nft_set_elem_destroy() can be called from call_rcu context. Annotate
netns and table in set object so we can populate the context object.
Moreover, pass context object to nf_tables_set_elem_destroy() from the
commit phase, since it is already available from there.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This patch provides an interface to maintain the list of connections and
the lookup function to obtain the number of connections in the list.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The extracted functions will likely be usefull to implement tproxy
support in nf_tables.
Extrancted functions:
- nf_tproxy_sk_is_transparent
- nf_tproxy_laddr4
- nf_tproxy_handle_time_wait4
- nf_tproxy_get_sock_v4
- nf_tproxy_laddr6
- nf_tproxy_handle_time_wait6
- nf_tproxy_get_sock_v6
(nf_)tproxy_handle_time_wait6 also needed some refactor as its current
implementation was xtables-specific.
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
There is a function in include/net/netfilter/nf_socket.h to decide if a
socket has IP(V6)_TRANSPARENT socket option set or not. However this
does the same as inet_sk_transparent() in include/net/tcp.h
include/net/tcp.h:1733
/* This helper checks if socket has IP_TRANSPARENT set */
static inline bool inet_sk_transparent(const struct sock *sk)
{
switch (sk->sk_state) {
case TCP_TIME_WAIT:
return inet_twsk(sk)->tw_transparent;
case TCP_NEW_SYN_RECV:
return inet_rsk(inet_reqsk(sk))->no_srccheck;
}
return inet_sk(sk)->transparent;
}
tproxy_sk_is_transparent has also been refactored to use this function
instead of reimplementing it.
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Add support for FTP commands with extended format (RFC 2428):
- FTP EPRT: IPv4 and IPv6, active mode, similar to PORT
- FTP EPSV: IPv4 and IPv6, passive mode, similar to PASV.
EPSV response usually contains only port but we allow real
server to provide different address
We restrict control and data connection to be from same
address family.
Allow the "(" and ")" to be optional in PASV response.
Also, add ipvsh argument to the pkt_in/pkt_out handlers to better
access the payload after transport header.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Prepare NFCT to support IPv6 for FTP:
- Do not restrict the expectation callback to PF_INET
- Split the debug messages, so that the 160-byte limitation
in IP_VS_DBG_BUF is not exceeded when printing many IPv6
addresses. This means no more than 3 addresses in one message,
i.e. 1 tuple with 2 addresses or 1 connection with 3 addresses.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This allows us to forward packets from the netdev family via neighbour
layer, so you don't need an explicit link-layer destination when using
this expression from rules. The ttl/hop_limit field is decremented.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
In the quest to remove all stack VLA usage from the kernel[1], this
allocates the maximum size expected for all possible attrs and adds
sanity-checks at both registration and usage to make sure nothing
gets out of sync.
[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Some drivers, such as vxlan and wireguard, use the skb's dst in order to
determine things like PMTU. They therefore loose functionality when flow
offloading is enabled. So, we ensure the skb has it before xmit'ing it
in the offloading path.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The following ruleset:
add table ip filter
add chain ip filter input { type filter hook input priority 4; }
add chain ip filter ap
add rule ip filter input jump ap
add rule ip filter ap masquerade
results in a panic, because the masquerade extension should be rejected
from the filter chain. The existing validation is missing a chain
dependency check when the rule is added to the non-base chain.
This patch fixes the problem by walking down the rules from the
basechains, searching for either immediate or lookup expressions, then
jumping to non-base chains and again walking down the rules to perform
the expression validation, so we make sure the full ruleset graph is
validated. This is done only once from the commit phase, in case of
problem, we abort the transaction and perform fine grain validation for
error reporting. This patch requires 003087911a ("netfilter:
nfnetlink: allow commit to fail") to achieve this behaviour.
This patch also adds a cleanup callback to nfnl batch interface to reset
the validate state from the exit path.
As a result of this patch, nf_tables_check_loops() doesn't use
->validate to check for loops, instead it just checks for immediate
expressions.
Reported-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This extends log statement to support the behaviour achieved with
AUDIT target in iptables.
Audit logging is enabled via a pseudo log level 8. In this case any
other settings like log prefix are ignored since audit log format is
fixed.
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Now it can only match the transparent flag of an ip/ipv6 socket.
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
net/netfilter/nft_numgen.c:117:1-3: WARNING: PTR_ERR_OR_ZERO can be used
net/netfilter/nft_hash.c:180:1-3: WARNING: PTR_ERR_OR_ZERO can be used
net/netfilter/nft_hash.c:223:1-3: WARNING: PTR_ERR_OR_ZERO can be used
Use PTR_ERR_OR_ZERO rather than if(IS_ERR(...)) + PTR_ERR
Generated by: scripts/coccinelle/api/ptr_ret.cocci
Fixes: b9ccc07e3f ("netfilter: nft_hash: add map lookups for hashing operations")
Fixes: d734a28889 ("netfilter: nft_numgen: add map lookups for numgen statements")
CC: Laura Garcia Liebana <nevola@gmail.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Acked-by: Laura Garcia Liebana <nevola@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The comment and trace_loginfo are not used anymore.
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
We can make all dumps and lookups lockless.
Dumps currently only hold the nfnl mutex on the dump request itself.
Dumps can span multiple syscalls, dump continuation doesn't acquire the
nfnl mutex anywhere, i.e. the dump callbacks in nf_tables already use
rcu and never rely on nfnl mutex being held.
So, just switch all dumpers to rcu.
This requires taking a module reference before dropping the rcu lock
so rmmod is blocked, we also need to hold module reference over
the entire dump operation sequence. netlink already supports this
via the .module member in the netlink_dump_control struct.
For the non-dump case (i.e. lookup of a specific tables, chains, etc),
we need to swtich to _rcu list iteration primitive and make sure we
use GFP_ATOMIC.
This patch also adds the new nft_netlink_dump_start_rcu() helper that
takes care of the get_ref, drop-rcu-lock,start dump,
get-rcu-lock,put-ref sequence.
The helper will be reused for all dumps.
Rationale in all dump requests is:
- use the nft_netlink_dump_start_rcu helper added in first patch
- use GFP_ATOMIC and rcu list iteration
- switch to .call_rcu
... thus making all dumps in nf_tables not depend on the
nfnl mutex anymore.
In the nf_tables_getgen: This callback just fetches the current base
sequence, there is no need to serialize this with nfnl nft mutex.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
abort batch processing and return so task can exit faster.
Otherwise even SIGKILL has no immediate effect.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
harmless, but it avoids sparse warnings:
nf_tables_api.c:2813:16: warning: incorrect type in return expression (different base types)
nf_tables_api.c:2863:47: warning: incorrect type in argument 3 (different base types)
nf_tables_api.c:3524:47: warning: incorrect type in argument 3 (different base types)
nf_tables_api.c:3538:55: warning: incorrect type in argument 3 (different base types)
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Just use .call_rcu instead. We can drop the rcu read lock
after obtaining a reference and re-acquire on return.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Fixes the following sparse warning:
net/netfilter/nf_nat_core.c:1039:20: warning:
symbol 'nat_hook' was not declared. Should it be static?
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
synchronize_rcu() is expensive.
The commit phase currently enforces an unconditional
synchronize_rcu() after incrementing the generation counter.
This is to make sure that a packet always sees a consistent chain, either
nft_do_chain is still using old generation (it will skip the newly added
rules), or the new one (it will skip old ones that might still be linked
into the list).
We could just remove the synchronize_rcu(), it would not cause a crash but
it could cause us to evaluate a rule that was removed and new rule for the
same packet, instead of either-or.
To resolve this, add rule pointer array holding two generations, the
current one and the future generation.
In commit phase, allocate the rule blob and populate it with the rules that
will be active in the new generation.
Then, make this rule blob public, replacing the old generation pointer.
Then the generation counter can be incremented.
nft_do_chain() will either continue to use the current generation
(in case loop was invoked right before increment), or the new one.
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
->commit() cannot fail at the moment.
Followup-patch adds kmalloc calls in the commit phase, so we'll need
to be able to handle errors.
Make it so that -EGAIN causes a full replay, and make other errors
cause the transaction to fail.
Failing is ok from a consistency point of view as long as we
perform all actions that could return an error before
we increment the generation counter and the base seq.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Similar to previous patch, this time, merge redirect+nat.
The redirect module is just 2k in size, get rid of it and make
redirect part available from the nat core.
before:
text data bss dec hex filename
19461 1484 4138 25083 61fb net/netfilter/nf_nat.ko
1236 792 0 2028 7ec net/netfilter/nf_nat_redirect.ko
after:
20340 1508 4138 25986 6582 net/netfilter/nf_nat.ko
Signed-off-by: Florian Westphal <fw@strlen.de>
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 your net-next
tree, they are:
1) Remove obsolete nf_log tracing from nf_tables, from Florian Westphal.
2) Add support for map lookups to numgen, random and hash expressions,
from Laura Garcia.
3) Allow to register nat hooks for iptables and nftables at the same
time. Patchset from Florian Westpha.
4) Timeout support for rbtree sets.
5) ip6_rpfilter works needs interface for link-local addresses, from
Vincent Bernat.
6) Add nf_ct_hook and nf_nat_hook structures and use them.
7) Do not drop packets on packets raceing to insert conntrack entries
into hashes, this is particularly a problem in nfqueue setups.
8) Address fallout from xt_osf separation to nf_osf, patches
from Florian Westphal and Fernando Mancera.
9) Remove reference to struct nft_af_info, which doesn't exist anymore.
From Taehee Yoo.
This batch comes with is a conflict between 25fd386e0b ("netfilter:
core: add missing __rcu annotation") in your tree and 2c205dd398
("netfilter: add struct nf_nat_hook and use it") coming in this batch.
This conflict can be solved by leaving the __rcu tag on
__netfilter_net_init() - added by 25fd386e0b - and remove all code
related to nf_nat_decode_session_hook - which is gone after
2c205dd398, as described by:
diff --cc net/netfilter/core.c
index e0ae4aae96f5,206fb2c4c319..168af54db975
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@@ -611,7 -580,13 +611,8 @@@ const struct nf_conntrack_zone nf_ct_zo
EXPORT_SYMBOL_GPL(nf_ct_zone_dflt);
#endif /* CONFIG_NF_CONNTRACK */
- static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max)
-#ifdef CONFIG_NF_NAT_NEEDED
-void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
-EXPORT_SYMBOL(nf_nat_decode_session_hook);
-#endif
-
+ static void __net_init
+ __netfilter_net_init(struct nf_hook_entries __rcu **e, int max)
{
int h;
I can also merge your net-next tree into nf-next, solve the conflict and
resend the pull request if you prefer so.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In nfqueue, two consecutive skbuffs may race to create the conntrack
entry. Hence, the one that loses the race gets dropped due to clash in
the insertion into the hashes from the nf_conntrack_confirm() path.
This patch adds a new nf_conntrack_update() function which searches for
possible clashes and resolve them. NAT mangling for the packet losing
race is corrected by using the conntrack information that won race.
In order to avoid direct module dependencies with conntrack and NAT, the
nf_ct_hook and nf_nat_hook structures are used for this purpose.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This reverts commit f92b40a8b2
("netfilter: core: only allow one nat hook per hook point"), this
limitation is no longer needed. The nat core now invokes these
functions and makes sure that hook evaluation stops after a mapping is
created and a null binding is created otherwise.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Currently the packet rewrite and instantiation of nat NULL bindings
happens from the protocol specific nat backend.
Invocation occurs either via ip(6)table_nat or the nf_tables nat chain type.
Invocation looks like this (simplified):
NF_HOOK()
|
`---iptable_nat
|
`---> nf_nat_l3proto_ipv4 -> nf_nat_packet
|
new packet? pass skb though iptables nat chain
|
`---> iptable_nat: ipt_do_table
In nft case, this looks the same (nft_chain_nat_ipv4 instead of
iptable_nat).
This is a problem for two reasons:
1. Can't use iptables nat and nf_tables nat at the same time,
as the first user adds a nat binding (nf_nat_l3proto_ipv4 adds a
NULL binding if do_table() did not find a matching nat rule so we
can detect post-nat tuple collisions).
2. If you use e.g. nft_masq, snat, redir, etc. uses must also register
an empty base chain so that the nat core gets called fro NF_HOOK()
to do the reverse translation, which is neither obvious nor user
friendly.
After this change, the base hook gets registered not from iptable_nat or
nftables nat hooks, but from the l3 nat core.
iptables/nft nat base hooks get registered with the nat core instead:
NF_HOOK()
|
`---> nf_nat_l3proto_ipv4 -> nf_nat_packet
|
new packet? pass skb through iptables/nftables nat chains
|
+-> iptables_nat: ipt_do_table
+-> nft nat chain x
`-> nft nat chain y
The nat core deals with null bindings and reverse translation.
When no mapping exists, it calls the registered nat lookup hooks until
one creates a new mapping.
If both iptables and nftables nat hooks exist, the first matching
one is used (i.e., higher priority wins).
Also, nft users do not need to create empty nat hooks anymore,
nat core always registers the base hooks that take care of reverse/reply
translation.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This adds the infrastructure to register nat hooks with the nat core
instead of the netfilter core.
nat hooks are used to configure nat bindings. Such hooks are registered
from ip(6)table_nat or by the nftables core when a nat chain is added.
After next patch, nat hooks will be registered with nf_nat instead of
netfilter core. This allows to use many nat lookup functions at the
same time while doing the real packet rewrite (nat transformation) in
one place.
This change doesn't convert the intended users yet to ease review.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This will allow the nat core to reuse the nf_hook infrastructure
to maintain nat lookup functions.
The raw versions don't assume a particular hook location, the
functions get added/deleted from the hook blob that is passed to the
functions.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Will be used in followup patch when nat types no longer
use nf_register_net_hook() but will instead register with the nat core.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Copy-pasted, both l3 helpers almost use same code here.
Split out the common part into an 'inet' helper.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
S390 bpf_jit.S is removed in net-next and had changes in 'net',
since that code isn't used any more take the removal.
TLS data structures split the TX and RX components in 'net-next',
put the new struct members from the bug fix in 'net' into the RX
part.
The 'net-next' tree had some reworking of how the ERSPAN code works in
the GRE tunneling code, overlapping with a one-line headroom
calculation fix in 'net'.
Overlapping changes in __sock_map_ctx_update_elem(), keep the bits
that read the prog members via READ_ONCE() into local variables
before using them.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch creates new attributes to accept a map as argument and
then perform the lookup with the generated hash accordingly.
Both current hash functions are supported: Jenkins and Symmetric Hash.
Signed-off-by: Laura Garcia Liebana <nevola@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This patch uses the map lookup already included to be applied
for random number generation.
Signed-off-by: Laura Garcia Liebana <nevola@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
nfnetlink tracing is available since nft 0.6 (June 2016).
Remove old nf_log based tracing to avoid rule counter in main loop.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Currently the -EBUSY error return path is not free'ing resources
allocated earlier, leaving a memory leak. Fix this by exiting via the
error exit label err5 that performs the necessary resource clean
up.
Detected by CoverityScan, CID#1432975 ("Resource leak")
Fixes: 9744a6fcef ("netfilter: nf_tables: check if same extensions are set when adding elements")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
When removing a rule that jumps to chain and such chain in the same
batch, this bogusly hits EBUSY. Add activate and deactivate operations
to expression that can be called from the preparation and the
commit/abort phases.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
currently matchinfo gets stored in the expression, but some xt matches
are very large.
To handle those we either need to switch nft core to kvmalloc and increase
size limit, or allocate the info blob of large matches separately.
This does the latter, this limits the scope of the changes to
nft_compat.
I picked a threshold of 192, this allows most matches to work as before and
handle only few ones via separate alloation (cgroup, u32, sctp, rt).
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Next patch will make it possible for *info to be stored in
a separate allocation instead of the expr private area.
This removes the 'expr priv area is info blob' assumption
from the match init/destroy/eval functions.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
nft_chain_stats_replace() and all other spots assume ->stats can be
NULL, but nft_update_chain_stats does not. It must do this check,
just because the jump label is set doesn't mean all basechains have stats
assigned.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
fixes these warnings:
'nfnl_cthelper_create' at net/netfilter/nfnetlink_cthelper.c:237:2,
'nfnl_cthelper_new' at net/netfilter/nfnetlink_cthelper.c:450:9:
./include/linux/string.h:246:9: warning: '__builtin_strncpy' specified bound 16 equals destination size [-Wstringop-truncation]
return __builtin_strncpy(p, q, size);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Moreover, strncpy assumes null-terminated source buffers, but thats
not the case here.
Unlike strlcpy, nla_strlcpy *does* pad the destination buffer
while also considering nla attribute size.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Local clients are not properly synchronized on 32-bit CPUs when
updating stats (3.10+). Now it is possible estimation_timer (timer),
a stats reader, to interrupt the local client in the middle of
write_seqcount_{begin,end} sequence leading to loop (DEADLOCK).
The same interrupt can happen from received packet (SoftIRQ)
which updates the same per-CPU stats.
Fix it by disabling BH while updating stats.
Found with debug:
WARNING: inconsistent lock state
4.17.0-rc2-00105-g35cb6d7-dirty #2 Not tainted
--------------------------------
inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
ftp/2545 [HC0[0]:SC0[0]:HE1:SE1] takes:
86845479 (&syncp->seq#6){+.+-}, at: ip_vs_schedule+0x1c5/0x59e [ip_vs]
{IN-SOFTIRQ-R} state was registered at:
lock_acquire+0x44/0x5b
estimation_timer+0x1b3/0x341 [ip_vs]
call_timer_fn+0x54/0xcd
run_timer_softirq+0x10c/0x12b
__do_softirq+0xc1/0x1a9
do_softirq_own_stack+0x1d/0x23
irq_exit+0x4a/0x64
smp_apic_timer_interrupt+0x63/0x71
apic_timer_interrupt+0x3a/0x40
default_idle+0xa/0xc
arch_cpu_idle+0x9/0xb
default_idle_call+0x21/0x23
do_idle+0xa0/0x167
cpu_startup_entry+0x19/0x1b
start_secondary+0x133/0x182
startup_32_smp+0x164/0x168
irq event stamp: 42213
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&syncp->seq#6);
<Interrupt>
lock(&syncp->seq#6);
*** DEADLOCK ***
Fixes: ac69269a45 ("ipvs: do not disable bh for long time")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Taehee Yoo reported following bug:
iptables-compat -I OUTPUT -m cpu --cpu 0
iptables-compat -F
lsmod |grep xt_cpu
xt_cpu 16384 1
Quote:
"When above command is given, a netlink message has two expressions that
are the cpu compat and the nft_counter.
The nft_expr_type_get() in the nf_tables_expr_parse() successes
first expression then, calls select_ops callback.
(allocates memory and holds module)
But, second nft_expr_type_get() in the nf_tables_expr_parse()
returns -EAGAIN because of request_module().
In that point, by the 'goto err1',
the 'module_put(info[i].ops->type->owner)' is called.
There is no release routine."
The core problem is that unlike all other expression,
nft_compat select_ops has side effects.
1. it allocates dynamic memory which holds an nft ops struct.
In all other expressions, ops has static storage duration.
2. It grabs references to the xt module that it is supposed to
invoke.
Depending on where things go wrong, error unwinding doesn't
always do the right thing.
In the above scenario, a new nft_compat_expr is created and
xt_cpu module gets loaded with a refcount of 1.
Due to to -EAGAIN, the netlink messages get re-parsed.
When that happens, nft_compat finds that xt_cpu is already present
and increments module refcount again.
This fixes the problem by making select_ops to have no visible
side effects and removes all extra module_get/put.
When select_ops creates a new nft_compat expression, the new
expression has a refcount of 0, and the xt module gets its refcount
incremented.
When error happens, the next call finds existing entry, but will no
longer increase the reference count -- the presence of existing
nft_xt means we already hold a module reference.
Because nft_xt_put is only called from nft_compat destroy hook,
it will never see the initial zero reference count.
->destroy can only be called after ->init(), and that will increase the
refcount.
Lastly, we now free nft_xt struct with kfree_rcu.
Else, we get use-after free in nf_tables_rule_destroy:
while (expr != nft_expr_last(rule) && expr->ops) {
nf_tables_expr_destroy(ctx, expr);
expr = nft_expr_next(expr); // here
nft_expr_next() dereferences expr->ops. This is safe
for all users, as ops have static storage duration.
In nft_compat case however, its ->destroy callback can
free the memory that hold the ops structure.
Tested-by: Taehee Yoo <ap420073@gmail.com>
Reported-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Pablo Neira Ayuso says:
====================
Netfilter/IPVS updates for net-next
The following patchset contains Netfilter/IPVS updates for your net-next
tree, more relevant updates in this batch are:
1) Add Maglev support to IPVS. Moreover, store lastest server weight in
IPVS since this is needed by maglev, patches from from Inju Song.
2) Preparation works to add iptables flowtable support, patches
from Felix Fietkau.
3) Hand over flows back to conntrack slow path in case of TCP RST/FIN
packet is seen via new teardown state, also from Felix.
4) Add support for extended netlink error reporting for nf_tables.
5) Support for larger timeouts that 23 days in nf_tables, patch from
Florian Westphal.
6) Always set an upper limit to dynamic sets, also from Florian.
7) Allow number generator to make map lookups, from Laura Garcia.
8) Use hash_32() instead of opencode hashing in IPVS, from Vicent Bernat.
9) Extend ip6tables SRH match to support previous, next and last SID,
from Ahmed Abdelsalam.
10) Move Passive OS fingerprint nf_osf.c, from Fernando Fernandez.
11) Expose nf_conntrack_max through ctnetlink, from Florent Fourcot.
12) Several housekeeping patches for xt_NFLOG, x_tables and ebtables,
from Taehee Yoo.
13) Unify meta bridge with core nft_meta, then make nft_meta built-in.
Make rt and exthdr built-in too, again from Florian.
14) Missing initialization of tbl->entries in IPVS, from Cong Wang.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
