Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for your net-next
tree. Basically, updates to the conntrack core, enhancements for
nf_tables, conversion of netfilter hooks from linked list to array to
improve memory locality and asorted improvements for the Netfilter
codebase. More specifically, they are:
1) Add expection to hashes after timer initialization to prevent
access from another CPU that walks on the hashes and calls
del_timer(), from Florian Westphal.
2) Don't update nf_tables chain counters from hot path, this is only
used by the x_tables compatibility layer.
3) Get rid of nested rcu_read_lock() calls from netfilter hook path.
Hooks are always guaranteed to run from rcu read side, so remove
nested rcu_read_lock() where possible. Patch from Taehee Yoo.
4) nf_tables new ruleset generation notifications include PID and name
of the process that has updated the ruleset, from Phil Sutter.
5) Use skb_header_pointer() from nft_fib, so we can reuse this code from
the nf_family netdev family. Patch from Pablo M. Bermudo.
6) Add support for nft_fib in nf_tables netdev family, also from Pablo.
7) Use deferrable workqueue for conntrack garbage collection, to reduce
power consumption, from Patch from Subash Abhinov Kasiviswanathan.
8) Add nf_ct_expect_iterate_net() helper and use it. From Florian
Westphal.
9) Call nf_ct_unconfirmed_destroy only from cttimeout, from Florian.
10) Drop references on conntrack removal path when skbuffs has escaped via
nfqueue, from Florian.
11) Don't queue packets to nfqueue with dying conntrack, from Florian.
12) Constify nf_hook_ops structure, from Florian.
13) Remove neededlessly branch in nf_tables trace code, from Phil Sutter.
14) Add nla_strdup(), from Phil Sutter.
15) Rise nf_tables objects name size up to 255 chars, people want to use
DNS names, so increase this according to what RFC 1035 specifies.
Patch series from Phil Sutter.
16) Kill nf_conntrack_default_on, it's broken. Default on conntrack hook
registration on demand, suggested by Eric Dumazet, patch from Florian.
17) Remove unused variables in compat_copy_entry_from_user both in
ip_tables and arp_tables code. Patch from Taehee Yoo.
18) Constify struct nf_conntrack_l4proto, from Julia Lawall.
19) Constify nf_loginfo structure, also from Julia.
20) Use a single rb root in connlimit, from Taehee Yoo.
21) Remove unused netfilter_queue_init() prototype, from Taehee Yoo.
22) Use audit_log() instead of open-coding it, from Geliang Tang.
23) Allow to mangle tcp options via nft_exthdr, from Florian.
24) Allow to fetch TCP MSS from nft_rt, from Florian. This includes
a fix for a miscalculation of the minimal length.
25) Simplify branch logic in h323 helper, from Nick Desaulniers.
26) Calculate netlink attribute size for conntrack tuple at compile
time, from Florian.
27) Remove protocol name field from nf_conntrack_{l3,l4}proto structure.
From Florian.
28) Remove holes in nf_conntrack_l4proto structure, so it becomes
smaller. From Florian.
29) Get rid of print_tuple() indirection for /proc conntrack listing.
Place all the code in net/netfilter/nf_conntrack_standalone.c.
Patch from Florian.
30) Do not built in print_conntrack() if CONFIG_NF_CONNTRACK_PROCFS is
off. From Florian.
31) Constify most nf_conntrack_{l3,l4}proto helper functions, from
Florian.
32) Fix broken indentation in ebtables extensions, from Colin Ian King.
33) Fix several harmless sparse warning, from Florian.
34) Convert netfilter hook infrastructure to use array for better memory
locality, joint work done by Florian and Aaron Conole. Moreover, add
some instrumentation to debug this.
35) Batch nf_unregister_net_hooks() calls, to call synchronize_net once
per batch, from Florian.
36) Get rid of noisy logging in ICMPv6 conntrack helper, from Florian.
37) Get rid of obsolete NFDEBUG() instrumentation, from Varsha Rao.
38) Remove unused code in the generic protocol tracker, from Davide
Caratti.
I think I will have material for a second Netfilter batch in my queue if
time allow to make it fit in this merge window.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a second device index, sdif, to inet6 socket lookups. sdif is the
index for ingress devices enslaved to an l3mdev. It allows the lookups
to consider the enslaved device as well as the L3 domain when searching
for a socket.
TCP moves the data in the cb. Prior to tcp_v4_rcv (e.g., early demux) the
ingress index is obtained from IPCB using inet_sdif and after tcp_v4_rcv
tcp_v4_sdif is used.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a second device index, sdif, to inet socket lookups. sdif is the
index for ingress devices enslaved to an l3mdev. It allows the lookups
to consider the enslaved device as well as the L3 domain when searching
for a socket.
TCP moves the data in the cb. Prior to tcp_v4_rcv (e.g., early demux) the
ingress index is obtained from IPCB using inet_sdif and after the cb move
in tcp_v4_rcv the tcp_v4_sdif helper is used.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes duplicate rcu_read_lock().
1. IPVS part:
According to Julian Anastasov's mention, contexts of ipvs are described
at: http://marc.info/?l=netfilter-devel&m=149562884514072&w=2, in summary:
- packet RX/TX: does not need locks because packets come from hooks.
- sync msg RX: backup server uses RCU locks while registering new
connections.
- ip_vs_ctl.c: configuration get/set, RCU locks needed.
- xt_ipvs.c: It is a netfilter match, running from hook context.
As result, rcu_read_lock and rcu_read_unlock can be removed from:
- ip_vs_core.c: all
- ip_vs_ctl.c:
- only from ip_vs_has_real_service
- ip_vs_ftp.c: all
- ip_vs_proto_sctp.c: all
- ip_vs_proto_tcp.c: all
- ip_vs_proto_udp.c: all
- ip_vs_xmit.c: all (contains only packet processing)
2. Netfilter part:
There are three types of functions that are guaranteed the rcu_read_lock().
First, as result, functions are only called by nf_hook():
- nf_conntrack_broadcast_help(), pptp_expectfn(), set_expected_rtp_rtcp().
- tcpmss_reverse_mtu(), tproxy_laddr4(), tproxy_laddr6().
- match_lookup_rt6(), check_hlist(), hashlimit_mt_common().
- xt_osf_match_packet().
Second, functions that caller already held the rcu_read_lock().
- destroy_conntrack(), ctnetlink_conntrack_event().
- ctnl_timeout_find_get(), nfqnl_nf_hook_drop().
Third, functions that are mixed with type1 and type2.
These functions are called by nf_hook() also these are called by
ordinary functions that already held the rcu_read_lock():
- __ctnetlink_glue_build(), ctnetlink_expect_event().
- ctnetlink_proto_size().
Applied files are below:
- nf_conntrack_broadcast.c, nf_conntrack_core.c, nf_conntrack_netlink.c.
- nf_conntrack_pptp.c, nf_conntrack_sip.c, nfnetlink_cttimeout.c.
- nfnetlink_queue.c, xt_TCPMSS.c, xt_TPROXY.c, xt_addrtype.c.
- xt_connlimit.c, xt_hashlimit.c, xt_osf.c
Detailed calltrace can be found at:
http://marc.info/?l=netfilter-devel&m=149667610710350&w=2
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
This patch uses refcount_inc_not_zero() instead of
atomic_inc_not_zero_hint() due to absense of a _hint()
version of refcount API. If the hint() version must
be used, we might need to revisit API.
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet6_dev->addr_list is protected by inet6_dev->lock, so only using
rcu_read_lock is not enough, we should acquire read_lock_bh(&idev->lock)
before the inet6_dev->addr_list traversal.
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
nf_defrag modules for ipv4 and ipv6 export an empty stub function.
Any module that needs the defragmentation hooks registered simply 'calls'
this empty function to create a phony module dependency -- modprobe will
then load the defrag module too.
This extends netfilter ipv4/ipv6 defragmentation modules to delay the hook
registration until the functionality is requested within a network namespace
instead of module load time for all namespaces.
Hooks are only un-registered on module unload or when a namespace that used
such defrag functionality exits.
We have to use struct net for this as the register hooks can be called
before netns initialization here from the ipv4/ipv6 conntrack module
init path.
There is no unregister functionality support, defrag will always be
active once it was requested inside a net namespace.
The reason is that defrag has impact on nft and iptables rulesets
(without defrag we might see framents).
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Place pointer to hook state in xt_action_param structure instead of
copying the fields that we need. After this change xt_action_param fits
into one cacheline.
This patch also adds a set of new wrapper functions to fetch relevant
hook state structure fields.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
inet_lookup_listener() and inet6_lookup_listener() no longer
take a reference on the found listener.
This minimal patch adds back the refcounting, but we might do
this differently in net-next later.
Fixes: 3b24d854cb ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Reported-and-tested-by: Denys Fedoryshchenko <nuclearcat@nuclearcat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This is a preliminary step to allow fast socket lookup of SO_REUSEPORT
groups. Doing so with a BPF filter will require access to the
skb in question. This change plumbs the skb (and offset to payload
data) through the call stack to the listening socket lookup
implementations where it will be used in a following patch.
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet_twsk_deschedule() calls are followed by inet_twsk_put().
Only particular case is in inet_twsk_purge() but there is no point
to defer the inet_twsk_put() after re-enabling BH.
Lets rename inet_twsk_deschedule() to inet_twsk_deschedule_put()
and move the inet_twsk_put() inside.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using a timer wheel for timewait sockets was nice ~15 years ago when
memory was expensive and machines had a single processor.
This does not scale, code is ugly and source of huge latencies
(Typically 30 ms have been seen, cpus spinning on death_lock spinlock.)
We can afford to use an extra 64 bytes per timewait sock and spread
timewait load to all cpus to have better behavior.
Tested:
On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1
on the target (lpaa24)
Before patch :
lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
419594
lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
437171
While test is running, we can observe 25 or even 33 ms latencies.
lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms
rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2
lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms
rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2
After patch :
About 90% increase of throughput :
lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
810442
lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
800992
And latencies are kept to minimal values during this load, even
if network utilization is 90% higher :
lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms
rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/netfilter/nf_tables_core.c
The nf_tables_core.c conflict was resolved using a conflict resolution
from Stephen Rothwell as a guide.
Signed-off-by: David S. Miller <davem@davemloft.net>
We have to check for IP6T_INV_PROTO in invflags, instead of flags.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Balazs Scheidler <bazsi@balabit.hu>
TCP request socks soon will be visible in ehash table.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We've removed nf_tproxy_core.ko, so also remove its header.
The lookup helpers are split and then moved to tproxy target/socket match.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The module was "permanent", due to the special tproxy skb->destructor.
Nowadays we have tcp early demux and its sock_edemux destructor in
networking core which can be used instead.
Thanks to early demux changes the input path now also handles
"skb->sk is tw socket" correctly, so this no longer needs the special
handling introduced with commit d503b30bd6
(netfilter: tproxy: do not assign timewait sockets to skb->sk).
Thus:
- move assign_sock function to where its needed
- don't prevent timewait sockets from being assigned to the skb
- remove nf_tproxy_core.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Fix incorrect start markers, wrapped summary lines, missing section
breaks, incorrect separators, and some name mismatches.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the flags parameter to ipv6_find_hdr. This flags
allows us to:
* know if this is a fragment.
* stop at the AH header, so the information contained in that header
can be used for some specific packet handling.
This patch also adds the offset parameter for inspection of one
inner IPv6 header that is contained in error messages.
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Use IS_ENABLED(CONFIG_FOO)
instead of defined(CONFIG_FOO) || defined (CONFIG_FOO_MODULE)
Signed-off-by: Igor Maravić <igorm@etf.rs>
Signed-off-by: David S. Miller <davem@davemloft.net>
Assigning a socket in timewait state to skb->sk can trigger
kernel oops, e.g. in nfnetlink_log, which does:
if (skb->sk) {
read_lock_bh(&skb->sk->sk_callback_lock);
if (skb->sk->sk_socket && skb->sk->sk_socket->file) ...
in the timewait case, accessing sk->sk_callback_lock and sk->sk_socket
is invalid.
Either all of these spots will need to add a test for sk->sk_state != TCP_TIME_WAIT,
or xt_TPROXY must not assign a timewait socket to skb->sk.
This does the latter.
If a TW socket is found, assign the tproxy nfmark, but skip the skb->sk assignment,
thus mimicking behaviour of a '-m socket .. -j MARK/ACCEPT' re-routing rule.
The 'SYN to TW socket' case is left unchanged -- we try to redirect to the
listener socket.
Cc: Balazs Scheidler <bazsi@balabit.hu>
Cc: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
One of the previous tproxy related patches split IPv6 defragmentation and
connection tracking, but did not correctly add Kconfig stanzas to handle the
new dependencies correctly. This patch fixes that by making the config options
mirror the setup we have for IPv4: a distinct config option for defragmentation
that is automatically selected by both connection tracking and
xt_TPROXY/xt_socket.
The patch also changes the #ifdefs enclosing IPv6 specific code in xt_socket
and xt_TPROXY: we only compile these in case we have ip6tables support enabled.
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
The REDIRECT target and the older TProxy versions used the primary address
of the incoming interface as the default value of the --on-ip parameter.
This was unintentionally changed during the initial TProxy submission and
caused confusion among users.
Since IPv6 has no notion of primary address, we just select the first address
on the list: this way the socket lookup finds wildcard bound sockets
properly and we cannot really do better without the user telling us the
IPv6 address of the proxy.
This is implemented for both IPv4 and IPv6.
Signed-off-by: Balazs Scheidler <bazsi@balabit.hu>
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This requires a new revision as the old target structure was
IPv4 specific.
Signed-off-by: Balazs Scheidler <bazsi@balabit.hu>
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Without tproxy redirections an incoming SYN kicks out conflicting
TIME_WAIT sockets, in order to handle clients that reuse ports
within the TIME_WAIT period.
The same mechanism didn't work in case TProxy is involved in finding
the proper socket, as the time_wait processing code looked up the
listening socket assuming that the listener addr/port matches those
of the established connection.
This is not the case with TProxy as the listener addr/port is possibly
changed with the tproxy rule.
Signed-off-by: Balazs Scheidler <bazsi@balabit.hu>
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
The field family of xt_target should be NFPROTO_IPV4, though
NFPROTO_IPV4 and AF_INET are the same.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
According to the Documentation/CodingStyle, the length of lines should
be within 80.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Restore function signatures from bool to int so that we can report
memory allocation failures or similar using -ENOMEM rather than
always having to pass -EINVAL back.
// <smpl>
@@
type bool;
identifier check, par;
@@
-bool check
+int check
(struct xt_tgchk_param *par) { ... }
// </smpl>
Minus the change it does to xt_ct_find_proto.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Supplement to 1159683ef4.
Downgrade the log level to INFO for most checkentry messages as they
are, IMO, just an extra information to the -EINVAL code that is
returned as part of a parameter "constraint violation". Leave errors
to real errors, such as being unable to create a LED trigger.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
This patch does this for target extensions' checkentry functions.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This patch does this for target extensions' target functions.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
The TPROXY target implements redirection of non-local TCP/UDP traffic to local
sockets. Additionally, it's possible to manipulate the packet mark if and only
if a socket has been found. (We need this because we cannot use multiple
targets in the same iptables rule.)
Signed-off-by: KOVACS Krisztian <hidden@sch.bme.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
David S. Miller