sctp_process_asconf_param() stores a newly added peer transport in
asoc->new_transport. After all parameters in the ASCONF chunk have been
processed, sctp_sf_do_asconf() uses this pointer to send a HEARTBEAT to the
new transport.
An authenticated ASCONF from a remote SCTP peer can add a transport and
remove it again with a wildcard DEL-IP parameter in the same chunk. The
wildcard deletion preserves the transport on which the ASCONF arrived, but
removes the newly added transport through
sctp_assoc_del_nonprimary_peers(). The removal does not clear
asoc->new_transport, leaving it pointing to the removed transport.
sctp_sf_do_asconf() then creates a HEARTBEAT whose chunk->transport points
to the removed transport without holding a transport reference. During
local address replacement, src_out_of_asoc_ok keeps this HEARTBEAT on
control_chunk_list. After the transport is freed by RCU, a successful
ASCONF_ACK for the replacement address releases the queued HEARTBEAT and
sctp_outq_select_transport() reads the freed transport's state.
The issue was found during a static audit of SCTP objects. With an
authenticated peer, the reproducer triggered the same KASAN report in 2
of 2 unpatched runs on a KASAN-enabled netdev/main kernel:
BUG: KASAN: slab-use-after-free in sctp_outq_select_transport
Read of size 4 at addr ffff88800b9bd95c by task python3/197
Call Trace:
sctp_outq_select_transport+0x549/0x8b0 [sctp]
sctp_outq_flush+0x306/0x2c60 [sctp]
sctp_transport_immediate_rtx+0xaf/0x260 [sctp]
sctp_process_asconf_ack+0xa48/0xf70 [sctp]
Allocated by task 197:
sctp_transport_new+0x68/0x650 [sctp]
sctp_assoc_add_peer+0x258/0x12a0 [sctp]
sctp_process_asconf+0x5e9/0x1090 [sctp]
Last potentially related work creation:
__call_rcu_common.constprop.0+0x77/0xb70
sctp_assoc_del_nonprimary_peers+0x7c/0xd0 [sctp]
sctp_process_asconf+0xd9c/0x1090 [sctp]
The first invalid access was a four-byte read of transport->state at
net/sctp/outqueue.c:833. The same reproducer completed the full
authenticated ASCONF and local-address replacement sequence with this
change without a KASAN report or oops.
Clear new_transport when its peer is removed, before it can be used to
create the HEARTBEAT.
Fixes: 6af29ccc22 ("sctp: Bundle HEAERTBEAT into ASCONF_ACK")
Cc: stable@vger.kernel.org
Signed-off-by: Qing Ming <a0yami@mailbox.org>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://patch.msgid.link/20260811152803.5629-1-a0yami@mailbox.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A dibs device interrupt handler can be active after dibs_dev_del() and
may still access dmb_clientid_arr. (UAF)
In case of a failure in dibs_dev_add() being called by dibs_lo_dev_probe()
dmb_clientid_arr is freed twice (double free).
Free dmb_clientid_arr in dibs_dev_release() after last reference is gone.
Note that allocating in dibs_dev_add() instead of dibs_dev_alloc() is ok
for now, because no dmbs can be registered before dibs_dev_add().
Fixes: cc21191b58 ("dibs: Move data path to dibs layer")
Cc: stable@vger.kernel.org
Co-developed-by: Hidayath Khan <hidayath@linux.ibm.com>
Signed-off-by: Hidayath Khan <hidayath@linux.ibm.com>
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Link: https://patch.msgid.link/20260810111432.2334900-1-wintera@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pablo Neira Ayuso says:
====================
Netfilter/IPVS fixes for net
The following patchset contains Netfilter/IPVS fixes for net. Still
large batch for this late -rc cycle but at least half of these fixes
in this batch have been cooking for several weeks before:
1) Fix race between ipset list:set GC and swap, use write_lock instead
of rcu read lock section when accessing the index to ensure
interference with ip_set_swap(), from Xiang Mei.
2) Release template conntrack in bridge conntrack when packet is
neither IPv4 nor IPv6 before setting skb as untracked.
From Zhiling Zou.
3) A series of 3 patches for IPVS to address sashiko reports:
Schedulers read destination overload state while connection
accounting and destination configuration can update it concurrently.
The first patch adds a single total connection counter. The second
patch uses it to identify threshold crossings precisely, and updates
OVERLOAD at the crossings and on a threshold edit under dst_lock.
The third patch moves configuration-controlled AVAILABLE to a
separate cflags word, so it cannot clobber OVERLOAD through an
unrelated read-modify-write update.
4) Log invalid packets in TCP and SCTP connection tracking to address
a deadlock when nfnetlink_log is used as logging backend and the
nfnetlink_log conntrack glue support is used. From Zihan Xi.
5) Wait for rcu grace period before releasing pernet state in
nfnetlink_log, otherwise packets can end up access already released
memory, triggering UaF. From Florian Westphal.
6) IPVS needs to reset IP information in control buffer in skbuff when
encapsulating IP packets in ICMP, from Kyle Zeng.
7) IPVS needs to validate ihl field of inner headers in when handling
ICMP response, from Julian Anastasov.
8) Remove a WARN_ON_ONCE reachable from the nf_tables hardware offload
when triggering ENOMEM on GFP_KERNEL allocation,
from Alexey Velichayshiy.
9) Publish reply tuple into the flowtable hashtable first, otherwise
GC might walk over a released tuple when insertion of the original
tuple fail. From Jeremy Jean.
10) Elide counter increment when replacing an ipset element,
from Florian Westphal.
11) Remove unneeded ipset accounting resets on destruction/flush,
from Florian Westphal.
* tag 'nf-26-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
netfilter: ipset: let destroy callbacks adjust ext mem size
netfilter: ipset: fix list type element drift bug
netfilter: flowtable: publish GC-visible tuple last
netfilter: nf_tables_offload: suppress WARN_ON_ONCE for ENOMEM in abort path
ipvs: revalidate ihl to prevent out-of-bounds access
ipvs: clear IPv4 options after rebasing tunnel ICMP errors
netfilter: nfnetlink_log: wait for rcu grace period before freeing pernet state
netfilter: nf_conntrack: defer invalid log until after unlock
ipvs: separate destination availability state
ipvs: properly update the overload flag on dest edit
ipvs: add totalconns for dest
netfilter: bridge: release template ct on non-IP path
netfilter: ipset: fix refcount race between list:set GC and swap
====================
Link: https://patch.msgid.link/20260810190621.894119-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
u32_walk() enumerates both struct tc_u_hnode and struct tc_u_knode
through the walker callback. u32_bind_class() unconditionally casts the
passed fh to tc_u_knode and accesses &n->res, so when fh is actually a
tc_u_hnode, which has no tcf_result member, this results in a
slab-out-of-bounds read of res->classid in tc_cls_bind_class().
The issue can be reproduced with the following commands:
tc qdisc add dev lo root handle 1: hfsc
tc class add dev lo parent 1: classid 1:1 hfsc sc rate 1000kbit
tc filter add dev lo parent 1:1 protocol ip prio 1 u32 match u32 0 0 flowid 1:1
tc class add dev lo parent 1: classid 1:2 hfsc sc rate 2000kbit
Fix this by skipping hash tables via the TC_U32_KEY(handle) check.
Fixes: 07d79fc7d9 ("net_sched: add reverse binding for tc class")
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/1786089038-36366-1-git-send-email-zhangchangzhong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Harshitha Ramamurthy says:
====================
gve: Bug fixes for header-split and PTP
This series contains 2 bug fixes for gve.
Patch 1 fixes an issue which causes TX timeouts due to HW detection of
an illegal descriptor. This happens when receiving header-only packets
with header split enabled - this produces an SKB with a zero-length
fragment.
Patch 2 prevents a kernel NULL pointer dereference by stubbing the PTP
adjfine callback.
====================
Link: https://patch.msgid.link/20260807224315.234152-1-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tcf_action_exec() handles TC_ACT_GOTO_CHAIN by first checking
rcu_access_pointer(a->goto_chain) and then calling
tcf_action_goto_chain_exec(), which does a second, independent
rcu_dereference_bh(a->goto_chain) read and immediately dereferences
chain->filter_chain. A concurrent tcf_action_set_ctrlact() (e.g. the gact
replace path) can clear a->goto_chain between the two reads, so the second
read returns NULL and tcf_action_goto_chain_exec() dereferences NULL.
Fix the race by doing a single rcu_dereference_bh() read of a->goto_chain
in tcf_action_exec(), checking it once for NULL, and passing the resulting
chain pointer into tcf_action_goto_chain_exec(). This turns the split
check/use into a single check/use on one value.
Fixes: ee3bbfe806 ("net/sched: let actions use RCU to access 'goto_chain'")
Reported-by: vega@nebusec.ai
Tested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Davide Caratti <dcaratti@redhat.com>
Link: https://patch.msgid.link/20260809090928.868186-1-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
syzbot reported a WARNING in __dev_queue_xmit() triggered via tpacket_snd():
skb_assert_len
WARNING: at include/linux/skbuff.h:2753 skb_assert_len
WARNING: at __dev_queue_xmit+0x21bc/0x4970 net/core/dev.c:4781
Call Trace:
<TASK>
dev_queue_xmit include/linux/netdevice.h:3448 [inline]
packet_xmit+0x243/0x310 net/packet/af_packet.c:276
tpacket_snd net/packet/af_packet.c:2907 [inline]
packet_sendmsg+0x28d6/0x4eb0 net/packet/af_packet.c:3134
When sending 0-byte packets via TPACKET ring buffer on devices with no
hard header (e.g. dev->hard_header_len == 0), tpacket_fill_skb()
populates an skb with skb->len == 0 and returns 0. tpacket_snd() then
forwards this empty skb to packet_xmit(), causing __dev_queue_xmit() to
hit skb_assert_len(skb).
Similar checks exist in packet_snd() via commit dc633700f0
("net/af_packet: check len when min_header_len equals to 0") and in
packet_sendmsg_spkt() via commit 6a341729fb ("af_packet: Don't send
zero-byte data in packet_sendmsg_spkt().").
Return -EINVAL in tpacket_fill_skb() when skb->len is zero to reject
zero-length packets in tpacket_snd().
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: syzbot+30b93b6845b19cc38581@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6a79e807.01d0871a.3a0d52.00ac.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://patch.msgid.link/20260810150447.1220864-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tipc_node_link_down() caches the link pointer before taking n->lock:
struct tipc_link *l = le->link; /* unlocked */
if (!l)
return;
tipc_node_write_lock(n);
if (!tipc_link_is_establishing(l)) { /* deref l */
...
tipc_link_reset(l); /* write into l */
if (delete) {
kfree(l);
le->link = NULL;
The delete=true caller frees that very object under n->lock, so the lock
does not protect the cached pointer against it:
- CPU A, delete=false: tipc_rcv() on TIPC_LINK_DOWN_EVT, or the link
supervision timer via tipc_node_timeout(), reads l unlocked and then
dereferences it under n->lock;
- CPU B, delete=true: netlink TIPC_NL_BEARER_DISABLE -> bearer_disable()
-> tipc_node_delete_links() -> tipc_node_link_down(n, bearer_id, true)
-> kfree(l).
The link is freed with plain kfree(), not kfree_rcu(), and for UDP bearers
disable_media() only schedules the asynchronous cleanup_bearer() work, so
its synchronize_net() runs after the links are already gone. An in-flight
CPU A that has read l therefore dereferences freed memory once B frees it:
a use-after-free read in tipc_link_is_establishing(), and a use-after-free
write via tipc_link_reset() on the establishing branch.
The following trace was captured on 7.2.0-rc5-00284-gaf39eb111ce6:
BUG: KASAN: slab-use-after-free in tipc_link_is_establishing (net/tipc/link.c:285)
Read of size 4 at addr ffff88802e2aa068 by task swapper/2/0
tipc_link_is_establishing (net/tipc/link.c:285)
tipc_node_link_down (net/tipc/node.c:1076)
tipc_node_timeout (net/tipc/node.c:843)
Allocated by task 9549:
tipc_link_create (net/tipc/link.c:490)
tipc_node_check_dest (net/tipc/node.c:1279)
tipc_disc_rcv (net/tipc/discover.c:252)
tipc_udp_recv (net/tipc/udp_media.c:389)
Freed by task 9549:
tipc_node_link_down (net/tipc/node.c:1084)
tipc_node_delete_links (net/tipc/node.c:1320)
bearer_disable (net/tipc/bearer.c:414)
__tipc_nl_bearer_disable (net/tipc/bearer.c:992)
Move the le->link read inside tipc_node_write_lock(), so it is serialised
against the kfree() in the delete path. A racing teardown now either has
not run yet, and we see a valid link, or has already run, and we see NULL.
Fixes: 73f646cec3 ("tipc: delay ESTABLISH state event when link is established")
Cc: stable@kernel.org
Reported-by: TencentOS Corvus AI <corvus@tencent.com>
Assisted-by: tencentos-corvus-ai:kimi-k3
Signed-off-by: Jun Yang <junvyyang@tencent.com>
Reviewed-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Link: https://patch.msgid.link/20260810102147.48191-1-juny24602@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Chuck Lever says:
====================
net/tls: Fail splice after a failed async decrypt
tls_sw_recvmsg() and tls_sw_read_sock() both read ctx->async_wait.err
once they hold the reader lock, so a record that failed
authentication fails the call. tls_sw_splice_read() has no such
check. sk_err does not stand in for one. The first reader to reach
sock_error() clears sk_err, while async_wait.err persists. A splice
therefore keeps delivering records on a connection the other two
readers have already refused.
Both patches come from a receive-path series for zero-length data
records. Jakub asked for them separately, since the rest of that
series is still under discussion.
Link to the original series:
https://patch.msgid.link/20260726-tls-follow-on-v1-0-99bf4cc1c729@kernel.org
====================
Link: https://patch.msgid.link/20260806-tls-splice-crypto-fix-v1-0-a2624005a286@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Nothing in this file splices a socket whose last decrypt failed, so
the check that fails tls_sw_splice_read() on a broken connection can
be removed without a test noticing. Such a splice hands the
application plaintext that recvmsg() and read_sock() already refuse
to return.
Extend the bad_auth pattern. Corrupt an authenticated record, confirm
recvmsg() reports EBADMSG, then splice the same socket and require
EBADMSG again. A synchronous decrypt fails again on the still-queued
record, so only an async decrypt reaches EBADMSG through the
recorded-failure check alone.
bad_auth builds the same corrupted record, so its construction moves
into a helper the two tests share.
Signed-off-by: Chuck Lever <cel@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20260806-tls-splice-crypto-fix-v1-2-a2624005a286@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When an async decrypt fails, tls_decrypt_done() records the error in
ctx->async_wait.err and calls tls_err_abort(), which stores it in
sk_err. tls_sw_recvmsg() and tls_sw_read_sock() each read
async_wait.err once they hold the reader lock and fail the call: a
record that did not authenticate breaks the connection.
tls_sw_splice_read() has no such check, and sk_err does not stand in
for one. tls_rx_rec_wait() tests sk_err only inside the loop it
skips whenever a record is already parsed, and the first reader to
reach sock_error() clears it, while async_wait.err persists. A
splice therefore keeps delivering records on a connection that
recvmsg() and read_sock() refuse to read.
Read async_wait.err in tls_sw_splice_read() as the other two readers
do.
Fixes: f314bfee81 ("tls: rx: return the already-copied data on crypto error")
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Chuck Lever <cel@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20260806-tls-splice-crypto-fix-v1-1-a2624005a286@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In non-MSI-X mode (such as legacy INTx or single MSI), wx->msix_entry is
not allocated or initialized. Calling NGBE_INTR_MISC(wx) dereferences
wx->msix_entry->entry, leading to a NULL pointer dereference crash.
This issue was introduced by fixing the IRQ vector when the number of
VFs is 7. Fix the issue by explicitly checking `pdev->msix_enabled` to
determine the correct vector index.
Additionally, as a side fix, set the interrupt mask to BIT(0) for the
non-MSI-X fallback. In MSI/INTx mode, the MISC and queue interrupts
share vector 0, and the WX_PX_MISC_IVAR register is only valid in the
MSI-X case. Thus, BIT(0) is the correct mask for the miscellaneous cause
when MSI-X is disabled.
Fixes: 4174c0c331 ("net: ngbe: specify IRQ vector when the number of VFs is 7")
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/B2693E9A8BFAD110+20260807062214.410838-1-jiawenwu@trustnetic.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Wei Fang says:
====================
Fix wrong transport_header when sending VLAN-tagged frames
When sending a VLAN-tagged frame via AF_PACKET or tap, calling
skb_set_network_header() before skb_probe_transport_header() causes
the flow dissector to misinterpret the inner protocol header as a
VLAN header. As a result, transport_header is never set and remains
at its uninitialized sentinel value (~0U).
Move skb_probe_transport_header() to before skb_set_network_header()
so the flow dissector sees network_header still pointing to the VLAN
header and can correctly identify the transport layer.
====================
Link: https://patch.msgid.link/20260807063405.688780-1-wei.fang@oss.nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In tap_get_user_xdp(), when processing a VLAN-tagged frame (e.g.
ETH_P_8021Q), skb_set_network_header() is called first to advance
network_header past the VLAN tag to the inner protocol header.
skb_probe_transport_header() is then called with skb->protocol still
set to ETH_P_8021Q, while nhoff (derived from skb_network_offset())
already points past the VLAN tag to the inner protocol header.
In __skb_flow_dissect(), proto is initialized to ETH_P_8021Q and nhoff
points past the VLAN tag. When the dissector hits case ETH_P_8021Q, it
reads a struct vlan_hdr at the current nhoff via __skb_header_pointer(),
but that offset contains the inner protocol header (e.g. an IP header).
The bytes are misinterpreted as a VLAN header, yielding a garbage
encapsulated EtherType that matches no known protocol. The dissector
returns false, so skb_probe_transport_header() never calls
skb_set_transport_header(), leaving transport_header at its uninitialized
sentinel value (~0U).
Move skb_set_network_header() to after skb_probe_transport_header(). At
the time skb_probe_transport_header() is called, network_header still
points to the VLAN header (offset ETH_HLEN), so nhoff is correct and the
flow dissector can parse the VLAN header, extract the inner EtherType,
and advance nhoff to the inner protocol header, allowing transport_header
to be set correctly.
Fixes: 8c76e77f90 ("tap: call skb_probe_transport_header after setting skb->dev")
Assisted-by: WChat:claude-opus-4-8
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260807063405.688780-3-wei.fang@oss.nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In packet_parse_headers(), when processing a VLAN-tagged frame,
skb_set_network_header() is called to advance network_header past the
VLAN tag to the inner protocol header. skb_probe_transport_header() is
then called with skb->protocol still set to the outer VLAN EtherType
(e.g. ETH_P_8021Q), while nhoff (derived from skb_network_offset())
already points past the VLAN tag to the inner protocol header.
In __skb_flow_dissect(), proto is initialized to ETH_P_8021Q and nhoff
points past the VLAN tag. When the dissector hits case ETH_P_8021Q, it
reads a struct vlan_hdr at nhoff via __skb_header_pointer(), but that
offset contains the inner protocol header (e.g. an IP header). The bytes
are misinterpreted as a VLAN header, yielding a garbage encapsulated
EtherType that matches no known protocol. The dissector returns false,
so skb_probe_transport_header() never calls skb_set_transport_header(),
leaving transport_header at its uninitialized sentinel value (~0U).
Move skb_probe_transport_header() to before skb_set_network_header(). At
the time skb_probe_transport_header() is called, network_header still
points to the VLAN header, so nhoff correctly points to the VLAN header.
The flow dissector can then parse the VLAN header, extract the inner
EtherType, and advance nhoff to the inner protocol header, allowing
transport_header to be set correctly.
Fixes: dfed913e8b ("net/af_packet: add VLAN support for AF_PACKET SOCK_RAW GSO")
Assisted-by: WChat:claude-opus-4-8
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260807063405.688780-2-wei.fang@oss.nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
vxlan_changelink() arms vxlan->age_timer whenever the requested ageing
interval differs from the configured one:
if (conf.age_interval != vxlan->cfg.age_interval)
mod_timer(&vxlan->age_timer, jiffies);
There is no netif_running() test, so the timer is armed even on a device
that was never brought up. The only synchronous cancel in the driver is
the timer_delete_sync() in vxlan_stop(), which is .ndo_stop.
netif_close_many() drops devices without IFF_UP before
__dev_close_many() runs, so that cancel is skipped for such a device.
vxlan_setup() sets dev->needs_free_netdev = true and age_timer is a
member of struct vxlan_dev, so free_netdev() releases the allocation the
timer lives in while it is still queued on a timer_base.
expire_timers() unlinks the entry before it loads timer->function, so
the timer core writes through the freed object's list pointers:
BUG: KASAN: slab-use-after-free in __run_timers+0x208/0x654
Write of size 8 at addr ffff00001adace68 by task true/192
__asan_store8+0x84/0xac
__run_timers+0x208/0x654
run_timer_softirq+0x154/0x18c
Allocated by task 189:
alloc_netdev_mqs+0x64/0x720
rtnl_create_link+0x4ac/0x520
rtnl_newlink+0x758/0xd00
Freed by task 191:
netdev_release+0x40/0x58
netdev_run_todo+0x4a4/0x8c0
rtnl_dellink+0x200/0x4e8
The rtnl operations involved are netns-scoped, so an unprivileged user
can perform them in a new user and network namespace.
Arming the timer on a down device never had an effect: vxlan_cleanup()
returns early on !netif_running(), and vxlan_open() arms the timer for
any non-zero interval once the device is brought up. Add the missing
test.
Discovered by XBOW, triaged by Baul Lee <baul.lee@xbow.com>
Fixes: 40051c4dca ("vxlan: Allow changing ageing time")
Cc: stable@vger.kernel.org
Signed-off-by: Baul Lee <baul.lee@xbow.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260809111829.78834-1-baul.lee@xbow.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
fib_nhc_update_mtu() walks the nexthop exception table under RTNL, but
RTNL does not serialize this walk with PMTU exception updates. The walk
uses rcu_dereference_protected() with a constant true condition without
holding fnhe_lock.
The following interleaving can therefore occur:
CPU 0 CPU 1
fib_nhc_update_mtu() update_or_create_fnhe()
load fnhe spin_lock_bh(&fnhe_lock)
fnhe_remove_oldest()
unlink fnhe
kfree_rcu(fnhe, rcu)
<quiescent state>
access fnhe after grace period
KASAN reported:
BUG: KASAN: slab-use-after-free in fib_nhc_update_mtu+0x3df/0x410
Read of size 8 at addr ffff888107d49000 by task poc/90
Call Trace:
fib_nhc_update_mtu+0x3df/0x410
fib_sync_mtu+0x7a/0xd0
fib_netdev_event+0x229/0x3f0
netif_set_mtu_ext+0x33a/0x570
dev_set_mtu+0x88/0x120
The same walk updates fnhe_pmtu and fnhe_mtu_locked. These fields form a
pair and other writers serialize them with fnhe_lock. RCU alone prevents
reclamation, but would still allow concurrent writers to leave a mixed
pair.
Walk the table under RCU and acquire fnhe_lock only while updating each
exception. RCU keeps the current entry alive while the short critical
section serializes its paired PMTU fields. This avoids holding the global
lock while scanning all 2048 buckets for every nexthop.
Fixes: af7d6cce53 ("net: ipv4: update fnhe_pmtu when first hop's MTU changes")
Cc: stable@vger.kernel.org
Suggested-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Chengfeng Ye <nicoyip.dev@gmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260807181710.1178747-1-nicoyip.dev@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
ntb_netdev_rx_handler() hands the received skb to the network stack
before allocating its replacement. If the allocation fails, nothing is
reposted. Every failure therefore takes one buffer out of the RX queue
while the interface remains up, and enough failures eventually stall
reception.
A retry path could refill the queue later, but ntb_netdev has none.
Allocate the replacement first instead. If that fails, drop the packet
and repost the same skb. This keeps the queue full and lets packet
delivery resume as soon as memory is available again.
Fixes: 548c237c0a ("net: Add support for NTB virtual ethernet device")
Cc: stable@vger.kernel.org
Signed-off-by: Koichiro Den <den@valinux.co.jp>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260806032537.3526498-1-den@valinux.co.jp
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add a tdc case covering the leak fixed by the previous patch.
The test attaches "action ct" to a clsact ingress chain and injects ten
IPv6 frames whose nexthdr says hop-by-hop but which carry nothing after
the 40-byte header, so ipv6_find_hdr() fails and
tcf_ct_ipv6_is_fragment() returns -EPROTO.
Before the fix act_ct returned TC_ACT_CONSUMED for these packets, so
tc_run() never reached its TC_ACT_SHOT arm and the clsact drop counter
stayed at zero while the skbs leaked. After the fix the packets are
dropped properly and the counter reflects them, which is what the test
matches on:
before: Sent 476 bytes 11 pkt (dropped 0, overlimits 0 requeues 0)
after: Sent 400 bytes 10 pkt (dropped 10, overlimits 0 requeues 0)
Signed-off-by: Hyunjung Ko <hj351016@gmail.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260806101235.809370-2-hj351016@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tcf_ct_handle_fragments() runs its header sanity checks before handing
anything to the defragmentation engine:
if (family == NFPROTO_IPV4)
err = tcf_ct_ipv4_is_fragment(skb, &frag);
else
err = tcf_ct_ipv6_is_fragment(skb, &frag);
if (err || !frag)
return err;
tcf_ct_ipv4_is_fragment() returns -EINVAL or -ENOMEM;
tcf_ct_ipv6_is_fragment() adds -EPROTO when ipv6_find_hdr() fails. None of
them frees or queues the skb, so on that path the caller still owns it.
tcf_ct_act() however funnels every non-zero return into the
ownership-transfer exit:
err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
if (err)
goto out_frag;
...
out_frag:
if (err != -EINPROGRESS)
tcf_action_inc_drop_qstats(&c->common);
return TC_ACT_CONSUMED;
TC_ACT_CONSUMED means the action took ownership of the skb, so no caller
frees it - sch_handle_ingress(), sch_handle_egress() and
tcf_qevent_handle() all deliberately skip the free for that verdict. The
skb is therefore orphaned: one sk_buff plus its data buffer is leaked per
malformed packet, unbounded. Note the drop counter is already incremented
for these errors, so the statistics claim a drop that never happens.
Three different ownership states reach out_frag: today - the skb may be
queued by the defrag engine (-EINPROGRESS), already freed by
nf_ct_handle_fragments(), or still owned by us. Tell the caller which of
those it is, and free the packet ourselves in the last case, which
restores the TC_ACT_SHOT behaviour that predated the Fixes: commit.
Reproduced on v7.2-rc6 with a 54-byte frame carrying a 40-byte IPv6
header with nexthdr = 0 (hop-by-hop) and nothing after it, on a
clsact ingress chain with "action ct". kmemleak reports one leaked
232-byte skbuff_head_cache object plus its 704-byte data buffer per
packet; with this patch it reports none.
Fixes: 3f14b377d0 ("net/sched: act_ct: fix skb leak and crash on ooo frags")
Cc: stable@vger.kernel.org # v6.8+
Signed-off-by: Hyunjung Ko <hj351016@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260806101235.809370-1-hj351016@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In rtlgen_write_mmd(), the MDIO_AN_EEE_ADV case swaps the arguments to
rtlgen_write_vend2(): it passes the MMD register number as the OCP address
and the OCP address constant as the value. The caller's value is discarded
and the write lands on the wrong register, so the EEE advertisement cannot
be configured on the affected PHYs.
Mirror rtlgen_read_mmd() and write the value to RTL_MDIO_AN_EEE_ADV.
Fixes: da681ed73f ("net: phy: realtek: improve mmd register access for internal PHY's")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Nicolai Buchwitz <nb@tipi-net.de>
Link: https://patch.msgid.link/20260806134716.3511821-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
On cross-region connections we observed delayed ACKs suddenly turning
into immediate ACKs plus a TCP_MAX_QUICKACKS burst, as if the
connection had just received its first data segment.
Commit 95b9a87c6a ("tcp: record last received ipv6 flowlabel")
squeezed icsk_ack.ato into 8 bits, sized for TCP_DELACK_MAX. But both
writers still bound ato by icsk_rto, which can be well above 255
jiffies, so the bitfield assignment silently wraps mod 256: repeated
delack timer misses double ato up to icsk_rto, storing 320 as 64 and
256 as 0, and ato == 0 is the "first data packet" sentinel in
tcp_event_data_recv().
Clamp both writers to TCP_DELACK_MAX, which the static_assert already
guarantees to fit and tcp_send_delayed_ack() effectively caps ato at
anyway.
Fixes: 95b9a87c6a ("tcp: record last received ipv6 flowlabel")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20260807014437.36687-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tcf_action_check_ctrlact() range checks the primary control action:
if (!opcode)
ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0;
TC_ACT_VALUE_MAX is TC_ACT_TRAP, so kernel-internal verdicts above it
cannot be set that way. But act_gact and act_police each carry a second,
independent control action supplied by user space that never reaches that
helper - TCA_GACT_PROB.paction and TCA_POLICE_RESULT. Both only reject
TC_ACT_GOTO_CHAIN, so any other value is stored verbatim and returned
verbatim from the action.
In particular user space can store TC_ACT_CONSUMED, which is
TC_ACT_VALUE_MAX + 1 and is deliberately not part of the UAPI value
range. That verdict tells every caller the action took ownership of the
skb, so nobody frees it: sch_handle_ingress(), sch_handle_egress() and
tcf_qevent_handle() all deliberately skip the free for it. The result is
one leaked sk_buff plus its data buffer per packet traversing the filter,
unbounded, for all traffic on the chain including kernel-generated
packets.
Both are trivially deterministic. act_gact clamps tcfg_pval to >= 1, so
with pval = 1 gact_determ() returns the fallback for every packet.
act_police has no mandatory rate, so rate = 0 leaves tcfp_mtu = ~0 and
tcf_police_mtu_check() always passes.
TC_ACT_CONSUMED was added by commit 720f22fed8 ("net: sched: refactor
reinsert action"), after both goto-chain guards were written:
commit 9469f375ab ("net/sched: act_gact: disallow 'goto chain' on
fallback control action") and
commit c08f5ed5d6 ("net/sched: act_police: disallow 'goto chain' on
fallback control action"). Neither guard was widened when the new
verdict appeared.
Factor the existing range test out of tcf_action_check_ctrlact() as
tcf_action_valid() and apply it to both fallbacks. The helper cannot call
tcf_action_check_ctrlact() directly because that also allocates a
goto_chain, which is exactly what these two sites must not do.
Reproduced on v7.2-rc6: kmemleak reports one leaked 232-byte
skbuff_head_cache object plus its 704-byte data buffer per packet. With
this patch both configurations are rejected with -EINVAL and kmemleak
reports none.
Fixes: 720f22fed8 ("net: sched: refactor reinsert action")
Cc: stable@vger.kernel.org # v5.3+
Signed-off-by: Hyunjung Ko <hj351016@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Tested-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260806101252.809593-1-hj351016@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
veth_poll() derives the index of the peer TX queue to wake from
rq->xdp_rxq.queue_index. That field is only initialized by
xdp_rxq_info_reg() in veth_enable_xdp_range(), which runs only when an
XDP program is attached. On the plain GRO/NAPI path
(veth_napi_enable_range()) xdp_rxq_info_reg() is never called, so
queue_index stays 0 for every queue, as priv->rq is zero-allocated.
So in a multi-queue setup with GRO enabled and no XDP program attached,
every NAPI instance looks at the peer's TX queue 0. If veth_xmit() stops
peer TX queue 1 because the ptr_ring is full (NETDEV_TX_BUSY), nothing
ever wakes it again: the poller draining queue 1 wakes queue 0 instead.
veth implements no ndo_tx_timeout, so the netdev watchdog does not kick
in either, and the queue stays stopped indefinitely.
Derive the index from the position of the rq within priv->rq instead,
which is correct regardless of whether XDP was ever enabled.
Scripts to reproduce the stall are available at
https://github.com/netoptimizer/veth-backpressure-performance-testing
Fixes: dc82a33297 ("veth: apply qdisc backpressure on full ptr_ring to reduce TX drops")
Signed-off-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Tested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://patch.msgid.link/20260806-veth-fix-poll-queue-idx-v1-1-c5357fb7573d@tu-berlin.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdev_queue_get_dma_dev() uses "compat" locking assert which wants
either the rtnl_lock or netdev instance lock. This is not right,
the callers are taking the instance lock unconditionally. All entry
points for queue config are purely instance locked.
In other words the callers use netdev_get_by_index_lock(), not
netdev_get_by_index_lock_ops_compat(). All the state we will
access is effectively instance lock protected (it's const for
devices which are not ops-locked).
Update the assert to avoid false positive warnings.
Cc: stable@vger.kernel.org
Fixes: b6c5f9454e ("io_uring/zcrx: call netdev_queue_get_dma_dev() under instance lock")
Reported-by: syzbot+a78926bdac2adb52dc0e@syzkaller.appspotmail.com
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/20260806225627.3998672-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
macvlan devices inherit hard_header_len from lowerdev during macvlan_init(),
but leave needed_headroom and needed_tailroom set to 0.
When the underlying lowerdev requires extra headroom or tailroom for
headers/trailers (e.g. macsec, ipsec, wireguard, tunnels, or veth with rx
headroom), upper layers calculating packet headroom and tailroom fail to
reserve sufficient space.
This can result in reallocation overhead, skb headroom underflows, or KASAN
slab-use-after-free crashes when dev_hard_header() / macvlan_hard_header()
prepends header data or when lower devices append tailroom.
Fix this by:
1. Inheriting needed_headroom and needed_tailroom from lowerdev in macvlan_init().
2. Propagating needed_headroom and needed_tailroom updates to attached macvlans
in macvlan_device_event() when receiving NETDEV_FEAT_CHANGE events.
Fixes: b863ceb7dd ("[NET]: Add macvlan driver")
Reported-by: Tangxin Xie <xietangxin@h-partners.com>
Closes: https://lore.kernel.org/netdev/CANn89i+1EW-sFNK8xoq98gMbPCeLS7e=+rs9gHfLg5Wj+4x0sw@mail.gmail.com/T/#m16adf0ff972cbfd8066c3a8e656e75eaeb12d021
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Hangbin Liu <liuhangbin@kylinos.cn>
Link: https://patch.msgid.link/20260806141938.287660-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jakub Kicinski says:
====================
eth: bnxt: fix IRQ notifier bugs
I was trying to make bnxt preserve IRQ mappings across reconfiguration.
While hacking on that I noticed 2 bugs in the notifiers that should
probably be fixed before development work.
First one is simple - TPH recofig makes aARFs not work. There can only
be one notifier per IRQ and TPH "steals" the callback from the rmap
updates. Fix by patches 1 and 2.
Second one is a deadlock between the affinity notifier and reconfig.
This one is a bit more involved (patch 3 and 4).
Unfortunately, I can't really verify the problem or test the fix.
I managed to get my hands on a system with an AMD Venice CPU which
is supposed to support TPH, but the ACPI is missing some bits to
actually advertise it. pcie_tph_get_cpu_st() returns -EINVAL.
====================
Link: https://patch.msgid.link/20260803193135.2030368-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Unregistering IRQ affinity notifiers waits for the callback synchronously.
bnxt takes the netdev instance lock in the notifier (to restart the queue)
and cancels the work under the same lock. This may obviously deadlock.
Move the restart to the async service task. The queue restart isn't
super time sensitive. Store the new TPH tag, schedule the task.
Safely canceling the service task is already ironed out.
In bnxt_request_irq() the order of registering notifier, affinity and
initial TPH programming has to be inverted. I think it was racy
previously since user may trigger an update as soon as notifier
is installed.
There's a small known gap - if pcie_tph_get_cpu_st() fails at init
and the target tag is 0 we may miss programming the entry.
This does not seem worth fixing, the code has skip-on-failure
all over the place, anyway.
Fixes: c214410c47 ("bnxt_en: Add TPH support in BNXT driver")
Tested-by: Vishvambar Panth S <vishvambar.panth-s@broadcom.com>
Link: https://patch.msgid.link/20260803193135.2030368-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The TPH support must have broken aRFS in bnxt. IRQ can only have one
notifier, so installing the TPH notifier is overriding the one implicitly
installed by irq_cpu_rmap_add().
Make sure we call cpu_rmap_update() from the TPH notifier.
We need to be careful with the ordering and not free the rmap
until we unregistered the notifier. Note that moving the rmap
freeing after the early return in bnxt_free_irq() is fine -
there's no path that could leave rmap with irq_tbl being NULL.
Fixes: c214410c47 ("bnxt_en: Add TPH support in BNXT driver")
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260803193135.2030368-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
For bitmap this change makes no difference, because destructors are
called synchronously.
List type however calls them via call_rcu() so accounting decrement can
happen after list_set_flush() set ext_size to 0.
'set->elements = 0' can be removed for the same reason in the list type
case, it calls 'set->elements--' for each element.
Fixes: 9e41f26a50 ("netfilter: ipset: Count non-static extension memory for userspace")
Suggested-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
nf_flow_table_iterate() only treats original-direction tuple nodes as
owning entries. Publishing the original node first lets GC observe and
free a flow while flow_offload_add() is still inserting the reply node.
Publish the reply node first and the original node last so GC never
sees a partially installed flow.
KASAN can trigger slab-use-after-free read and write reports in the
flowtable/rhashtable path (rht_deferred_worker, jhash, flow_offload_del,
flow_offload_lookup, etc.).
Fixes: ac2a66665e ("netfilter: add generic flow table infrastructure")
Signed-off-by: Jérémy Jean <Jeremy.Jean@oss.cyber.gouv.fr>
Assisted-by: Codex:gpt-5
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
In nft_flow_rule_offload_abort(), WARN_ON_ONCE(err) is triggered on every
error during rollback, including -ENOMEM. Memory allocation failures are
expected under low-memory conditions and do not indicate a kernel bug.
Trace for example:
nft_flow_offload_chain() // FLOW_BLOCK_BIND
nft_flow_block_chain()
nft_chain_offload_cmd()
nft_block_offload_cmd()
->ndo_setup_tc()
nsim_setup_tc()
flow_block_cb_setup_simple()
flow_block_cb_alloc() // fails to -ENOMEM
The warning was reproduced on the 5.10 stable kernel under memory pressure
via fault injection, but the underlying bug exists in mainline as well,
as demonstrated by the ENOMEM trace above. The following splat was
triggered during nf_tables transaction processing:
WARNING: CPU: 0 PID: 8567 at net/netfilter/nf_tables_offload.c:532 nft_flow_rule_offload_abort net/netfilter/nf_tables_offload.c:532 [inline]
WARNING: CPU: 0 PID: 8567 at net/netfilter/nf_tables_offload.c:532 nft_flow_rule_offload_commit+0x971/0xcd0 net/netfilter/nf_tables_offload.c:591
Modules linked in:
CPU: 0 PID: 8567 Comm: syz-executor.0 Not tainted 5.10.260-syzkaller #0
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
RIP: 0010:nft_flow_rule_offload_abort net/netfilter/nf_tables_offload.c:532 [inline]
RIP: 0010:nft_flow_rule_offload_commit+0x971/0xcd0 net/netfilter/nf_tables_offload.c:591
Call Trace:
nf_tables_commit+0x3bd/0x4bd0 net/netfilter/nf_tables_api.c:8604
nfnetlink_rcv_batch+0xb1e/0x1f20 net/netfilter/nfnetlink.c:509
nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:579 [inline]
nfnetlink_rcv+0x3b3/0x420 net/netfilter/nfnetlink.c:597
netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
netlink_unicast+0x6cd/0xa00 net/netfilter/af_netlink.c:1340
netlink_sendmsg+0x906/0xe10 net/netfilter/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:651 [inline]
__sock_sendmsg+0x155/0x190 net/socket.c:663
____sys_sendmsg+0x705/0x870 net/socket.c:2379
___sys_sendmsg+0x100/0x170 net/socket.c:2433
__sys_sendmsg+0xe9/0x1c0 net/socket.c:2462
do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46
entry_SYSCALL_64_after_hwframe+0x67/0xd1
Change the condition to WARN_ON_ONCE(err && err != -ENOMEM) so that
warnings are only emitted for unexpected errors. This aligns with the
common kernel practice of not warning on -ENOMEM.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
Fixes: 63b48c73ff ("netfilter: nf_tables_offload: undo updates if transaction fails")
Signed-off-by: Alexey Velichayshiy <a.velichayshiy@ispras.ru>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
While the outer IP header is already pulled into the skb head,
we must be careful and revalidate the embedded headers after
reading them from the skb frags to prevent out-of-bounds
access.
One such place reported by Sashiko is ip_vs_nat_icmp() where
local process can change the ihl field and after
skb_ensure_writable() we can see larger value which is a
problem for the ip_send_check(cih) calls.
Add check to drop the packet if the ihl field is changed.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Link: https://sashiko.dev/#/patchset/20260730183506.87473-1-ja%40ssi.bg
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
ip_vs_in_icmp() rebases an skb from the outer ICMP packet to the
quoted original request before passing it to icmp_send(). However,
IPCB(skb)->opt still describes the outer IPv4 header.
A timestamp option in the outer header can therefore leave an offset
that points into the quoted transport header after the rebase.
__ip_options_echo() treats a byte at that stale location as the option
length and copies it into the fixed-size option storage on the
__icmp_send() stack, causing a stack out-of-bounds write.
Clear the stale option metadata after resetting the network header.
Keep the remaining control block fields, including the ingress
interface used by the ICMP response path.
Fixes: f2edb9f770 ("ipvs: implement passive PMTUD for IPIP packets")
Cc: stable@vger.kernel.org
Assisted-by: Codex:gpt-5.6-sol Codex:gpt-5.5-cyber
Signed-off-by: Kyle Zeng <kylebot@openai.com>
Co-developed-by: David Lee <david.lee@trailofbits.com>
Signed-off-by: David Lee <david.lee@trailofbits.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
sashiko reports: "nfnl_log_net_exit() calls nf_log_unset(), which
clears the logger pointer without an RCU grace period. Immediately after,
ops_free_list() frees the per-net state while concurrent packets might
still be executing nf_log_packet() under rcu_read_lock()."
Clear the pointer via .pre_exit to make sure rcu readers have completed
before pernet storage is free'd. The change in nf_log_syslog.c is only
done for consistency: it doesn't use pernet data.
Link: https://sashiko.dev/#/patchset/20260731151806.849724-1-pablo%40netfilter.org
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
TCP and SCTP conntrack paths can emit invalid-packet logs while ct->lock
is still held.
When invalid logging is routed to nfnetlink_log and conntrack export is
enabled, the log path can re-enter conntrack netlink glue and dump the
same conntrack again. Protocol attribute dumping may take ct->lock, so
logging while holding that lock can deadlock.
Defer the TCP invalid logs by storing only the minimal log context while
ct->lock is held and emitting the log after unlocking. Also make the TCP
timeout-lowering invalid path return whether a log is needed, then emit
that log after unlocking.
Do the same for the SCTP invalid state-transition log that can be reached
while ct->lock is held.
Add a lockdep assertion to nf_ct_l4proto_log_invalid() so future callers
that log invalid conntracks while holding ct->lock are caught outside TCP
and SCTP as well.
Fixes: 628d694344 ("netfilter: conntrack: reduce timeout when receiving out-of-window fin or rst")
Fixes: d9a6f0d0df ("netfilter: conntrack: prepare tcp_in_window for ternary return value")
Fixes: f71cb8f45d ("netfilter: conntrack: sctp: use nf log infrastructure for invalid packets")
Cc: stable@vger.kernel.org
Reported-by: Vega <vega@nebusec.ai>
Assisted-by: Codex:gpt-5.4
Signed-off-by: Zihan Xi <zihanx@nebusec.ai>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
IPVS configuration paths update destination availability while connection
accounting updates destination overload state. The two independent states
share dest->flags, so their read-modify-write updates can race and lose one
another.
Keep OVERLOAD in flags, where the preceding patch serializes its updates
with dst_lock, and move AVAILABLE to cflags. This keeps configuration-
controlled availability out of the scheduler hot cacheline until a
scheduler needs to check it. It also prevents availability updates from
clobbering overload state.
The destination status bits are not exposed through the IPVS sockopt or
netlink interfaces, so keep their definitions in the internal IPVS header.
Readers can still observe stale destination state; this does not provide a
cross-field snapshot.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
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>
Link: https://lore.kernel.org/all/8913381c-1e02-35c7-0ec4-61de5a12fd35@ssi.bg/
Assisted-by: Claude-Code:GLM-5.2
Suggested-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The upper/lower connection thresholds for dest can be changed,
so use ip_vs_dest_update_overload() to properly update the
dest overload flag.
The thresholds were not limited, fit them in the 0 .. INT_MAX
range as already done in ipvsadm.
As the thresholds are also read when connections are created
and expired, use WRITE_ONCE/READ_ONCE to access them.
As the lower threshold is optional, use (u - (u >> 2)) to
calculate the 75% default value based on the upper threshold
by preserving the integer rounding, as suggested by Yizhou Zhao.
Trigger flag update when totalconns reaches one of the
thresholds and use dst_lock to serialize the updating.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Replace the inactconns dest counter with totalconns, now
inactconns can be obtained from totalconns - activeconns.
This reduces the atomic inc/dec ops for TCP/SCTP from
6 to 4 if the connection is established and then closed.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
A bridge nftables ct zone set rule can attach a conntrack template to
an skb before nf_ct_bridge_pre() sees it. For non-IPv4 and non-IPv6
EtherTypes, nf_ct_bridge_pre() currently overwrites skb->_nfct with
IP_CT_UNTRACKED without releasing the existing template reference.
That makes the per-cpu template, and any temporary templates allocated
for concurrent use, unreachable and leaks memory until the host runs out
of slab.
Reset the skb conntrack state before marking the frame untracked so the
existing template reference is dropped on the non-IP path.
Fixes: 3c171f496e ("netfilter: bridge: add connection tracking system")
Cc: stable@vger.kernel.org
Reported-by: Vega <vega@nebusec.ai>
Signed-off-by: Zhiling Zou <zhilinz@nebusec.ai>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
__ip_set_put_byindex() resolved the index to a set pointer under RCU,
then took ip_set_ref_lock in __ip_set_put() to decrement set->ref.
ip_set_swap() holds that same lock while swapping both the ip_set_list
slots and the two sets' ref counters, so it can interleave between the
dereference and the lock acquisition, leaving the caller to decrement a
set whose reference already moved to the other index and hit
BUG_ON(set->ref == 0). list_set_gc() reaches this from timer softirq,
which the nfnl mutex does not serialize against swap: an expiring
list:set member calls list_set_del() -> ip_set_put_byindex() while
IPSET_CMD_SWAP runs on the referenced sets.
Resolve the index and decrement under ip_set_ref_lock, as ip_set_swap()
already does, keeping the refcount tied to the index rather than to a
stale set pointer.
kernel BUG at net/netfilter/ipset/ip_set_core.c:685!
Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
RIP: 0010:ip_set_put_byindex (net/netfilter/ipset/ip_set_core.c:870)
Call Trace:
<IRQ>
list_set_del (net/netfilter/ipset/ip_set_list_set.c:159)
set_cleanup_entries (net/netfilter/ipset/ip_set_list_set.c:181)
list_set_gc (net/netfilter/ipset/ip_set_list_set.c:578)
call_timer_fn (kernel/time/timer.c:1748)
__run_timers (kernel/time/timer.c:1799 kernel/time/timer.c:2374)
run_timer_softirq (kernel/time/timer.c:2405)
</IRQ>
Kernel panic - not syncing: Fatal exception in interrupt
Fixes: 9076aea765 ("netfilter: ipset: Increase the number of maximal sets automatically")
Reported-by: AutonomousCodeSecurity@microsoft.com
Signed-off-by: Xiang Mei (Microsoft) <xmei5@asu.edu>
Acked-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Sun Jian says:
====================
fix skb length accounting after XDP frag adjustment
This series fixes skb length accounting after an XDP program adjusts its
fragment area, in both the generic XDP path (net/core/dev.c) and the veth
native path (drivers/net/veth.c). When the fragment area is resized,
skb->len and skb->data_len can go out of sync, and in the reproduced UDP
receive path this leaked skb_shared_info contents (including a kernel
pointer) to userspace while truncating real payload.
====================
Link: https://patch.msgid.link/20260804054040.613675-1-sun.jian.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
veth exposes non-linear skb fragments through an xdp_buff. If an XDP
program adjusts the fragment area, veth_xdp_rcv_skb() copies
xdp_frags_size back to skb->data_len but leaves skb->len containing the
old fragment contribution.
After a fragment shrink, this makes skb_headlen() larger than the actual
linear area. In the reproduced UDP receive path, __skb_datagram_iter()
copied 1024 bytes past the actual linear tail to userspace, starting at
struct skb_shared_info. The copied bytes included the affected skb's
nr_frags, xdp_frags_size, and a kernel pointer from
skb_shinfo(skb)->frags[0]. Real packet data was displaced by the same
amount and truncated at the end.
Subtract the old data_len before replacing it and add the new data_len
afterwards, keeping skb->len and skb->data_len synchronized.
Additionally, bpf_xdp_pull_data() can advance data_end while leaving
frags present. The skb is then still non-linear, so the old
__skb_put(skb, off) triggers SKB_LINEAR_ASSERT().
Use skb_set_tail_pointer() and update skb->len explicitly instead,
following bpf_prog_run_generic_xdp(). Unlike __skb_put(),
skb_set_tail_pointer() does not require a linear skb.
A 60000-byte UDP datagram on a veth pair with MTU 64000 was shortened by
1024 bytes from its fragment area. Before the fix, all 10 runs produced
corrupted payloads. After the fix, all 10 runs matched the expected
payload exactly. A forced-tailroom reproducer also exercises
bpf_xdp_pull_data() with frags still present; the old code triggers
SKB_LINEAR_ASSERT(), while this fix passes 10/10 runs.
Fixes: 718a18a0c8 ("veth: Rework veth_xdp_rcv_skb in order to accept non-linear skb")
Cc: stable@vger.kernel.org
Reported-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://lore.kernel.org/bpf/80687d9c-9c27-494c-b3f2-efd0230b1895@gmail.com/
Suggested-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
Link: https://patch.msgid.link/20260804054040.613675-3-sun.jian.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
