2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* IPv6 output functions
|
2007-02-09 22:24:49 +08:00
|
|
|
* Linux INET6 implementation
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Authors:
|
2007-02-09 22:24:49 +08:00
|
|
|
* Pedro Roque <roque@di.fc.ul.pt>
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Based on linux/net/ipv4/ip_output.c
|
|
|
|
*
|
|
|
|
* 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:
|
|
|
|
* A.N.Kuznetsov : airthmetics in fragmentation.
|
|
|
|
* extension headers are implemented.
|
|
|
|
* route changes now work.
|
|
|
|
* ip6_forward does not confuse sniffers.
|
|
|
|
* etc.
|
|
|
|
*
|
|
|
|
* H. von Brand : Added missing #include <linux/string.h>
|
|
|
|
* Imran Patel : frag id should be in NBO
|
|
|
|
* Kazunori MIYAZAWA @USAGI
|
|
|
|
* : add ip6_append_data and related functions
|
|
|
|
* for datagram xmit
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/errno.h>
|
2008-01-12 11:15:08 +08:00
|
|
|
#include <linux/kernel.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/socket.h>
|
|
|
|
#include <linux/net.h>
|
|
|
|
#include <linux/netdevice.h>
|
|
|
|
#include <linux/if_arp.h>
|
|
|
|
#include <linux/in6.h>
|
|
|
|
#include <linux/tcp.h>
|
|
|
|
#include <linux/route.h>
|
2006-05-28 14:05:54 +08:00
|
|
|
#include <linux/module.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 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <linux/netfilter.h>
|
|
|
|
#include <linux/netfilter_ipv6.h>
|
|
|
|
|
|
|
|
#include <net/sock.h>
|
|
|
|
#include <net/snmp.h>
|
|
|
|
|
|
|
|
#include <net/ipv6.h>
|
|
|
|
#include <net/ndisc.h>
|
|
|
|
#include <net/protocol.h>
|
|
|
|
#include <net/ip6_route.h>
|
|
|
|
#include <net/addrconf.h>
|
|
|
|
#include <net/rawv6.h>
|
|
|
|
#include <net/icmp.h>
|
|
|
|
#include <net/xfrm.h>
|
|
|
|
#include <net/checksum.h>
|
2008-04-03 08:22:53 +08:00
|
|
|
#include <linux/mroute6.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-12-17 19:42:42 +08:00
|
|
|
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-12 11:15:08 +08:00
|
|
|
int __ip6_local_out(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
int len;
|
|
|
|
|
|
|
|
len = skb->len - sizeof(struct ipv6hdr);
|
|
|
|
if (len > IPV6_MAXPLEN)
|
|
|
|
len = 0;
|
|
|
|
ipv6_hdr(skb)->payload_len = htons(len);
|
|
|
|
|
2010-03-23 11:09:07 +08:00
|
|
|
return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
|
|
|
|
skb_dst(skb)->dev, dst_output);
|
2008-01-12 11:15:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int ip6_local_out(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = __ip6_local_out(skb);
|
|
|
|
if (likely(err == 1))
|
|
|
|
err = dst_output(skb);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(ip6_local_out);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* dev_loopback_xmit for use with netfilter. */
|
|
|
|
static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
|
|
|
|
{
|
2007-03-20 06:30:44 +08:00
|
|
|
skb_reset_mac_header(newskb);
|
2007-03-11 09:16:10 +08:00
|
|
|
__skb_pull(newskb, skb_network_offset(newskb));
|
2005-04-17 06:20:36 +08:00
|
|
|
newskb->pkt_type = PACKET_LOOPBACK;
|
|
|
|
newskb->ip_summed = CHECKSUM_UNNECESSARY;
|
2009-06-02 13:19:30 +08:00
|
|
|
WARN_ON(!skb_dst(newskb));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-04-15 17:13:03 +08:00
|
|
|
netif_rx_ni(newskb);
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-04-13 21:28:11 +08:00
|
|
|
static int ip6_finish_output2(struct sk_buff *skb)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-06-02 13:19:30 +08:00
|
|
|
struct dst_entry *dst = skb_dst(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct net_device *dev = dst->dev;
|
|
|
|
|
|
|
|
skb->protocol = htons(ETH_P_IPV6);
|
|
|
|
skb->dev = dev;
|
|
|
|
|
2007-04-26 08:54:47 +08:00
|
|
|
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
|
2009-06-02 13:19:30 +08:00
|
|
|
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-01-07 12:37:01 +08:00
|
|
|
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
|
ipv6: ip6mr: support multiple tables
This patch adds support for multiple independant multicast routing instances,
named "tables".
Userspace multicast routing daemons can bind to a specific table instance by
issuing a setsockopt call using a new option MRT6_TABLE. The table number is
stored in the raw socket data and affects all following ip6mr setsockopt(),
getsockopt() and ioctl() calls. By default, a single table (RT6_TABLE_DFLT)
is created with a default routing rule pointing to it. Newly created pim6reg
devices have the table number appended ("pim6regX"), with the exception of
devices created in the default table, which are named just "pim6reg" for
compatibility reasons.
Packets are directed to a specific table instance using routing rules,
similar to how regular routing rules work. Currently iif, oif and mark
are supported as keys, source and destination addresses could be supported
additionally.
Example usage:
- bind pimd/xorp/... to a specific table:
uint32_t table = 123;
setsockopt(fd, SOL_IPV6, MRT6_TABLE, &table, sizeof(table));
- create routing rules directing packets to the new table:
# ip -6 mrule add iif eth0 lookup 123
# ip -6 mrule add oif eth0 lookup 123
Signed-off-by: Patrick McHardy <kaber@trash.net>
2010-05-11 20:40:55 +08:00
|
|
|
((mroute6_socket(dev_net(dev), skb) &&
|
2008-12-11 08:07:08 +08:00
|
|
|
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
|
2008-04-03 08:22:53 +08:00
|
|
|
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
|
|
|
|
&ipv6_hdr(skb)->saddr))) {
|
2005-04-17 06:20:36 +08:00
|
|
|
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
|
|
|
|
|
|
|
|
/* Do not check for IFF_ALLMULTI; multicast routing
|
|
|
|
is not supported in any case.
|
|
|
|
*/
|
|
|
|
if (newskb)
|
2010-03-23 11:09:07 +08:00
|
|
|
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
|
|
|
|
newskb, NULL, newskb->dev,
|
2005-04-17 06:20:36 +08:00
|
|
|
ip6_dev_loopback_xmit);
|
|
|
|
|
2007-04-26 08:54:47 +08:00
|
|
|
if (ipv6_hdr(skb)->hop_limit == 0) {
|
2008-10-09 01:54:51 +08:00
|
|
|
IP6_INC_STATS(dev_net(dev), idev,
|
|
|
|
IPSTATS_MIB_OUTDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-04-27 17:45:02 +08:00
|
|
|
IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
|
|
|
|
skb->len);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2010-04-13 21:28:11 +08:00
|
|
|
if (dst->hh)
|
|
|
|
return neigh_hh_output(dst->hh, skb);
|
|
|
|
else if (dst->neighbour)
|
|
|
|
return dst->neighbour->output(skb);
|
|
|
|
|
|
|
|
IP6_INC_STATS_BH(dev_net(dst->dev),
|
|
|
|
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
|
|
|
|
kfree_skb(skb);
|
|
|
|
return -EINVAL;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2010-04-13 21:28:11 +08:00
|
|
|
static int ip6_finish_output(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
|
|
|
|
dst_allfrag(skb_dst(skb)))
|
|
|
|
return ip6_fragment(skb, ip6_finish_output2);
|
|
|
|
else
|
|
|
|
return ip6_finish_output2(skb);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
int ip6_output(struct sk_buff *skb)
|
|
|
|
{
|
2010-04-13 21:28:11 +08:00
|
|
|
struct net_device *dev = skb_dst(skb)->dev;
|
2009-06-02 13:19:30 +08:00
|
|
|
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
|
2008-06-28 13:17:11 +08:00
|
|
|
if (unlikely(idev->cnf.disable_ipv6)) {
|
2010-04-13 21:28:11 +08:00
|
|
|
IP6_INC_STATS(dev_net(dev), idev,
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_OUTDISCARDS);
|
2008-06-28 13:17:11 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-04-13 21:32:16 +08:00
|
|
|
return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
|
|
|
|
ip6_finish_output,
|
|
|
|
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2010-04-16 00:48:48 +08:00
|
|
|
* xmit an sk_buff (used by TCP, SCTP and DCCP)
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
|
2010-04-16 00:43:08 +08:00
|
|
|
struct ipv6_txoptions *opt)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-10-09 01:54:51 +08:00
|
|
|
struct net *net = sock_net(sk);
|
2006-03-23 17:17:25 +08:00
|
|
|
struct ipv6_pinfo *np = inet6_sk(sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct in6_addr *first_hop = &fl->fl6_dst;
|
2009-06-02 13:19:30 +08:00
|
|
|
struct dst_entry *dst = skb_dst(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct ipv6hdr *hdr;
|
2011-03-12 13:29:39 +08:00
|
|
|
u8 proto = fl->flowi_proto;
|
2005-04-17 06:20:36 +08:00
|
|
|
int seg_len = skb->len;
|
2009-08-09 16:12:48 +08:00
|
|
|
int hlimit = -1;
|
|
|
|
int tclass = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
u32 mtu;
|
|
|
|
|
|
|
|
if (opt) {
|
2007-10-24 12:07:32 +08:00
|
|
|
unsigned int head_room;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* First: exthdrs may take lots of space (~8K for now)
|
|
|
|
MAX_HEADER is not enough.
|
|
|
|
*/
|
|
|
|
head_room = opt->opt_nflen + opt->opt_flen;
|
|
|
|
seg_len += head_room;
|
|
|
|
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
|
|
|
|
|
|
|
|
if (skb_headroom(skb) < head_room) {
|
|
|
|
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
|
2006-11-04 19:11:37 +08:00
|
|
|
if (skb2 == NULL) {
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2006-11-04 19:11:37 +08:00
|
|
|
IPSTATS_MIB_OUTDISCARDS);
|
|
|
|
kfree_skb(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
return -ENOBUFS;
|
|
|
|
}
|
2006-11-04 19:11:37 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
skb = skb2;
|
2010-05-01 07:42:08 +08:00
|
|
|
skb_set_owner_w(skb, sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
if (opt->opt_flen)
|
|
|
|
ipv6_push_frag_opts(skb, opt, &proto);
|
|
|
|
if (opt->opt_nflen)
|
|
|
|
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
|
|
|
|
}
|
|
|
|
|
2007-04-11 11:46:21 +08:00
|
|
|
skb_push(skb, sizeof(struct ipv6hdr));
|
|
|
|
skb_reset_network_header(skb);
|
2007-04-26 08:54:47 +08:00
|
|
|
hdr = ipv6_hdr(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Fill in the IPv6 header
|
|
|
|
*/
|
2009-08-09 16:12:48 +08:00
|
|
|
if (np) {
|
|
|
|
tclass = np->tclass;
|
2005-04-17 06:20:36 +08:00
|
|
|
hlimit = np->hop_limit;
|
2009-08-09 16:12:48 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
if (hlimit < 0)
|
2008-03-10 18:00:30 +08:00
|
|
|
hlimit = ip6_dst_hoplimit(dst);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-11-08 16:25:17 +08:00
|
|
|
*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;
|
2005-09-08 09:19:03 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
hdr->payload_len = htons(seg_len);
|
|
|
|
hdr->nexthdr = proto;
|
|
|
|
hdr->hop_limit = hlimit;
|
|
|
|
|
|
|
|
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
|
|
|
|
ipv6_addr_copy(&hdr->daddr, first_hop);
|
|
|
|
|
2006-01-09 14:37:26 +08:00
|
|
|
skb->priority = sk->sk_priority;
|
2008-01-31 11:08:16 +08:00
|
|
|
skb->mark = sk->sk_mark;
|
2006-01-09 14:37:26 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
mtu = dst_mtu(dst);
|
2008-08-04 12:15:59 +08:00
|
|
|
if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2009-04-27 17:45:02 +08:00
|
|
|
IPSTATS_MIB_OUT, skb->len);
|
2010-03-23 11:09:07 +08:00
|
|
|
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
|
|
|
|
dst->dev, dst_output);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (net_ratelimit())
|
|
|
|
printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
|
|
|
|
skb->dev = dst->dev;
|
2010-02-18 16:25:24 +08:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
|
2005-04-17 06:20:36 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
return -EMSGSIZE;
|
|
|
|
}
|
|
|
|
|
2007-02-22 21:05:40 +08:00
|
|
|
EXPORT_SYMBOL(ip6_xmit);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* To avoid extra problems ND packets are send through this
|
|
|
|
* routine. It's code duplication but I really want to avoid
|
|
|
|
* extra checks since ipv6_build_header is used by TCP (which
|
|
|
|
* is for us performance critical)
|
|
|
|
*/
|
|
|
|
|
|
|
|
int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev,
|
[IPV6]: Make address arguments const.
- net/ipv6/addrconf.c:
ipv6_get_ifaddr(), ipv6_dev_get_saddr()
- net/ipv6/mcast.c:
ipv6_sock_mc_join(), ipv6_sock_mc_drop(),
inet6_mc_check(),
ipv6_dev_mc_inc(), __ipv6_dev_mc_dec(), ipv6_dev_mc_dec(),
ipv6_chk_mcast_addr()
- net/ipv6/route.c:
rt6_lookup(), icmp6_dst_alloc()
- net/ipv6/ip6_output.c:
ip6_nd_hdr()
- net/ipv6/ndisc.c:
ndisc_send_ns(), ndisc_send_rs(), ndisc_send_redirect(),
ndisc_get_neigh(), __ndisc_send()
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
2008-04-10 14:42:10 +08:00
|
|
|
const struct in6_addr *saddr, const struct in6_addr *daddr,
|
2005-04-17 06:20:36 +08:00
|
|
|
int proto, int len)
|
|
|
|
{
|
|
|
|
struct ipv6_pinfo *np = inet6_sk(sk);
|
|
|
|
struct ipv6hdr *hdr;
|
|
|
|
|
|
|
|
skb->protocol = htons(ETH_P_IPV6);
|
|
|
|
skb->dev = dev;
|
|
|
|
|
2007-03-15 08:05:03 +08:00
|
|
|
skb_reset_network_header(skb);
|
|
|
|
skb_put(skb, sizeof(struct ipv6hdr));
|
2007-04-26 08:54:47 +08:00
|
|
|
hdr = ipv6_hdr(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-11-08 16:27:11 +08:00
|
|
|
*(__be32*)hdr = htonl(0x60000000);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
hdr->payload_len = htons(len);
|
|
|
|
hdr->nexthdr = proto;
|
|
|
|
hdr->hop_limit = np->hop_limit;
|
|
|
|
|
|
|
|
ipv6_addr_copy(&hdr->saddr, saddr);
|
|
|
|
ipv6_addr_copy(&hdr->daddr, daddr);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
|
|
|
|
{
|
|
|
|
struct ip6_ra_chain *ra;
|
|
|
|
struct sock *last = NULL;
|
|
|
|
|
|
|
|
read_lock(&ip6_ra_lock);
|
|
|
|
for (ra = ip6_ra_chain; ra; ra = ra->next) {
|
|
|
|
struct sock *sk = ra->sk;
|
2005-08-10 10:44:42 +08:00
|
|
|
if (sk && ra->sel == sel &&
|
|
|
|
(!sk->sk_bound_dev_if ||
|
|
|
|
sk->sk_bound_dev_if == skb->dev->ifindex)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
if (last) {
|
|
|
|
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
|
|
|
|
if (skb2)
|
|
|
|
rawv6_rcv(last, skb2);
|
|
|
|
}
|
|
|
|
last = sk;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (last) {
|
|
|
|
rawv6_rcv(last, skb);
|
|
|
|
read_unlock(&ip6_ra_lock);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
read_unlock(&ip6_ra_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-09-23 05:41:44 +08:00
|
|
|
static int ip6_forward_proxy_check(struct sk_buff *skb)
|
|
|
|
{
|
2007-04-26 08:54:47 +08:00
|
|
|
struct ipv6hdr *hdr = ipv6_hdr(skb);
|
2006-09-23 05:41:44 +08:00
|
|
|
u8 nexthdr = hdr->nexthdr;
|
|
|
|
int offset;
|
|
|
|
|
|
|
|
if (ipv6_ext_hdr(nexthdr)) {
|
|
|
|
offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
|
|
|
|
if (offset < 0)
|
|
|
|
return 0;
|
|
|
|
} else
|
|
|
|
offset = sizeof(struct ipv6hdr);
|
|
|
|
|
|
|
|
if (nexthdr == IPPROTO_ICMPV6) {
|
|
|
|
struct icmp6hdr *icmp6;
|
|
|
|
|
2007-04-11 11:50:43 +08:00
|
|
|
if (!pskb_may_pull(skb, (skb_network_header(skb) +
|
|
|
|
offset + 1 - skb->data)))
|
2006-09-23 05:41:44 +08:00
|
|
|
return 0;
|
|
|
|
|
2007-04-11 11:50:43 +08:00
|
|
|
icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset);
|
2006-09-23 05:41:44 +08:00
|
|
|
|
|
|
|
switch (icmp6->icmp6_type) {
|
|
|
|
case NDISC_ROUTER_SOLICITATION:
|
|
|
|
case NDISC_ROUTER_ADVERTISEMENT:
|
|
|
|
case NDISC_NEIGHBOUR_SOLICITATION:
|
|
|
|
case NDISC_NEIGHBOUR_ADVERTISEMENT:
|
|
|
|
case NDISC_REDIRECT:
|
|
|
|
/* For reaction involving unicast neighbor discovery
|
|
|
|
* message destined to the proxied address, pass it to
|
|
|
|
* input function.
|
|
|
|
*/
|
|
|
|
return 1;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-09-23 05:42:18 +08:00
|
|
|
/*
|
|
|
|
* The proxying router can't forward traffic sent to a link-local
|
|
|
|
* address, so signal the sender and discard the packet. This
|
|
|
|
* behavior is clarified by the MIPv6 specification.
|
|
|
|
*/
|
|
|
|
if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) {
|
|
|
|
dst_link_failure(skb);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2006-09-23 05:41:44 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline int ip6_forward_finish(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
return dst_output(skb);
|
|
|
|
}
|
|
|
|
|
|
|
|
int ip6_forward(struct sk_buff *skb)
|
|
|
|
{
|
2009-06-02 13:19:30 +08:00
|
|
|
struct dst_entry *dst = skb_dst(skb);
|
2007-04-26 08:54:47 +08:00
|
|
|
struct ipv6hdr *hdr = ipv6_hdr(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct inet6_skb_parm *opt = IP6CB(skb);
|
2008-03-25 20:47:49 +08:00
|
|
|
struct net *net = dev_net(dst->dev);
|
2010-02-26 20:34:49 +08:00
|
|
|
u32 mtu;
|
2007-02-09 22:24:49 +08:00
|
|
|
|
2008-07-20 13:35:03 +08:00
|
|
|
if (net->ipv6.devconf_all->forwarding == 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
goto error;
|
|
|
|
|
2008-06-20 07:22:28 +08:00
|
|
|
if (skb_warn_if_lro(skb))
|
|
|
|
goto drop;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
|
2008-10-09 01:54:51 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
2011-01-12 16:34:08 +08:00
|
|
|
if (skb->pkt_type != PACKET_HOST)
|
|
|
|
goto drop;
|
|
|
|
|
2007-03-27 14:22:20 +08:00
|
|
|
skb_forward_csum(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We DO NOT make any processing on
|
|
|
|
* RA packets, pushing them to user level AS IS
|
|
|
|
* without ane WARRANTY that application will be able
|
|
|
|
* to interpret them. The reason is that we
|
|
|
|
* cannot make anything clever here.
|
|
|
|
*
|
|
|
|
* We are not end-node, so that if packet contains
|
|
|
|
* AH/ESP, we cannot make anything.
|
|
|
|
* Defragmentation also would be mistake, RA packets
|
|
|
|
* cannot be fragmented, because there is no warranty
|
|
|
|
* that different fragments will go along one path. --ANK
|
|
|
|
*/
|
|
|
|
if (opt->ra) {
|
2007-04-11 11:50:43 +08:00
|
|
|
u8 *ptr = skb_network_header(skb) + opt->ra;
|
2005-04-17 06:20:36 +08:00
|
|
|
if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* check and decrement ttl
|
|
|
|
*/
|
|
|
|
if (hdr->hop_limit <= 1) {
|
|
|
|
/* Force OUTPUT device used as source address */
|
|
|
|
skb->dev = dst->dev;
|
2010-02-18 16:25:24 +08:00
|
|
|
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
|
2008-10-09 02:09:27 +08:00
|
|
|
IP6_INC_STATS_BH(net,
|
|
|
|
ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
kfree_skb(skb);
|
|
|
|
return -ETIMEDOUT;
|
|
|
|
}
|
|
|
|
|
2006-09-23 05:43:49 +08:00
|
|
|
/* XXX: idev->cnf.proxy_ndp? */
|
2008-07-20 13:35:03 +08:00
|
|
|
if (net->ipv6.devconf_all->proxy_ndp &&
|
2008-03-08 03:14:16 +08:00
|
|
|
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
|
2006-09-23 05:42:18 +08:00
|
|
|
int proxied = ip6_forward_proxy_check(skb);
|
|
|
|
if (proxied > 0)
|
2006-09-23 05:41:44 +08:00
|
|
|
return ip6_input(skb);
|
2006-09-23 05:42:18 +08:00
|
|
|
else if (proxied < 0) {
|
2008-10-09 01:54:51 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(dst),
|
|
|
|
IPSTATS_MIB_INDISCARDS);
|
2006-09-23 05:42:18 +08:00
|
|
|
goto drop;
|
|
|
|
}
|
2006-09-23 05:41:44 +08:00
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!xfrm6_route_forward(skb)) {
|
2008-10-09 01:54:51 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto drop;
|
|
|
|
}
|
2009-06-02 13:19:30 +08:00
|
|
|
dst = skb_dst(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* IPv6 specs say nothing about it, but it is clear that we cannot
|
|
|
|
send redirects to source routed frames.
|
2007-08-24 18:08:55 +08:00
|
|
|
We don't send redirects to frames decapsulated from IPsec.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2007-08-24 18:08:55 +08:00
|
|
|
if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 &&
|
2008-10-29 04:24:06 +08:00
|
|
|
!skb_sec_path(skb)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
struct in6_addr *target = NULL;
|
|
|
|
struct rt6_info *rt;
|
|
|
|
struct neighbour *n = dst->neighbour;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* incoming and outgoing devices are the same
|
|
|
|
* send a redirect.
|
|
|
|
*/
|
|
|
|
|
|
|
|
rt = (struct rt6_info *) dst;
|
|
|
|
if ((rt->rt6i_flags & RTF_GATEWAY))
|
|
|
|
target = (struct in6_addr*)&n->primary_key;
|
|
|
|
else
|
|
|
|
target = &hdr->daddr;
|
|
|
|
|
2011-02-05 07:55:25 +08:00
|
|
|
if (!rt->rt6i_peer)
|
|
|
|
rt6_bind_peer(rt, 1);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Limit redirects both by destination (here)
|
|
|
|
and by source (inside ndisc_send_redirect)
|
|
|
|
*/
|
2011-02-05 07:55:25 +08:00
|
|
|
if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
|
2005-04-17 06:20:36 +08:00
|
|
|
ndisc_send_redirect(skb, n, target);
|
2007-05-10 04:53:44 +08:00
|
|
|
} else {
|
|
|
|
int addrtype = ipv6_addr_type(&hdr->saddr);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* This check is security critical. */
|
2008-06-25 15:55:26 +08:00
|
|
|
if (addrtype == IPV6_ADDR_ANY ||
|
|
|
|
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
|
2007-05-10 04:53:44 +08:00
|
|
|
goto error;
|
|
|
|
if (addrtype & IPV6_ADDR_LINKLOCAL) {
|
|
|
|
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
|
2010-02-18 16:25:24 +08:00
|
|
|
ICMPV6_NOT_NEIGHBOUR, 0);
|
2007-05-10 04:53:44 +08:00
|
|
|
goto error;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2010-02-26 20:34:49 +08:00
|
|
|
mtu = dst_mtu(dst);
|
|
|
|
if (mtu < IPV6_MIN_MTU)
|
|
|
|
mtu = IPV6_MIN_MTU;
|
|
|
|
|
2010-05-28 07:14:30 +08:00
|
|
|
if (skb->len > mtu && !skb_is_gso(skb)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Again, force OUTPUT device used as source address */
|
|
|
|
skb->dev = dst->dev;
|
2010-02-26 20:34:49 +08:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2008-10-09 02:09:27 +08:00
|
|
|
IP6_INC_STATS_BH(net,
|
|
|
|
ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
|
|
|
|
IP6_INC_STATS_BH(net,
|
|
|
|
ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
|
2005-04-17 06:20:36 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
return -EMSGSIZE;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (skb_cow(skb, dst->dev->hard_header_len)) {
|
2008-10-09 01:54:51 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
2007-04-26 08:54:47 +08:00
|
|
|
hdr = ipv6_hdr(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Mangling hops number delayed to point after skb COW */
|
2007-02-09 22:24:49 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
hdr->hop_limit--;
|
|
|
|
|
2008-10-09 02:09:27 +08:00
|
|
|
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
|
2010-03-23 11:09:07 +08:00
|
|
|
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
|
2007-11-20 10:53:30 +08:00
|
|
|
ip6_forward_finish);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
error:
|
2008-10-09 02:09:27 +08:00
|
|
|
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
|
2005-04-17 06:20:36 +08:00
|
|
|
drop:
|
|
|
|
kfree_skb(skb);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
|
|
|
|
{
|
|
|
|
to->pkt_type = from->pkt_type;
|
|
|
|
to->priority = from->priority;
|
|
|
|
to->protocol = from->protocol;
|
2009-06-02 13:19:30 +08:00
|
|
|
skb_dst_drop(to);
|
|
|
|
skb_dst_set(to, dst_clone(skb_dst(from)));
|
2005-04-17 06:20:36 +08:00
|
|
|
to->dev = from->dev;
|
2006-11-10 07:19:14 +08:00
|
|
|
to->mark = from->mark;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_NET_SCHED
|
|
|
|
to->tc_index = from->tc_index;
|
|
|
|
#endif
|
2007-03-15 07:44:01 +08:00
|
|
|
nf_copy(to, from);
|
2007-07-08 13:21:23 +08:00
|
|
|
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
|
|
|
|
defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
|
|
|
|
to->nf_trace = from->nf_trace;
|
|
|
|
#endif
|
2006-06-09 15:29:17 +08:00
|
|
|
skb_copy_secmark(to, from);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
|
|
|
|
{
|
|
|
|
u16 offset = sizeof(struct ipv6hdr);
|
2007-04-26 08:54:47 +08:00
|
|
|
struct ipv6_opt_hdr *exthdr =
|
|
|
|
(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
|
2007-04-20 11:29:13 +08:00
|
|
|
unsigned int packet_len = skb->tail - skb->network_header;
|
2005-04-17 06:20:36 +08:00
|
|
|
int found_rhdr = 0;
|
2007-04-26 08:54:47 +08:00
|
|
|
*nexthdr = &ipv6_hdr(skb)->nexthdr;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
while (offset + 1 <= packet_len) {
|
|
|
|
|
|
|
|
switch (**nexthdr) {
|
|
|
|
|
|
|
|
case NEXTHDR_HOP:
|
2006-08-24 10:29:47 +08:00
|
|
|
break;
|
2005-04-17 06:20:36 +08:00
|
|
|
case NEXTHDR_ROUTING:
|
2006-08-24 10:29:47 +08:00
|
|
|
found_rhdr = 1;
|
|
|
|
break;
|
2005-04-17 06:20:36 +08:00
|
|
|
case NEXTHDR_DEST:
|
2007-06-27 14:56:32 +08:00
|
|
|
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
|
2006-08-24 10:29:47 +08:00
|
|
|
if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
|
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
if (found_rhdr)
|
|
|
|
return offset;
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
|
|
|
default :
|
|
|
|
return offset;
|
|
|
|
}
|
2006-08-24 10:29:47 +08:00
|
|
|
|
|
|
|
offset += ipv6_optlen(exthdr);
|
|
|
|
*nexthdr = &exthdr->nexthdr;
|
2007-04-11 11:50:43 +08:00
|
|
|
exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
|
|
|
|
offset);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return offset;
|
|
|
|
}
|
|
|
|
|
2010-12-17 19:42:42 +08:00
|
|
|
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct sk_buff *frag;
|
2009-06-02 13:19:30 +08:00
|
|
|
struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
|
2006-02-25 05:18:33 +08:00
|
|
|
struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct ipv6hdr *tmp_hdr;
|
|
|
|
struct frag_hdr *fh;
|
|
|
|
unsigned int mtu, hlen, left, len;
|
2006-11-08 16:27:11 +08:00
|
|
|
__be32 frag_id = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
int ptr, offset = 0, err=0;
|
|
|
|
u8 *prevhdr, nexthdr = 0;
|
2009-06-02 13:19:30 +08:00
|
|
|
struct net *net = dev_net(skb_dst(skb)->dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
hlen = ip6_find_1stfragopt(skb, &prevhdr);
|
|
|
|
nexthdr = *prevhdr;
|
|
|
|
|
2007-04-21 06:53:27 +08:00
|
|
|
mtu = ip6_skb_dst_mtu(skb);
|
2007-04-21 06:52:39 +08:00
|
|
|
|
|
|
|
/* We must not fragment if the socket is set to force MTU discovery
|
2010-02-26 20:34:49 +08:00
|
|
|
* or if the skb it not generated by a local socket.
|
2007-04-21 06:52:39 +08:00
|
|
|
*/
|
2010-04-19 00:58:22 +08:00
|
|
|
if (!skb->local_df && skb->len > mtu) {
|
2009-06-02 13:19:30 +08:00
|
|
|
skb->dev = skb_dst(skb)->dev;
|
2010-02-18 16:25:24 +08:00
|
|
|
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_FRAGFAILS);
|
2007-04-21 06:52:39 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
return -EMSGSIZE;
|
|
|
|
}
|
|
|
|
|
2006-02-25 05:18:33 +08:00
|
|
|
if (np && np->frag_size < mtu) {
|
|
|
|
if (np->frag_size)
|
|
|
|
mtu = np->frag_size;
|
|
|
|
}
|
|
|
|
mtu -= hlen + sizeof(struct frag_hdr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-23 15:13:46 +08:00
|
|
|
if (skb_has_frag_list(skb)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
int first_len = skb_pagelen(skb);
|
2010-09-21 16:47:45 +08:00
|
|
|
struct sk_buff *frag2;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if (first_len - hlen > mtu ||
|
|
|
|
((first_len - hlen) & 7) ||
|
|
|
|
skb_cloned(skb))
|
|
|
|
goto slow_path;
|
|
|
|
|
2009-06-09 15:20:05 +08:00
|
|
|
skb_walk_frags(skb, frag) {
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Correct geometry. */
|
|
|
|
if (frag->len > mtu ||
|
|
|
|
((frag->len & 7) && frag->next) ||
|
|
|
|
skb_headroom(frag) < hlen)
|
2010-09-21 16:47:45 +08:00
|
|
|
goto slow_path_clean;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Partially cloned skb? */
|
|
|
|
if (skb_shared(frag))
|
2010-09-21 16:47:45 +08:00
|
|
|
goto slow_path_clean;
|
2005-05-19 13:52:33 +08:00
|
|
|
|
|
|
|
BUG_ON(frag->sk);
|
|
|
|
if (skb->sk) {
|
|
|
|
frag->sk = skb->sk;
|
|
|
|
frag->destructor = sock_wfree;
|
|
|
|
}
|
2010-09-21 16:47:45 +08:00
|
|
|
skb->truesize -= frag->truesize;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
offset = 0;
|
|
|
|
frag = skb_shinfo(skb)->frag_list;
|
2009-06-09 15:20:05 +08:00
|
|
|
skb_frag_list_init(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
/* BUILD HEADER */
|
|
|
|
|
2006-12-06 05:47:21 +08:00
|
|
|
*prevhdr = NEXTHDR_FRAGMENT;
|
2007-04-11 11:50:43 +08:00
|
|
|
tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!tmp_hdr) {
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_FRAGFAILS);
|
2005-04-17 06:20:36 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
__skb_pull(skb, hlen);
|
|
|
|
fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
|
2007-04-11 11:46:21 +08:00
|
|
|
__skb_push(skb, hlen);
|
|
|
|
skb_reset_network_header(skb);
|
2007-04-11 11:50:43 +08:00
|
|
|
memcpy(skb_network_header(skb), tmp_hdr, hlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-07-09 16:10:01 +08:00
|
|
|
ipv6_select_ident(fh);
|
2005-04-17 06:20:36 +08:00
|
|
|
fh->nexthdr = nexthdr;
|
|
|
|
fh->reserved = 0;
|
|
|
|
fh->frag_off = htons(IP6_MF);
|
|
|
|
frag_id = fh->identification;
|
|
|
|
|
|
|
|
first_len = skb_pagelen(skb);
|
|
|
|
skb->data_len = first_len - skb_headlen(skb);
|
|
|
|
skb->len = first_len;
|
2007-04-26 08:54:47 +08:00
|
|
|
ipv6_hdr(skb)->payload_len = htons(first_len -
|
|
|
|
sizeof(struct ipv6hdr));
|
2006-11-04 19:11:37 +08:00
|
|
|
|
2010-06-11 14:31:35 +08:00
|
|
|
dst_hold(&rt->dst);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
/* Prepare header of the next frame,
|
|
|
|
* before previous one went down. */
|
|
|
|
if (frag) {
|
|
|
|
frag->ip_summed = CHECKSUM_NONE;
|
2007-03-14 00:06:52 +08:00
|
|
|
skb_reset_transport_header(frag);
|
2005-04-17 06:20:36 +08:00
|
|
|
fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr));
|
2007-04-11 11:46:21 +08:00
|
|
|
__skb_push(frag, hlen);
|
|
|
|
skb_reset_network_header(frag);
|
2007-04-11 11:50:43 +08:00
|
|
|
memcpy(skb_network_header(frag), tmp_hdr,
|
|
|
|
hlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
offset += skb->len - hlen - sizeof(struct frag_hdr);
|
|
|
|
fh->nexthdr = nexthdr;
|
|
|
|
fh->reserved = 0;
|
|
|
|
fh->frag_off = htons(offset);
|
|
|
|
if (frag->next != NULL)
|
|
|
|
fh->frag_off |= htons(IP6_MF);
|
|
|
|
fh->identification = frag_id;
|
2007-04-26 08:54:47 +08:00
|
|
|
ipv6_hdr(frag)->payload_len =
|
|
|
|
htons(frag->len -
|
|
|
|
sizeof(struct ipv6hdr));
|
2005-04-17 06:20:36 +08:00
|
|
|
ip6_copy_metadata(frag, skb);
|
|
|
|
}
|
2007-02-09 22:24:49 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
err = output(skb);
|
2006-08-03 04:41:21 +08:00
|
|
|
if(!err)
|
2010-06-11 14:31:35 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_FRAGCREATES);
|
2006-08-03 04:41:21 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (err || !frag)
|
|
|
|
break;
|
|
|
|
|
|
|
|
skb = frag;
|
|
|
|
frag = skb->next;
|
|
|
|
skb->next = NULL;
|
|
|
|
}
|
|
|
|
|
2005-11-09 01:41:34 +08:00
|
|
|
kfree(tmp_hdr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if (err == 0) {
|
2010-06-11 14:31:35 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_FRAGOKS);
|
2010-06-11 14:31:35 +08:00
|
|
|
dst_release(&rt->dst);
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
while (frag) {
|
|
|
|
skb = frag->next;
|
|
|
|
kfree_skb(frag);
|
|
|
|
frag = skb;
|
|
|
|
}
|
|
|
|
|
2010-06-11 14:31:35 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_FRAGFAILS);
|
2010-06-11 14:31:35 +08:00
|
|
|
dst_release(&rt->dst);
|
2005-04-17 06:20:36 +08:00
|
|
|
return err;
|
2010-09-21 16:47:45 +08:00
|
|
|
|
|
|
|
slow_path_clean:
|
|
|
|
skb_walk_frags(skb, frag2) {
|
|
|
|
if (frag2 == frag)
|
|
|
|
break;
|
|
|
|
frag2->sk = NULL;
|
|
|
|
frag2->destructor = NULL;
|
|
|
|
skb->truesize += frag2->truesize;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
slow_path:
|
|
|
|
left = skb->len - hlen; /* Space per frame */
|
|
|
|
ptr = hlen; /* Where to start from */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Fragment the datagram.
|
|
|
|
*/
|
|
|
|
|
|
|
|
*prevhdr = NEXTHDR_FRAGMENT;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Keep copying data until we run out.
|
|
|
|
*/
|
|
|
|
while(left > 0) {
|
|
|
|
len = left;
|
|
|
|
/* IF: it doesn't fit, use 'mtu' - the data space left */
|
|
|
|
if (len > mtu)
|
|
|
|
len = mtu;
|
|
|
|
/* IF: we are not sending upto and including the packet end
|
|
|
|
then align the next start on an eight byte boundary */
|
|
|
|
if (len < left) {
|
|
|
|
len &= ~7;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Allocate buffer.
|
|
|
|
*/
|
|
|
|
|
2010-06-11 14:31:35 +08:00
|
|
|
if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) {
|
2005-08-10 11:50:53 +08:00
|
|
|
NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2006-11-04 19:11:37 +08:00
|
|
|
IPSTATS_MIB_FRAGFAILS);
|
2005-04-17 06:20:36 +08:00
|
|
|
err = -ENOMEM;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set up data on packet
|
|
|
|
*/
|
|
|
|
|
|
|
|
ip6_copy_metadata(frag, skb);
|
2010-06-11 14:31:35 +08:00
|
|
|
skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev));
|
2005-04-17 06:20:36 +08:00
|
|
|
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
|
2007-04-11 11:45:18 +08:00
|
|
|
skb_reset_network_header(frag);
|
2007-03-14 00:06:52 +08:00
|
|
|
fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
|
2007-04-11 12:21:55 +08:00
|
|
|
frag->transport_header = (frag->network_header + hlen +
|
|
|
|
sizeof(struct frag_hdr));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Charge the memory for the fragment to any owner
|
|
|
|
* it might possess
|
|
|
|
*/
|
|
|
|
if (skb->sk)
|
|
|
|
skb_set_owner_w(frag, skb->sk);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Copy the packet header into the new buffer.
|
|
|
|
*/
|
2007-03-28 05:55:52 +08:00
|
|
|
skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Build fragment header.
|
|
|
|
*/
|
|
|
|
fh->nexthdr = nexthdr;
|
|
|
|
fh->reserved = 0;
|
2005-10-04 05:19:15 +08:00
|
|
|
if (!frag_id) {
|
2009-07-09 16:10:01 +08:00
|
|
|
ipv6_select_ident(fh);
|
2005-04-17 06:20:36 +08:00
|
|
|
frag_id = fh->identification;
|
|
|
|
} else
|
|
|
|
fh->identification = frag_id;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Copy a block of the IP datagram.
|
|
|
|
*/
|
[IPV6]: Fix kernel panic while send SCTP data with IP fragments
If ICMP6 message with "Packet Too Big" is received after send SCTP DATA,
kernel panic will occur when SCTP DATA is send again.
This is because of a bad dest address when call to skb_copy_bits().
The messages sequence is like this:
Endpoint A Endpoint B
<------- SCTP DATA (size=1432)
ICMP6 message ------->
(Packet Too Big pmtu=1280)
<------- Resend SCTP DATA (size=1432)
------------kernel panic---------------
printing eip:
c05be62a
*pde = 00000000
Oops: 0002 [#1]
SMP
Modules linked in: scomm l2cap bluetooth ipv6 dm_mirror dm_mod video output sbs battery lp floppy sg i2c_piix4 i2c_core pcnet32 mii button ac parport_pc parport ide_cd cdrom serio_raw mptspi mptscsih mptbase scsi_transport_spi sd_mod scsi_mod ext3 jbd ehci_hcd ohci_hcd uhci_hcd
CPU: 0
EIP: 0060:[<c05be62a>] Not tainted VLI
EFLAGS: 00010282 (2.6.23-rc2 #1)
EIP is at skb_copy_bits+0x4f/0x1ef
eax: 000004d0 ebx: ce12a980 ecx: 00000134 edx: cfd5a880
esi: c8246858 edi: 00000000 ebp: c0759b14 esp: c0759adc
ds: 007b es: 007b fs: 00d8 gs: 0000 ss: 0068
Process swapper (pid: 0, ti=c0759000 task=c06d0340 task.ti=c0713000)
Stack: c0759b88 c0405867 ce12a980 c8bff838 c789c084 00000000 00000028 cfd5a880
d09f1890 000005dc 0000007b ce12a980 cfd5a880 c8bff838 c0759b88 d09bc521
000004d0 fffff96c 00000200 00000100 c0759b50 cfd5a880 00000246 c0759bd4
Call Trace:
[<c0405e1d>] show_trace_log_lvl+0x1a/0x2f
[<c0405ecd>] show_stack_log_lvl+0x9b/0xa3
[<c040608d>] show_registers+0x1b8/0x289
[<c0406271>] die+0x113/0x246
[<c0625dbc>] do_page_fault+0x4ad/0x57e
[<c0624642>] error_code+0x72/0x78
[<d09bc521>] ip6_output+0x8e5/0xab2 [ipv6]
[<d09bcec1>] ip6_xmit+0x2ea/0x3a3 [ipv6]
[<d0a3f2ca>] sctp_v6_xmit+0x248/0x253 [sctp]
[<d0a3c934>] sctp_packet_transmit+0x53f/0x5ae [sctp]
[<d0a34bf8>] sctp_outq_flush+0x555/0x587 [sctp]
[<d0a34d3c>] sctp_retransmit+0xf8/0x10f [sctp]
[<d0a3d183>] sctp_icmp_frag_needed+0x57/0x5b [sctp]
[<d0a3ece2>] sctp_v6_err+0xcd/0x148 [sctp]
[<d09cf1ce>] icmpv6_notify+0xe6/0x167 [ipv6]
[<d09d009a>] icmpv6_rcv+0x7d7/0x849 [ipv6]
[<d09be240>] ip6_input+0x1dc/0x310 [ipv6]
[<d09be965>] ipv6_rcv+0x294/0x2df [ipv6]
[<c05c3789>] netif_receive_skb+0x2d2/0x335
[<c05c5733>] process_backlog+0x7f/0xd0
[<c05c58f6>] net_rx_action+0x96/0x17e
[<c042e722>] __do_softirq+0x64/0xcd
[<c0406f37>] do_softirq+0x5c/0xac
=======================
Code: 00 00 29 ca 89 d0 2b 45 e0 89 55 ec 85 c0 7e 35 39 45 08 8b 55 e4 0f 4e 45 08 8b 75 e0 8b 7d dc 89 c1 c1 e9 02 03 b2 a0 00 00 00 <f3> a5 89 c1 83 e1 03 74 02 f3 a4 29 45 08 0f 84 7b 01 00 00 01
EIP: [<c05be62a>] skb_copy_bits+0x4f/0x1ef SS:ESP 0068:c0759adc
Kernel panic - not syncing: Fatal exception in interrupt
Arnaldo says:
====================
Thanks! I'm to blame for this one, problem was introduced in:
b0e380b1d8a8e0aca215df97702f99815f05c094
@@ -761,7 +762,7 @@ slow_path:
/*
* Copy a block of the IP datagram.
*/
- if (skb_copy_bits(skb, ptr, frag->h.raw, len))
+ if (skb_copy_bits(skb, ptr, skb_transport_header(skb),
len))
BUG();
left -= len;
====================
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-08-22 11:59:08 +08:00
|
|
|
if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len))
|
2005-04-17 06:20:36 +08:00
|
|
|
BUG();
|
|
|
|
left -= len;
|
|
|
|
|
|
|
|
fh->frag_off = htons(offset);
|
|
|
|
if (left > 0)
|
|
|
|
fh->frag_off |= htons(IP6_MF);
|
2007-04-26 08:54:47 +08:00
|
|
|
ipv6_hdr(frag)->payload_len = htons(frag->len -
|
|
|
|
sizeof(struct ipv6hdr));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ptr += len;
|
|
|
|
offset += len;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Put this fragment into the sending queue.
|
|
|
|
*/
|
|
|
|
err = output(frag);
|
|
|
|
if (err)
|
|
|
|
goto fail;
|
2006-08-03 04:41:21 +08:00
|
|
|
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2008-10-09 01:54:51 +08:00
|
|
|
IPSTATS_MIB_FRAGCREATES);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2006-11-04 19:11:37 +08:00
|
|
|
IPSTATS_MIB_FRAGOKS);
|
2005-04-17 06:20:36 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
return err;
|
|
|
|
|
|
|
|
fail:
|
2009-06-02 13:19:30 +08:00
|
|
|
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
|
2006-11-04 19:11:37 +08:00
|
|
|
IPSTATS_MIB_FRAGFAILS);
|
2007-02-09 22:24:49 +08:00
|
|
|
kfree_skb(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2006-08-24 08:19:18 +08:00
|
|
|
static inline int ip6_rt_check(struct rt6key *rt_key,
|
|
|
|
struct in6_addr *fl_addr,
|
|
|
|
struct in6_addr *addr_cache)
|
|
|
|
{
|
2010-09-23 04:43:57 +08:00
|
|
|
return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
|
|
|
|
(addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache));
|
2006-08-24 08:19:18 +08:00
|
|
|
}
|
|
|
|
|
2006-07-31 11:19:33 +08:00
|
|
|
static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
|
|
|
|
struct dst_entry *dst,
|
|
|
|
struct flowi *fl)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2006-07-31 11:19:33 +08:00
|
|
|
struct ipv6_pinfo *np = inet6_sk(sk);
|
|
|
|
struct rt6_info *rt = (struct rt6_info *)dst;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-07-31 11:19:33 +08:00
|
|
|
if (!dst)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* Yes, checking route validity in not connected
|
|
|
|
* case is not very simple. Take into account,
|
|
|
|
* that we do not support routing by source, TOS,
|
|
|
|
* and MSG_DONTROUTE --ANK (980726)
|
|
|
|
*
|
2006-08-24 08:19:18 +08:00
|
|
|
* 1. ip6_rt_check(): If route was host route,
|
|
|
|
* check that cached destination is current.
|
2006-07-31 11:19:33 +08:00
|
|
|
* If it is network route, we still may
|
|
|
|
* check its validity using saved pointer
|
|
|
|
* to the last used address: daddr_cache.
|
|
|
|
* We do not want to save whole address now,
|
|
|
|
* (because main consumer of this service
|
|
|
|
* is tcp, which has not this problem),
|
|
|
|
* so that the last trick works only on connected
|
|
|
|
* sockets.
|
|
|
|
* 2. oif also should be the same.
|
|
|
|
*/
|
2006-08-24 08:19:18 +08:00
|
|
|
if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) ||
|
2006-08-30 08:15:09 +08:00
|
|
|
#ifdef CONFIG_IPV6_SUBTREES
|
|
|
|
ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) ||
|
|
|
|
#endif
|
2011-03-12 13:29:39 +08:00
|
|
|
(fl->flowi_oif && fl->flowi_oif != dst->dev->ifindex)) {
|
2006-07-31 11:19:33 +08:00
|
|
|
dst_release(dst);
|
|
|
|
dst = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2006-07-31 11:19:33 +08:00
|
|
|
out:
|
|
|
|
return dst;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ip6_dst_lookup_tail(struct sock *sk,
|
|
|
|
struct dst_entry **dst, struct flowi *fl)
|
|
|
|
{
|
|
|
|
int err;
|
2008-03-26 01:26:21 +08:00
|
|
|
struct net *net = sock_net(sk);
|
2006-07-31 11:19:33 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (*dst == NULL)
|
2008-03-08 03:14:16 +08:00
|
|
|
*dst = ip6_route_output(net, sk, fl);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if ((err = (*dst)->error))
|
|
|
|
goto out_err_release;
|
|
|
|
|
|
|
|
if (ipv6_addr_any(&fl->fl6_src)) {
|
2008-08-15 06:33:21 +08:00
|
|
|
err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev,
|
2008-03-25 08:37:42 +08:00
|
|
|
&fl->fl6_dst,
|
|
|
|
sk ? inet6_sk(sk)->srcprefs : 0,
|
|
|
|
&fl->fl6_src);
|
2005-07-28 02:45:17 +08:00
|
|
|
if (err)
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out_err_release;
|
|
|
|
}
|
|
|
|
|
2007-04-26 08:08:10 +08:00
|
|
|
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
|
2008-09-10 04:51:35 +08:00
|
|
|
/*
|
|
|
|
* Here if the dst entry we've looked up
|
|
|
|
* has a neighbour entry that is in the INCOMPLETE
|
|
|
|
* state and the src address from the flow is
|
|
|
|
* marked as OPTIMISTIC, we release the found
|
|
|
|
* dst entry and replace it instead with the
|
|
|
|
* dst entry of the nexthop router
|
|
|
|
*/
|
|
|
|
if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
|
|
|
|
struct inet6_ifaddr *ifp;
|
|
|
|
struct flowi fl_gw;
|
|
|
|
int redirect;
|
|
|
|
|
|
|
|
ifp = ipv6_get_ifaddr(net, &fl->fl6_src,
|
|
|
|
(*dst)->dev, 1);
|
|
|
|
|
|
|
|
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
|
|
|
|
if (ifp)
|
|
|
|
in6_ifa_put(ifp);
|
|
|
|
|
|
|
|
if (redirect) {
|
|
|
|
/*
|
|
|
|
* We need to get the dst entry for the
|
|
|
|
* default router instead
|
|
|
|
*/
|
|
|
|
dst_release(*dst);
|
|
|
|
memcpy(&fl_gw, fl, sizeof(struct flowi));
|
|
|
|
memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
|
|
|
|
*dst = ip6_route_output(net, sk, &fl_gw);
|
|
|
|
if ((err = (*dst)->error))
|
|
|
|
goto out_err_release;
|
2007-04-26 08:08:10 +08:00
|
|
|
}
|
2008-09-10 04:51:35 +08:00
|
|
|
}
|
2007-04-26 08:08:10 +08:00
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_err_release:
|
2007-12-06 14:31:47 +08:00
|
|
|
if (err == -ENETUNREACH)
|
2008-10-09 02:09:27 +08:00
|
|
|
IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES);
|
2005-04-17 06:20:36 +08:00
|
|
|
dst_release(*dst);
|
|
|
|
*dst = NULL;
|
|
|
|
return err;
|
|
|
|
}
|
2005-11-30 08:28:56 +08:00
|
|
|
|
2006-07-31 11:19:33 +08:00
|
|
|
/**
|
|
|
|
* ip6_dst_lookup - perform route lookup on flow
|
|
|
|
* @sk: socket which provides route info
|
|
|
|
* @dst: pointer to dst_entry * for result
|
|
|
|
* @fl: flow to lookup
|
|
|
|
*
|
|
|
|
* This function performs a route lookup on the given flow.
|
|
|
|
*
|
|
|
|
* It returns zero on success, or a standard errno code on error.
|
|
|
|
*/
|
|
|
|
int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
|
|
|
|
{
|
|
|
|
*dst = NULL;
|
|
|
|
return ip6_dst_lookup_tail(sk, dst, fl);
|
|
|
|
}
|
2005-12-14 15:23:20 +08:00
|
|
|
EXPORT_SYMBOL_GPL(ip6_dst_lookup);
|
|
|
|
|
2006-07-31 11:19:33 +08:00
|
|
|
/**
|
2011-03-02 05:19:07 +08:00
|
|
|
* ip6_dst_lookup_flow - perform route lookup on flow with ipsec
|
|
|
|
* @sk: socket which provides route info
|
|
|
|
* @fl: flow to lookup
|
|
|
|
* @final_dst: final destination address for ipsec lookup
|
2011-03-02 06:32:04 +08:00
|
|
|
* @can_sleep: we are in a sleepable context
|
2011-03-02 05:19:07 +08:00
|
|
|
*
|
|
|
|
* This function performs a route lookup on the given flow.
|
|
|
|
*
|
|
|
|
* It returns a valid dst pointer on success, or a pointer encoded
|
|
|
|
* error code.
|
|
|
|
*/
|
|
|
|
struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
|
|
|
|
const struct in6_addr *final_dst,
|
2011-03-02 06:32:04 +08:00
|
|
|
bool can_sleep)
|
2011-03-02 05:19:07 +08:00
|
|
|
{
|
|
|
|
struct dst_entry *dst = NULL;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = ip6_dst_lookup_tail(sk, &dst, fl);
|
|
|
|
if (err)
|
|
|
|
return ERR_PTR(err);
|
|
|
|
if (final_dst)
|
|
|
|
ipv6_addr_copy(&fl->fl6_dst, final_dst);
|
2011-03-02 06:59:04 +08:00
|
|
|
if (can_sleep)
|
2011-03-12 13:29:39 +08:00
|
|
|
fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
|
2011-03-02 06:59:04 +08:00
|
|
|
|
2011-03-03 05:27:41 +08:00
|
|
|
return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
|
2011-03-02 05:19:07 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow
|
2006-07-31 11:19:33 +08:00
|
|
|
* @sk: socket which provides the dst cache and route info
|
|
|
|
* @fl: flow to lookup
|
2011-03-02 05:19:07 +08:00
|
|
|
* @final_dst: final destination address for ipsec lookup
|
2011-03-02 06:32:04 +08:00
|
|
|
* @can_sleep: we are in a sleepable context
|
2006-07-31 11:19:33 +08:00
|
|
|
*
|
|
|
|
* This function performs a route lookup on the given flow with the
|
|
|
|
* possibility of using the cached route in the socket if it is valid.
|
|
|
|
* It will take the socket dst lock when operating on the dst cache.
|
|
|
|
* As a result, this function can only be used in process context.
|
|
|
|
*
|
2011-03-02 05:19:07 +08:00
|
|
|
* It returns a valid dst pointer on success, or a pointer encoded
|
|
|
|
* error code.
|
2006-07-31 11:19:33 +08:00
|
|
|
*/
|
2011-03-02 05:19:07 +08:00
|
|
|
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
|
|
|
|
const struct in6_addr *final_dst,
|
2011-03-02 06:32:04 +08:00
|
|
|
bool can_sleep)
|
2006-07-31 11:19:33 +08:00
|
|
|
{
|
2011-03-02 05:19:07 +08:00
|
|
|
struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
|
|
|
|
int err;
|
2006-07-31 11:19:33 +08:00
|
|
|
|
2011-03-02 05:19:07 +08:00
|
|
|
dst = ip6_sk_dst_check(sk, dst, fl);
|
|
|
|
|
|
|
|
err = ip6_dst_lookup_tail(sk, &dst, fl);
|
|
|
|
if (err)
|
|
|
|
return ERR_PTR(err);
|
|
|
|
if (final_dst)
|
|
|
|
ipv6_addr_copy(&fl->fl6_dst, final_dst);
|
2011-03-02 06:59:04 +08:00
|
|
|
if (can_sleep)
|
2011-03-12 13:29:39 +08:00
|
|
|
fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
|
2011-03-02 06:59:04 +08:00
|
|
|
|
2011-03-03 05:27:41 +08:00
|
|
|
return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
|
2006-07-31 11:19:33 +08:00
|
|
|
}
|
2011-03-02 05:19:07 +08:00
|
|
|
EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
|
2006-07-31 11:19:33 +08:00
|
|
|
|
2005-11-30 08:28:56 +08:00
|
|
|
static inline int ip6_ufo_append_data(struct sock *sk,
|
2005-10-19 06:46:41 +08:00
|
|
|
int getfrag(void *from, char *to, int offset, int len,
|
|
|
|
int odd, struct sk_buff *skb),
|
|
|
|
void *from, int length, int hh_len, int fragheaderlen,
|
|
|
|
int transhdrlen, int mtu,unsigned int flags)
|
|
|
|
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
/* There is support for UDP large send offload by network
|
|
|
|
* device, so create one single skb packet containing complete
|
|
|
|
* udp datagram
|
|
|
|
*/
|
|
|
|
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
|
|
|
|
skb = sock_alloc_send_skb(sk,
|
|
|
|
hh_len + fragheaderlen + transhdrlen + 20,
|
|
|
|
(flags & MSG_DONTWAIT), &err);
|
|
|
|
if (skb == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
/* reserve space for Hardware header */
|
|
|
|
skb_reserve(skb, hh_len);
|
|
|
|
|
|
|
|
/* create space for UDP/IP header */
|
|
|
|
skb_put(skb,fragheaderlen + transhdrlen);
|
|
|
|
|
|
|
|
/* initialize network header pointer */
|
2007-04-11 11:45:18 +08:00
|
|
|
skb_reset_network_header(skb);
|
2005-10-19 06:46:41 +08:00
|
|
|
|
|
|
|
/* initialize protocol header pointer */
|
2007-04-11 12:21:55 +08:00
|
|
|
skb->transport_header = skb->network_header + fragheaderlen;
|
2005-10-19 06:46:41 +08:00
|
|
|
|
2006-08-30 07:44:56 +08:00
|
|
|
skb->ip_summed = CHECKSUM_PARTIAL;
|
2005-10-19 06:46:41 +08:00
|
|
|
skb->csum = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = skb_append_datato_frags(sk,skb, getfrag, from,
|
|
|
|
(length - transhdrlen));
|
|
|
|
if (!err) {
|
|
|
|
struct frag_hdr fhdr;
|
|
|
|
|
2009-07-09 16:09:58 +08:00
|
|
|
/* Specify the length of each IPv6 datagram fragment.
|
|
|
|
* It has to be a multiple of 8.
|
|
|
|
*/
|
|
|
|
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
|
|
|
|
sizeof(struct frag_hdr)) & ~7;
|
2006-07-01 04:37:03 +08:00
|
|
|
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
|
2009-07-09 16:10:01 +08:00
|
|
|
ipv6_select_ident(&fhdr);
|
2005-10-19 06:46:41 +08:00
|
|
|
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
|
|
|
|
__skb_queue_tail(&sk->sk_write_queue, skb);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
/* There is not enough support do UPD LSO,
|
|
|
|
* so follow normal path
|
|
|
|
*/
|
|
|
|
kfree_skb(skb);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-02-06 07:15:50 +08:00
|
|
|
static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
|
|
|
|
gfp_t gfp)
|
|
|
|
{
|
|
|
|
return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
|
|
|
|
gfp_t gfp)
|
|
|
|
{
|
|
|
|
return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
|
|
|
|
}
|
|
|
|
|
2005-09-08 09:19:03 +08:00
|
|
|
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
|
|
|
|
int offset, int len, int odd, struct sk_buff *skb),
|
|
|
|
void *from, int length, int transhdrlen,
|
|
|
|
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
|
2010-04-23 19:26:08 +08:00
|
|
|
struct rt6_info *rt, unsigned int flags, int dontfrag)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
|
|
struct ipv6_pinfo *np = inet6_sk(sk);
|
|
|
|
struct sk_buff *skb;
|
|
|
|
unsigned int maxfraglen, fragheaderlen;
|
|
|
|
int exthdrlen;
|
|
|
|
int hh_len;
|
|
|
|
int mtu;
|
|
|
|
int copy;
|
|
|
|
int err;
|
|
|
|
int offset = 0;
|
|
|
|
int csummode = CHECKSUM_NONE;
|
2011-03-01 04:32:11 +08:00
|
|
|
__u8 tx_flags = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if (flags&MSG_PROBE)
|
|
|
|
return 0;
|
|
|
|
if (skb_queue_empty(&sk->sk_write_queue)) {
|
|
|
|
/*
|
|
|
|
* setup for corking
|
|
|
|
*/
|
|
|
|
if (opt) {
|
2009-02-06 07:15:50 +08:00
|
|
|
if (WARN_ON(np->cork.opt))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
2009-02-06 07:15:50 +08:00
|
|
|
|
|
|
|
np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
|
|
|
|
if (unlikely(np->cork.opt == NULL))
|
|
|
|
return -ENOBUFS;
|
|
|
|
|
|
|
|
np->cork.opt->tot_len = opt->tot_len;
|
|
|
|
np->cork.opt->opt_flen = opt->opt_flen;
|
|
|
|
np->cork.opt->opt_nflen = opt->opt_nflen;
|
|
|
|
|
|
|
|
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
|
|
|
|
sk->sk_allocation);
|
|
|
|
if (opt->dst0opt && !np->cork.opt->dst0opt)
|
|
|
|
return -ENOBUFS;
|
|
|
|
|
|
|
|
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
|
|
|
|
sk->sk_allocation);
|
|
|
|
if (opt->dst1opt && !np->cork.opt->dst1opt)
|
|
|
|
return -ENOBUFS;
|
|
|
|
|
|
|
|
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
|
|
|
|
sk->sk_allocation);
|
|
|
|
if (opt->hopopt && !np->cork.opt->hopopt)
|
|
|
|
return -ENOBUFS;
|
|
|
|
|
|
|
|
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
|
|
|
|
sk->sk_allocation);
|
|
|
|
if (opt->srcrt && !np->cork.opt->srcrt)
|
|
|
|
return -ENOBUFS;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* need source address above miyazawa*/
|
|
|
|
}
|
2010-06-11 14:31:35 +08:00
|
|
|
dst_hold(&rt->dst);
|
|
|
|
inet->cork.dst = &rt->dst;
|
2005-04-17 06:20:36 +08:00
|
|
|
inet->cork.fl = *fl;
|
|
|
|
np->cork.hop_limit = hlimit;
|
2005-09-08 09:19:03 +08:00
|
|
|
np->cork.tclass = tclass;
|
2007-04-21 06:53:27 +08:00
|
|
|
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
|
2010-06-11 14:31:35 +08:00
|
|
|
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
|
2006-03-21 14:44:52 +08:00
|
|
|
if (np->frag_size < mtu) {
|
2006-02-25 05:18:33 +08:00
|
|
|
if (np->frag_size)
|
|
|
|
mtu = np->frag_size;
|
|
|
|
}
|
|
|
|
inet->cork.fragsize = mtu;
|
2010-06-11 14:31:35 +08:00
|
|
|
if (dst_allfrag(rt->dst.path))
|
2005-04-17 06:20:36 +08:00
|
|
|
inet->cork.flags |= IPCORK_ALLFRAG;
|
|
|
|
inet->cork.length = 0;
|
|
|
|
sk->sk_sndmsg_page = NULL;
|
|
|
|
sk->sk_sndmsg_off = 0;
|
2010-06-11 14:31:35 +08:00
|
|
|
exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) -
|
2007-12-21 12:41:12 +08:00
|
|
|
rt->rt6i_nfheader_len;
|
2005-04-17 06:20:36 +08:00
|
|
|
length += exthdrlen;
|
|
|
|
transhdrlen += exthdrlen;
|
|
|
|
} else {
|
2008-03-10 16:30:37 +08:00
|
|
|
rt = (struct rt6_info *)inet->cork.dst;
|
2005-04-17 06:20:36 +08:00
|
|
|
fl = &inet->cork.fl;
|
2009-02-06 07:15:50 +08:00
|
|
|
opt = np->cork.opt;
|
2005-04-17 06:20:36 +08:00
|
|
|
transhdrlen = 0;
|
|
|
|
exthdrlen = 0;
|
|
|
|
mtu = inet->cork.fragsize;
|
|
|
|
}
|
|
|
|
|
2010-06-11 14:31:35 +08:00
|
|
|
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-12-21 12:41:12 +08:00
|
|
|
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
|
2007-11-14 13:33:32 +08:00
|
|
|
(opt ? opt->opt_nflen : 0);
|
2005-04-17 06:20:36 +08:00
|
|
|
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
|
|
|
|
|
|
|
|
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
|
|
|
|
if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
|
|
|
|
ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
|
|
|
|
return -EMSGSIZE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-03-01 04:32:11 +08:00
|
|
|
/* For UDP, check if TX timestamp is enabled */
|
|
|
|
if (sk->sk_type == SOCK_DGRAM) {
|
|
|
|
err = sock_tx_timestamp(sk, &tx_flags);
|
|
|
|
if (err)
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Let's try using as much space as possible.
|
|
|
|
* Use MTU if total length of the message fits into the MTU.
|
|
|
|
* Otherwise, we need to reserve fragment header and
|
|
|
|
* fragment alignment (= 8-15 octects, in total).
|
|
|
|
*
|
|
|
|
* Note that we may need to "move" the data from the tail of
|
2007-02-09 22:24:49 +08:00
|
|
|
* of the buffer to the new fragment when we split
|
2005-04-17 06:20:36 +08:00
|
|
|
* the message.
|
|
|
|
*
|
2007-02-09 22:24:49 +08:00
|
|
|
* FIXME: It may be fragmented into multiple chunks
|
2005-04-17 06:20:36 +08:00
|
|
|
* at once if non-fragmentable extension headers
|
|
|
|
* are too large.
|
2007-02-09 22:24:49 +08:00
|
|
|
* --yoshfuji
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
inet->cork.length += length;
|
2010-04-23 19:26:09 +08:00
|
|
|
if (length > mtu) {
|
|
|
|
int proto = sk->sk_protocol;
|
|
|
|
if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
|
|
|
|
ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
|
|
|
|
return -EMSGSIZE;
|
|
|
|
}
|
2005-10-19 06:46:41 +08:00
|
|
|
|
2010-04-23 19:26:09 +08:00
|
|
|
if (proto == IPPROTO_UDP &&
|
2010-06-11 14:31:35 +08:00
|
|
|
(rt->dst.dev->features & NETIF_F_UFO)) {
|
2010-04-23 19:26:09 +08:00
|
|
|
|
|
|
|
err = ip6_ufo_append_data(sk, getfrag, from, length,
|
|
|
|
hh_len, fragheaderlen,
|
|
|
|
transhdrlen, mtu, flags);
|
|
|
|
if (err)
|
|
|
|
goto error;
|
|
|
|
return 0;
|
|
|
|
}
|
2005-10-19 06:46:41 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
|
|
|
|
goto alloc_new_skb;
|
|
|
|
|
|
|
|
while (length > 0) {
|
|
|
|
/* Check if the remaining data fits into current packet. */
|
|
|
|
copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
|
|
|
|
if (copy < length)
|
|
|
|
copy = maxfraglen - skb->len;
|
|
|
|
|
|
|
|
if (copy <= 0) {
|
|
|
|
char *data;
|
|
|
|
unsigned int datalen;
|
|
|
|
unsigned int fraglen;
|
|
|
|
unsigned int fraggap;
|
|
|
|
unsigned int alloclen;
|
|
|
|
struct sk_buff *skb_prev;
|
|
|
|
alloc_new_skb:
|
|
|
|
skb_prev = skb;
|
|
|
|
|
|
|
|
/* There's no room in the current skb */
|
|
|
|
if (skb_prev)
|
|
|
|
fraggap = skb_prev->len - maxfraglen;
|
|
|
|
else
|
|
|
|
fraggap = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If remaining data exceeds the mtu,
|
|
|
|
* we know we need more fragment(s).
|
|
|
|
*/
|
|
|
|
datalen = length + fraggap;
|
|
|
|
if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
|
|
|
|
datalen = maxfraglen - fragheaderlen;
|
|
|
|
|
|
|
|
fraglen = datalen + fragheaderlen;
|
|
|
|
if ((flags & MSG_MORE) &&
|
2010-06-11 14:31:35 +08:00
|
|
|
!(rt->dst.dev->features&NETIF_F_SG))
|
2005-04-17 06:20:36 +08:00
|
|
|
alloclen = mtu;
|
|
|
|
else
|
|
|
|
alloclen = datalen + fragheaderlen;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The last fragment gets additional space at tail.
|
|
|
|
* Note: we overallocate on fragments with MSG_MODE
|
|
|
|
* because we have no idea if we're the last one.
|
|
|
|
*/
|
|
|
|
if (datalen == length + fraggap)
|
2010-06-11 14:31:35 +08:00
|
|
|
alloclen += rt->dst.trailer_len;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We just reserve space for fragment header.
|
2007-02-09 22:24:49 +08:00
|
|
|
* Note: this may be overallocation if the message
|
2005-04-17 06:20:36 +08:00
|
|
|
* (without MSG_MORE) fits into the MTU.
|
|
|
|
*/
|
|
|
|
alloclen += sizeof(struct frag_hdr);
|
|
|
|
|
|
|
|
if (transhdrlen) {
|
|
|
|
skb = sock_alloc_send_skb(sk,
|
|
|
|
alloclen + hh_len,
|
|
|
|
(flags & MSG_DONTWAIT), &err);
|
|
|
|
} else {
|
|
|
|
skb = NULL;
|
|
|
|
if (atomic_read(&sk->sk_wmem_alloc) <=
|
|
|
|
2 * sk->sk_sndbuf)
|
|
|
|
skb = sock_wmalloc(sk,
|
|
|
|
alloclen + hh_len, 1,
|
|
|
|
sk->sk_allocation);
|
|
|
|
if (unlikely(skb == NULL))
|
|
|
|
err = -ENOBUFS;
|
2011-03-01 04:32:11 +08:00
|
|
|
else {
|
|
|
|
/* Only the initial fragment
|
|
|
|
* is time stamped.
|
|
|
|
*/
|
|
|
|
tx_flags = 0;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
if (skb == NULL)
|
|
|
|
goto error;
|
|
|
|
/*
|
|
|
|
* Fill in the control structures
|
|
|
|
*/
|
|
|
|
skb->ip_summed = csummode;
|
|
|
|
skb->csum = 0;
|
|
|
|
/* reserve for fragmentation */
|
|
|
|
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
|
|
|
|
|
2011-03-01 04:32:11 +08:00
|
|
|
if (sk->sk_type == SOCK_DGRAM)
|
|
|
|
skb_shinfo(skb)->tx_flags = tx_flags;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Find where to start putting bytes
|
|
|
|
*/
|
|
|
|
data = skb_put(skb, fraglen);
|
2007-03-12 09:39:41 +08:00
|
|
|
skb_set_network_header(skb, exthdrlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
data += fragheaderlen;
|
2007-04-11 12:21:55 +08:00
|
|
|
skb->transport_header = (skb->network_header +
|
|
|
|
fragheaderlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (fraggap) {
|
|
|
|
skb->csum = skb_copy_and_csum_bits(
|
|
|
|
skb_prev, maxfraglen,
|
|
|
|
data + transhdrlen, fraggap, 0);
|
|
|
|
skb_prev->csum = csum_sub(skb_prev->csum,
|
|
|
|
skb->csum);
|
|
|
|
data += fraggap;
|
2006-08-14 11:12:58 +08:00
|
|
|
pskb_trim_unique(skb_prev, maxfraglen);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
copy = datalen - transhdrlen - fraggap;
|
|
|
|
if (copy < 0) {
|
|
|
|
err = -EINVAL;
|
|
|
|
kfree_skb(skb);
|
|
|
|
goto error;
|
|
|
|
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
|
|
|
|
err = -EFAULT;
|
|
|
|
kfree_skb(skb);
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
|
|
|
|
offset += copy;
|
|
|
|
length -= datalen - fraggap;
|
|
|
|
transhdrlen = 0;
|
|
|
|
exthdrlen = 0;
|
|
|
|
csummode = CHECKSUM_NONE;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Put the packet on the pending queue
|
|
|
|
*/
|
|
|
|
__skb_queue_tail(&sk->sk_write_queue, skb);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (copy > length)
|
|
|
|
copy = length;
|
|
|
|
|
2010-06-11 14:31:35 +08:00
|
|
|
if (!(rt->dst.dev->features&NETIF_F_SG)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned int off;
|
|
|
|
|
|
|
|
off = skb->len;
|
|
|
|
if (getfrag(from, skb_put(skb, copy),
|
|
|
|
offset, copy, off, skb) < 0) {
|
|
|
|
__skb_trim(skb, off);
|
|
|
|
err = -EFAULT;
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
int i = skb_shinfo(skb)->nr_frags;
|
|
|
|
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
|
|
|
|
struct page *page = sk->sk_sndmsg_page;
|
|
|
|
int off = sk->sk_sndmsg_off;
|
|
|
|
unsigned int left;
|
|
|
|
|
|
|
|
if (page && (left = PAGE_SIZE - off) > 0) {
|
|
|
|
if (copy >= left)
|
|
|
|
copy = left;
|
|
|
|
if (page != frag->page) {
|
|
|
|
if (i == MAX_SKB_FRAGS) {
|
|
|
|
err = -EMSGSIZE;
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
get_page(page);
|
|
|
|
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
|
|
|
|
frag = &skb_shinfo(skb)->frags[i];
|
|
|
|
}
|
|
|
|
} else if(i < MAX_SKB_FRAGS) {
|
|
|
|
if (copy > PAGE_SIZE)
|
|
|
|
copy = PAGE_SIZE;
|
|
|
|
page = alloc_pages(sk->sk_allocation, 0);
|
|
|
|
if (page == NULL) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
sk->sk_sndmsg_page = page;
|
|
|
|
sk->sk_sndmsg_off = 0;
|
|
|
|
|
|
|
|
skb_fill_page_desc(skb, i, page, 0, 0);
|
|
|
|
frag = &skb_shinfo(skb)->frags[i];
|
|
|
|
} else {
|
|
|
|
err = -EMSGSIZE;
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
|
|
|
|
err = -EFAULT;
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
sk->sk_sndmsg_off += copy;
|
|
|
|
frag->size += copy;
|
|
|
|
skb->len += copy;
|
|
|
|
skb->data_len += copy;
|
2008-01-23 14:39:26 +08:00
|
|
|
skb->truesize += copy;
|
|
|
|
atomic_add(copy, &sk->sk_wmem_alloc);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
offset += copy;
|
|
|
|
length -= copy;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
error:
|
|
|
|
inet->cork.length -= length;
|
2008-10-09 01:54:51 +08:00
|
|
|
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2007-11-06 13:04:31 +08:00
|
|
|
static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
|
|
|
|
{
|
2009-02-06 07:15:50 +08:00
|
|
|
if (np->cork.opt) {
|
|
|
|
kfree(np->cork.opt->dst0opt);
|
|
|
|
kfree(np->cork.opt->dst1opt);
|
|
|
|
kfree(np->cork.opt->hopopt);
|
|
|
|
kfree(np->cork.opt->srcrt);
|
|
|
|
kfree(np->cork.opt);
|
|
|
|
np->cork.opt = NULL;
|
|
|
|
}
|
|
|
|
|
2008-03-10 16:30:37 +08:00
|
|
|
if (inet->cork.dst) {
|
|
|
|
dst_release(inet->cork.dst);
|
|
|
|
inet->cork.dst = NULL;
|
2007-11-06 13:04:31 +08:00
|
|
|
inet->cork.flags &= ~IPCORK_ALLFRAG;
|
|
|
|
}
|
|
|
|
memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
int ip6_push_pending_frames(struct sock *sk)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb, *tmp_skb;
|
|
|
|
struct sk_buff **tail_skb;
|
|
|
|
struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
|
|
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
|
|
struct ipv6_pinfo *np = inet6_sk(sk);
|
2008-10-09 01:54:51 +08:00
|
|
|
struct net *net = sock_net(sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct ipv6hdr *hdr;
|
|
|
|
struct ipv6_txoptions *opt = np->cork.opt;
|
2008-03-10 16:30:37 +08:00
|
|
|
struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct flowi *fl = &inet->cork.fl;
|
2011-03-12 13:29:39 +08:00
|
|
|
unsigned char proto = fl->flowi_proto;
|
2005-04-17 06:20:36 +08:00
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
|
|
|
|
goto out;
|
|
|
|
tail_skb = &(skb_shinfo(skb)->frag_list);
|
|
|
|
|
|
|
|
/* move skb->data to ip header from ext header */
|
2007-04-11 11:50:43 +08:00
|
|
|
if (skb->data < skb_network_header(skb))
|
2007-03-11 09:16:10 +08:00
|
|
|
__skb_pull(skb, skb_network_offset(skb));
|
2005-04-17 06:20:36 +08:00
|
|
|
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
|
2007-03-17 04:26:39 +08:00
|
|
|
__skb_pull(tmp_skb, skb_network_header_len(skb));
|
2005-04-17 06:20:36 +08:00
|
|
|
*tail_skb = tmp_skb;
|
|
|
|
tail_skb = &(tmp_skb->next);
|
|
|
|
skb->len += tmp_skb->len;
|
|
|
|
skb->data_len += tmp_skb->len;
|
|
|
|
skb->truesize += tmp_skb->truesize;
|
|
|
|
tmp_skb->destructor = NULL;
|
|
|
|
tmp_skb->sk = NULL;
|
|
|
|
}
|
|
|
|
|
2008-02-13 10:07:27 +08:00
|
|
|
/* Allow local fragmentation. */
|
2008-02-15 15:49:37 +08:00
|
|
|
if (np->pmtudisc < IPV6_PMTUDISC_DO)
|
2008-02-13 10:07:27 +08:00
|
|
|
skb->local_df = 1;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
ipv6_addr_copy(final_dst, &fl->fl6_dst);
|
2007-03-17 04:26:39 +08:00
|
|
|
__skb_pull(skb, skb_network_header_len(skb));
|
2005-04-17 06:20:36 +08:00
|
|
|
if (opt && opt->opt_flen)
|
|
|
|
ipv6_push_frag_opts(skb, opt, &proto);
|
|
|
|
if (opt && opt->opt_nflen)
|
|
|
|
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
|
|
|
|
|
2007-04-11 11:46:21 +08:00
|
|
|
skb_push(skb, sizeof(struct ipv6hdr));
|
|
|
|
skb_reset_network_header(skb);
|
2007-04-26 08:54:47 +08:00
|
|
|
hdr = ipv6_hdr(skb);
|
2007-02-09 22:24:49 +08:00
|
|
|
|
2006-11-08 16:25:17 +08:00
|
|
|
*(__be32*)hdr = fl->fl6_flowlabel |
|
2005-09-08 09:19:03 +08:00
|
|
|
htonl(0x60000000 | ((int)np->cork.tclass << 20));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
hdr->hop_limit = np->cork.hop_limit;
|
|
|
|
hdr->nexthdr = proto;
|
|
|
|
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
|
|
|
|
ipv6_addr_copy(&hdr->daddr, final_dst);
|
|
|
|
|
2006-01-09 14:37:26 +08:00
|
|
|
skb->priority = sk->sk_priority;
|
2008-01-31 11:08:16 +08:00
|
|
|
skb->mark = sk->sk_mark;
|
2006-01-09 14:37:26 +08:00
|
|
|
|
2010-06-11 14:31:35 +08:00
|
|
|
skb_dst_set(skb, dst_clone(&rt->dst));
|
2009-04-27 17:45:02 +08:00
|
|
|
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
|
2007-09-17 07:52:35 +08:00
|
|
|
if (proto == IPPROTO_ICMPV6) {
|
2009-06-02 13:19:30 +08:00
|
|
|
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
|
2007-09-17 07:52:35 +08:00
|
|
|
|
2008-10-09 01:34:14 +08:00
|
|
|
ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
|
2008-10-09 01:33:26 +08:00
|
|
|
ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
|
2007-09-17 07:52:35 +08:00
|
|
|
}
|
|
|
|
|
2008-01-12 11:15:08 +08:00
|
|
|
err = ip6_local_out(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (err) {
|
|
|
|
if (err > 0)
|
ip: Report qdisc packet drops
Christoph Lameter pointed out that packet drops at qdisc level where not
accounted in SNMP counters. Only if application sets IP_RECVERR, drops
are reported to user (-ENOBUFS errors) and SNMP counters updated.
IP_RECVERR is used to enable extended reliable error message passing,
but these are not needed to update system wide SNMP stats.
This patch changes things a bit to allow SNMP counters to be updated,
regardless of IP_RECVERR being set or not on the socket.
Example after an UDP tx flood
# netstat -s
...
IP:
1487048 outgoing packets dropped
...
Udp:
...
SndbufErrors: 1487048
send() syscalls, do however still return an OK status, to not
break applications.
Note : send() manual page explicitly says for -ENOBUFS error :
"The output queue for a network interface was full.
This generally indicates that the interface has stopped sending,
but may be caused by transient congestion.
(Normally, this does not occur in Linux. Packets are just silently
dropped when a device queue overflows.) "
This is not true for IP_RECVERR enabled sockets : a send() syscall
that hit a qdisc drop returns an ENOBUFS error.
Many thanks to Christoph, David, and last but not least, Alexey !
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-03 09:05:33 +08:00
|
|
|
err = net_xmit_errno(err);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (err)
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2007-11-06 13:04:31 +08:00
|
|
|
ip6_cork_release(inet, np);
|
2005-04-17 06:20:36 +08:00
|
|
|
return err;
|
|
|
|
error:
|
2009-09-02 09:37:16 +08:00
|
|
|
IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
void ip6_flush_pending_frames(struct sock *sk)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
|
|
|
while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
|
2009-06-02 13:19:30 +08:00
|
|
|
if (skb_dst(skb))
|
|
|
|
IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)),
|
2007-09-11 17:31:43 +08:00
|
|
|
IPSTATS_MIB_OUTDISCARDS);
|
2005-04-17 06:20:36 +08:00
|
|
|
kfree_skb(skb);
|
|
|
|
}
|
|
|
|
|
2007-11-06 13:04:31 +08:00
|
|
|
ip6_cork_release(inet_sk(sk), inet6_sk(sk));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|