linux/net/ipv4/netfilter/ipt_REJECT.c

233 lines
5.9 KiB
C
Raw Normal View History

/*
* This is a module which is used for rejecting packets.
*/
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.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 09:04:11 +01:00
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/route.h>
#include <net/dst.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv4/ipt_REJECT.h>
#ifdef CONFIG_BRIDGE_NETFILTER
#include <linux/netfilter_bridge.h>
#endif
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv4");
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
const struct iphdr *oiph;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _otcph, *tcph;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
return;
oiph = ip_hdr(oldskb);
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
skb_reserve(nskb, LL_MAX_HEADER);
skb_reset_network_header(nskb);
niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
niph->version = 4;
niph->ihl = sizeof(struct iphdr) / 4;
niph->tos = 0;
niph->id = 0;
niph->frag_off = htons(IP_DF);
niph->protocol = IPPROTO_TCP;
niph->check = 0;
niph->saddr = oiph->daddr;
niph->daddr = oiph->saddr;
netfilter: ip[6]t_REJECT: fix wrong transport header pointer in TCP reset The problem occurs when iptables constructs the tcp reset packet. It doesn't initialize the pointer to the tcp header within the skb. When the skb is passed to the ixgbe driver for transmit, the ixgbe driver attempts to access the tcp header and crashes. Currently, other drivers (such as our 1G e1000e or igb drivers) don't access the tcp header on transmit unless the TSO option is turned on. <1>BUG: unable to handle kernel NULL pointer dereference at 0000000d <1>IP: [<d081621c>] ixgbe_xmit_frame_ring+0x8cc/0x2260 [ixgbe] <4>*pdpt = 0000000085e5d001 *pde = 0000000000000000 <0>Oops: 0000 [#1] SMP [...] <4>Pid: 0, comm: swapper Tainted: P 2.6.35.12 #1 Greencity/Thurley <4>EIP: 0060:[<d081621c>] EFLAGS: 00010246 CPU: 16 <4>EIP is at ixgbe_xmit_frame_ring+0x8cc/0x2260 [ixgbe] <4>EAX: c7628820 EBX: 00000007 ECX: 00000000 EDX: 00000000 <4>ESI: 00000008 EDI: c6882180 EBP: dfc6b000 ESP: ced95c48 <4> DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 <0>Process swapper (pid: 0, ti=ced94000 task=ced73bd0 task.ti=ced94000) <0>Stack: <4> cbec7418 c779e0d8 c77cc888 c77cc8a8 0903010a 00000000 c77c0008 00000002 <4><0> cd4997c0 00000010 dfc6b000 00000000 d0d176c9 c77cc8d8 c6882180 cbec7318 <4><0> 00000004 00000004 cbec7230 cbec7110 00000000 cbec70c0 c779e000 00000002 <0>Call Trace: <4> [<d0d176c9>] ? 0xd0d176c9 <4> [<d0d18a4d>] ? 0xd0d18a4d <4> [<411e243e>] ? dev_hard_start_xmit+0x218/0x2d7 <4> [<411f03d7>] ? sch_direct_xmit+0x4b/0x114 <4> [<411f056a>] ? __qdisc_run+0xca/0xe0 <4> [<411e28b0>] ? dev_queue_xmit+0x2d1/0x3d0 <4> [<411e8120>] ? neigh_resolve_output+0x1c5/0x20f <4> [<411e94a1>] ? neigh_update+0x29c/0x330 <4> [<4121cf29>] ? arp_process+0x49c/0x4cd <4> [<411f80c9>] ? nf_hook_slow+0x3f/0xac <4> [<4121ca8d>] ? arp_process+0x0/0x4cd <4> [<4121ca8d>] ? arp_process+0x0/0x4cd <4> [<4121c6d5>] ? T.901+0x38/0x3b <4> [<4121c918>] ? arp_rcv+0xa3/0xb4 <4> [<4121ca8d>] ? arp_process+0x0/0x4cd <4> [<411e1173>] ? __netif_receive_skb+0x32b/0x346 <4> [<411e19e1>] ? netif_receive_skb+0x5a/0x5f <4> [<411e1ea9>] ? napi_skb_finish+0x1b/0x30 <4> [<d0816eb4>] ? ixgbe_xmit_frame_ring+0x1564/0x2260 [ixgbe] <4> [<41013468>] ? lapic_next_event+0x13/0x16 <4> [<410429b2>] ? clockevents_program_event+0xd2/0xe4 <4> [<411e1b03>] ? net_rx_action+0x55/0x127 <4> [<4102da1a>] ? __do_softirq+0x77/0xeb <4> [<4102dab1>] ? do_softirq+0x23/0x27 <4> [<41003a67>] ? do_IRQ+0x7d/0x8e <4> [<41002a69>] ? common_interrupt+0x29/0x30 <4> [<41007bcf>] ? mwait_idle+0x48/0x4d <4> [<4100193b>] ? cpu_idle+0x37/0x4c <0>Code: df 09 d7 0f 94 c2 0f b6 d2 e9 e7 fb ff ff 31 db 31 c0 e9 38 ff ff ff 80 78 06 06 0f 85 3e fb ff ff 8b 7c 24 38 8b 8f b8 00 00 00 <0f> b6 51 0d f6 c2 01 0f 85 27 fb ff ff 80 e2 02 75 0d 8b 6c 24 <0>EIP: [<d081621c>] ixgbe_xmit_frame_ring+0x8cc/0x2260 [ixgbe] SS:ESP Signed-off-by: Mukund Jampala <jbmukund@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2012-12-16 19:25:58 +01:00
skb_reset_transport_header(nskb);
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
memset(tcph, 0, sizeof(*tcph));
tcph->source = oth->dest;
tcph->dest = oth->source;
tcph->doff = sizeof(struct tcphdr) / 4;
if (oth->ack)
tcph->seq = oth->ack_seq;
else {
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
oldskb->len - ip_hdrlen(oldskb) -
(oth->doff << 2));
tcph->ack = 1;
}
tcph->rst = 1;
tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)tcph - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(nskb, RTN_UNSPEC))
goto free_nskb;
niph->ttl = ip4_dst_hoplimit(skb_dst(nskb));
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
#ifdef CONFIG_BRIDGE_NETFILTER
/* If we use ip_local_out for bridged traffic, the MAC source on
* the RST will be ours, instead of the destination's. This confuses
* some routers/firewalls, and they drop the packet. So we need to
* build the eth header using the original destination's MAC as the
* source, and send the RST packet directly.
*/
if (oldskb->nf_bridge) {
struct ethhdr *oeth = eth_hdr(oldskb);
nskb->dev = oldskb->nf_bridge->physindev;
niph->tot_len = htons(nskb->len);
ip_send_check(niph);
if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
oeth->h_source, oeth->h_dest, nskb->len) < 0)
goto free_nskb;
dev_queue_xmit(nskb);
} else
#endif
ip_local_out(nskb);
return;
free_nskb:
kfree_skb(nskb);
}
static inline void send_unreach(struct sk_buff *skb_in, int code)
{
icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
}
static unsigned int
reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_reject_info *reject = par->targinfo;
switch (reject->with) {
case IPT_ICMP_NET_UNREACHABLE:
send_unreach(skb, ICMP_NET_UNREACH);
break;
case IPT_ICMP_HOST_UNREACHABLE:
send_unreach(skb, ICMP_HOST_UNREACH);
break;
case IPT_ICMP_PROT_UNREACHABLE:
send_unreach(skb, ICMP_PROT_UNREACH);
break;
case IPT_ICMP_PORT_UNREACHABLE:
send_unreach(skb, ICMP_PORT_UNREACH);
break;
case IPT_ICMP_NET_PROHIBITED:
send_unreach(skb, ICMP_NET_ANO);
break;
case IPT_ICMP_HOST_PROHIBITED:
send_unreach(skb, ICMP_HOST_ANO);
break;
case IPT_ICMP_ADMIN_PROHIBITED:
send_unreach(skb, ICMP_PKT_FILTERED);
break;
case IPT_TCP_RESET:
send_reset(skb, par->hooknum);
case IPT_ICMP_ECHOREPLY:
/* Doesn't happen. */
break;
}
return NF_DROP;
}
static int reject_tg_check(const struct xt_tgchk_param *par)
{
const struct ipt_reject_info *rejinfo = par->targinfo;
const struct ipt_entry *e = par->entryinfo;
if (rejinfo->with == IPT_ICMP_ECHOREPLY) {
pr_info("ECHOREPLY no longer supported.\n");
return -EINVAL;
} else if (rejinfo->with == IPT_TCP_RESET) {
/* Must specify that it's a TCP packet */
if (e->ip.proto != IPPROTO_TCP ||
(e->ip.invflags & XT_INV_PROTO)) {
pr_info("TCP_RESET invalid for non-tcp\n");
return -EINVAL;
}
}
return 0;
}
static struct xt_target reject_tg_reg __read_mostly = {
.name = "REJECT",
.family = NFPROTO_IPV4,
.target = reject_tg,
.targetsize = sizeof(struct ipt_reject_info),
.table = "filter",
.hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) |
(1 << NF_INET_LOCAL_OUT),
.checkentry = reject_tg_check,
.me = THIS_MODULE,
};
static int __init reject_tg_init(void)
{
return xt_register_target(&reject_tg_reg);
}
static void __exit reject_tg_exit(void)
{
xt_unregister_target(&reject_tg_reg);
}
module_init(reject_tg_init);
module_exit(reject_tg_exit);