When netlink mmap on receive side is the consumer of nf queue data,
it can happen that in some edge cases, we write skb shared info into
the user space mmap buffer:
Assume a possible rx ring frame size of only 4096, and the network skb,
which is being zero-copied into the netlink skb, contains page frags
with an overall skb->len larger than the linear part of the netlink
skb.
skb_zerocopy(), which is generic and thus not aware of the fact that
shared info cannot be accessed for such skbs then tries to write and
fill frags, thus leaking kernel data/pointers and in some corner cases
possibly writing out of bounds of the mmap area (when filling the
last slot in the ring buffer this way).
I.e. the ring buffer slot is then of status NL_MMAP_STATUS_VALID, has
an advertised length larger than 4096, where the linear part is visible
at the slot beginning, and the leaked sizeof(struct skb_shared_info)
has been written to the beginning of the next slot (also corrupting
the struct nl_mmap_hdr slot header incl. status etc), since skb->end
points to skb->data + ring->frame_size - NL_MMAP_HDRLEN.
The fix adds and lets __netlink_alloc_skb() take the actual needed
linear room for the network skb + meta data into account. It's completely
irrelevant for non-mmaped netlink sockets, but in case mmap sockets
are used, it can be decided whether the available skb_tailroom() is
really large enough for the buffer, or whether it needs to internally
fallback to a normal alloc_skb().
>From nf queue side, the information whether the destination port is
an mmap RX ring is not really available without extra port-to-socket
lookup, thus it can only be determined in lower layers i.e. when
__netlink_alloc_skb() is called that checks internally for this. I
chose to add the extra ldiff parameter as mmap will then still work:
We have data_len and hlen in nfqnl_build_packet_message(), data_len
is the full length (capped at queue->copy_range) for skb_zerocopy()
and hlen some possible part of data_len that needs to be copied; the
rem_len variable indicates the needed remaining linear mmap space.
The only other workaround in nf queue internally would be after
allocation time by f.e. cap'ing the data_len to the skb_tailroom()
iff we deal with an mmap skb, but that would 1) expose the fact that
we use a mmap skb to upper layers, and 2) trim the skb where we
otherwise could just have moved the full skb into the normal receive
queue.
After the patch, in my test case the ring slot doesn't fit and therefore
shows NL_MMAP_STATUS_COPY, where a full skb carries all the data and
thus needs to be picked up via recv().
Fixes: 3ab1f683bf ("nfnetlink: add support for memory mapped netlink")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
include/net/netfilter/nf_conntrack.h
The conflict was an overlap between changing the type of the zone
argument to nf_ct_tmpl_alloc() whilst exporting nf_ct_tmpl_free.
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains Netfilter fixes for net, they are:
1) Oneliner to restore maps in nf_tables since we support addressing registers
at 32 bits level.
2) Restore previous default behaviour in bridge netfilter when CONFIG_IPV6=n,
oneliner from Bernhard Thaler.
3) Out of bound access in ipset hash:net* set types, reported by Dave Jones'
KASan utility, patch from Jozsef Kadlecsik.
4) Fix ipset compilation with gcc 4.4.7 related to C99 initialization of
unnamed unions, patch from Elad Raz.
5) Add a workaround to address inconsistent endianess in the res_id field of
nfnetlink batch messages, reported by Florian Westphal.
6) Fix error paths of CT/synproxy since the conntrack template was moved to use
kmalloc, patch from Daniel Borkmann.
All of them look good to me to reach 4.2, I can route this to -stable myself
too, just let me know what you prefer.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Fengguang reported, that some randconfig generated the following linker
issue with nf_ct_zone_dflt object involved:
[...]
CC init/version.o
LD init/built-in.o
net/built-in.o: In function `ipv4_conntrack_defrag':
nf_defrag_ipv4.c:(.text+0x93e95): undefined reference to `nf_ct_zone_dflt'
net/built-in.o: In function `ipv6_defrag':
nf_defrag_ipv6_hooks.c:(.text+0xe3ffe): undefined reference to `nf_ct_zone_dflt'
make: *** [vmlinux] Error 1
Given that configurations exist where we have a built-in part, which is
accessing nf_ct_zone_dflt such as the two handlers nf_ct_defrag_user()
and nf_ct6_defrag_user(), and a part that configures nf_conntrack as a
module, we must move nf_ct_zone_dflt into a fixed, guaranteed built-in
area when netfilter is configured in general.
Therefore, split the more generic parts into a common header under
include/linux/netfilter/ and move nf_ct_zone_dflt into the built-in
section that already holds parts related to CONFIG_NF_CONNTRACK in the
netfilter core. This fixes the issue on my side.
Fixes: 308ac9143e ("netfilter: nf_conntrack: push zone object into functions")
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 0838aa7fcf ("netfilter: fix netns dependencies with conntrack
templates") migrated templates to the new allocator api, but forgot to
update error paths for them in CT and synproxy to use nf_ct_tmpl_free()
instead of nf_conntrack_free().
Due to that, memory is being freed into the wrong kmemcache, but also
we drop the per net reference count of ct objects causing an imbalance.
In Brad's case, this leads to a wrap-around of net->ct.count and thus
lets __nf_conntrack_alloc() refuse to create a new ct object:
[ 10.340913] xt_addrtype: ipv6 does not support BROADCAST matching
[ 10.810168] nf_conntrack: table full, dropping packet
[ 11.917416] r8169 0000:07:00.0 eth0: link up
[ 11.917438] IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
[ 12.815902] nf_conntrack: table full, dropping packet
[ 15.688561] nf_conntrack: table full, dropping packet
[ 15.689365] nf_conntrack: table full, dropping packet
[ 15.690169] nf_conntrack: table full, dropping packet
[ 15.690967] nf_conntrack: table full, dropping packet
[...]
With slab debugging, it also reports the wrong kmemcache (kmalloc-512 vs.
nf_conntrack_ffffffff81ce75c0) and reports poison overwrites, etc. Thus,
to fix the problem, export and use nf_ct_tmpl_free() instead.
Fixes: 0838aa7fcf ("netfilter: fix netns dependencies with conntrack templates")
Reported-by: Brad Jackson <bjackson0971@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter/IPVS updates for your net-next tree.
In sum, patches to address fallout from the previous round plus updates from
the IPVS folks via Simon Horman, they are:
1) Add a new scheduler to IPVS: The weighted overflow scheduling algorithm
directs network connections to the server with the highest weight that is
currently available and overflows to the next when active connections exceed
the node's weight. From Raducu Deaconu.
2) Fix locking ordering in IPVS, always take rtnl_lock in first place. Patch
from Julian Anastasov.
3) Allow to indicate the MTU to the IPVS in-kernel state sync daemon. From
Julian Anastasov.
4) Enhance multicast configuration for the IPVS state sync daemon. Also from
Julian.
5) Resolve sparse warnings in the nf_dup modules.
6) Fix a linking problem when CONFIG_NF_DUP_IPV6 is not set.
7) Add ICMP codes 5 and 6 to IPv6 REJECT target, they are more informative
subsets of code 1. From Andreas Herz.
8) Revert the jumpstack size calculation from mark_source_chains due to chain
depth miscalculations, from Florian Westphal.
9) Calm down more sparse warning around the Netfilter tree, again from Florian
Westphal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The convention in nfnetlink is to use network byte order in every header field
as well as in the attribute payload. The initial version of the batching
infrastructure assumes that res_id comes in host byte order though.
The only client of the batching infrastructure is nf_tables, so let's add a
workaround to address this inconsistency. We currently have 11 nfnetlink
subsystems according to NFNL_SUBSYS_COUNT, so we can assume that the subsystem
2560, ie. htons(10), will not be allocated anytime soon, so it can be an alias
of nf_tables from the nfnetlink batching path when interpreting the res_id
field.
Based on original patch from Florian Westphal.
Reported-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
In continue to proposed Vinson Lee's post [1], this patch fixes compilation
issues founded at gcc 4.4.7. The initialization of .cidr field of unnamed
unions causes compilation error in gcc 4.4.x.
References
Visible links
[1] https://lkml.org/lkml/2015/7/5/74
Signed-off-by: Elad Raz <eladr@mellanox.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
bridge/netfilter/ebtables.c:290:26: warning: incorrect type in assignment (different modifiers)
-> remove __pure annotation.
ipv6/netfilter/ip6t_SYNPROXY.c:240:27: warning: cast from restricted __be16
-> switch ntohs to htons and vice versa.
netfilter/core.c:391:30: warning: symbol 'nfq_ct_nat_hook' was not declared. Should it be static?
-> delete it, got removed
net/netfilter/nf_synproxy_core.c:221:48: warning: cast to restricted __be32
-> Use __be32 instead of u32.
Tested with objdiff that these changes do not affect generated code.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Add functions to change connlabel length into nf_conntrack_labels.c so
they may be reused by other modules like OVS and nftables without
needing to jump through xt_match_check() hoops.
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Florian Westphal <fw@strlen.de>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
The following patches will reuse this code from OVS.
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman says:
====================
Second Round of IPVS Updates for v4.3
I realise these are a little late in the cycle, so if you would prefer
me to repost them for v4.4 then just let me know.
The updates include:
* A new scheduler from Raducu Deaconu
* Enhanced configurability of the sync daemon from Julian Anastasov
====================
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Instead of IS_ENABLED(CONFIG_IPV6), otherwise we hit:
et/built-in.o: In function `tee_tg6':
>> xt_TEE.c:(.text+0x6cd8c): undefined reference to `nf_dup_ipv6'
when:
CONFIG_IPV6=y
CONFIG_NF_DUP_IPV4=y
# CONFIG_NF_DUP_IPV6 is not set
CONFIG_NETFILTER_XT_TARGET_TEE=y
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
- mcast_group: configure the multicast address, now IPv6
is supported too
- mcast_port: configure the multicast port
- mcast_ttl: configure the multicast TTL/HOP_LIMIT
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Allow setups with large MTU to send large sync packets by
adding sync_maxlen parameter. The default value is now based
on MTU but no more than 1500 for compatibility reasons.
To avoid problems if MTU changes allow fragmentation by
sending packets with DF=0. Problem reported by Dan Carpenter.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
When the sync damon is started we need to hold rtnl
lock while calling ip_mc_join_group. Currently, we have
a wrong locking order because the correct one is
rtnl_lock->__ip_vs_mutex. It is implied from the usage
of __ip_vs_mutex in ip_vs_dst_event() which is called
under rtnl lock during NETDEV_* notifications.
Fix the problem by calling rtnl_lock early only for the
start_sync_thread call. As a bonus this fixes the usage
__dev_get_by_name which was not called under rtnl lock.
This patch actually extends and depends on commit 54ff9ef36b
("ipv4, ipv6: kill ip_mc_{join, leave}_group and
ipv6_sock_mc_{join, drop}").
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The weighted overflow scheduling algorithm directs network connections
to the server with the highest weight that is currently available
and overflows to the next when active connections exceed the node's weight.
Signed-off-by: Raducu Deaconu <rhadoo.io88@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
make payload expression aware of the fact that VLAN offload may have
removed a vlan header.
When we encounter tagged skb, transparently insert the tag into the
register so that vlan header matching can work without userspace being
aware of offload features.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
inet_proto_csum_replace4,2,16 take a pseudohdr argument which indicates
the checksum field carries a pseudo header. This argument should be a
boolean instead of an int.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This work adds the possibility of deriving the zone id from the skb->mark
field in a scalable manner. This allows for having only a single template
serving hundreds/thousands of different zones, for example, instead of the
need to have one match for each zone as an extra CT jump target.
Note that we'd need to have this information attached to the template as at
the time when we're trying to lookup a possible ct object, we already need
to know zone information for a possible match when going into
__nf_conntrack_find_get(). This work provides a minimal implementation for
a possible mapping.
In order to not add/expose an extra ct->status bit, the zone structure has
been extended to carry a flag for deriving the mark.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This work adds a direction parameter to netfilter zones, so identity
separation can be performed only in original/reply or both directions
(default). This basically opens up the possibility of doing NAT with
conflicting IP address/port tuples from multiple, isolated tenants
on a host (e.g. from a netns) without requiring each tenant to NAT
twice resp. to use its own dedicated IP address to SNAT to, meaning
overlapping tuples can be made unique with the zone identifier in
original direction, where the NAT engine will then allocate a unique
tuple in the commonly shared default zone for the reply direction.
In some restricted, local DNAT cases, also port redirection could be
used for making the reply traffic unique w/o requiring SNAT.
The consensus we've reached and discussed at NFWS and since the initial
implementation [1] was to directly integrate the direction meta data
into the existing zones infrastructure, as opposed to the ct->mark
approach we proposed initially.
As we pass the nf_conntrack_zone object directly around, we don't have
to touch all call-sites, but only those, that contain equality checks
of zones. Thus, based on the current direction (original or reply),
we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID.
CT expectations are direction-agnostic entities when expectations are
being compared among themselves, so we can only use the identifier
in this case.
Note that zone identifiers can not be included into the hash mix
anymore as they don't contain a "stable" value that would be equal
for both directions at all times, f.e. if only zone->id would
unconditionally be xor'ed into the table slot hash, then replies won't
find the corresponding conntracking entry anymore.
If no particular direction is specified when configuring zones, the
behaviour is exactly as we expect currently (both directions).
Support has been added for the CT netlink interface as well as the
x_tables raw CT target, which both already offer existing interfaces
to user space for the configuration of zones.
Below a minimal, simplified collision example (script in [2]) with
netperf sessions:
+--- tenant-1 ---+ mark := 1
| netperf |--+
+----------------+ | CT zone := mark [ORIGINAL]
[ip,sport] := X +--------------+ +--- gateway ---+
| mark routing |--| SNAT |-- ... +
+--------------+ +---------------+ |
+--- tenant-2 ---+ | ~~~|~~~
| netperf |--+ +-----------+ |
+----------------+ mark := 2 | netserver |------ ... +
[ip,sport] := X +-----------+
[ip,port] := Y
On the gateway netns, example:
iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL
iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully
iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark
iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark
conntrack dump from gateway netns:
netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns
tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=1
src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024
[ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1
tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2
src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555
[ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=1
tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1
src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438
[ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1
tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2
src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889
[ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=2
Taking this further, test script in [2] creates 200 tenants and runs
original-tuple colliding netperf sessions each. A conntrack -L dump in
the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED
state as expected.
I also did run various other tests with some permutations of the script,
to mention some: SNAT in random/random-fully/persistent mode, no zones (no
overlaps), static zones (original, reply, both directions), etc.
[1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/
[2] https://paste.fedoraproject.org/242835/65657871/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Conflicts:
drivers/net/ethernet/cavium/Kconfig
The cavium conflict was overlapping dependency
changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch replaces the zone id which is pushed down into functions
with the actual zone object. It's a bigger one-time change, but
needed for later on extending zones with a direction parameter, and
thus decoupling this additional information from all call-sites.
No functional changes in this patch.
The default zone becomes a global const object, namely nf_ct_zone_dflt
and will be returned directly in various cases, one being, when there's
f.e. no zoning support.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
- Move the nfnl_acct_list into the network namespace, initialize
and destroy it per namespace
- Keep track of refcnt on nfacct objects, the old logic does not
longer work with a per namespace list
- Adjust xt_nfacct to pass the namespace when registring objects
Signed-off-by: Andreas Schultz <aschultz@tpip.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This patch adds a new NFTA_LIMIT_TYPE netlink attribute to indicate the type of
limiting.
Contrary to per-packet limiting, the cost is calculated from the packet path
since this depends on the packet length.
The burst attribute indicates the number of bytes in which the rate can be
exceeded.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The cost per packet can be calculated from the control plane path since this
doesn't ever change.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This patch adds the burst parameter. This burst indicates the number of packets
that can exceed the limit.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Rework the limit expression to use a token-based limiting approach that refills
the bucket gradually. The tokens are calculated at nanosecond granularity
instead jiffies to improve precision.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Extracted from the xtables TEE target. This creates two new modules for IPv4
and IPv6 that are shared between the TEE target and the new nf_tables dup
expressions.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This patch converts the existing seqlock to per-cpu counters.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The flags were ignored for this function when it was introduced. Also
fix the style problem in kzalloc.
Fixes: 0838aa7fc (netfilter: fix netns dependencies with conntrack
templates)
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for net-next, they are:
1) A couple of cleanups for the netfilter core hook from Eric Biederman.
2) Net namespace hook registration, also from Eric. This adds a dependency with
the rtnl_lock. This should be fine by now but we have to keep an eye on this
because if we ever get the per-subsys nfnl_lock before rtnl we have may
problems in the future. But we have room to remove this in the future by
propagating the complexity to the clients, by registering hooks for the init
netns functions.
3) Update nf_tables to use the new net namespace hook infrastructure, also from
Eric.
4) Three patches to refine and to address problems from the new net namespace
hook infrastructure.
5) Switch to alternate jumpstack in xtables iff the packet is reentering. This
only applies to a very special case, the TEE target, but Eric Dumazet
reports that this is slowing down things for everyone else. So let's only
switch to the alternate jumpstack if the tee target is in used through a
static key. This batch also comes with offline precalculation of the
jumpstack based on the callchain depth. From Florian Westphal.
6) Minimal SCTP multihoming support for our conntrack helper, from Michal
Kubecek.
7) Reduce nf_bridge_info per skbuff scratchpad area to 32 bytes, from Florian
Westphal.
8) Fix several checkpatch errors in bridge netfilter, from Bernhard Thaler.
9) Get rid of useless debug message in ip6t_REJECT, from Subash Abhinov.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
arch/s390/net/bpf_jit_comp.c
drivers/net/ethernet/ti/netcp_ethss.c
net/bridge/br_multicast.c
net/ipv4/ip_fragment.c
All four conflicts were cases of simple overlapping
changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
We recently changed this from nf_conntrack_alloc() to nf_ct_tmpl_alloc()
so the error handling needs to changed to check for NULL instead of
IS_ERR().
Fixes: 0838aa7fcf ('netfilter: fix netns dependencies with conntrack templates')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Currently nf_conntrack_proto_sctp module handles only packets between
primary addresses used to establish the connection. Any packets between
secondary addresses are classified as invalid so that usual firewall
configurations drop them. Allowing HEARTBEAT and HEARTBEAT-ACK chunks to
establish a new conntrack would allow traffic between secondary
addresses to pass through. A more sophisticated solution based on the
addresses advertised in the initial handshake (and possibly also later
dynamic address addition and removal) would be much harder to implement.
Moreover, in general we cannot assume to always see the initial
handshake as it can be routed through a different path.
The patch adds two new conntrack states:
SCTP_CONNTRACK_HEARTBEAT_SENT - a HEARTBEAT chunk seen but not acked
SCTP_CONNTRACK_HEARTBEAT_ACKED - a HEARTBEAT acked by HEARTBEAT-ACK
State transition rules:
- HEARTBEAT_SENT responds to usual chunks the same way as NONE (so that
the behaviour changes as little as possible)
- HEARTBEAT_ACKED responds to usual chunks the same way as ESTABLISHED
does, except the resulting state is HEARTBEAT_ACKED rather than
ESTABLISHED
- previously existing states except NONE are preserved when HEARTBEAT or
HEARTBEAT-ACK is seen
- NONE (in the initial direction) changes to HEARTBEAT_SENT on HEARTBEAT
and to CLOSED on HEARTBEAT-ACK
- HEARTBEAT_SENT changes to HEARTBEAT_ACKED on HEARTBEAT-ACK in the
reply direction
- HEARTBEAT_SENT and HEARTBEAT_ACKED are preserved on HEARTBEAT and
HEARTBEAT-ACK otherwise
Normally, vtag is set from the INIT chunk for the reply direction and
from the INIT-ACK chunk for the originating direction (i.e. each of
these defines vtag value for the opposite direction). For secondary
conntracks, we can't rely on seeing INIT/INIT-ACK and even if we have
seen them, we would need to connect two different conntracks. Therefore
simplified logic is applied: vtag of first packet in each direction
(HEARTBEAT in the originating and HEARTBEAT-ACK in reply direction) is
saved and all following packets in that direction are compared with this
saved value. While INIT and INIT-ACK define vtag for the opposite
direction, vtags extracted from HEARTBEAT and HEARTBEAT-ACK are always
for their direction.
Default timeout values for new states are
HEARTBEAT_SENT: 30 seconds (default hb_interval)
HEARTBEAT_ACKED: 210 seconds (hb_interval * path_max_retry + max_rto)
(We cannot expect to see the shutdown sequence so that, unlike
ESTABLISHED, the HEARTBEAT_ACKED timeout shouldn't be too long.)
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Since 88eab472ec ("netfilter: conntrack: adjust nf_conntrack_buckets default
value"), the hashtable can easily hit this warning. We got reports from users
that are getting this message in a quite spamming fashion, so better silence
this.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Florian Westphal <fw@strlen.de>
085db2c045 ("netfilter: Per network namespace netfilter hooks.") introduced a
new nf_hook_list that is global, so let's avoid this overlap.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
nf_unregister_net_hook() uses the nf_hook_ops fields as tuple to look up for
the corresponding hook in the list. However, we may have two hooks with exactly
the same configuration.
This shouldn't be a problem for nftables since every new chain has an unique
priv field set, but this may still cause us problems in the future, so better
address this problem now by keeping a reference to the original nf_hook_ops
structure to make sure we delete the right hook from nf_unregister_net_hook().
Fixes: 085db2c045 ("netfilter: Per network namespace netfilter hooks.")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
When zones were originally introduced, the expectation functions were
all extended to perform lookup using the zone. However, insertion was
not modified to check the zone. This means that two expectations which
are intended to apply for different connections that have the same tuple
but exist in different zones cannot both be tracked.
Fixes: 5d0aa2ccd4 (netfilter: nf_conntrack: add support for "conntrack zones")
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The sk_classid member is only required when CONFIG_CGROUP_NET_CLASSID is
enabled. #ifdefify it to reduce the size of struct sock on 32 bit
systems, at least.
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman says:
====================
IPVS Fixes for v4.2
please consider this fix for v4.2.
For reasons that are not clear to me it is a bumper crop.
It seems to me that they are all relevant to stable.
Please let me know if you need my help to get the fixes into stable.
* ipvs: fix ipv6 route unreach panic
This problem appears to be present since IPv6 support was added to
IPVS in v2.6.28.
* ipvs: skb_orphan in case of forwarding
This appears to resolve a problem resulting from a side effect of
41063e9dd1 ("ipv4: Early TCP socket demux.") which was included in v3.6.
* ipvs: do not use random local source address for tunnels
This appears to resolve a problem introduced by
026ace060d ("ipvs: optimize dst usage for real server") in v3.10.
* ipvs: fix crash if scheduler is changed
This appears to resolve a problem introduced by
ceec4c3816 ("ipvs: convert services to rcu") in v3.10.
Julian has provided backports of the fix:
* [PATCHv2 3.10.81] ipvs: fix crash if scheduler is changed
http://www.spinics.net/lists/lvs-devel/msg04008.html
* [PATCHv2 3.12.44,3.14.45,3.18.16,4.0.6] ipvs: fix crash if scheduler is changed
http://www.spinics.net/lists/lvs-devel/msg04007.html
Please let me know how you would like to handle guiding these
backports into stable.
* ipvs: fix crash with sync protocol v0 and FTP
This appears to resolve a problem introduced by
749c42b620 ("ipvs: reduce sync rate with time thresholds") in v3.5
====================
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Quoting Daniel Borkmann:
"When adding connection tracking template rules to a netns, f.e. to
configure netfilter zones, the kernel will endlessly busy-loop as soon
as we try to delete the given netns in case there's at least one
template present, which is problematic i.e. if there is such bravery that
the priviledged user inside the netns is assumed untrusted.
Minimal example:
ip netns add foo
ip netns exec foo iptables -t raw -A PREROUTING -d 1.2.3.4 -j CT --zone 1
ip netns del foo
What happens is that when nf_ct_iterate_cleanup() is being called from
nf_conntrack_cleanup_net_list() for a provided netns, we always end up
with a net->ct.count > 0 and thus jump back to i_see_dead_people. We
don't get a soft-lockup as we still have a schedule() point, but the
serving CPU spins on 100% from that point onwards.
Since templates are normally allocated with nf_conntrack_alloc(), we
also bump net->ct.count. The issue why they are not yet nf_ct_put() is
because the per netns .exit() handler from x_tables (which would eventually
invoke xt_CT's xt_ct_tg_destroy() that drops reference on info->ct) is
called in the dependency chain at a *later* point in time than the per
netns .exit() handler for the connection tracker.
This is clearly a chicken'n'egg problem: after the connection tracker
.exit() handler, we've teared down all the connection tracking
infrastructure already, so rightfully, xt_ct_tg_destroy() cannot be
invoked at a later point in time during the netns cleanup, as that would
lead to a use-after-free. At the same time, we cannot make x_tables depend
on the connection tracker module, so that the xt_ct_tg_destroy() would
be invoked earlier in the cleanup chain."
Daniel confirms this has to do with the order in which modules are loaded or
having compiled nf_conntrack as modules while x_tables built-in. So we have no
guarantees regarding the order in which netns callbacks are executed.
Fix this by allocating the templates through kmalloc() from the respective
SYNPROXY and CT targets, so they don't depend on the conntrack kmem cache.
Then, release then via nf_ct_tmpl_free() from destroy_conntrack(). This branch
is marked as unlikely since conntrack templates are rarely allocated and only
from the configuration plane path.
Note that templates are not kept in any list to avoid further dependencies with
nf_conntrack anymore, thus, the tmpl larval list is removed.
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
In the rare case that when it is a attempted to use a per network device
netfilter hook and the network device does not exist the newly allocated
structure can leak.
Be a good citizen and free the newly allocated structure in the error
handling code.
Fixes: 085db2c045 ("netfilter: Per network namespace netfilter hooks.")
Reported-by: kbuild@01.org
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Don't bother testing if we need to switch to alternate stack
unless TEE target is used.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
In most cases there is no reentrancy into ip/ip6tables.
For skbs sent by REJECT or SYNPROXY targets, there is one level
of reentrancy, but its not relevant as those targets issue an absolute
verdict, i.e. the jumpstack can be clobbered since its not used
after the target issues absolute verdict (ACCEPT, DROP, STOLEN, etc).
So the only special case where it is relevant is the TEE target, which
returns XT_CONTINUE.
This patch changes ip(6)_do_table to always use the jump stack starting
from 0.
When we detect we're operating on an skb sent via TEE (percpu
nf_skb_duplicated is 1) we switch to an alternate stack to leave
the original one alone.
Since there is no TEE support for arptables, it doesn't need to
test if tee is active.
The jump stack overflow tests are no longer needed as well --
since ->stacksize is the largest call depth we cannot exceed it.
A much better alternative to the external jumpstack would be to just
declare a jumps[32] stack on the local stack frame, but that would mean
we'd have to reject iptables rulesets that used to work before.
Another alternative would be to start rejecting rulesets with a larger
call depth, e.g. 1000 -- in this case it would be feasible to allocate the
entire stack in the percpu area which would avoid one dereference.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Daniel Borkmann