With TCP-timestamps (padded) taking 12 bytes and ADD_ADDR IPv6 + port
taking 30 bytes, the 40-byte limit for the TCP options is reached. In
this case, it is then not possible to send the signal.
To be able to send this ADD_ADDR, the TCP timestamps option can now be
dropped. This is done, when needed by setting the *drop_ts parameter
from mptcp_established_options. This feature is controlled by a new
net.mptcp.add_addr_v6_port_drop_ts sysctl knob, enabled by default.
It is important to keep in mind that dropping the TCP timestamps option
for one packet of the connection could eventually disrupt some
middleboxes: even if it should be unlikely, they could drop the packet
or even block the connection. That's why this new feature can be
controlled by a sysctl knob.
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/448
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260605-net-next-mptcp-add-addr6-port-ts-v2-6-758e7ca73f4d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
With TCP-timestamps (padded) taking 12 bytes and ADD_ADDR IPv6 + port
taking 30 bytes, the 40-byte limit for the TCP options is reached. In
this case, it is then not possible to send the address signal.
The idea is to let MPTCP dropping the TCP-timestamps option for some
specific packets, to be able to send some specific pure ACK carrying >28
bytes of MPTCP options, like with this specific ADD_ADDR. A new
parameter is passed from tcp_established_options to the MPTCP side to
indicate if the TCP TS option is used, and if it should be dropped. The
next commit implements the part on MPTCP side, but split into two
patches to help TCP maintainers to identify the modifications on TCP
side. This feature will be controlled by a new add_addr_v6_port_drop_ts
MPTCP sysctl knob.
It is important to keep in mind that dropping the TCP timestamps option
for one packet of the connection could eventually disrupt some
middleboxes: even if it should be unlikely, they could drop the packet
or even block the connection. That's why this new feature will be
controlled by a sysctl knob.
Note that it would be technically possible to squeeze both options into
the header if the ADD_ADDR is first written, and then the TCP timestamps
without the NOPs preceding it. But this means more modifications on TCP
side, plus some middleboxes could still be disrupted by that.
In this implementation, an unused bit is used in mptcp_out_options
structure to avoid passing an address to a local variable. Reading and
setting it needs CONFIG_MPTCP, so the whole block now has this #if
condition: mptcp_established_options() is then no longer used without
CONFIG_MPTCP.
About alternatives, instead of passing a new boolean (has_ts), another
option would be to pass the whole option structure (opts), but
'struct tcp_out_options' is currently defined in tcp_output.c, and it
would need to be exported. Plus that means the removal of the TCP TS
option would be done on the MPTCP side, and not here on the TCP side.
It feels clearer to remove other TCP options from the TCP side, than
hiding that from the MPTCP side.
Yet an other alternative would be to pass the size already taken by the
other TCP options, and have a way to drop them all when needed. But this
feels better to target only the timestamps option where dropping it
should be safe, even if it is currently the only option that would be
set before MPTCP, when MPTCP is used.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260605-net-next-mptcp-add-addr6-port-ts-v2-5-758e7ca73f4d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This sysctl is going to be used in the next commits to drop TCP
timestamps option, to be able to send an ADD_ADDR with a v6 IP address
and a port number. It is enabled by default.
This knob is explicitly disabled in the MPTCP Join selftest, with the
"signal addr list progresses after tx drop" subtest, to continue
verifying the previous behaviour where the ADD_ADDR is not sent due to a
lack of space.
While at it, move syn_retrans_before_tcp_fallback down from struct
mptcp_pernet, to avoid creating another 3 bytes hole.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260605-net-next-mptcp-add-addr6-port-ts-v2-4-758e7ca73f4d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
mptcp_add_addr_len helper was called twice: in mptcp_pm_add_addr_signal,
then just after in mptcp_established_options_add_addr. Both to check
the remaining space.
The second call is not needed: if there is not enough space,
mptcp_pm_add_addr_signal will return false, and the caller,
mptcp_established_options_add_addr, will do the same without re-checking
the size again. Instead, mptcp_pm_add_addr_signal can directly set the
size.
Note that the returned size can be negative when other suboptions are
dropped, e.g. to send an echo ADD_ADDR with a v4 address, and no port.
While at it:
- move mptcp_add_addr_len to pm.c, as it is now only used from there
- use 'int' in mptcp_add_addr_len for the size, instead of having a mix
- use a bool for 'ret' in mptcp_pm_add_addr_signal
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260605-net-next-mptcp-add-addr6-port-ts-v2-3-758e7ca73f4d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
mptcp_rm_addr_len helper was called twice: in mptcp_pm_rm_addr_signal,
then just after in mptcp_established_options_rm_addr. Both to check the
remaining space.
The second call is not needed: if there is not enough space,
mptcp_pm_rm_addr_signal will return false, and the caller,
mptcp_established_options_rm_addr, will do the same without re-checking
the size again. Instead, mptcp_pm_rm_addr_signal can directly set the
size.
While at it, move mptcp_rm_addr_len to pm.c, as it is now only used
there, once.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260605-net-next-mptcp-add-addr6-port-ts-v2-2-758e7ca73f4d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use a signed int for the returned size, because when other options are
dropped, the size can be negative, e.g. to send an echo ADD_ADDR with a
v4 address, and no port.
The behaviour is not changed, because it was working as expected with an
overflow. But it is clearer like this, and it will help later on.
Even if, for the moment, only the ADD_ADDR size can be negative in some
cases, a signed int is now used for all mptcp_established_options_*()
helpers, not to mismatch the type, and as a question of uniformity.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260605-net-next-mptcp-add-addr6-port-ts-v2-1-758e7ca73f4d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR (net-7.1-rc8).
Conflicts:
drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
f67aead16e ("net: txgbe: rework service event handling")
57d39faed4 ("net: txgbe: improve functions of AML 40G devices")
net/rds/info.c
512db8267b ("rds: mark snapshot pages dirty in rds_info_getsockopt()")
6e94eeb2a2 ("rds: convert to getsockopt_iter")
Adjacent changes:
include/net/sock.h
1ee90b77b7 ("net: guard timestamp cmsgs to real error queue skbs")
f0de88303d ("net: make is_skb_wmem() available to modules")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sch_cbs and sch_taprio print ecmd.base.speed, even if
netif_get_link_ksettings() failed. When netif_get_link_ksettings()
fails the ecmd may not be initialized.
Use the always-initialized speed variable instead.
The semantics change slightly because UNKNOWN will
never be printed, but that doesn't seem important
enough to complicate the code for.
This is a _dbg() print, anyway.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20260609183353.1109641-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This is a minor performance / conceptual fix.
1) ip6erspan_tunnel_xmit()
ERSPAN tunnel can mirror both IPv4 and IPv6 traffic, skb
(the packet being mirrored) can be an IPv4 packet,
and thus dst can be an IPv4 destination entry
Use dst_mtu() which contains generic logic for both families.
2) ip4ip6_err()
skb2 has been prepared as an IPv4 packet, and its destination
is an IPv4 route.
dst6_mtu() is optimized for IPv6 destinations and uses INDIRECT_CALL_1
to call ip6_mtu() directly if the ops match.
We should use dst4_mtu() instead.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260609091337.2672441-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Various AI scan tools may complain that we don't support resuming
the cap dump. This is true, but the cap dumps are tiny.
net_shaper_nl_cap_pre_dumpit() sets up the dump for just
one device, so the size of the dump scales with NET_SHAPER_SCOPE_MAX (3).
We don't expect them to ever need more than a 4kB page.
Document this.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20260609183224.1108521-5-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The shaper insertion and update code takes xa_lock() explicitly.
Paolo explained that the locking was purely to avoid re-taking
the lock in loops. But it may be mis-read as if it was expecting
readers to be fenced off by xa_lock. Readers of XArray are purely
under RCU. Remove explicit taking of xa_lock().
All writers to hierarchy->shapers are serialized by the netdev
instance lock (or run after netdev is made inaccessible to readers).
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20260609183224.1108521-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains Netfilter fixes for net:
1) Revalidate bridge ports, add missing NULL checks to fetch the bridge
device by the port. From Florian Westphal.
2) Fix netdevice refcount leak in the error path of nft_fwd hardware
offload function, also from Florian.
3) Unregister helper expectfn callback on conntrack helper module
removal, otherwise dangling pointer remains in place,
from Weiming Shi.
4) Fix possible pointer infoleak in getsockopt() IPT_SO_GET_ENTRIES,
From Kyle Zeng.
5) Validate that device MAC header is present before nf_syslog
accesses it. From Xiang Mei.
6-8) Three patches to address a possible infoleak of stale stack
data in three nf_tables expressions, due to mismatch in the
_init() and _eval() function which is possible since 14fb07130c.
From Davide Ornaghi and Florian Westphal.
netfilter pull request 26-06-10
* tag 'nf-26-06-10' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
netfilter: nft_meta_bridge: fix stale stack leak via IIFHWADDR register
netfilter: nft_fib: fix stale stack leak via the OIFNAME register
netfilter: nft_exthdr: fix register tracking for F_PRESENT flag
netfilter: nf_log: validate MAC header was set before dumping it
netfilter: x_tables: avoid leaking percpu counter pointers
netfilter: nf_conntrack: destroy stale expectfn expectations on unregister
netfilter: nf_tables_offload: drop device refcount on error
netfilter: revalidate bridge ports
====================
Link: https://patch.msgid.link/20260610161629.214092-1-pablo@netfilter.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Convert RDS socket's getsockopt implementation to use the new
getsockopt_iter callback with sockopt_t.
Key changes:
- Replace (char __user *optval, int __user *optlen) with sockopt_t *opt
- Use opt->optlen for buffer length (input) and returned size (output)
- Use copy_to_iter() instead of put_user()/copy_to_user()
The RDS_INFO_* snapshot path in rds_info_getsockopt() used to pin the
userspace buffer with pin_user_pages_fast() on the raw optval address;
the info producers then memcpy into those pages under a spinlock via
kmap_atomic() and so must not fault. Obtain the same page array and
starting offset from opt->iter_out with iov_iter_extract_pages(), which
pins for write because iter_out is ITER_DEST.
The page array is preallocated here (sized with iov_iter_npages()) and
passed in, so iov_iter_extract_pages() fills it in place rather than
allocating one for us; RDS therefore keeps ownership of the array on
every return path and frees it itself. The rds_info_iterator /
rds_info_copy machinery and all producer callbacks are unchanged.
Kernel buffers (ITER_KVEC) are not page-backed in a way the info
producers can use, so the RDS_INFO path returns -EOPNOTSUPP for them;
this matches the previous behaviour, where a kernel-buffer getsockopt
hit the WARN_ONCE() path in do_sock_getsockopt() and returned
-EOPNOTSUPP. The simple RDS_RECVERR and SO_RDS_TRANSPORT options keep
working for kernel buffers via copy_to_iter().
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260608-getsock_more-v3-2-706ecf2ea332@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Steffen Klassert says:
====================
pull request (net): ipsec 2026-06-10
1) xfrm: iptfs: preserve shared-frag marker in iptfs_consume_frags()
Propagate SKBFL_SHARED_FRAG when paged fragments are moved between
skbs so ESP can decide whether in-place crypto is safe.
2) xfrm: iptfs: fix use-after-free on first_skb in __input_process_payload
Replace the unlocked read of xtfs->ra_newskb with a local flag so a
concurrent reassembly can no longer free first_skb between
spin_unlock and the post-loop check.
3) xfrm: policy: fix use-after-free on inexact bin in xfrm_policy_bysel_ctx()
Prune the inexact bin under xfrm_policy_lock so a concurrent
xfrm_hash_rebuild() can no longer free it before xfrm_policy_kill()
dereferences it.
4) xfrm: iptfs: fix ABBA deadlock in iptfs_destroy_state()
Move hrtimer_cancel() for the output and drop timers ahead of their
spinlocks, breaking the softirq/lock cycle that could deadlock
against the timer callbacks on SMP.
5) xfrm: espintcp: do not reuse an in-progress partial send
Fail a new send when espintcp_push_msgs() returns with emsg->len
still set, so a blocking caller can no longer overwrite ctx->partial
while a previous transfer still owns it.
6) esp: fix page frag reference leak on skb_to_sgvec failure
Add a flag to esp_ssg_unref() to unconditionally unref the source
scatterlist, releasing the old page references that are otherwise
leaked when the second skb_to_sgvec() in esp_output_tail() fails.
Please pull or let me know if there are problems.
ipsec-2026-06-10
* tag 'ipsec-2026-06-10' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
esp: fix page frag reference leak on skb_to_sgvec failure
xfrm: espintcp: do not reuse an in-progress partial send
xfrm: iptfs: fix ABBA deadlock in iptfs_destroy_state()
xfrm: policy: fix use-after-free on inexact bin in xfrm_policy_bysel_ctx()
xfrm: iptfs: fix use-after-free on first_skb in __input_process_payload
xfrm: iptfs: preserve shared-frag marker in iptfs_consume_frags()
====================
Link: https://patch.msgid.link/20260610140800.2562818-1-steffen.klassert@secunet.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
addrconf_get_prefix_route() can return the fib6_null_entry sentinel
entry which has a NULL fib6_table pointer. Therefore, before setting the
route's expiration time, check that we are not working with this entry,
as otherwise a NPD will be triggered [1].
Note that the other callers of addrconf_get_prefix_route() are not
susceptible to this bug:
1. addrconf_prefix_rcv(): Requests a route with the 'RTF_ADDRCONF |
RTF_PREFIX_RT' flags which are not set on fib6_null_entry.
2. modify_prefix_route(): Fixed by commit a747e02430 ("ipv6: avoid
possible NULL deref in modify_prefix_route()").
3. __ipv6_ifa_notify(): Calls ip6_del_rt() which specifically checks for
fib6_null_entry and returns an error.
[1]
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
[...]
Call Trace:
<TASK>
__kasan_check_byte (mm/kasan/common.c:573)
lock_acquire.part.0 (kernel/locking/lockdep.c:5842 (discriminator 1))
_raw_spin_lock_bh (kernel/locking/spinlock.c:182 (discriminator 1))
cleanup_prefix_route (net/ipv6/addrconf.c:1280)
ipv6_del_addr (net/ipv6/addrconf.c:1342)
inet6_addr_del.isra.0 (net/ipv6/addrconf.c:3119)
inet6_rtm_deladdr (net/ipv6/addrconf.c:4812)
rtnetlink_rcv_msg (net/core/rtnetlink.c:6997)
netlink_rcv_skb (net/netlink/af_netlink.c:2555)
netlink_unicast (net/netlink/af_netlink.c:1344)
netlink_sendmsg (net/netlink/af_netlink.c:1899)
__sock_sendmsg (net/socket.c:802 (discriminator 4))
____sys_sendmsg (net/socket.c:2698)
___sys_sendmsg (net/socket.c:2752)
__sys_sendmsg (net/socket.c:2784)
do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121)
Fixes: 5eb902b8e7 ("net/ipv6: Remove expired routes with a separated list of routes.")
Reported-by: Ji'an Zhou <eilaimemedsnaimel@gmail.com>
Reviewed-by: David Ahern <dahern@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260609145448.768318-1-idosch@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
NFT_META_BRI_IIFHWADDR declares its destination register with
len = ETH_ALEN (6 bytes), which the register-init tracking rounds up to
two 32-bit registers (8 bytes). nft_meta_bridge_get_eval() then does
memcpy(dest, br_dev->dev_addr, ETH_ALEN), writing only 6 bytes and
leaving the upper 2 bytes of the second register as uninitialised
nft_do_chain() stack. A downstream load of that register span leaks
those stale bytes to userspace.
Zero the second register before the memcpy so the full declared span is
written.
Fixes: cbd2257dc9 ("netfilter: nft_meta_bridge: introduce NFT_META_BRI_IIFHWADDR support")
Cc: stable@vger.kernel.org
Signed-off-by: Davide Ornaghi <d.ornaghi97@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
For NFT_FIB_RESULT_OIFNAME the destination register is declared with
len = IFNAMSIZ (four 32-bit registers), but on the lookup-fail,
RTN_LOCAL and oif-mismatch paths nft_fib{4,6}_eval() only writes one
register via "*dest = 0". The remaining three registers are left as
whatever was on the stack in nft_do_chain()'s struct nft_regs, and a
downstream expression that loads the register span can leak that
uninitialised kernel stack to userspace.
The NFTA_FIB_F_PRESENT existence check has the same shape: it is only
meaningful for NFT_FIB_RESULT_OIF, yet it was accepted for any result type
while the eval stores a single byte via nft_reg_store8(), leaving the rest
of the declared span stale.
Fix both:
- replace the bare "*dest = 0" in the eval with nft_fib_store_result(),
which strscpy_pad()s the whole IFNAMSIZ for OIFNAME (and is already
used on the other early-return path), and
- restrict NFTA_FIB_F_PRESENT to NFT_FIB_RESULT_OIF and declare its
destination as a single u8, so the marked span matches the one byte
the eval writes.
Fixes: f6d0cbcf09 ("netfilter: nf_tables: add fib expression")
Suggested-by: Florian Westphal <fw@strlen.de>
Cc: stable@vger.kernel.org
Signed-off-by: Davide Ornaghi <d.ornaghi97@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
nft_exthdr_init() passes user-controlled priv->len to
nft_parse_register_store(), which marks that many bytes in the
register bitmap as initialized. However, when NFT_EXTHDR_F_PRESENT
is set, the eval paths write only 1 byte (nft_reg_store8) or
4 bytes (*dest = 0 on TCP/DCCP error path). When len > 4,
registers beyond the first are never written, retaining
uninitialized stack data from nft_regs.
Bail out if userspace requests too much data when F_PRESENT is set.
Reported-by: Ji'an Zhou <eilaimemedsnaimel@gmail.com>
Fixes: c078ca3b0c ("netfilter: nft_exthdr: Add support for existence check")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The fallback path of dump_mac_header() guards the MAC header access
only with "skb->mac_header != skb->network_header", without checking
skb_mac_header_was_set(). When the MAC header is unset, mac_header is
0xffff, so the test passes and skb_mac_header(skb) returns
skb->head + 0xffff, ~64 KiB past the buffer; the loop then reads
dev->hard_header_len bytes out of bounds into the kernel log.
This is reachable via the netdev logger: nf_log_unknown_packet() calls
dump_mac_header() unconditionally, and an skb sent through AF_PACKET
with PACKET_QDISC_BYPASS reaches the egress hook with mac_header still
unset (__dev_queue_xmit(), which would reset it, is bypassed).
Add the skb_mac_header_was_set() check the ARPHRD_ETHER path already
uses, and replace the open-coded MAC header length test with
skb_mac_header_len(). Only skbs with an unset MAC header are affected;
valid ones are dumped as before.
BUG: KASAN: slab-out-of-bounds in dump_mac_header (net/netfilter/nf_log_syslog.c:831)
Read of size 1 at addr ffff88800ea49d3f by task exploit/148
Call Trace:
kasan_report (mm/kasan/report.c:595)
dump_mac_header (net/netfilter/nf_log_syslog.c:831)
nf_log_netdev_packet (net/netfilter/nf_log_syslog.c:938 net/netfilter/nf_log_syslog.c:963)
nf_log_packet (net/netfilter/nf_log.c:260)
nft_log_eval (net/netfilter/nft_log.c:60)
nft_do_chain (net/netfilter/nf_tables_core.c:285)
nft_do_chain_netdev (net/netfilter/nft_chain_filter.c:307)
nf_hook_slow (net/netfilter/core.c:619)
nf_hook_direct_egress (net/packet/af_packet.c:257)
packet_xmit (net/packet/af_packet.c:280)
packet_sendmsg (net/packet/af_packet.c:3114)
__sys_sendto (net/socket.c:2265)
Fixes: 7eb9282cd0 ("netfilter: ipt_LOG/ip6t_LOG: add option to print decoded MAC header")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The native and compat get-entries paths copy the fixed rule entry header
from the kernelized rule blob to userspace before overwriting the entry's
counter fields with a sanitized counter snapshot.
On SMP kernels, entry->counters.pcnt contains the percpu allocation
address used by x_tables rule counters. A caller can provide a userspace
buffer that faults during the initial fixed-header copy after pcnt has
been copied but before the later sanitized counter copy runs. The syscall
then returns -EFAULT while leaving the raw percpu pointer in userspace.
Copy only the fixed entry prefix before counters from the kernelized rule
blob, then copy the sanitized counter snapshot into the counter field.
Apply this ordering to the IPv4, IPv6, and ARP native and compat
get-entries implementations so a fault cannot expose the internal percpu
counter pointer.
Fixes: 71ae0dff02 ("netfilter: xtables: use percpu rule counters")
Signed-off-by: Kyle Zeng <kylebot@openai.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
NAT helpers such as nf_nat_h323 store a raw pointer to module text in
exp->expectfn (e.g. ip_nat_q931_expect). nf_ct_helper_expectfn_unregister()
only unlinks the callback descriptor and never walks the expectation table,
so an expectation pending at module removal survives with a dangling
exp->expectfn into freed module text.
When the expected connection arrives, init_conntrack() invokes
exp->expectfn(), now a stale pointer into the unloaded module. Reproduced
on a KASAN build by loading the H.323 helpers, creating a Q.931
expectation, unloading nf_nat_h323, then connecting to the expected port:
Oops: int3: 0000 [#1] SMP KASAN NOPTI
RIP: 0010:0xffffffffa06102d1
init_conntrack.isra.0 (net/netfilter/nf_conntrack_core.c:1862)
nf_conntrack_in (net/netfilter/nf_conntrack_core.c:2049)
ipv4_conntrack_local (net/netfilter/nf_conntrack_proto.c:223)
nf_hook_slow (net/netfilter/core.c:619)
__ip_local_out (net/ipv4/ip_output.c:120)
__tcp_transmit_skb (net/ipv4/tcp_output.c:1715)
tcp_connect (net/ipv4/tcp_output.c:4374)
tcp_v4_connect (net/ipv4/tcp_ipv4.c:345)
__sys_connect (net/socket.c:2167)
Modules linked in: nf_conntrack_h323 [last unloaded: nf_nat_h323]
Reaching the dangling state requires CAP_SYS_MODULE in the initial user
namespace to remove a NAT helper that still has live expectations, so this
is a robustness fix; leaving an expectation pointing at freed text is wrong
regardless.
Add nf_ct_helper_expectfn_destroy(), which walks the expectation table and
drops every expectation whose ->expectfn matches the descriptor being torn
down. Call it from each NAT helper's exit path after the existing RCU grace
period, so no expectation outlives the code it points at and no extra
synchronize_rcu() is introduced. With the fix, the same reproducer runs to
completion without the Oops.
Fixes: f587de0e2f ("[NETFILTER]: nf_conntrack/nf_nat: add H.323 helper port")
Reported-by: Xiang Mei <xmei5@asu.edu>
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Reported by sashiko:
If nft_flow_action_entry_next() returns NULL, dev reference leaks.
Fixes: c6f8557758 ("netfilter: nf_tables_offload: add nft_flow_action_entry_next() and use it")
Reported-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
ebt_redirect_tg() dereferences br_port_get_rcu() return without a
NULL check, causing a kernel panic when the bridge port has been
removed between the original hook invocation and an NFQUEUE
reinject.
A mere NULL check isn't sufficient, however. As sashiko review
points out userspace can not only remove the port from the bridge,
it could also place the device in a different virtual device, e.g.
macvlan.
If this happens, we must drop the packet, there is no way for us to
reinject it into the bridge path.
Switch to _upper API, we don't need the bridge port structure.
Also, this fix keeps another bug intact:
Both nfnetlink_log and nfnetlink_queue use CONFIG_BRIDGE_NETFILTER
too aggressive, which prevents certain logging features when queueing
in bridge family: NETFILTER_FAMILY_BRIDGE can be enabled while the old
CONFIG_BRIDGE_NETFILTER cruft is off.
Fixes tag is a common ancestor, this was always broken.
Fixes: f350a0a873 ("bridge: use rx_handler_data pointer to store net_bridge_port pointer")
Reported-by: Ji'an Zhou <eilaimemedsnaimel@gmail.com>
Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
sctp_v4_add_protocol() and sctp_v6_add_protocol() register their
address notifiers before registering the SCTP protocol handlers. If
protocol registration fails, the functions return without unregistering
the notifiers.
Unregister the notifiers on the protocol registration failure paths.
Also propagate notifier registration failures instead of ignoring them.
Signed-off-by: Yuho Choi <dbgh9129@gmail.com>
Link: https://patch.msgid.link/20260608162230.46644-1-dbgh9129@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
rds_info_getsockopt() pins the destination user pages with FOLL_WRITE and
the RDS_INFO_* producers memcpy the snapshot into them through
kmap_atomic(). Because that copy goes through the kernel direct map, the
dirty bit on the user PTE is never set, so unpin_user_pages() releases the
pages without marking them dirty. A file-backed destination page can then
be reclaimed without writeback, silently discarding the copied data.
Use unpin_user_pages_dirty_lock() with make_dirty=true so the modified
pages are marked dirty before they are unpinned.
Fixes: a8c879a7ee ("RDS: Info and stats")
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260608-rds_fix-v1-1-006c88543408@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In vti6_tnl_lookup(), when an exact match for a tunnel fails,
the code falls back to searching for wildcard tunnels:
- Tunnels matching the packet's local address, with any remote address
wildcard remote).
- Tunnels matching the packet's remote address, with any local address
(wildcard local).
However, vti6 stores all these different types of tunnels in the same
hash table (ip6n->tnls_r_l) prone to hash collisions.
The bug is that the fallback search loops in vti6_tnl_lookup() were
missing checks to ensure that the candidate tunnel actually has
a wildcard address.
Fixes: fbe68ee875 ("vti6: Add a lookup method for tunnels with wildcard endpoints.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://patch.msgid.link/20260608164613.933023-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
fddi_type_trans() reads FDDI header fields from skb->data without first
checking that the received frame is long enough for those fields.
The destination address spans offsets 1-6 and the LLC dsap field is at
offset 13. For SNAP frames, fddi->hdr.llc_snap.ethertype is at offsets
19-20. A truncated 15-byte frame with dsap != 0xe0 therefore enters the
SNAP branch and reads the ethertype past the end of the frame.
KASAN reports this when such a frame is processed through a dummy FDDI
netdev that calls the real fddi_type_trans() on an exact kmalloc() copy
of the frame:
BUG: KASAN: slab-out-of-bounds in fddi_type_trans+0x385/0x3a0
Read of size 2 at addr ffff888009c6fe33
The buggy address is located 4 bytes to the right of
allocated 15-byte region [ffff888009c6fe20, ffff888009c6fe2f)
Reject short frames before reading the fields: require the minimum 802.2
header length before accessing dsap or daddr, and require the full SNAP
header length before reading the SNAP ethertype. Returning protocol 0
causes the malformed packet to be ignored by protocol handlers.
Cc: <stable+noautosel@kernel.org> # devices should drop runt frames, repro uses a fake driver
Reported-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Reported-by: Yuxiang Yang <yangyx22@mails.tsinghua.edu.cn>
Reported-by: Ao Wang <wangao@seu.edu.cn>
Reported-by: Xuewei Feng <fengxw06@126.com>
Reported-by: Qi Li <qli01@tsinghua.edu.cn>
Reported-by: Ke Xu <xuke@tsinghua.edu.cn>
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260607112408.92988-1-zhaoyz24@mails.tsinghua.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
rds_ib_xmit_atomic() always programs a masked atomic opcode
(IB_WR_MASKED_ATOMIC_CMP_AND_SWP or IB_WR_MASKED_ATOMIC_FETCH_AND_ADD)
for every RDS atomic cmsg. But the completion-side switch in
rds_ib_send_unmap_op() only handles the non-masked opcodes, so a masked
atomic completion falls through to default and returns rm == NULL while
send->s_op is left set. rds_ib_send_cqe_handler() then dereferences the
NULL rm via rm->m_final_op, oopsing in softirq context. An unprivileged
AF_RDS sendmsg() of an atomic cmsg over an active RDS/IB connection
triggers it; on hardware that natively accepts masked atomics (mlx4,
mlx5) no extra setup is needed.
RDS/IB: rds_ib_send_unmap_op: unexpected opcode 0xd in WR!
Oops: general protection fault [#1] SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000190-0x0000000000000197]
RIP: rds_ib_send_cqe_handler+0x25c/0xb10 (net/rds/ib_send.c:282)
Call Trace:
<IRQ>
rds_ib_send_cqe_handler (net/rds/ib_send.c:282)
poll_scq (net/rds/ib_cm.c:274)
rds_ib_tasklet_fn_send (net/rds/ib_cm.c:294)
tasklet_action_common (kernel/softirq.c:943)
handle_softirqs (kernel/softirq.c:573)
run_ksoftirqd (kernel/softirq.c:479)
</IRQ>
Kernel panic - not syncing: Fatal exception in interrupt
Handle the masked atomic opcodes in the same case as the non-masked
ones: they map to the same struct rds_message.atomic union member, so
the existing container_of()/rds_ib_send_unmap_atomic() body is correct
for them.
Fixes: 20c72bd5f5 ("RDS: Implement masked atomic operations")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Reviewed-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260606192447.1179255-2-bestswngs@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
skb_is_err_queue() treats PACKET_OUTGOING as the sole marker for an skb
from sk_error_queue. That assumption is not true for AF_PACKET sockets:
outgoing packet taps are also delivered to packet sockets with
skb->pkt_type == PACKET_OUTGOING, but their skb->cb is owned by AF_PACKET
instead of struct sock_exterr_skb.
If such an skb is received with timestamping enabled, the generic
timestamp cmsg path can read AF_PACKET control-buffer state as
sock_exterr_skb::opt_stats. With SO_RXQ_OVFL enabled, the packet drop
counter overlaps opt_stats. An odd drop count makes the path emit
SCM_TIMESTAMPING_OPT_STATS with skb->len and skb->data. For non-linear
skbs this copies past the linear head and can trigger hardened usercopy or
disclose adjacent heap contents.
Keep skb_is_err_queue() local to net/socket.c, but make it verify that
the PACKET_OUTGOING marker is paired with the sock_rmem_free destructor
installed by sock_queue_err_skb(). AF_PACKET receive skbs use normal
receive ownership and no longer pass as error-queue skbs, while legitimate
sk_error_queue entries keep the PACKET_OUTGOING marker and sock_rmem_free
ownership.
Fixes: 8605330aac ("tcp: fix SCM_TIMESTAMPING_OPT_STATS for normal skbs")
Signed-off-by: Kyle Zeng <kylebot@openai.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260607021819.49698-1-kylebot@openai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sctp_unpack_cookie() only checked that the embedded INIT chunk length
did not exceed the remaining cookie payload, but did not ensure that the
INIT chunk is large enough to contain a complete INIT header.
A malformed COOKIE_ECHO can therefore carry a truncated INIT chunk whose
length field is smaller than sizeof(struct sctp_init_chunk). Later,
sctp_process_init() accesses INIT parameters unconditionally, which may
lead to out-of-bounds reads.
In addition, raw_addr_list_len is not fully validated against the
remaining cookie payload. When cookie authentication is disabled, an
attacker can supply an oversized raw_addr_list_len and cause
sctp_raw_to_bind_addrs() to read beyond the end of the cookie. The
address parser also lacks sufficient bounds checks for parameter headers
and lengths, allowing malformed address parameters to trigger
out-of-bounds reads.
Fix this by:
- requiring the embedded INIT chunk length to be at least sizeof(struct
sctp_init_chunk);
- validating that the INIT chunk and raw address list together fit
within the cookie payload;
- verifying sufficient data exists for each address parameter header and
payload before parsing it.
Note that sctp_verify_init() must be called after sctp_unpack_cookie()
and before sctp_process_init() when cookie authentication is disabled.
This will be addressed in a separate patch.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Link: https://patch.msgid.link/75af23a89adf881a0895d511775e4770da367cbf.1780873427.git.lucien.xin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When ndo_set_rx_mode_async returns an error, schedule a retry with
exponential backoff (1s, 2s, 4s, 8s -- 15s total). Give up after the
4th retry and log an error via netdev_err().
This moves retry logic from individual drivers into the core stack.
Timer callback does not hold a ref on dev. Safe because the timer can
only be armed when dev is IFF_UP, and __dev_close_many runs
timer_delete_sync before clearing IFF_UP. Unregister always closes
IFF_UP devices first, so by the time dev can be freed the timer is
dead and cannot be re-armed.
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260608154014.227538-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
__sctp_rcv_asconf_lookup() in net/sctp/input.c only checks that the ASCONF
chunk can hold the ADDIP header and a parameter header, then calls
af->from_addr_param(), which reads the full address (16 bytes for IPv6)
trusting the parameter's declared length.
An unauthenticated peer can send a truncated trailing ASCONF chunk that
declares an IPv6 address parameter but stops after the 4-byte parameter
header; reached from the no-association lookup path, from_addr_param() then
reads uninitialized bytes past the parameter.
Impact: an unauthenticated SCTP peer makes the receive path read up to 16
bytes of uninitialized memory past a truncated ASCONF address parameter.
The sibling __sctp_rcv_init_lookup() bounds parameters with
sctp_walk_params(); this path open-codes the fetch and omits the bound.
Verify the whole address parameter lies within the chunk before
from_addr_param() reads it, the same class of fix as commit 51e5ad549c
("net: sctp: fix KMSAN uninit-value in sctp_inq_pop").
Fixes: df21857714 ("[SCTP]: Update association lookup to look at ASCONF chunks as well")
Signed-off-by: Michael Bommarito <michael.bommarito@gmail.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://patch.msgid.link/20260608122234.459098-1-michael.bommarito@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since the use of "pcbc(des)" in rxkad_decrypt_ticket() is the only
remaining user of the crypto API "pcbc" template, just implement
DES-PCBC by locally implementing PCBC mode on top of the DES library.
Note that only the decryption direction is needed.
This will allow support for the obsolete PCBC mode to be removed from
the crypto API.
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Link: https://patch.msgid.link/20260522050740.84561-4-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use the local implementation of FCrypt-PCBC instead of the crypto API
one. This will allow the crypto API one to be removed. It also
simplifies the code quite a bit.
The local FCrypt-PCBC implementation is also significantly faster than
the crypto API one, since the crypto API one had a lot of overhead. For
example, benchmarking on an x86_64 CPU, I see that FCrypt-PCBC
decryption throughput improved from 83 MB/s to 157 MB/s.
(Meanwhile, AES-256-GCM decryption is 8064 MB/s on the same CPU.
Clearly, anyone looking for good performance, or anything that is
actually secure for that matter, needs to look elsewhere anyway.)
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Link: https://patch.msgid.link/20260522050740.84561-3-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a local implementation of FCrypt-PCBC encryption and decryption.
This will be used instead of the crypto API one, allowing the crypto API
one to be removed. It will also simplify rxkad.c quite a bit.
A KUnit test is included. The FCrypt-PCBC test vectors are borrowed
from the existing ones in crypto/testmgr.h. Note that this adds the
first KUnit test for net/rxrpc/, which previously had no KUnit tests.
The FCrypt code is based on crypto/fcrypt.c, but I simplified it a bit.
The PCBC part is straightforward and I just wrote it from scratch.
Tested with:
kunit.py run --kunitconfig net/rxrpc/
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Link: https://patch.msgid.link/20260522050740.84561-2-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Convert the IOCTL path similarly to how we converted Netlink.
The device lookup gets a little hairy. We could take rtnl_lock
unconditionally and drop it before calling the driver (this would
avoid the reference + liveness check). But I think being able
to make progress even if rtnl is dead-locked is quite useful.
First extra concern is handling features. List all the cmds which
modify features and always take rtnl_lock. We could fold this list
into ethtool_ioctl_needs_rtnl() but seems cleaner to keep
ethtool_ioctl_needs_rtnl() driver-related. If a driver changed
features and we were not holding rtnl_lock - warn about it.
It can only happen on buggy ops locked drivers (buggy because
they should have set appropriate "I need rtnl for op X" bit).
Second wrinkle is the PHY ID hack which drops the locks while
sleeping. Convert its static "busy" variable which used to
be protected by rtnl_lock to a field in struct ethtool_netdev_state.
This feature is about identifying an adapter or a port within
a system, so being able to blink multiple LEDs at the same
time is likely not very useful in practice. But it's the simplest
fix, we can add a mutex if someone thinks a system should only
be ID'ing one port at a time.
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20260605002912.3456868-12-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Skip rtnl_lock in RSS context handlers if device is ops-locked.
Fairly trivial conversion. bnxt needed rtnl_lock for changing
the main context but looks like additional contexts are fine
without it.
Note (for review bots?) that ethnl_ops_begin() checks whether
the device is still registered.
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20260605002912.3456868-10-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Make ethtool not take rtnl_lock for SET commands when operation
is performed on an ops-locked driver. cfg/cfg_pending are now
ops-locked, since only ethtool modifies them.
Some SET driver callbacks will still need rtnl_lock, most notably
those which may end up calling netdev_update_features() or the qdisc
layer (via netif_set_real_num_tx_queues()). Let drivers selectively
opt back into the rtnl_lock with a new bitfield in ops.
We need two helpers since Netlink and ioctl cmds have different
values. Keep the helpers side by side in common.h to make sure
they get updated together, even tho they will only get called
from ioctl.c and netlink.c.
SET commands which don't use ethnl_default_set_doit() are converted
by subsequent commits.
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20260605002912.3456868-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Matthieu Baerts (NGI0)
Kuniyuki Iwashima
Jakub Kicinski
Eric Dumazet
Paolo Abeni
Breno Leitao
Ido Schimmel
Davide Ornaghi
Florian Westphal
Xiang Mei
Kyle Zeng
Weiming Shi
Yuho Choi
David Yang
Yizhou Zhao
David Laight
Xin Long
Stanislav Fomichev
Michael Bommarito
Wyatt Feng
Eric Biggers