2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* ip_vs_xmit.c: various packet transmitters for IPVS
|
|
|
|
*
|
|
|
|
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
|
|
|
|
* Julian Anastasov <ja@ssi.bg>
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*
|
|
|
|
* Changes:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2009-07-30 21:29:44 +00:00
|
|
|
#define KMSG_COMPONENT "IPVS"
|
|
|
|
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/kernel.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
|
|
|
#include <linux/slab.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/tcp.h> /* for tcphdr */
|
2008-01-12 03:14:00 +00:00
|
|
|
#include <net/ip.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <net/tcp.h> /* for csum_tcpudp_magic */
|
|
|
|
#include <net/udp.h>
|
|
|
|
#include <net/icmp.h> /* for icmp_send */
|
|
|
|
#include <net/route.h> /* for ip_route_output */
|
2008-09-02 13:55:44 +00:00
|
|
|
#include <net/ipv6.h>
|
|
|
|
#include <net/ip6_route.h>
|
|
|
|
#include <linux/icmpv6.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/netfilter.h>
|
2010-07-23 10:46:32 +00:00
|
|
|
#include <net/netfilter/nf_conntrack.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/netfilter_ipv4.h>
|
|
|
|
|
|
|
|
#include <net/ip_vs.h>
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Destination cache to speed up outgoing route lookup
|
|
|
|
*/
|
|
|
|
static inline void
|
|
|
|
__ip_vs_dst_set(struct ip_vs_dest *dest, u32 rtos, struct dst_entry *dst)
|
|
|
|
{
|
|
|
|
struct dst_entry *old_dst;
|
|
|
|
|
|
|
|
old_dst = dest->dst_cache;
|
|
|
|
dest->dst_cache = dst;
|
|
|
|
dest->dst_rtos = rtos;
|
|
|
|
dst_release(old_dst);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct dst_entry *
|
|
|
|
__ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos, u32 cookie)
|
|
|
|
{
|
|
|
|
struct dst_entry *dst = dest->dst_cache;
|
|
|
|
|
|
|
|
if (!dst)
|
|
|
|
return NULL;
|
2008-09-02 13:55:44 +00:00
|
|
|
if ((dst->obsolete
|
|
|
|
|| (dest->af == AF_INET && rtos != dest->dst_rtos)) &&
|
2005-04-16 22:20:36 +00:00
|
|
|
dst->ops->check(dst, cookie) == NULL) {
|
|
|
|
dest->dst_cache = NULL;
|
|
|
|
dst_release(dst);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
dst_hold(dst);
|
|
|
|
return dst;
|
|
|
|
}
|
|
|
|
|
[IPVS]: Kill some bloat
net/ipv4/ipvs/ip_vs_xmit.c:
ip_vs_icmp_xmit | -638
ip_vs_tunnel_xmit | -674
ip_vs_nat_xmit | -716
ip_vs_dr_xmit | -682
4 functions changed, 2710 bytes removed, diff: -2710
net/ipv4/ipvs/ip_vs_xmit.c:
__ip_vs_get_out_rt | +595
1 function changed, 595 bytes added, diff: +595
net/ipv4/ipvs/ip_vs_xmit.o:
5 functions changed, 595 bytes added, 2710 bytes removed, diff: -2115
Without some CONFIG.*DEBUGs:
net/ipv4/ipvs/ip_vs_xmit.o:
5 functions changed, 383 bytes added, 1513 bytes removed, diff: -1130
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-06 07:12:40 +00:00
|
|
|
static struct rtable *
|
2005-04-16 22:20:36 +00:00
|
|
|
__ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
|
|
|
|
{
|
|
|
|
struct rtable *rt; /* Route to the other host */
|
|
|
|
struct ip_vs_dest *dest = cp->dest;
|
|
|
|
|
|
|
|
if (dest) {
|
|
|
|
spin_lock(&dest->dst_lock);
|
|
|
|
if (!(rt = (struct rtable *)
|
|
|
|
__ip_vs_dst_check(dest, rtos, 0))) {
|
|
|
|
struct flowi fl = {
|
|
|
|
.oif = 0,
|
|
|
|
.nl_u = {
|
|
|
|
.ip4_u = {
|
2008-09-02 13:55:33 +00:00
|
|
|
.daddr = dest->addr.ip,
|
2005-04-16 22:20:36 +00:00
|
|
|
.saddr = 0,
|
|
|
|
.tos = rtos, } },
|
|
|
|
};
|
|
|
|
|
2008-01-23 06:07:34 +00:00
|
|
|
if (ip_route_output_key(&init_net, &rt, &fl)) {
|
2005-04-16 22:20:36 +00:00
|
|
|
spin_unlock(&dest->dst_lock);
|
2008-10-31 07:54:29 +00:00
|
|
|
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
|
|
|
|
&dest->addr.ip);
|
2005-04-16 22:20:36 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
2010-06-11 06:31:35 +00:00
|
|
|
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst));
|
2008-10-31 07:54:29 +00:00
|
|
|
IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n",
|
|
|
|
&dest->addr.ip,
|
2010-06-11 06:31:35 +00:00
|
|
|
atomic_read(&rt->dst.__refcnt), rtos);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
spin_unlock(&dest->dst_lock);
|
|
|
|
} else {
|
|
|
|
struct flowi fl = {
|
|
|
|
.oif = 0,
|
|
|
|
.nl_u = {
|
|
|
|
.ip4_u = {
|
2008-09-02 13:55:33 +00:00
|
|
|
.daddr = cp->daddr.ip,
|
2005-04-16 22:20:36 +00:00
|
|
|
.saddr = 0,
|
|
|
|
.tos = rtos, } },
|
|
|
|
};
|
|
|
|
|
2008-01-23 06:07:34 +00:00
|
|
|
if (ip_route_output_key(&init_net, &rt, &fl)) {
|
2008-10-31 07:54:29 +00:00
|
|
|
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
|
|
|
|
&cp->daddr.ip);
|
2005-04-16 22:20:36 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return rt;
|
|
|
|
}
|
|
|
|
|
2008-09-02 13:55:44 +00:00
|
|
|
#ifdef CONFIG_IP_VS_IPV6
|
|
|
|
static struct rt6_info *
|
|
|
|
__ip_vs_get_out_rt_v6(struct ip_vs_conn *cp)
|
|
|
|
{
|
|
|
|
struct rt6_info *rt; /* Route to the other host */
|
|
|
|
struct ip_vs_dest *dest = cp->dest;
|
|
|
|
|
|
|
|
if (dest) {
|
|
|
|
spin_lock(&dest->dst_lock);
|
|
|
|
rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0, 0);
|
|
|
|
if (!rt) {
|
|
|
|
struct flowi fl = {
|
|
|
|
.oif = 0,
|
|
|
|
.nl_u = {
|
|
|
|
.ip6_u = {
|
|
|
|
.daddr = dest->addr.in6,
|
|
|
|
.saddr = {
|
|
|
|
.s6_addr32 =
|
|
|
|
{ 0, 0, 0, 0 },
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
};
|
|
|
|
|
|
|
|
rt = (struct rt6_info *)ip6_route_output(&init_net,
|
|
|
|
NULL, &fl);
|
|
|
|
if (!rt) {
|
|
|
|
spin_unlock(&dest->dst_lock);
|
2008-10-29 19:52:50 +00:00
|
|
|
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n",
|
2008-10-28 23:08:13 +00:00
|
|
|
&dest->addr.in6);
|
2008-09-02 13:55:44 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
2010-06-11 06:31:35 +00:00
|
|
|
__ip_vs_dst_set(dest, 0, dst_clone(&rt->dst));
|
2008-10-29 19:52:50 +00:00
|
|
|
IP_VS_DBG(10, "new dst %pI6, refcnt=%d\n",
|
2008-10-28 23:08:13 +00:00
|
|
|
&dest->addr.in6,
|
2010-06-11 06:31:35 +00:00
|
|
|
atomic_read(&rt->dst.__refcnt));
|
2008-09-02 13:55:44 +00:00
|
|
|
}
|
|
|
|
spin_unlock(&dest->dst_lock);
|
|
|
|
} else {
|
|
|
|
struct flowi fl = {
|
|
|
|
.oif = 0,
|
|
|
|
.nl_u = {
|
|
|
|
.ip6_u = {
|
|
|
|
.daddr = cp->daddr.in6,
|
|
|
|
.saddr = {
|
|
|
|
.s6_addr32 = { 0, 0, 0, 0 },
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
};
|
|
|
|
|
|
|
|
rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl);
|
|
|
|
if (!rt) {
|
2008-10-29 19:52:50 +00:00
|
|
|
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n",
|
2008-10-28 23:08:13 +00:00
|
|
|
&cp->daddr.in6);
|
2008-09-02 13:55:44 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return rt;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Release dest->dst_cache before a dest is removed
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
ip_vs_dst_reset(struct ip_vs_dest *dest)
|
|
|
|
{
|
|
|
|
struct dst_entry *old_dst;
|
|
|
|
|
|
|
|
old_dst = dest->dst_cache;
|
|
|
|
dest->dst_cache = NULL;
|
|
|
|
dst_release(old_dst);
|
|
|
|
}
|
|
|
|
|
2008-09-02 13:55:44 +00:00
|
|
|
#define IP_VS_XMIT(pf, skb, rt) \
|
2005-04-16 22:20:36 +00:00
|
|
|
do { \
|
2005-08-10 02:24:19 +00:00
|
|
|
(skb)->ipvs_property = 1; \
|
2007-07-30 23:20:12 +00:00
|
|
|
skb_forward_csum(skb); \
|
2008-09-02 13:55:44 +00:00
|
|
|
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
|
2010-06-11 06:31:35 +00:00
|
|
|
(rt)->dst.dev, dst_output); \
|
2005-04-16 22:20:36 +00:00
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* NULL transmitter (do nothing except return NF_ACCEPT)
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Bypass transmitter
|
|
|
|
* Let packets bypass the destination when the destination is not
|
|
|
|
* available, it may be only used in transparent cache cluster.
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rtable *rt; /* Route to the other host */
|
2007-04-21 05:47:35 +00:00
|
|
|
struct iphdr *iph = ip_hdr(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
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);
|
|
|
|
|
2008-01-23 06:07:34 +00:00
|
|
|
if (ip_route_output_key(&init_net, &rt, &fl)) {
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): ip_route_output error, dest: %pI4\n",
|
|
|
|
__func__, &iph->daddr);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error_icmp;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2007-03-07 05:19:10 +00:00
|
|
|
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
|
2005-04-16 22:20:36 +00:00
|
|
|
ip_rt_put(rt);
|
|
|
|
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Call ip_send_check because we are not sure it is called
|
|
|
|
* after ip_defrag. Is copy-on-write needed?
|
|
|
|
*/
|
|
|
|
if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
|
|
|
|
ip_rt_put(rt);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
2007-04-21 05:47:35 +00:00
|
|
|
ip_send_check(ip_hdr(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
|
2008-09-02 13:55:45 +00:00
|
|
|
#ifdef CONFIG_IP_VS_IPV6
|
|
|
|
int
|
|
|
|
ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rt6_info *rt; /* Route to the other host */
|
|
|
|
struct ipv6hdr *iph = ipv6_hdr(skb);
|
|
|
|
int mtu;
|
|
|
|
struct flowi fl = {
|
|
|
|
.oif = 0,
|
|
|
|
.nl_u = {
|
|
|
|
.ip6_u = {
|
|
|
|
.daddr = iph->daddr,
|
|
|
|
.saddr = { .s6_addr32 = {0, 0, 0, 0} }, } },
|
|
|
|
};
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl);
|
|
|
|
if (!rt) {
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): ip6_route_output error, dest: %pI6\n",
|
|
|
|
__func__, &iph->daddr);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error_icmp;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
if (skb->len > mtu) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2010-02-18 08:25:24 +00:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Call ip_send_check because we are not sure it is called
|
|
|
|
* after ip_defrag. Is copy-on-write needed?
|
|
|
|
*/
|
|
|
|
skb = skb_share_check(skb, GFP_ATOMIC);
|
|
|
|
if (unlikely(skb == NULL)) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
#endif
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2010-07-23 10:46:32 +00:00
|
|
|
static void
|
|
|
|
ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
|
|
|
|
{
|
|
|
|
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
|
|
|
|
struct nf_conntrack_tuple new_tuple;
|
|
|
|
|
|
|
|
if (ct == NULL || nf_ct_is_untracked(ct) || nf_ct_is_confirmed(ct))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The connection is not yet in the hashtable, so we update it.
|
|
|
|
* CIP->VIP will remain the same, so leave the tuple in
|
|
|
|
* IP_CT_DIR_ORIGINAL untouched. When the reply comes back from the
|
|
|
|
* real-server we will see RIP->DIP.
|
|
|
|
*/
|
|
|
|
new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
|
|
|
|
new_tuple.src.u3 = cp->daddr;
|
|
|
|
/*
|
|
|
|
* This will also take care of UDP and other protocols.
|
|
|
|
*/
|
|
|
|
new_tuple.src.u.tcp.port = cp->dport;
|
|
|
|
nf_conntrack_alter_reply(ct, &new_tuple);
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* NAT transmitter (only for outside-to-inside nat forwarding)
|
|
|
|
* Not used for related ICMP
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rtable *rt; /* Route to the other host */
|
|
|
|
int mtu;
|
2007-04-21 05:47:35 +00:00
|
|
|
struct iphdr *iph = ip_hdr(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
/* check if it is a connection of no-client-port */
|
|
|
|
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
|
2006-09-28 21:29:52 +00:00
|
|
|
__be16 _pt, *p;
|
2005-04-16 22:20:36 +00:00
|
|
|
p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt);
|
|
|
|
if (p == NULL)
|
|
|
|
goto tx_error;
|
|
|
|
ip_vs_conn_fill_cport(cp, *p);
|
|
|
|
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos))))
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2007-03-07 05:19:10 +00:00
|
|
|
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
|
2005-04-16 22:20:36 +00:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* copy-on-write the packet before mangling it */
|
2007-10-14 07:39:33 +00:00
|
|
|
if (!skb_make_writable(skb, sizeof(struct iphdr)))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error_put;
|
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
if (skb_cow(skb, rt->dst.dev->hard_header_len))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error_put;
|
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* mangle the packet */
|
2007-10-15 07:53:15 +00:00
|
|
|
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
2008-09-02 13:55:33 +00:00
|
|
|
ip_hdr(skb)->daddr = cp->daddr.ip;
|
2007-04-21 05:47:35 +00:00
|
|
|
ip_send_check(ip_hdr(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
|
|
|
|
|
2010-07-23 10:46:32 +00:00
|
|
|
ip_vs_update_conntrack(skb, cp);
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/* FIXME: when application helper enlarges the packet and the length
|
|
|
|
is larger than the MTU of outgoing device, there will be still
|
|
|
|
MTU problem. */
|
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
LeaveFunction(10);
|
|
|
|
kfree_skb(skb);
|
|
|
|
return NF_STOLEN;
|
|
|
|
tx_error_put:
|
|
|
|
ip_rt_put(rt);
|
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
2008-09-02 13:55:45 +00:00
|
|
|
#ifdef CONFIG_IP_VS_IPV6
|
|
|
|
int
|
|
|
|
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rt6_info *rt; /* Route to the other host */
|
|
|
|
int mtu;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
/* check if it is a connection of no-client-port */
|
|
|
|
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
|
|
|
|
__be16 _pt, *p;
|
|
|
|
p = skb_header_pointer(skb, sizeof(struct ipv6hdr),
|
|
|
|
sizeof(_pt), &_pt);
|
|
|
|
if (p == NULL)
|
|
|
|
goto tx_error;
|
|
|
|
ip_vs_conn_fill_cport(cp, *p);
|
|
|
|
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
|
|
|
|
}
|
|
|
|
|
|
|
|
rt = __ip_vs_get_out_rt_v6(cp);
|
|
|
|
if (!rt)
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
if (skb->len > mtu) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2010-02-18 08:25:24 +00:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2008-09-02 13:55:45 +00:00
|
|
|
IP_VS_DBG_RL_PKT(0, pp, skb, 0,
|
|
|
|
"ip_vs_nat_xmit_v6(): frag needed for");
|
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* copy-on-write the packet before mangling it */
|
|
|
|
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
|
|
|
|
goto tx_error_put;
|
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
if (skb_cow(skb, rt->dst.dev->hard_header_len))
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error_put;
|
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
/* mangle the packet */
|
|
|
|
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
|
|
|
|
goto tx_error;
|
|
|
|
ipv6_hdr(skb)->daddr = cp->daddr.in6;
|
|
|
|
|
|
|
|
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
|
|
|
|
|
2010-07-23 10:46:32 +00:00
|
|
|
ip_vs_update_conntrack(skb, cp);
|
|
|
|
|
2008-09-02 13:55:45 +00:00
|
|
|
/* FIXME: when application helper enlarges the packet and the length
|
|
|
|
is larger than the MTU of outgoing device, there will be still
|
|
|
|
MTU problem. */
|
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
LeaveFunction(10);
|
|
|
|
kfree_skb(skb);
|
|
|
|
return NF_STOLEN;
|
|
|
|
tx_error_put:
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* IP Tunneling transmitter
|
|
|
|
*
|
|
|
|
* This function encapsulates the packet in a new IP packet, its
|
|
|
|
* destination will be set to cp->daddr. Most code of this function
|
|
|
|
* is taken from ipip.c.
|
|
|
|
*
|
|
|
|
* It is used in VS/TUN cluster. The load balancer selects a real
|
|
|
|
* server from a cluster based on a scheduling algorithm,
|
|
|
|
* encapsulates the request packet and forwards it to the selected
|
|
|
|
* server. For example, all real servers are configured with
|
|
|
|
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
|
|
|
|
* the encapsulated packet, it will decapsulate the packet, processe
|
|
|
|
* the request and return the response packets directly to the client
|
|
|
|
* without passing the load balancer. This can greatly increase the
|
|
|
|
* scalability of virtual server.
|
|
|
|
*
|
|
|
|
* Used for ANY protocol
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rtable *rt; /* Route to the other host */
|
|
|
|
struct net_device *tdev; /* Device to other host */
|
2007-04-21 05:47:35 +00:00
|
|
|
struct iphdr *old_iph = ip_hdr(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
u8 tos = old_iph->tos;
|
2006-01-06 21:24:29 +00:00
|
|
|
__be16 df = old_iph->frag_off;
|
[SK_BUFF]: Use offsets for skb->{mac,network,transport}_header on 64bit architectures
With this we save 8 bytes per network packet, leaving a 4 bytes hole to be used
in further shrinking work, likely with the offsetization of other pointers,
such as ->{data,tail,end}, at the cost of adds, that were minimized by the
usual practice of setting skb->{mac,nh,n}.raw to a local variable that is then
accessed multiple times in each function, it also is not more expensive than
before with regards to most of the handling of such headers, like setting one
of these headers to another (transport to network, etc), or subtracting, adding
to/from it, comparing them, etc.
Now we have this layout for sk_buff on a x86_64 machine:
[acme@mica net-2.6.22]$ pahole vmlinux sk_buff
struct sk_buff {
struct sk_buff * next; /* 0 8 */
struct sk_buff * prev; /* 8 8 */
struct rb_node rb; /* 16 24 */
struct sock * sk; /* 40 8 */
ktime_t tstamp; /* 48 8 */
struct net_device * dev; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
struct net_device * input_dev; /* 64 8 */
sk_buff_data_t transport_header; /* 72 4 */
sk_buff_data_t network_header; /* 76 4 */
sk_buff_data_t mac_header; /* 80 4 */
/* XXX 4 bytes hole, try to pack */
struct dst_entry * dst; /* 88 8 */
struct sec_path * sp; /* 96 8 */
char cb[48]; /* 104 48 */
/* cacheline 2 boundary (128 bytes) was 24 bytes ago*/
unsigned int len; /* 152 4 */
unsigned int data_len; /* 156 4 */
unsigned int mac_len; /* 160 4 */
union {
__wsum csum; /* 4 */
__u32 csum_offset; /* 4 */
}; /* 164 4 */
__u32 priority; /* 168 4 */
__u8 local_df:1; /* 172 1 */
__u8 cloned:1; /* 172 1 */
__u8 ip_summed:2; /* 172 1 */
__u8 nohdr:1; /* 172 1 */
__u8 nfctinfo:3; /* 172 1 */
__u8 pkt_type:3; /* 173 1 */
__u8 fclone:2; /* 173 1 */
__u8 ipvs_property:1; /* 173 1 */
/* XXX 2 bits hole, try to pack */
__be16 protocol; /* 174 2 */
void (*destructor)(struct sk_buff *); /* 176 8 */
struct nf_conntrack * nfct; /* 184 8 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct sk_buff * nfct_reasm; /* 192 8 */
struct nf_bridge_info *nf_bridge; /* 200 8 */
__u16 tc_index; /* 208 2 */
__u16 tc_verd; /* 210 2 */
dma_cookie_t dma_cookie; /* 212 4 */
__u32 secmark; /* 216 4 */
__u32 mark; /* 220 4 */
unsigned int truesize; /* 224 4 */
atomic_t users; /* 228 4 */
unsigned char * head; /* 232 8 */
unsigned char * data; /* 240 8 */
unsigned char * tail; /* 248 8 */
/* --- cacheline 4 boundary (256 bytes) --- */
unsigned char * end; /* 256 8 */
}; /* size: 264, cachelines: 5 */
/* sum members: 260, holes: 1, sum holes: 4 */
/* bit holes: 1, sum bit holes: 2 bits */
/* last cacheline: 8 bytes */
On 32 bits nothing changes, and pointers continue to be used with the compiler
turning all this abstraction layer into dust. But there are some sk_buff
validation tricks that are now possible, humm... :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-11 04:22:35 +00:00
|
|
|
sk_buff_data_t old_transport_header = skb->transport_header;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct iphdr *iph; /* Our new IP header */
|
2007-10-24 04:07:32 +00:00
|
|
|
unsigned int max_headroom; /* The extra header space needed */
|
2005-04-16 22:20:36 +00:00
|
|
|
int mtu;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
2007-03-07 05:19:10 +00:00
|
|
|
if (skb->protocol != htons(ETH_P_IP)) {
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): protocol error, "
|
2005-04-16 22:20:36 +00:00
|
|
|
"ETH_P_IP: %d, skb protocol: %d\n",
|
2009-08-02 11:05:41 +00:00
|
|
|
__func__, htons(ETH_P_IP), skb->protocol);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(tos))))
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
tdev = rt->dst.dev;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (mtu < 68) {
|
|
|
|
ip_rt_put(rt);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
2009-06-02 05:19:30 +00:00
|
|
|
if (skb_dst(skb))
|
|
|
|
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-03-07 05:19:10 +00:00
|
|
|
df |= (old_iph->frag_off & htons(IP_DF));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-03-07 05:19:10 +00:00
|
|
|
if ((old_iph->frag_off & htons(IP_DF))
|
2005-04-16 22:20:36 +00:00
|
|
|
&& mtu < ntohs(old_iph->tot_len)) {
|
|
|
|
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
|
|
|
|
ip_rt_put(rt);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Okay, now see if we can stuff it in the buffer as-is.
|
|
|
|
*/
|
|
|
|
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
|
|
|
|
|
|
|
|
if (skb_headroom(skb) < max_headroom
|
|
|
|
|| skb_cloned(skb) || skb_shared(skb)) {
|
|
|
|
struct sk_buff *new_skb =
|
|
|
|
skb_realloc_headroom(skb, max_headroom);
|
|
|
|
if (!new_skb) {
|
|
|
|
ip_rt_put(rt);
|
|
|
|
kfree_skb(skb);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_ERR_RL("%s(): no memory\n", __func__);
|
2005-04-16 22:20:36 +00:00
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
kfree_skb(skb);
|
|
|
|
skb = new_skb;
|
2007-04-21 05:47:35 +00:00
|
|
|
old_iph = ip_hdr(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2007-04-11 04:21:55 +00:00
|
|
|
skb->transport_header = old_transport_header;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* fix old IP header checksum */
|
|
|
|
ip_send_check(old_iph);
|
|
|
|
|
2007-04-11 03:46:21 +00:00
|
|
|
skb_push(skb, sizeof(struct iphdr));
|
|
|
|
skb_reset_network_header(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
|
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Push down and install the IPIP header.
|
|
|
|
*/
|
2007-04-21 05:47:35 +00:00
|
|
|
iph = ip_hdr(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
iph->version = 4;
|
|
|
|
iph->ihl = sizeof(struct iphdr)>>2;
|
|
|
|
iph->frag_off = df;
|
|
|
|
iph->protocol = IPPROTO_IPIP;
|
|
|
|
iph->tos = tos;
|
|
|
|
iph->daddr = rt->rt_dst;
|
|
|
|
iph->saddr = rt->rt_src;
|
|
|
|
iph->ttl = old_iph->ttl;
|
2010-06-11 06:31:35 +00:00
|
|
|
ip_select_ident(iph, &rt->dst, NULL);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2008-01-12 03:14:00 +00:00
|
|
|
ip_local_out(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
|
2008-09-02 13:55:45 +00:00
|
|
|
#ifdef CONFIG_IP_VS_IPV6
|
|
|
|
int
|
|
|
|
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rt6_info *rt; /* Route to the other host */
|
|
|
|
struct net_device *tdev; /* Device to other host */
|
|
|
|
struct ipv6hdr *old_iph = ipv6_hdr(skb);
|
|
|
|
sk_buff_data_t old_transport_header = skb->transport_header;
|
|
|
|
struct ipv6hdr *iph; /* Our new IP header */
|
|
|
|
unsigned int max_headroom; /* The extra header space needed */
|
|
|
|
int mtu;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
if (skb->protocol != htons(ETH_P_IPV6)) {
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): protocol error, "
|
2008-09-02 13:55:45 +00:00
|
|
|
"ETH_P_IPV6: %d, skb protocol: %d\n",
|
2009-08-02 11:05:41 +00:00
|
|
|
__func__, htons(ETH_P_IPV6), skb->protocol);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
rt = __ip_vs_get_out_rt_v6(cp);
|
|
|
|
if (!rt)
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
tdev = rt->dst.dev;
|
2008-09-02 13:55:45 +00:00
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
|
2008-09-02 13:55:45 +00:00
|
|
|
/* TODO IPv6: do we need this check in IPv6? */
|
|
|
|
if (mtu < 1280) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): mtu less than 1280\n", __func__);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
2009-06-02 05:19:30 +00:00
|
|
|
if (skb_dst(skb))
|
|
|
|
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) {
|
2010-02-18 08:25:24 +00:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Okay, now see if we can stuff it in the buffer as-is.
|
|
|
|
*/
|
|
|
|
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
|
|
|
|
|
|
|
|
if (skb_headroom(skb) < max_headroom
|
|
|
|
|| skb_cloned(skb) || skb_shared(skb)) {
|
|
|
|
struct sk_buff *new_skb =
|
|
|
|
skb_realloc_headroom(skb, max_headroom);
|
|
|
|
if (!new_skb) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
kfree_skb(skb);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_ERR_RL("%s(): no memory\n", __func__);
|
2008-09-02 13:55:45 +00:00
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
kfree_skb(skb);
|
|
|
|
skb = new_skb;
|
|
|
|
old_iph = ipv6_hdr(skb);
|
|
|
|
}
|
|
|
|
|
|
|
|
skb->transport_header = old_transport_header;
|
|
|
|
|
|
|
|
skb_push(skb, sizeof(struct ipv6hdr));
|
|
|
|
skb_reset_network_header(skb);
|
|
|
|
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
|
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Push down and install the IPIP header.
|
|
|
|
*/
|
|
|
|
iph = ipv6_hdr(skb);
|
|
|
|
iph->version = 6;
|
|
|
|
iph->nexthdr = IPPROTO_IPV6;
|
2008-11-11 00:46:06 +00:00
|
|
|
iph->payload_len = old_iph->payload_len;
|
|
|
|
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
|
2008-09-02 13:55:45 +00:00
|
|
|
iph->priority = old_iph->priority;
|
|
|
|
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
|
|
|
|
iph->daddr = rt->rt6i_dst.addr;
|
|
|
|
iph->saddr = cp->vaddr.in6; /* rt->rt6i_src.addr; */
|
|
|
|
iph->hop_limit = old_iph->hop_limit;
|
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
|
|
|
ip6_local_out(skb);
|
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Direct Routing transmitter
|
|
|
|
* Used for ANY protocol
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rtable *rt; /* Route to the other host */
|
2007-04-21 05:47:35 +00:00
|
|
|
struct iphdr *iph = ip_hdr(skb);
|
2005-04-16 22:20:36 +00:00
|
|
|
int mtu;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos))))
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2007-03-07 05:19:10 +00:00
|
|
|
if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
|
2005-04-16 22:20:36 +00:00
|
|
|
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
|
|
|
|
ip_rt_put(rt);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Call ip_send_check because we are not sure it is called
|
|
|
|
* after ip_defrag. Is copy-on-write needed?
|
|
|
|
*/
|
|
|
|
if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
|
|
|
|
ip_rt_put(rt);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
2007-04-21 05:47:35 +00:00
|
|
|
ip_send_check(ip_hdr(skb));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
|
2008-09-02 13:55:45 +00:00
|
|
|
#ifdef CONFIG_IP_VS_IPV6
|
|
|
|
int
|
|
|
|
ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp)
|
|
|
|
{
|
|
|
|
struct rt6_info *rt; /* Route to the other host */
|
|
|
|
int mtu;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
rt = __ip_vs_get_out_rt_v6(cp);
|
|
|
|
if (!rt)
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
if (skb->len > mtu) {
|
2010-02-18 08:25:24 +00:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Call ip_send_check because we are not sure it is called
|
|
|
|
* after ip_defrag. Is copy-on-write needed?
|
|
|
|
*/
|
|
|
|
skb = skb_share_check(skb, GFP_ATOMIC);
|
|
|
|
if (unlikely(skb == NULL)) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* drop old route */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
LeaveFunction(10);
|
|
|
|
return NF_STOLEN;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* ICMP packet transmitter
|
|
|
|
* called by the ip_vs_in_icmp
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp, int offset)
|
|
|
|
{
|
|
|
|
struct rtable *rt; /* Route to the other host */
|
|
|
|
int mtu;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
|
|
|
|
forwarded directly here, because there is no need to
|
|
|
|
translate address/port back */
|
|
|
|
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
|
|
|
|
if (cp->packet_xmit)
|
|
|
|
rc = cp->packet_xmit(skb, cp, pp);
|
|
|
|
else
|
|
|
|
rc = NF_ACCEPT;
|
|
|
|
/* do not touch skb anymore */
|
|
|
|
atomic_inc(&cp->in_pkts);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* mangle and send the packet here (only for VS/NAT)
|
|
|
|
*/
|
|
|
|
|
2007-04-21 05:47:35 +00:00
|
|
|
if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(ip_hdr(skb)->tos))))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error_icmp;
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2007-04-21 05:47:35 +00:00
|
|
|
if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) {
|
2005-04-16 22:20:36 +00:00
|
|
|
ip_rt_put(rt);
|
|
|
|
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* copy-on-write the packet before mangling it */
|
2007-10-14 07:39:33 +00:00
|
|
|
if (!skb_make_writable(skb, offset))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error_put;
|
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
if (skb_cow(skb, rt->dst.dev->hard_header_len))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto tx_error_put;
|
|
|
|
|
|
|
|
/* drop the old route when skb is not shared */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
ip_vs_nat_icmp(skb, pp, cp, 0);
|
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV4, skb, rt);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
rc = NF_STOLEN;
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
dev_kfree_skb(skb);
|
|
|
|
rc = NF_STOLEN;
|
|
|
|
out:
|
|
|
|
LeaveFunction(10);
|
|
|
|
return rc;
|
|
|
|
tx_error_put:
|
|
|
|
ip_rt_put(rt);
|
|
|
|
goto tx_error;
|
|
|
|
}
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
#ifdef CONFIG_IP_VS_IPV6
|
|
|
|
int
|
|
|
|
ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
|
|
|
|
struct ip_vs_protocol *pp, int offset)
|
|
|
|
{
|
|
|
|
struct rt6_info *rt; /* Route to the other host */
|
|
|
|
int mtu;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
EnterFunction(10);
|
|
|
|
|
|
|
|
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
|
|
|
|
forwarded directly here, because there is no need to
|
|
|
|
translate address/port back */
|
|
|
|
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
|
|
|
|
if (cp->packet_xmit)
|
|
|
|
rc = cp->packet_xmit(skb, cp, pp);
|
|
|
|
else
|
|
|
|
rc = NF_ACCEPT;
|
|
|
|
/* do not touch skb anymore */
|
|
|
|
atomic_inc(&cp->in_pkts);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* mangle and send the packet here (only for VS/NAT)
|
|
|
|
*/
|
|
|
|
|
|
|
|
rt = __ip_vs_get_out_rt_v6(cp);
|
|
|
|
if (!rt)
|
|
|
|
goto tx_error_icmp;
|
|
|
|
|
|
|
|
/* MTU checking */
|
2010-06-11 06:31:35 +00:00
|
|
|
mtu = dst_mtu(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
if (skb->len > mtu) {
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2010-02-18 08:25:24 +00:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2009-08-02 11:05:41 +00:00
|
|
|
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* copy-on-write the packet before mangling it */
|
|
|
|
if (!skb_make_writable(skb, offset))
|
|
|
|
goto tx_error_put;
|
|
|
|
|
2010-06-11 06:31:35 +00:00
|
|
|
if (skb_cow(skb, rt->dst.dev->hard_header_len))
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error_put;
|
|
|
|
|
|
|
|
/* drop the old route when skb is not shared */
|
2009-06-02 05:19:30 +00:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 06:31:35 +00:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
ip_vs_nat_icmp_v6(skb, pp, cp, 0);
|
|
|
|
|
|
|
|
/* Another hack: avoid icmp_send in ip_fragment */
|
|
|
|
skb->local_df = 1;
|
|
|
|
|
2010-03-23 03:08:46 +00:00
|
|
|
IP_VS_XMIT(NFPROTO_IPV6, skb, rt);
|
2008-09-02 13:55:45 +00:00
|
|
|
|
|
|
|
rc = NF_STOLEN;
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
|
|
|
dev_kfree_skb(skb);
|
|
|
|
rc = NF_STOLEN;
|
|
|
|
out:
|
|
|
|
LeaveFunction(10);
|
|
|
|
return rc;
|
|
|
|
tx_error_put:
|
2010-06-11 06:31:35 +00:00
|
|
|
dst_release(&rt->dst);
|
2008-09-02 13:55:45 +00:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
#endif
|