Age | Commit message (Collapse) | Author |
|
[ Upstream commit a54754ec9891830ba548e2010c889e3c8146e449 ]
Number of buckets being stored in 32bit variables, we have to
ensure that no overflows occur in nft_hash_buckets()
syzbot injected a size == 0x40000000 and reported:
UBSAN: shift-out-of-bounds in ./include/linux/log2.h:57:13
shift exponent 64 is too large for 64-bit type 'long unsigned int'
CPU: 1 PID: 29539 Comm: syz-executor.4 Not tainted 5.12.0-rc7-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:79 [inline]
dump_stack+0x141/0x1d7 lib/dump_stack.c:120
ubsan_epilogue+0xb/0x5a lib/ubsan.c:148
__ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327
__roundup_pow_of_two include/linux/log2.h:57 [inline]
nft_hash_buckets net/netfilter/nft_set_hash.c:411 [inline]
nft_hash_estimate.cold+0x19/0x1e net/netfilter/nft_set_hash.c:652
nft_select_set_ops net/netfilter/nf_tables_api.c:3586 [inline]
nf_tables_newset+0xe62/0x3110 net/netfilter/nf_tables_api.c:4322
nfnetlink_rcv_batch+0xa09/0x24b0 net/netfilter/nfnetlink.c:488
nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:612 [inline]
nfnetlink_rcv+0x3af/0x420 net/netfilter/nfnetlink.c:630
netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline]
netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1338
netlink_sendmsg+0x856/0xd90 net/netlink/af_netlink.c:1927
sock_sendmsg_nosec net/socket.c:654 [inline]
sock_sendmsg+0xcf/0x120 net/socket.c:674
____sys_sendmsg+0x6e8/0x810 net/socket.c:2350
___sys_sendmsg+0xf3/0x170 net/socket.c:2404
__sys_sendmsg+0xe5/0x1b0 net/socket.c:2433
do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
Fixes: 0ed6389c483d ("netfilter: nf_tables: rename set implementations")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 3b02b0adc242a72b5e46019b6a9e4f84823592f6 ]
Call jhash_1word() for the 4-bytes key case from the insertion and
deactivation path, otherwise big endian arch set lookups fail.
Fixes: 446a8268b7f5 ("netfilter: nft_set_hash: add lookup variant for fixed size hashtable")
Reported-by: Florian Westphal <fw@strlen.de>
Tested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 9970a8e40d4c39e23d62d32540366d1d7d2cce9b ]
GC of set uses call_rcu() to destroy elements.
So that elements would be destroyed after destroying sets and chains.
But, elements should be destroyed before destroying sets and chains.
In order to wait calling call_rcu(), a rcu_barrier() is added.
In order to test correctly, below patch should be applied.
https://patchwork.ozlabs.org/patch/940883/
test scripts:
%cat test.nft
table ip aa {
map map1 {
type ipv4_addr : verdict; flags timeout;
elements = {
0 : jump a0,
1 : jump a0,
2 : jump a0,
3 : jump a0,
4 : jump a0,
5 : jump a0,
6 : jump a0,
7 : jump a0,
8 : jump a0,
9 : jump a0,
}
timeout 1s;
}
chain a0 {
}
}
flush ruleset
[ ... ]
table ip aa {
map map1 {
type ipv4_addr : verdict; flags timeout;
elements = {
0 : jump a0,
1 : jump a0,
2 : jump a0,
3 : jump a0,
4 : jump a0,
5 : jump a0,
6 : jump a0,
7 : jump a0,
8 : jump a0,
9 : jump a0,
}
timeout 1s;
}
chain a0 {
}
}
flush ruleset
Splat looks like:
[ 200.795603] kernel BUG at net/netfilter/nf_tables_api.c:1363!
[ 200.806944] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 200.812253] CPU: 1 PID: 1582 Comm: nft Not tainted 4.17.0+ #24
[ 200.820297] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015
[ 200.830309] RIP: 0010:nf_tables_chain_destroy.isra.34+0x62/0x240 [nf_tables]
[ 200.838317] Code: 43 50 85 c0 74 26 48 8b 45 00 48 8b 4d 08 ba 54 05 00 00 48 c7 c6 60 6d 29 c0 48 c7 c7 c0 65 29 c0
4c 8b 40 08 e8 58 e5 fd f8 <0f> 0b 48 89 da 48 b8 00 00 00 00 00 fc ff
[ 200.860366] RSP: 0000:ffff880118dbf4d0 EFLAGS: 00010282
[ 200.866354] RAX: 0000000000000061 RBX: ffff88010cdeaf08 RCX: 0000000000000000
[ 200.874355] RDX: 0000000000000061 RSI: 0000000000000008 RDI: ffffed00231b7e90
[ 200.882361] RBP: ffff880118dbf4e8 R08: ffffed002373bcfb R09: ffffed002373bcfa
[ 200.890354] R10: 0000000000000000 R11: ffffed002373bcfb R12: dead000000000200
[ 200.898356] R13: dead000000000100 R14: ffffffffbb62af38 R15: dffffc0000000000
[ 200.906354] FS: 00007fefc31fd700(0000) GS:ffff88011b800000(0000) knlGS:0000000000000000
[ 200.915533] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 200.922355] CR2: 0000557f1c8e9128 CR3: 0000000106880000 CR4: 00000000001006e0
[ 200.930353] Call Trace:
[ 200.932351] ? nf_tables_commit+0x26f6/0x2c60 [nf_tables]
[ 200.939525] ? nf_tables_setelem_notify.constprop.49+0x1a0/0x1a0 [nf_tables]
[ 200.947525] ? nf_tables_delchain+0x6e0/0x6e0 [nf_tables]
[ 200.952383] ? nft_add_set_elem+0x1700/0x1700 [nf_tables]
[ 200.959532] ? nla_parse+0xab/0x230
[ 200.963529] ? nfnetlink_rcv_batch+0xd06/0x10d0 [nfnetlink]
[ 200.968384] ? nfnetlink_net_init+0x130/0x130 [nfnetlink]
[ 200.975525] ? debug_show_all_locks+0x290/0x290
[ 200.980363] ? debug_show_all_locks+0x290/0x290
[ 200.986356] ? sched_clock_cpu+0x132/0x170
[ 200.990352] ? find_held_lock+0x39/0x1b0
[ 200.994355] ? sched_clock_local+0x10d/0x130
[ 200.999531] ? memset+0x1f/0x40
Fixes: 9d0982927e79 ("netfilter: nft_hash: add support for timeouts")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
jhash_1word of a u16 is a different value from jhash of the same u16 with
length 2.
Since elements are always inserted in sets using jhash over the actual
klen, this would lead to incorrect lookups on fixed-size sets with a key
length of 2, as they would be inserted with hash value jhash(key, 2) and
looked up with hash value jhash_1word(key), which is different.
Example reproducer(v4.13+), using anonymous sets which always have a
fixed size:
table inet t {
chain c {
type filter hook output priority 0; policy accept;
tcp dport { 10001, 10003, 10005, 10007, 10009 } counter packets 4 bytes 240 reject
tcp dport 10001 counter packets 4 bytes 240 reject
tcp dport 10003 counter packets 4 bytes 240 reject
tcp dport 10005 counter packets 4 bytes 240 reject
tcp dport 10007 counter packets 0 bytes 0 reject
tcp dport 10009 counter packets 4 bytes 240 reject
}
}
then use nc -z localhost <port> to probe; incorrectly hashed ports will
pass through the set lookup and increment the counter of an individual
rule.
jhash being seeded with a random value, it is not deterministic which
ports will incorrectly hash, but in testing with 5 ports in the set I
always had 4 or 5 with an incorrect hash value.
Signed-off-by: Anatole Denis <anatole@rezel.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch provides a faster variant of the lookup function for 2 and 4
byte keys. Optimizing the one byte case is not worth, as the set backend
selection will always select the bitmap set type for such case.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch adds a simple non-resizable hashtable implementation. If the
user specifies the set size, then this new faster hashtable flavour is
selected.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Add nft_hash_buckets() helper function to calculate the number of
hashtable buckets based on the elements. This function can be reused
from the follow up patch to add non-resizable hashtables.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The new non-resizable hashtable variant needs this to calculate the
size of the bucket array.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch adds the infrastructure to support several implementations of
the same set type. This selection will be based on the set description
and the features available for this set. This allow us to select set
backend implementation that will result in better performance numbers.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch prepares the introduction of a non-resizable hashtable
implementation that is significantly faster.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This size estimation is ignored by the existing set backend selection
logic, since this estimation structure is stack allocated, set this to
~0 to make it easier to catch bugs in future changes.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Replace struct rhashtable_params forward declaration by the structure
definition itself.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
When dumping the elements related to a specified set, we may invoke the
nf_tables_dump_set with the NFNL_SUBSYS_NFTABLES lock not acquired. So
we should use the proper rcu operation to avoid race condition, just
like other nft dump operations.
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The following Coccinelle script was used to detect this:
@r@
expression x;
void* e;
type T;
identifier f;
@@
(
*((T *)e)
|
((T *)x)[...]
|
((T*)x)->f
|
- (T*)
e
)
Unnecessary parantheses are also remove.
Signed-off-by: simran singhal <singhalsimran0@gmail.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Check for NFT_SET_OBJECT feature flag, otherwise we may end up selecting
the wrong set backend.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The space notation allows us to classify the set backend implementation
based on the amount of required memory. This provides an order of the
set representation scalability in terms of memory. The size field is
still left in place so use this if the userspace provides no explicit
number of elements, so we cannot calculate the real memory that this set
needs. This also helps us break ties in the set backend selection
routine, eg. two backend implementations provide the same performance.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Use lookup as field name instead, to prepare the introduction of the
memory class in a follow up patch.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Although semantics are similar to deactivate() with no implicit element
lookup, this is only called from the set flush path, so better rename
this to flush().
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This new parameter is required by the new bitmap set type that comes in a
follow up patch.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The flush operation needs to modify set and element objects, so let's
deconstify this.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch adds support for set flushing, that consists of walking over
the set elements if the NFTA_SET_ELEM_LIST_ELEMENTS attribute is set.
This patch requires the following changes:
1) Add set->ops->deactivate_one() operation: This allows us to
deactivate an element from the set element walk path, given we can
skip the lookup that happens in ->deactivate().
2) Add a new nft_trans_alloc_gfp() function since we need to allocate
transactions using GFP_ATOMIC given the set walk path happens with
held rcu_read_lock.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This new function allows us to deactivate one single element, this is
required by the set flush command that comes in a follow up patch.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Packets may race when create the new element in nft_hash_update:
CPU0 CPU1
lookup_fast - fail lookup_fast - fail
new - ok new - ok
insert - ok insert - fail(EEXIST)
So when race happened, we reuse the existing element. Otherwise,
these *racing* packets will not be handled properly.
Fixes: 22fe54d5fefc ("netfilter: nf_tables: add support for dynamic set updates")
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
When nft_expr_clone failed, a series of problems will happen:
1. module refcnt will leak, we call __module_get at the beginning but
we forget to put it back if ops->clone returns fail
2. memory will be leaked, if clone fail, we just return NULL and forget
to free the alloced element
3. set->nelems will become incorrect when set->size is specified. If
clone fail, we should decrease the set->nelems
Now this patch fixes these problems. And fortunately, clone fail will
only happen on counter expression when memory is exhausted.
Fixes: 086f332167d6 ("netfilter: nf_tables: add clone interface to expression operations")
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
If the NLM_F_EXCL flag is set, then new elements that clash with an
existing one return EEXIST. In case you try to add an element whose
data area differs from what we have, then this returns EBUSY. If no
flag is specified at all, then this returns success to userspace.
This patch also update the set insert operation so we can fetch the
existing element that clashes with the one you want to add, we need
this to make sure the element data doesn't differ.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Use nft_set_* prefix for backend set implementations, thus we can use
nft_hash for the new hash expression.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|