ip_vs_schedule(svc, skb);
- if (!*cpp) {
+ *cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+ if (!*cpp && !ignored) {
*verdict = ip_vs_leave(svc, skb, pp);
return 0;
}
@@ -102,15 +104,15 @@ udp_partial_csum_update(int af, struct udphdr *uhdr,
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
uhdr->check =
- csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
+ ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
ip_vs_check_diff2(oldlen, newlen,
- ~csum_unfold(uhdr->check))));
+ csum_unfold(uhdr->check))));
else
#endif
uhdr->check =
- csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
+ ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
ip_vs_check_diff2(oldlen, newlen,
- ~csum_unfold(uhdr->check))));
+ csum_unfold(uhdr->check))));
}
@@ -121,6 +123,7 @@ udp_snat_handler(struct sk_buff *skb,
struct udphdr *udph;
unsigned int udphoff;
int oldlen;
+ int payload_csum = 0;
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
@@ -135,6 +138,8 @@ udp_snat_handler(struct sk_buff *skb,
return 0;
if (unlikely(cp->app != NULL)) {
+ int ret;
+
/* Some checks before mangling */
if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
return 0;
@@ -142,8 +147,13 @@ udp_snat_handler(struct sk_buff *skb,
/*
* Call application helper if needed
*/
- if (!ip_vs_app_pkt_out(cp, skb))
+ if (!(ret = ip_vs_app_pkt_out(cp, skb)))
return 0;
+ /* ret=2: csum update is needed after payload mangling */
+ if (ret == 1)
+ oldlen = skb->len - udphoff;
+ else
+ payload_csum = 1;
}
udph = (void *)skb_network_header(skb) + udphoff;
@@ -156,12 +166,13 @@ udp_snat_handler(struct sk_buff *skb,
udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr,
htons(oldlen),
htons(skb->len - udphoff));
- } else if (!cp->app && (udph->check != 0)) {
+ } else if (!payload_csum && (udph->check != 0)) {
/* Only port and addr are changed, do fast csum update */
udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr,
cp->dport, cp->vport);
if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = (cp->app && pp->csum_check) ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
} else {
/* full checksum calculation */
udph->check = 0;
@@ -181,6 +192,7 @@ udp_snat_handler(struct sk_buff *skb,
skb->csum);
if (udph->check == 0)
udph->check = CSUM_MANGLED_0;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
pp->name, udph->check,
(char*)&(udph->check) - (char*)udph);
@@ -196,6 +208,7 @@ udp_dnat_handler(struct sk_buff *skb,
struct udphdr *udph;
unsigned int udphoff;
int oldlen;
+ int payload_csum = 0;
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
@@ -210,6 +223,8 @@ udp_dnat_handler(struct sk_buff *skb,
return 0;
if (unlikely(cp->app != NULL)) {
+ int ret;
+
/* Some checks before mangling */
if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
return 0;
@@ -218,8 +233,13 @@ udp_dnat_handler(struct sk_buff *skb,
* Attempt ip_vs_app call.
* It will fix ip_vs_conn
*/
- if (!ip_vs_app_pkt_in(cp, skb))
+ if (!(ret = ip_vs_app_pkt_in(cp, skb)))
return 0;
+ /* ret=2: csum update is needed after payload mangling */
+ if (ret == 1)
+ oldlen = skb->len - udphoff;
+ else
+ payload_csum = 1;
}
udph = (void *)skb_network_header(skb) + udphoff;
@@ -229,15 +249,16 @@ udp_dnat_handler(struct sk_buff *skb,
* Adjust UDP checksums
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr,
+ udp_partial_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr,
htons(oldlen),
htons(skb->len - udphoff));
- } else if (!cp->app && (udph->check != 0)) {
+ } else if (!payload_csum && (udph->check != 0)) {
/* Only port and addr are changed, do fast csum update */
udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr,
cp->vport, cp->dport);
if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = (cp->app && pp->csum_check) ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
} else {
/* full checksum calculation */
udph->check = 0;
@@ -293,7 +314,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
skb->len - udphoff,
ipv6_hdr(skb)->nexthdr,
skb->csum)) {
- IP_VS_DBG_RL_PKT(0, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
"Failed checksum for");
return 0;
}
@@ -304,7 +325,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
skb->len - udphoff,
ip_hdr(skb)->protocol,
skb->csum)) {
- IP_VS_DBG_RL_PKT(0, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
"Failed checksum for");
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b0bd8afbf368..de04ea39cde8 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -11,6 +11,16 @@
*
* Changes:
*
+ * Description of forwarding methods:
+ * - all transmitters are called from LOCAL_IN (remote clients) and
+ * LOCAL_OUT (local clients) but for ICMP can be called from FORWARD
+ * - not all connections have destination server, for example,
+ * connections in backup server when fwmark is used
+ * - bypass connections use daddr from packet
+ * LOCAL_OUT rules:
+ * - skb->dev is NULL, skb->protocol is not set (both are set in POST_ROUTING)
+ * - skb->pkt_type is not set yet
+ * - the only place where we can see skb->sk != NULL
*/
#define KMSG_COMPONENT "IPVS"
@@ -67,12 +77,19 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
return dst;
}
+/*
+ * Get route to destination or remote server
+ * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest,
+ * &4=Allow redirect from remote daddr to local
+ */
static struct rtable *
-__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_conn *cp, u32 rtos)
+__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
+ __be32 daddr, u32 rtos, int rt_mode)
{
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
- struct ip_vs_dest *dest = cp->dest;
+ struct rtable *ort; /* Original route */
+ int local;
if (dest) {
spin_lock(&dest->dst_lock);
@@ -104,23 +121,95 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_conn *cp, u32 rtos)
.oif = 0,
.nl_u = {
.ip4_u = {
- .daddr = cp->daddr.ip,
+ .daddr = daddr,
.saddr = 0,
.tos = rtos, } },
};
if (ip_route_output_key(net, &rt, &fl)) {
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
- &cp->daddr.ip);
+ &daddr);
return NULL;
}
}
+ local = rt->rt_flags & RTCF_LOCAL;
+ if (!((local ? 1 : 2) & rt_mode)) {
+ IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
+ (rt->rt_flags & RTCF_LOCAL) ?
+ "local":"non-local", &rt->rt_dst);
+ ip_rt_put(rt);
+ return NULL;
+ }
+ if (local && !(rt_mode & 4) && !((ort = skb_rtable(skb)) &&
+ ort->rt_flags & RTCF_LOCAL)) {
+ IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
+ "requires NAT method, dest: %pI4\n",
+ &ip_hdr(skb)->daddr, &rt->rt_dst);
+ ip_rt_put(rt);
+ return NULL;
+ }
+ if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) {
+ IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 "
+ "to non-local address, dest: %pI4\n",
+ &ip_hdr(skb)->saddr, &rt->rt_dst);
+ ip_rt_put(rt);
+ return NULL;
+ }
+
return rt;
}
+/* Reroute packet to local IPv4 stack after DNAT */
+static int
+__ip_vs_reroute_locally(struct sk_buff *skb)
+{
+ struct rtable *rt = skb_rtable(skb);
+ struct net_device *dev = rt->dst.dev;
+ struct net *net = dev_net(dev);
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (rt->fl.iif) {
+ unsigned long orefdst = skb->_skb_refdst;
+
+ if (ip_route_input(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev))
+ return 0;
+ refdst_drop(orefdst);
+ } else {
+ struct flowi fl = {
+ .oif = 0,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = iph->daddr,
+ .saddr = iph->saddr,
+ .tos = RT_TOS(iph->tos),
+ }
+ },
+ .mark = skb->mark,
+ };
+ struct rtable *rt;
+
+ if (ip_route_output_key(net, &rt, &fl))
+ return 0;
+ if (!(rt->rt_flags & RTCF_LOCAL)) {
+ ip_rt_put(rt);
+ return 0;
+ }
+ /* Drop old route. */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ }
+ return 1;
+}
+
#ifdef CONFIG_IP_VS_IPV6
+static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
+{
+ return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK;
+}
+
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
@@ -155,14 +244,21 @@ out_err:
return NULL;
}
+/*
+ * Get route to destination or remote server
+ * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest,
+ * &4=Allow redirect from remote daddr to local
+ */
static struct rt6_info *
-__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
- struct in6_addr *ret_saddr, int do_xfrm)
+__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
+ struct in6_addr *daddr, struct in6_addr *ret_saddr,
+ int do_xfrm, int rt_mode)
{
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net(skb_dst(skb)->dev);
struct rt6_info *rt; /* Route to the other host */
- struct ip_vs_dest *dest = cp->dest;
+ struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
+ int local;
if (dest) {
spin_lock(&dest->dst_lock);
@@ -188,13 +284,38 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
ipv6_addr_copy(ret_saddr, &dest->dst_saddr);
spin_unlock(&dest->dst_lock);
} else {
- dst = __ip_vs_route_output_v6(net, &cp->daddr.in6, ret_saddr,
- do_xfrm);
+ dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
return NULL;
rt = (struct rt6_info *) dst;
}
+ local = __ip_vs_is_local_route6(rt);
+ if (!((local ? 1 : 2) & rt_mode)) {
+ IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
+ local ? "local":"non-local", daddr);
+ dst_release(&rt->dst);
+ return NULL;
+ }
+ if (local && !(rt_mode & 4) &&
+ !((ort = (struct rt6_info *) skb_dst(skb)) &&
+ __ip_vs_is_local_route6(ort))) {
+ IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
+ "requires NAT method, dest: %pI6\n",
+ &ipv6_hdr(skb)->daddr, daddr);
+ dst_release(&rt->dst);
+ return NULL;
+ }
+ if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
+ ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
+ IPV6_ADDR_LOOPBACK)) {
+ IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
+ "to non-local address, dest: %pI6\n",
+ &ipv6_hdr(skb)->saddr, daddr);
+ dst_release(&rt->dst);
+ return NULL;
+ }
+
return rt;
}
#endif
@@ -217,30 +338,37 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
({ \
int __ret = NF_ACCEPT; \
\
+ (skb)->ipvs_property = 1; \
if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
__ret = ip_vs_confirm_conntrack(skb, cp); \
if (__ret == NF_ACCEPT) { \
nf_reset(skb); \
- (skb)->ip_summed = CHECKSUM_NONE; \
+ skb_forward_csum(skb); \
} \
__ret; \
})
-#define IP_VS_XMIT_NAT(pf, skb, cp) \
+#define IP_VS_XMIT_NAT(pf, skb, cp, local) \
do { \
+ (skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
- (skb)->ipvs_property = 1; \
+ ip_vs_notrack(skb); \
else \
ip_vs_update_conntrack(skb, cp, 1); \
+ if (local) \
+ return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
-#define IP_VS_XMIT(pf, skb, cp) \
+#define IP_VS_XMIT(pf, skb, cp, local) \
do { \
+ (skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
- (skb)->ipvs_property = 1; \
+ ip_vs_notrack(skb); \
+ if (local) \
+ return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
@@ -255,7 +383,7 @@ ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
/* we do not touch skb and do not need pskb ptr */
- return NF_ACCEPT;
+ IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
@@ -268,27 +396,15 @@ int
ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
- struct net *net = dev_net(skb->dev);
struct rtable *rt; /* Route to the other host */
struct iphdr *iph = ip_hdr(skb);
- u8 tos = iph->tos;
int mtu;
- struct flowi fl = {
- .oif = 0,
- .nl_u = {
- .ip4_u = {
- .daddr = iph->daddr,
- .saddr = 0,
- .tos = RT_TOS(tos), } },
- };
EnterFunction(10);
- if (ip_route_output_key(net, &rt, &fl)) {
- IP_VS_DBG_RL("%s(): ip_route_output error, dest: %pI4\n",
- __func__, &iph->daddr);
+ if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr,
+ RT_TOS(iph->tos), 2)))
goto tx_error_icmp;
- }
/* MTU checking */
mtu = dst_mtu(&rt->dst);
@@ -316,7 +432,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp);
+ IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
@@ -334,24 +450,25 @@ int
ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
- struct net *net = dev_net(skb->dev);
- struct dst_entry *dst;
struct rt6_info *rt; /* Route to the other host */
struct ipv6hdr *iph = ipv6_hdr(skb);
int mtu;
EnterFunction(10);
- dst = __ip_vs_route_output_v6(net, &iph->daddr, NULL, 0);
- if (!dst)
+ if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, 2)))
goto tx_error_icmp;
- rt = (struct rt6_info *) dst;
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
- dst_release(&rt->dst);
+ if (!skb->dev) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ skb->dev = net->loopback_dev;
+ }
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
}
@@ -373,7 +490,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp);
+ IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
@@ -398,6 +515,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct rtable *rt; /* Route to the other host */
int mtu;
struct iphdr *iph = ip_hdr(skb);
+ int local;
EnterFunction(10);
@@ -411,16 +529,42 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
- if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(iph->tos))))
+ if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ RT_TOS(iph->tos), 1|2|4)))
goto tx_error_icmp;
+ local = rt->rt_flags & RTCF_LOCAL;
+ /*
+ * Avoid duplicate tuple in reply direction for NAT traffic
+ * to local address when connection is sync-ed
+ */
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ if (cp->flags & IP_VS_CONN_F_SYNC && local) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct && !nf_ct_is_untracked(ct)) {
+ IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
+ "ip_vs_nat_xmit(): "
+ "stopping DNAT to local address");
+ goto tx_error_put;
+ }
+ }
+#endif
+
+ /* From world but DNAT to loopback address? */
+ if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) {
+ IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
+ "stopping DNAT to loopback address");
+ goto tx_error_put;
+ }
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
- ip_rt_put(rt);
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
- IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for");
- goto tx_error;
+ IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
+ "ip_vs_nat_xmit(): frag needed for");
+ goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
@@ -430,17 +574,28 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
- goto tx_error;
+ goto tx_error_put;
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
- IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ if (!local) {
+ /* drop old route */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ } else {
+ ip_rt_put(rt);
+ /*
+ * Some IPv4 replies get local address from routes,
+ * not from iph, so while we DNAT after routing
+ * we need this second input/output route.
+ */
+ if (!__ip_vs_reroute_locally(skb))
+ goto tx_error;
+ }
+
+ IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
@@ -449,7 +604,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp);
+ IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
@@ -472,6 +627,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
+ int local;
EnterFunction(10);
@@ -486,18 +642,49 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
- rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0);
- if (!rt)
+ if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
+ 0, 1|2|4)))
goto tx_error_icmp;
+ local = __ip_vs_is_local_route6(rt);
+ /*
+ * Avoid duplicate tuple in reply direction for NAT traffic
+ * to local address when connection is sync-ed
+ */
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ if (cp->flags & IP_VS_CONN_F_SYNC && local) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct && !nf_ct_is_untracked(ct)) {
+ IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
+ "ip_vs_nat_xmit_v6(): "
+ "stopping DNAT to local address");
+ goto tx_error_put;
+ }
+ }
+#endif
+
+ /* From world but DNAT to loopback address? */
+ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
+ ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
+ IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
+ "ip_vs_nat_xmit_v6(): "
+ "stopping DNAT to loopback address");
+ goto tx_error_put;
+ }
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
- dst_release(&rt->dst);
+ if (!skb->dev) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ skb->dev = net->loopback_dev;
+ }
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP_VS_DBG_RL_PKT(0, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): frag needed for");
- goto tx_error;
+ goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
@@ -507,16 +694,21 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error;
- ipv6_hdr(skb)->daddr = cp->daddr.in6;
+ ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6);
- IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ if (!local || !skb->dev) {
+ /* drop the old route when skb is not shared */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ } else {
+ /* destined to loopback, do we need to change route? */
+ dst_release(&rt->dst);
+ }
+
+ IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
@@ -525,7 +717,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp);
+ IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
@@ -578,23 +770,20 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
- if (skb->protocol != htons(ETH_P_IP)) {
- IP_VS_DBG_RL("%s(): protocol error, "
- "ETH_P_IP: %d, skb protocol: %d\n",
- __func__, htons(ETH_P_IP), skb->protocol);
- goto tx_error;
- }
-
- if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(tos))))
+ if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ RT_TOS(tos), 1|2)))
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_rt_put(rt);
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
- goto tx_error;
+ goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
@@ -604,9 +793,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if ((old_iph->frag_off & htons(IP_DF))
&& mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error;
+ goto tx_error_put;
}
/*
@@ -675,6 +863,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
+tx_error_put:
+ ip_rt_put(rt);
+ goto tx_error;
}
#ifdef CONFIG_IP_VS_IPV6
@@ -693,34 +884,34 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
- if (skb->protocol != htons(ETH_P_IPV6)) {
- IP_VS_DBG_RL("%s(): protocol error, "
- "ETH_P_IPV6: %d, skb protocol: %d\n",
- __func__, htons(ETH_P_IPV6), skb->protocol);
- goto tx_error;
- }
-
- rt = __ip_vs_get_out_rt_v6(skb, cp, &saddr, 1);
- if (!rt)
+ if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
+ &saddr, 1, 1|2)))
goto tx_error_icmp;
+ if (__ip_vs_is_local_route6(rt)) {
+ dst_release(&rt->dst);
+ IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
+ }
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
if (mtu < IPV6_MIN_MTU) {
- dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
- goto tx_error;
+ goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) {
+ if (!skb->dev) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ skb->dev = net->loopback_dev;
+ }
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error;
+ goto tx_error_put;
}
/*
@@ -786,6 +977,9 @@ tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
+tx_error_put:
+ dst_release(&rt->dst);
+ goto tx_error;
}
#endif
@@ -804,8 +998,13 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(iph->tos))))
+ if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ RT_TOS(iph->tos), 1|2)))
goto tx_error_icmp;
+ if (rt->rt_flags & RTCF_LOCAL) {
+ ip_rt_put(rt);
+ IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
+ }
/* MTU checking */
mtu = dst_mtu(&rt->dst);
@@ -833,7 +1032,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp);
+ IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
@@ -856,13 +1055,22 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
- rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0);
- if (!rt)
+ if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
+ 0, 1|2)))
goto tx_error_icmp;
+ if (__ip_vs_is_local_route6(rt)) {
+ dst_release(&rt->dst);
+ IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
+ }
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
+ if (!skb->dev) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ skb->dev = net->loopback_dev;
+ }
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -886,7 +1094,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp);
+ IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
@@ -912,6 +1120,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct rtable *rt; /* Route to the other host */
int mtu;
int rc;
+ int local;
EnterFunction(10);
@@ -932,16 +1141,43 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
* mangle and send the packet here (only for VS/NAT)
*/
- if (!(rt = __ip_vs_get_out_rt(skb, cp, RT_TOS(ip_hdr(skb)->tos))))
+ if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ RT_TOS(ip_hdr(skb)->tos), 1|2|4)))
goto tx_error_icmp;
+ local = rt->rt_flags & RTCF_LOCAL;
+
+ /*
+ * Avoid duplicate tuple in reply direction for NAT traffic
+ * to local address when connection is sync-ed
+ */
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ if (cp->flags & IP_VS_CONN_F_SYNC && local) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct && !nf_ct_is_untracked(ct)) {
+ IP_VS_DBG(10, "%s(): "
+ "stopping DNAT to local address %pI4\n",
+ __func__, &cp->daddr.ip);
+ goto tx_error_put;
+ }
+ }
+#endif
+
+ /* From world but DNAT to loopback address? */
+ if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) {
+ IP_VS_DBG(1, "%s(): "
+ "stopping DNAT to loopback %pI4\n",
+ __func__, &cp->daddr.ip);
+ goto tx_error_put;
+ }
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) {
- ip_rt_put(rt);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error;
+ goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
@@ -951,16 +1187,27 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
- /* drop the old route when skb is not shared */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
ip_vs_nat_icmp(skb, pp, cp, 0);
+ if (!local) {
+ /* drop the old route when skb is not shared */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ } else {
+ ip_rt_put(rt);
+ /*
+ * Some IPv4 replies get local address from routes,
+ * not from iph, so while we DNAT after routing
+ * we need this second input/output route.
+ */
+ if (!__ip_vs_reroute_locally(skb))
+ goto tx_error;
+ }
+
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp);
+ IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
rc = NF_STOLEN;
goto out;
@@ -986,6 +1233,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct rt6_info *rt; /* Route to the other host */
int mtu;
int rc;
+ int local;
EnterFunction(10);
@@ -1006,17 +1254,49 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
* mangle and send the packet here (only for VS/NAT)
*/
- rt = __ip_vs_get_out_rt_v6(skb, cp, NULL, 0);
- if (!rt)
+ if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
+ 0, 1|2|4)))
goto tx_error_icmp;
+ local = __ip_vs_is_local_route6(rt);
+ /*
+ * Avoid duplicate tuple in reply direction for NAT traffic
+ * to local address when connection is sync-ed
+ */
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ if (cp->flags & IP_VS_CONN_F_SYNC && local) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct && !nf_ct_is_untracked(ct)) {
+ IP_VS_DBG(10, "%s(): "
+ "stopping DNAT to local address %pI6\n",
+ __func__, &cp->daddr.in6);
+ goto tx_error_put;
+ }
+ }
+#endif
+
+ /* From world but DNAT to loopback address? */
+ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
+ ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
+ IP_VS_DBG(1, "%s(): "
+ "stopping DNAT to loopback %pI6\n",
+ __func__, &cp->daddr.in6);
+ goto tx_error_put;
+ }
+
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
- dst_release(&rt->dst);
+ if (!skb->dev) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ skb->dev = net->loopback_dev;
+ }
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error;
+ goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
@@ -1026,16 +1306,21 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
- /* drop the old route when skb is not shared */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
ip_vs_nat_icmp_v6(skb, pp, cp, 0);
+ if (!local || !skb->dev) {
+ /* drop the old route when skb is not shared */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ } else {
+ /* destined to loopback, do we need to change route? */
+ dst_release(&rt->dst);
+ }
+
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp);
+ IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
rc = NF_STOLEN;
goto out;