1
0
Fork 0
remarkable-linux/net/netfilter/nf_nat_proto_common.c

118 lines
3.2 KiB
C
Raw Permalink Normal View History

/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2008 Patrick McHardy <kaber@trash.net>
*
* 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.
*/
#include <linux/types.h>
#include <linux/random.h>
#include <linux/netfilter.h>
#include <linux/export.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
#include <net/netfilter/nf_nat_l4proto.h>
bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype,
const union nf_conntrack_man_proto *min,
const union nf_conntrack_man_proto *max)
{
__be16 port;
if (maniptype == NF_NAT_MANIP_SRC)
port = tuple->src.u.all;
else
port = tuple->dst.u.all;
return ntohs(port) >= ntohs(min->all) &&
ntohs(port) <= ntohs(max->all);
}
EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range);
void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
u16 *rover)
{
netfilter: nat: cope with negative port range commit db57ccf0f2f4624b4c4758379f8165277504fbd7 upstream. syzbot reported a division by 0 bug in the netfilter nat code: divide error: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 4168 Comm: syzkaller034710 Not tainted 4.16.0-rc1+ #309 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:nf_nat_l4proto_unique_tuple+0x291/0x530 net/netfilter/nf_nat_proto_common.c:88 RSP: 0018:ffff8801b2466778 EFLAGS: 00010246 RAX: 000000000000f153 RBX: ffff8801b2466dd8 RCX: ffff8801b2466c7c RDX: 0000000000000000 RSI: ffff8801b2466c58 RDI: ffff8801db5293ac RBP: ffff8801b24667d8 R08: ffff8801b8ba6dc0 R09: ffffffff88af5900 R10: ffff8801b24666f0 R11: 0000000000000000 R12: 000000002990f153 R13: 0000000000000001 R14: 0000000000000000 R15: ffff8801b2466c7c FS: 00000000017e3880(0000) GS:ffff8801db500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000208fdfe4 CR3: 00000001b5340002 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: dccp_unique_tuple+0x40/0x50 net/netfilter/nf_nat_proto_dccp.c:30 get_unique_tuple+0xc28/0x1c10 net/netfilter/nf_nat_core.c:362 nf_nat_setup_info+0x1c2/0xe00 net/netfilter/nf_nat_core.c:406 nf_nat_redirect_ipv6+0x306/0x730 net/netfilter/nf_nat_redirect.c:124 redirect_tg6+0x7f/0xb0 net/netfilter/xt_REDIRECT.c:34 ip6t_do_table+0xc2a/0x1a30 net/ipv6/netfilter/ip6_tables.c:365 ip6table_nat_do_chain+0x65/0x80 net/ipv6/netfilter/ip6table_nat.c:41 nf_nat_ipv6_fn+0x594/0xa80 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c:302 nf_nat_ipv6_local_fn+0x33/0x5d0 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c:407 ip6table_nat_local_fn+0x2c/0x40 net/ipv6/netfilter/ip6table_nat.c:69 nf_hook_entry_hookfn include/linux/netfilter.h:120 [inline] nf_hook_slow+0xba/0x1a0 net/netfilter/core.c:483 nf_hook include/linux/netfilter.h:243 [inline] NF_HOOK include/linux/netfilter.h:286 [inline] ip6_xmit+0x10ec/0x2260 net/ipv6/ip6_output.c:277 inet6_csk_xmit+0x2fc/0x580 net/ipv6/inet6_connection_sock.c:139 dccp_transmit_skb+0x9ac/0x10f0 net/dccp/output.c:142 dccp_connect+0x369/0x670 net/dccp/output.c:564 dccp_v6_connect+0xe17/0x1bf0 net/dccp/ipv6.c:946 __inet_stream_connect+0x2d4/0xf00 net/ipv4/af_inet.c:620 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:684 SYSC_connect+0x213/0x4a0 net/socket.c:1639 SyS_connect+0x24/0x30 net/socket.c:1620 do_syscall_64+0x282/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x26/0x9b RIP: 0033:0x441c69 RSP: 002b:00007ffe50cc0be8 EFLAGS: 00000217 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 0000000000441c69 RDX: 000000000000001c RSI: 00000000208fdfe4 RDI: 0000000000000003 RBP: 00000000006cc018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000538 R11: 0000000000000217 R12: 0000000000403590 R13: 0000000000403620 R14: 0000000000000000 R15: 0000000000000000 Code: 48 89 f0 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 46 02 00 00 48 8b 45 c8 44 0f b7 20 e8 88 97 04 fd 31 d2 41 0f b7 c4 4c 89 f9 <41> f7 f6 48 c1 e9 03 48 b8 00 00 00 00 00 fc ff df 0f b6 0c 01 RIP: nf_nat_l4proto_unique_tuple+0x291/0x530 net/netfilter/nf_nat_proto_common.c:88 RSP: ffff8801b2466778 The problem is that currently we don't have any check on the configured port range. A port range == -1 triggers the bug, while other negative values may require a very long time to complete the following loop. This commit addresses the issue swapping the two ends on negative ranges. The check is performed in nf_nat_l4proto_unique_tuple() since the nft nat loads the port values from nft registers at runtime. v1 -> v2: use the correct 'Fixes' tag v2 -> v3: update commit message, drop unneeded READ_ONCE() Fixes: 5b1158e909ec ("[NETFILTER]: Add NAT support for nf_conntrack") Reported-by: syzbot+8012e198bd037f4871e5@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-14 09:21:19 -07:00
unsigned int range_size, min, max, i;
__be16 *portptr;
u_int16_t off;
if (maniptype == NF_NAT_MANIP_SRC)
portptr = &tuple->src.u.all;
else
portptr = &tuple->dst.u.all;
/* If no range specified... */
if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
/* If it's dst rewrite, can't change port */
if (maniptype == NF_NAT_MANIP_DST)
return;
if (ntohs(*portptr) < 1024) {
/* Loose convention: >> 512 is credential passing */
if (ntohs(*portptr) < 512) {
min = 1;
range_size = 511 - min + 1;
} else {
min = 600;
range_size = 1023 - min + 1;
}
} else {
min = 1024;
range_size = 65535 - 1024 + 1;
}
} else {
min = ntohs(range->min_proto.all);
netfilter: nat: cope with negative port range commit db57ccf0f2f4624b4c4758379f8165277504fbd7 upstream. syzbot reported a division by 0 bug in the netfilter nat code: divide error: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 4168 Comm: syzkaller034710 Not tainted 4.16.0-rc1+ #309 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:nf_nat_l4proto_unique_tuple+0x291/0x530 net/netfilter/nf_nat_proto_common.c:88 RSP: 0018:ffff8801b2466778 EFLAGS: 00010246 RAX: 000000000000f153 RBX: ffff8801b2466dd8 RCX: ffff8801b2466c7c RDX: 0000000000000000 RSI: ffff8801b2466c58 RDI: ffff8801db5293ac RBP: ffff8801b24667d8 R08: ffff8801b8ba6dc0 R09: ffffffff88af5900 R10: ffff8801b24666f0 R11: 0000000000000000 R12: 000000002990f153 R13: 0000000000000001 R14: 0000000000000000 R15: ffff8801b2466c7c FS: 00000000017e3880(0000) GS:ffff8801db500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000208fdfe4 CR3: 00000001b5340002 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: dccp_unique_tuple+0x40/0x50 net/netfilter/nf_nat_proto_dccp.c:30 get_unique_tuple+0xc28/0x1c10 net/netfilter/nf_nat_core.c:362 nf_nat_setup_info+0x1c2/0xe00 net/netfilter/nf_nat_core.c:406 nf_nat_redirect_ipv6+0x306/0x730 net/netfilter/nf_nat_redirect.c:124 redirect_tg6+0x7f/0xb0 net/netfilter/xt_REDIRECT.c:34 ip6t_do_table+0xc2a/0x1a30 net/ipv6/netfilter/ip6_tables.c:365 ip6table_nat_do_chain+0x65/0x80 net/ipv6/netfilter/ip6table_nat.c:41 nf_nat_ipv6_fn+0x594/0xa80 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c:302 nf_nat_ipv6_local_fn+0x33/0x5d0 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c:407 ip6table_nat_local_fn+0x2c/0x40 net/ipv6/netfilter/ip6table_nat.c:69 nf_hook_entry_hookfn include/linux/netfilter.h:120 [inline] nf_hook_slow+0xba/0x1a0 net/netfilter/core.c:483 nf_hook include/linux/netfilter.h:243 [inline] NF_HOOK include/linux/netfilter.h:286 [inline] ip6_xmit+0x10ec/0x2260 net/ipv6/ip6_output.c:277 inet6_csk_xmit+0x2fc/0x580 net/ipv6/inet6_connection_sock.c:139 dccp_transmit_skb+0x9ac/0x10f0 net/dccp/output.c:142 dccp_connect+0x369/0x670 net/dccp/output.c:564 dccp_v6_connect+0xe17/0x1bf0 net/dccp/ipv6.c:946 __inet_stream_connect+0x2d4/0xf00 net/ipv4/af_inet.c:620 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:684 SYSC_connect+0x213/0x4a0 net/socket.c:1639 SyS_connect+0x24/0x30 net/socket.c:1620 do_syscall_64+0x282/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x26/0x9b RIP: 0033:0x441c69 RSP: 002b:00007ffe50cc0be8 EFLAGS: 00000217 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 0000000000441c69 RDX: 000000000000001c RSI: 00000000208fdfe4 RDI: 0000000000000003 RBP: 00000000006cc018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000538 R11: 0000000000000217 R12: 0000000000403590 R13: 0000000000403620 R14: 0000000000000000 R15: 0000000000000000 Code: 48 89 f0 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 46 02 00 00 48 8b 45 c8 44 0f b7 20 e8 88 97 04 fd 31 d2 41 0f b7 c4 4c 89 f9 <41> f7 f6 48 c1 e9 03 48 b8 00 00 00 00 00 fc ff df 0f b6 0c 01 RIP: nf_nat_l4proto_unique_tuple+0x291/0x530 net/netfilter/nf_nat_proto_common.c:88 RSP: ffff8801b2466778 The problem is that currently we don't have any check on the configured port range. A port range == -1 triggers the bug, while other negative values may require a very long time to complete the following loop. This commit addresses the issue swapping the two ends on negative ranges. The check is performed in nf_nat_l4proto_unique_tuple() since the nft nat loads the port values from nft registers at runtime. v1 -> v2: use the correct 'Fixes' tag v2 -> v3: update commit message, drop unneeded READ_ONCE() Fixes: 5b1158e909ec ("[NETFILTER]: Add NAT support for nf_conntrack") Reported-by: syzbot+8012e198bd037f4871e5@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-14 09:21:19 -07:00
max = ntohs(range->max_proto.all);
if (unlikely(max < min))
swap(max, min);
range_size = max - min + 1;
}
netfilter: nf_nat: add full port randomization support We currently use prandom_u32() for allocation of ports in tcp bind(0) and udp code. In case of plain SNAT we try to keep the ports as is or increment on collision. SNAT --random mode does use per-destination incrementing port allocation. As a recent paper pointed out in [1] that this mode of port allocation makes it possible to an attacker to find the randomly allocated ports through a timing side-channel in a socket overloading attack conducted through an off-path attacker. So, NF_NAT_RANGE_PROTO_RANDOM actually weakens the port randomization in regard to the attack described in this paper. As we need to keep compatibility, add another flag called NF_NAT_RANGE_PROTO_RANDOM_FULLY that would replace the NF_NAT_RANGE_PROTO_RANDOM hash-based port selection algorithm with a simple prandom_u32() in order to mitigate this attack vector. Note that the lfsr113's internal state is periodically reseeded by the kernel through a local secure entropy source. More details can be found in [1], the basic idea is to send bursts of packets to a socket to overflow its receive queue and measure the latency to detect a possible retransmit when the port is found. Because of increasing ports to given destination and port, further allocations can be predicted. This information could then be used by an attacker for e.g. for cache-poisoning, NS pinning, and degradation of service attacks against DNS servers [1]: The best defense against the poisoning attacks is to properly deploy and validate DNSSEC; DNSSEC provides security not only against off-path attacker but even against MitM attacker. We hope that our results will help motivate administrators to adopt DNSSEC. However, full DNSSEC deployment make take significant time, and until that happens, we recommend short-term, non-cryptographic defenses. We recommend to support full port randomisation, according to practices recommended in [2], and to avoid per-destination sequential port allocation, which we show may be vulnerable to derandomisation attacks. Joint work between Hannes Frederic Sowa and Daniel Borkmann. [1] https://sites.google.com/site/hayashulman/files/NIC-derandomisation.pdf [2] http://arxiv.org/pdf/1205.5190v1.pdf Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-12-20 14:40:29 -07:00
if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) {
off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC
? tuple->dst.u.all
: tuple->src.u.all);
netfilter: nf_nat: add full port randomization support We currently use prandom_u32() for allocation of ports in tcp bind(0) and udp code. In case of plain SNAT we try to keep the ports as is or increment on collision. SNAT --random mode does use per-destination incrementing port allocation. As a recent paper pointed out in [1] that this mode of port allocation makes it possible to an attacker to find the randomly allocated ports through a timing side-channel in a socket overloading attack conducted through an off-path attacker. So, NF_NAT_RANGE_PROTO_RANDOM actually weakens the port randomization in regard to the attack described in this paper. As we need to keep compatibility, add another flag called NF_NAT_RANGE_PROTO_RANDOM_FULLY that would replace the NF_NAT_RANGE_PROTO_RANDOM hash-based port selection algorithm with a simple prandom_u32() in order to mitigate this attack vector. Note that the lfsr113's internal state is periodically reseeded by the kernel through a local secure entropy source. More details can be found in [1], the basic idea is to send bursts of packets to a socket to overflow its receive queue and measure the latency to detect a possible retransmit when the port is found. Because of increasing ports to given destination and port, further allocations can be predicted. This information could then be used by an attacker for e.g. for cache-poisoning, NS pinning, and degradation of service attacks against DNS servers [1]: The best defense against the poisoning attacks is to properly deploy and validate DNSSEC; DNSSEC provides security not only against off-path attacker but even against MitM attacker. We hope that our results will help motivate administrators to adopt DNSSEC. However, full DNSSEC deployment make take significant time, and until that happens, we recommend short-term, non-cryptographic defenses. We recommend to support full port randomisation, according to practices recommended in [2], and to avoid per-destination sequential port allocation, which we show may be vulnerable to derandomisation attacks. Joint work between Hannes Frederic Sowa and Daniel Borkmann. [1] https://sites.google.com/site/hayashulman/files/NIC-derandomisation.pdf [2] http://arxiv.org/pdf/1205.5190v1.pdf Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-12-20 14:40:29 -07:00
} else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) {
off = prandom_u32();
} else {
off = *rover;
netfilter: nf_nat: add full port randomization support We currently use prandom_u32() for allocation of ports in tcp bind(0) and udp code. In case of plain SNAT we try to keep the ports as is or increment on collision. SNAT --random mode does use per-destination incrementing port allocation. As a recent paper pointed out in [1] that this mode of port allocation makes it possible to an attacker to find the randomly allocated ports through a timing side-channel in a socket overloading attack conducted through an off-path attacker. So, NF_NAT_RANGE_PROTO_RANDOM actually weakens the port randomization in regard to the attack described in this paper. As we need to keep compatibility, add another flag called NF_NAT_RANGE_PROTO_RANDOM_FULLY that would replace the NF_NAT_RANGE_PROTO_RANDOM hash-based port selection algorithm with a simple prandom_u32() in order to mitigate this attack vector. Note that the lfsr113's internal state is periodically reseeded by the kernel through a local secure entropy source. More details can be found in [1], the basic idea is to send bursts of packets to a socket to overflow its receive queue and measure the latency to detect a possible retransmit when the port is found. Because of increasing ports to given destination and port, further allocations can be predicted. This information could then be used by an attacker for e.g. for cache-poisoning, NS pinning, and degradation of service attacks against DNS servers [1]: The best defense against the poisoning attacks is to properly deploy and validate DNSSEC; DNSSEC provides security not only against off-path attacker but even against MitM attacker. We hope that our results will help motivate administrators to adopt DNSSEC. However, full DNSSEC deployment make take significant time, and until that happens, we recommend short-term, non-cryptographic defenses. We recommend to support full port randomisation, according to practices recommended in [2], and to avoid per-destination sequential port allocation, which we show may be vulnerable to derandomisation attacks. Joint work between Hannes Frederic Sowa and Daniel Borkmann. [1] https://sites.google.com/site/hayashulman/files/NIC-derandomisation.pdf [2] http://arxiv.org/pdf/1205.5190v1.pdf Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-12-20 14:40:29 -07:00
}
for (i = 0; ; ++off) {
*portptr = htons(min + off % range_size);
if (++i != range_size && nf_nat_used_tuple(tuple, ct))
continue;
netfilter: nf_nat: add full port randomization support We currently use prandom_u32() for allocation of ports in tcp bind(0) and udp code. In case of plain SNAT we try to keep the ports as is or increment on collision. SNAT --random mode does use per-destination incrementing port allocation. As a recent paper pointed out in [1] that this mode of port allocation makes it possible to an attacker to find the randomly allocated ports through a timing side-channel in a socket overloading attack conducted through an off-path attacker. So, NF_NAT_RANGE_PROTO_RANDOM actually weakens the port randomization in regard to the attack described in this paper. As we need to keep compatibility, add another flag called NF_NAT_RANGE_PROTO_RANDOM_FULLY that would replace the NF_NAT_RANGE_PROTO_RANDOM hash-based port selection algorithm with a simple prandom_u32() in order to mitigate this attack vector. Note that the lfsr113's internal state is periodically reseeded by the kernel through a local secure entropy source. More details can be found in [1], the basic idea is to send bursts of packets to a socket to overflow its receive queue and measure the latency to detect a possible retransmit when the port is found. Because of increasing ports to given destination and port, further allocations can be predicted. This information could then be used by an attacker for e.g. for cache-poisoning, NS pinning, and degradation of service attacks against DNS servers [1]: The best defense against the poisoning attacks is to properly deploy and validate DNSSEC; DNSSEC provides security not only against off-path attacker but even against MitM attacker. We hope that our results will help motivate administrators to adopt DNSSEC. However, full DNSSEC deployment make take significant time, and until that happens, we recommend short-term, non-cryptographic defenses. We recommend to support full port randomisation, according to practices recommended in [2], and to avoid per-destination sequential port allocation, which we show may be vulnerable to derandomisation attacks. Joint work between Hannes Frederic Sowa and Daniel Borkmann. [1] https://sites.google.com/site/hayashulman/files/NIC-derandomisation.pdf [2] http://arxiv.org/pdf/1205.5190v1.pdf Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-12-20 14:40:29 -07:00
if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL))
*rover = off;
return;
}
}
EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple);
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
struct nf_nat_range *range)
{
if (tb[CTA_PROTONAT_PORT_MIN]) {
range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]);
range->max_proto.all = range->min_proto.all;
range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
if (tb[CTA_PROTONAT_PORT_MAX]) {
range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]);
range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
return 0;
}
EXPORT_SYMBOL_GPL(nf_nat_l4proto_nlattr_to_range);
#endif