leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ipvs: optimize dst usage for real server

Browse Source 
Currently when forwarding requests to real servers
we use dst_lock and atomic operations when cloning the
dst_cache value. As the dst_cache value does not change
most of the time it is better to use RCU and to lock
dst_lock only when we need to replace the obsoleted dst.
For this to work we keep dst_cache in new structure protected
by RCU. For packets to remote real servers we will use noref
version of dst_cache, it will be valid while we are in RCU
read-side critical section because now dst_release for replaced
dsts will be invoked after the grace period. Packets to
local real servers that are passed to local stack with
NF_ACCEPT need a dst clone.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
This commit is contained in:
Julian Anastasov 2013-03-21 11:58:06 +02:00 committed by Pablo Neira Ayuso
parent 4115ded131
commit 026ace060d
4 changed files with 179 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
include/net/ip_vs.h
View File

@ -724,6 +724,13 @@ struct ip_vs_service {
struct ip_vs_pe *pe; struct ip_vs_pe *pe;
}; };
/* Information for cached dst */
struct ip_vs_dest_dst {
struct dst_entry *dst_cache; /* destination cache entry */
u32 dst_cookie;
union nf_inet_addr dst_saddr;
struct rcu_head rcu_head;
};
/* /*
* The real server destination forwarding entry * The real server destination forwarding entry
@ -752,9 +759,7 @@ struct ip_vs_dest {
/* for destination cache */ /* for destination cache */
spinlock_t dst_lock; /* lock of dst_cache */ spinlock_t dst_lock; /* lock of dst_cache */
struct dst_entry *dst_cache; /* destination cache entry */ struct ip_vs_dest_dst __rcu *dest_dst; /* cached dst info */
u32 dst_cookie;
union nf_inet_addr dst_saddr;
/* for virtual service */ /* for virtual service */
struct ip_vs_service *svc; /* service it belongs to */ struct ip_vs_service *svc; /* service it belongs to */
@ -1427,6 +1432,7 @@ extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset, struct ip_vs_protocol *pp, int offset,
unsigned int hooknum, struct ip_vs_iphdr *iph); unsigned int hooknum, struct ip_vs_iphdr *iph);
extern void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
#ifdef CONFIG_IP_VS_IPV6 #ifdef CONFIG_IP_VS_IPV6
extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,

11
net/netfilter/ipvs/ip_vs_core.c
View File

@ -1395,10 +1395,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
goto ignore_ipip; goto ignore_ipip;
/* Prefer the resulting PMTU */ /* Prefer the resulting PMTU */
if (dest) { if (dest) {
spin_lock(&dest->dst_lock); struct ip_vs_dest_dst *dest_dst;
if (dest->dst_cache)
mtu = dst_mtu(dest->dst_cache); rcu_read_lock();
spin_unlock(&dest->dst_lock); dest_dst = rcu_dereference(dest->dest_dst);
if (dest_dst)
mtu = dst_mtu(dest_dst->dst_cache);
rcu_read_unlock();
} }
if (mtu > 68 + sizeof(struct iphdr)) if (mtu > 68 + sizeof(struct iphdr))
mtu -= sizeof(struct iphdr); mtu -= sizeof(struct iphdr);

25
net/netfilter/ipvs/ip_vs_ctl.c
View File

@ -641,15 +641,26 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af,
return dest; return dest;
} }
/* Release dst_cache for dest in user context */ void ip_vs_dest_dst_rcu_free(struct rcu_head *head)
{
struct ip_vs_dest_dst *dest_dst = container_of(head,
struct ip_vs_dest_dst,
rcu_head);
dst_release(dest_dst->dst_cache);
kfree(dest_dst);
}
/* Release dest_dst and dst_cache for dest in user context */
static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest) static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest)
{ {
struct dst_entry *old_dst; struct ip_vs_dest_dst *old;
old_dst = dest->dst_cache; old = rcu_dereference_protected(dest->dest_dst, 1);
dest->dst_cache = NULL; if (old) {
dst_release(old_dst); RCU_INIT_POINTER(dest->dest_dst, NULL);
dest->dst_saddr.ip = 0; call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
}
} }
/* /*
@ -1513,7 +1524,7 @@ static inline void
ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev) ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
{ {
spin_lock_bh(&dest->dst_lock); spin_lock_bh(&dest->dst_lock);
if (dest->dst_cache && dest->dst_cache->dev == dev) { if (dest->dest_dst && dest->dest_dst->dst_cache->dev == dev) {
IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n",
dev->name, dev->name,
IP_VS_DBG_ADDR(dest->af, &dest->addr), IP_VS_DBG_ADDR(dest->af, &dest->addr),

192
net/netfilter/ipvs/ip_vs_xmit.c
View File

@ -17,6 +17,8 @@
* - not all connections have destination server, for example, * - not all connections have destination server, for example,
* connections in backup server when fwmark is used * connections in backup server when fwmark is used
* - bypass connections use daddr from packet * - bypass connections use daddr from packet
* - we can use dst without ref while sending in RCU section, we use
* ref when returning NF_ACCEPT for NAT-ed packet via loopback
* LOCAL_OUT rules: * LOCAL_OUT rules:
* - skb->dev is NULL, skb->protocol is not set (both are set in POST_ROUTING) * - skb->dev is NULL, skb->protocol is not set (both are set in POST_ROUTING)
* - skb->pkt_type is not set yet * - skb->pkt_type is not set yet
@ -54,34 +56,51 @@ enum {
IP_VS_RT_MODE_TUNNEL = 32,/* Tunnel mode */ IP_VS_RT_MODE_TUNNEL = 32,/* Tunnel mode */
}; };
static inline struct ip_vs_dest_dst *ip_vs_dest_dst_alloc(void)
{
return kmalloc(sizeof(struct ip_vs_dest_dst), GFP_ATOMIC);
}
static inline void ip_vs_dest_dst_free(struct ip_vs_dest_dst *dest_dst)
{
kfree(dest_dst);
}
/* /*
* Destination cache to speed up outgoing route lookup * Destination cache to speed up outgoing route lookup
*/ */
static inline void static inline void
__ip_vs_dst_set(struct ip_vs_dest *dest, struct dst_entry *dst, u32 dst_cookie) __ip_vs_dst_set(struct ip_vs_dest *dest, struct ip_vs_dest_dst *dest_dst,
struct dst_entry *dst, u32 dst_cookie)
{ {
struct dst_entry *old_dst; struct ip_vs_dest_dst *old;
old_dst = dest->dst_cache; old = rcu_dereference_protected(dest->dest_dst,
dest->dst_cache = dst; lockdep_is_held(&dest->dst_lock));
dest->dst_cookie = dst_cookie;
dst_release(old_dst); if (dest_dst) {
dest_dst->dst_cache = dst;
dest_dst->dst_cookie = dst_cookie;
}
rcu_assign_pointer(dest->dest_dst, dest_dst);
if (old)
call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
} }
static inline struct dst_entry * static inline struct ip_vs_dest_dst *
__ip_vs_dst_check(struct ip_vs_dest *dest) __ip_vs_dst_check(struct ip_vs_dest *dest)
{ {
struct dst_entry *dst = dest->dst_cache; struct ip_vs_dest_dst *dest_dst = rcu_dereference(dest->dest_dst);
struct dst_entry *dst;
if (!dst) if (!dest_dst)
return NULL; return NULL;
if (dst->obsolete && dst->ops->check(dst, dest->dst_cookie) == NULL) { dst = dest_dst->dst_cache;
dest->dst_cache = NULL; if (dst->obsolete &&
dst_release(dst); dst->ops->check(dst, dest_dst->dst_cookie) == NULL)
return NULL; return NULL;
} return dest_dst;
dst_hold(dst);
return dst;
} }
static inline bool static inline bool
@ -144,35 +163,48 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
{ {
struct net *net = dev_net(skb_dst(skb)->dev); struct net *net = dev_net(skb_dst(skb)->dev);
struct netns_ipvs *ipvs = net_ipvs(net); struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */ struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */ struct rtable *ort; /* Original route */
struct iphdr *iph; struct iphdr *iph;
__be16 df; __be16 df;
int mtu; int mtu;
int local; int local, noref = 1;
if (dest) { if (dest) {
spin_lock(&dest->dst_lock); dest_dst = __ip_vs_dst_check(dest);
rt = (struct rtable *) __ip_vs_dst_check(dest); if (likely(dest_dst))
if (!rt) { rt = (struct rtable *) dest_dst->dst_cache;
rt = do_output_route4(net, dest->addr.ip, rt_mode, else {
&dest->dst_saddr.ip); dest_dst = ip_vs_dest_dst_alloc();
if (!rt) { spin_lock(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock(&dest->dst_lock); spin_unlock(&dest->dst_lock);
goto err_unreach; goto err_unreach;
} }
__ip_vs_dst_set(dest, dst_clone(&rt->dst), 0); rt = do_output_route4(net, dest->addr.ip, rt_mode,
&dest_dst->dst_saddr.ip);
if (!rt) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach;
}
__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
spin_unlock(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n", IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
&dest->addr.ip, &dest->dst_saddr.ip, &dest->addr.ip, &dest_dst->dst_saddr.ip,
atomic_read(&rt->dst.__refcnt)); atomic_read(&rt->dst.__refcnt));
} }
daddr = dest->addr.ip; daddr = dest->addr.ip;
if (ret_saddr) if (ret_saddr)
*ret_saddr = dest->dst_saddr.ip; *ret_saddr = dest_dst->dst_saddr.ip;
spin_unlock(&dest->dst_lock);
} else { } else {
__be32 saddr = htonl(INADDR_ANY); __be32 saddr = htonl(INADDR_ANY);
noref = 0;
/* For such unconfigured boxes avoid many route lookups /* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr * for performance reasons because we do not remember saddr
*/ */
@ -210,7 +242,8 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
goto err_put; goto err_put;
} }
/* skb to local stack, preserve old route */ /* skb to local stack, preserve old route */
ip_rt_put(rt); if (!noref)
ip_rt_put(rt);
return local; return local;
} }
@ -240,12 +273,19 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
} }
skb_dst_drop(skb); skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst); if (noref) {
if (!local)
skb_dst_set_noref_force(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local; return local;
err_put: err_put:
ip_rt_put(rt); if (!noref)
ip_rt_put(rt);
return -1; return -1;
err_unreach: err_unreach:
@ -303,36 +343,48 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode) struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{ {
struct net *net = dev_net(skb_dst(skb)->dev); struct net *net = dev_net(skb_dst(skb)->dev);
struct ip_vs_dest_dst *dest_dst;
struct rt6_info *rt; /* Route to the other host */ struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */ struct rt6_info *ort; /* Original route */
struct dst_entry *dst; struct dst_entry *dst;
int mtu; int mtu;
int local; int local, noref = 1;
if (dest) { if (dest) {
spin_lock(&dest->dst_lock); dest_dst = __ip_vs_dst_check(dest);
rt = (struct rt6_info *)__ip_vs_dst_check(dest); if (likely(dest_dst))
if (!rt) { rt = (struct rt6_info *) dest_dst->dst_cache;
else {
u32 cookie; u32 cookie;
dest_dst = ip_vs_dest_dst_alloc();
spin_lock(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock(&dest->dst_lock);
goto err_unreach;
}
dst = __ip_vs_route_output_v6(net, &dest->addr.in6, dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest->dst_saddr.in6, &dest_dst->dst_saddr.in6,
do_xfrm); do_xfrm);
if (!dst) { if (!dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock(&dest->dst_lock); spin_unlock(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach; goto err_unreach;
} }
rt = (struct rt6_info *) dst; rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
__ip_vs_dst_set(dest, dst_clone(&rt->dst), cookie); __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
spin_unlock(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest->dst_saddr.in6, &dest->addr.in6, &dest_dst->dst_saddr.in6,
atomic_read(&rt->dst.__refcnt)); atomic_read(&rt->dst.__refcnt));
} }
if (ret_saddr) if (ret_saddr)
*ret_saddr = dest->dst_saddr.in6; *ret_saddr = dest_dst->dst_saddr.in6;
spin_unlock(&dest->dst_lock);
} else { } else {
noref = 0;
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst) if (!dst)
goto err_unreach; goto err_unreach;
@ -367,7 +419,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
goto err_put; goto err_put;
} }
/* skb to local stack, preserve old route */ /* skb to local stack, preserve old route */
dst_release(&rt->dst); if (!noref)
dst_release(&rt->dst);
return local; return local;
} }
@ -399,12 +452,19 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
} }
skb_dst_drop(skb); skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst); if (noref) {
if (!local)
skb_dst_set_noref_force(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local; return local;
err_put: err_put:
dst_release(&rt->dst); if (!noref)
dst_release(&rt->dst);
return -1; return -1;
err_unreach: err_unreach:
@ -494,6 +554,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
if (__ip_vs_get_out_rt(skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL, if (__ip_vs_get_out_rt(skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL,
NULL) < 0) NULL) < 0)
goto tx_error; goto tx_error;
@ -504,12 +565,14 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0); ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -521,6 +584,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
{ {
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
if (__ip_vs_get_out_rt_v6(skb, NULL, &ipvsh->daddr.in6, NULL, if (__ip_vs_get_out_rt_v6(skb, NULL, &ipvsh->daddr.in6, NULL,
ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0) ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0)
goto tx_error; goto tx_error;
@ -529,12 +593,14 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0); ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -553,6 +619,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
/* check if it is a connection of no-client-port */ /* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p; __be16 _pt, *p;
@ -620,12 +687,14 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return rc; return rc;
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -640,6 +709,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
/* check if it is a connection of no-client-port */ /* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !ipvsh->fragoffs)) { if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !ipvsh->fragoffs)) {
__be16 _pt, *p; __be16 _pt, *p;
@ -707,6 +777,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local); rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return rc; return rc;
@ -714,6 +785,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
tx_error: tx_error:
LeaveFunction(10); LeaveFunction(10);
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
return NF_STOLEN; return NF_STOLEN;
} }
#endif #endif
@ -755,6 +827,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
@ -762,8 +835,10 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_TUNNEL, &saddr); IP_VS_RT_MODE_TUNNEL, &saddr);
if (local < 0) if (local < 0)
goto tx_error; goto tx_error;
if (local) if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1); return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
rt = skb_rtable(skb); rt = skb_rtable(skb);
tdev = rt->dst.dev; tdev = rt->dst.dev;
@ -818,6 +893,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
ip_local_out(skb); ip_local_out(skb);
else if (ret == NF_DROP) else if (ret == NF_DROP)
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
@ -825,6 +901,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -844,6 +921,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
&saddr, ipvsh, 1, &saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_LOCAL |
@ -851,8 +929,10 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_TUNNEL); IP_VS_RT_MODE_TUNNEL);
if (local < 0) if (local < 0)
goto tx_error; goto tx_error;
if (local) if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1); return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
}
rt = (struct rt6_info *) skb_dst(skb); rt = (struct rt6_info *) skb_dst(skb);
tdev = rt->dst.dev; tdev = rt->dst.dev;
@ -901,6 +981,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
ip6_local_out(skb); ip6_local_out(skb);
else if (ret == NF_DROP) else if (ret == NF_DROP)
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
@ -908,6 +989,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -926,14 +1008,17 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_KNOWN_NH, NULL); IP_VS_RT_MODE_KNOWN_NH, NULL);
if (local < 0) if (local < 0)
goto tx_error; goto tx_error;
if (local) if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1); return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
ip_send_check(ip_hdr(skb)); ip_send_check(ip_hdr(skb));
@ -941,12 +1026,14 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0); ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -960,25 +1047,30 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10); EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
ipvsh, 0, ipvsh, 0,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL); IP_VS_RT_MODE_NON_LOCAL);
if (local < 0) if (local < 0)
goto tx_error; goto tx_error;
if (local) if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1); return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
}
/* Another hack: avoid icmp_send in ip_fragment */ /* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1; skb->local_df = 1;
ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0); ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
tx_error: tx_error:
kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10); LeaveFunction(10);
return NF_STOLEN; return NF_STOLEN;
} }
@ -1023,6 +1115,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
rt_mode = (hooknum != NF_INET_FORWARD) ? rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
rcu_read_lock();
local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, rt_mode, NULL); local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, rt_mode, NULL);
if (local < 0) if (local < 0)
goto tx_error; goto tx_error;
@ -1067,10 +1160,12 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
rcu_read_unlock();
goto out; goto out;
tx_error: tx_error:
dev_kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
rc = NF_STOLEN; rc = NF_STOLEN;
out: out:
LeaveFunction(10); LeaveFunction(10);
@ -1111,6 +1206,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
rt_mode = (hooknum != NF_INET_FORWARD) ? rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
ipvsh, 0, rt_mode); ipvsh, 0, rt_mode);
if (local < 0) if (local < 0)
@ -1156,10 +1252,12 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->local_df = 1; skb->local_df = 1;
rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local); rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
rcu_read_unlock();
goto out; goto out;
tx_error: tx_error:
dev_kfree_skb(skb); kfree_skb(skb);
rcu_read_unlock();
rc = NF_STOLEN; rc = NF_STOLEN;
out: out:
LeaveFunction(10); LeaveFunction(10);