The AccECN option ceb/cep heuristic algorithm is from AccECN spec
Appendix A.2.2 to mitigate against false ACE field overflows. Armed
with ceb delta from option, delivered bytes, and delivered packets it
is possible to estimate how many times ACE field wrapped.
This calculation is necessary only if more than one wrap is possible.
Without SACK, delivered bytes and packets are not always trustworthy in
which case TCP falls back to the simpler no-or-all wraps ceb algorithm.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-10-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
AccECN option may fail in various way, handle these:
- Attempt to negotiate the use of AccECN on the 1st retransmitted SYN
- From the 2nd retransmitted SYN, stop AccECN negotiation
- Remove option from SYN/ACK rexmits to handle blackholes
- If no option arrives in SYN/ACK, assume Option is not usable
- If an option arrives later, re-enabled
- If option is zeroed, disable AccECN option processing
This patch use existing padding bits in tcp_request_sock and
holes in tcp_sock without increasing the size.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-9-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Instead of sending the option in every ACK, limit sending to
those ACKs where the option is necessary:
- Handshake
- "Change-triggered ACK" + the ACK following it. The
2nd ACK is necessary to unambiguously indicate which
of the ECN byte counters in increasing. The first
ACK has two counters increasing due to the ecnfield
edge.
- ACKs with CE to allow CEP delta validations to take
advantage of the option.
- Force option to be sent every at least once per 2^22
bytes. The check is done using the bit edges of the
byte counters (avoids need for extra variables).
- AccECN option beacon to send a few times per RTT even if
nothing in the ECN state requires that. The default is 3
times per RTT, and its period can be set via
sysctl_tcp_ecn_option_beacon.
Below are the pahole outcomes before and after this patch,
in which the group size of tcp_sock_write_tx is increased
from 89 to 97 due to the new u64 accecn_opt_tstamp member:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u64 tcp_wstamp_ns; /* 2488 8 */
struct list_head tsorted_sent_queue; /* 2496 16 */
[...]
__cacheline_group_end__tcp_sock_write_tx[0]; /* 2521 0 */
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2521 0 */
u8 nonagle:4; /* 2521: 0 1 */
u8 rate_app_limited:1; /* 2521: 4 1 */
/* XXX 3 bits hole, try to pack */
/* Force alignment to the next boundary: */
u8 :0;
u8 received_ce_pending:4;/* 2522: 0 1 */
u8 unused2:4; /* 2522: 4 1 */
u8 accecn_minlen:2; /* 2523: 0 1 */
u8 est_ecnfield:2; /* 2523: 2 1 */
u8 unused3:4; /* 2523: 4 1 */
[...]
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2628 0 */
[...]
/* size: 3200, cachelines: 50, members: 171 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u64 tcp_wstamp_ns; /* 2488 8 */
u64 accecn_opt_tstamp; /* 2596 8 */
struct list_head tsorted_sent_queue; /* 2504 16 */
[...]
__cacheline_group_end__tcp_sock_write_tx[0]; /* 2529 0 */
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2529 0 */
u8 nonagle:4; /* 2529: 0 1 */
u8 rate_app_limited:1; /* 2529: 4 1 */
/* XXX 3 bits hole, try to pack */
/* Force alignment to the next boundary: */
u8 :0;
u8 received_ce_pending:4;/* 2530: 0 1 */
u8 unused2:4; /* 2530: 4 1 */
u8 accecn_minlen:2; /* 2531: 0 1 */
u8 est_ecnfield:2; /* 2531: 2 1 */
u8 accecn_opt_demand:2; /* 2531: 4 1 */
u8 prev_ecnfield:2; /* 2531: 6 1 */
[...]
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2636 0 */
[...]
/* size: 3200, cachelines: 50, members: 173 */
}
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Co-developed-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-8-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The Accurate ECN allows echoing back the sum of bytes for
each IP ECN field value in the received packets using
AccECN option. This change implements AccECN option tx & rx
side processing without option send control related features
that are added by a later change.
Based on specification:
https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
(Some features of the spec will be added in the later changes
rather than in this one).
A full-length AccECN option is always attempted but if it does
not fit, the minimum length is selected based on the counters
that have changed since the last update. The AccECN option
(with 24-bit fields) often ends in odd sizes so the option
write code tries to take advantage of some nop used to pad
the other TCP options.
The delivered_ecn_bytes pairs with received_ecn_bytes similar
to how delivered_ce pairs with received_ce. In contrast to
ACE field, however, the option is not always available to update
delivered_ecn_bytes. For ACK w/o AccECN option, the delivered
bytes calculated based on the cumulative ACK+SACK information
are assigned to one of the counters using an estimation
heuristic to select the most likely ECN byte counter. Any
estimation error is corrected when the next AccECN option
arrives. It may occur that the heuristic gets too confused
when there are enough different byte counter deltas between
ACKs with the AccECN option in which case the heuristic just
gives up on updating the counters for a while.
tcp_ecn_option sysctl can be used to select option sending
mode for AccECN: TCP_ECN_OPTION_DISABLED, TCP_ECN_OPTION_MINIMUM,
and TCP_ECN_OPTION_FULL.
This patch increases the size of tcp_info struct, as there is
no existing holes for new u32 variables. Below are the pahole
outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_info {
[...]
__u32 tcpi_total_rto_time; /* 244 4 */
/* size: 248, cachelines: 4, members: 61 */
}
[AFTER THIS PATCH]
struct tcp_info {
[...]
__u32 tcpi_total_rto_time; /* 244 4 */
__u32 tcpi_received_ce; /* 248 4 */
__u32 tcpi_delivered_e1_bytes; /* 252 4 */
__u32 tcpi_delivered_e0_bytes; /* 256 4 */
__u32 tcpi_delivered_ce_bytes; /* 260 4 */
__u32 tcpi_received_e1_bytes; /* 264 4 */
__u32 tcpi_received_e0_bytes; /* 268 4 */
__u32 tcpi_received_ce_bytes; /* 272 4 */
/* size: 280, cachelines: 5, members: 68 */
}
This patch uses the existing 1-byte holes in the tcp_sock_write_txrx
group for new u8 members, but adds a 4-byte hole in tcp_sock_write_rx
group after the new u32 delivered_ecn_bytes[3] member. Therefore, the
group size of tcp_sock_write_rx is increased from 96 to 112. Below
are the pahole outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u8 received_ce_pending:4; /* 2522: 0 1 */
u8 unused2:4; /* 2522: 4 1 */
/* XXX 1 byte hole, try to pack */
[...]
u32 rcv_rtt_last_tsecr; /* 2668 4 */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2728 0 */
[...]
/* size: 3200, cachelines: 50, members: 167 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u8 received_ce_pending:4;/* 2522: 0 1 */
u8 unused2:4; /* 2522: 4 1 */
u8 accecn_minlen:2; /* 2523: 0 1 */
u8 est_ecnfield:2; /* 2523: 2 1 */
u8 unused3:4; /* 2523: 4 1 */
[...]
u32 rcv_rtt_last_tsecr; /* 2668 4 */
u32 delivered_ecn_bytes[3];/* 2672 12 */
/* XXX 4 bytes hole, try to pack */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2744 0 */
[...]
/* size: 3200, cachelines: 50, members: 171 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-7-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
These three byte counters track IP ECN field payload byte sums for
all arriving (acceptable) packets for ECT0, ECT1, and CE. The
AccECN option (added by a later patch in the series) echoes these
counters back to sender side; therefore, it is placed within the
group of tcp_sock_write_txrx.
Below are the pahole outcomes before and after this patch, in which
the group size of tcp_sock_write_txrx is increased from 95 + 4 to
107 + 4 and an extra 4-byte hole is created but will be exploited
in later patches:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ce; /* 2576 4 */
u32 received_ce; /* 2580 4 */
u32 app_limited; /* 2584 4 */
u32 rcv_wnd; /* 2588 4 */
struct tcp_options_received rx_opt; /* 2592 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2616 0 */
[...]
/* size: 3200, cachelines: 50, members: 166 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ce; /* 2576 4 */
u32 received_ce; /* 2580 4 */
u32 received_ecn_bytes[3];/* 2584 12 */
u32 app_limited; /* 2596 4 */
u32 rcv_wnd; /* 2600 4 */
struct tcp_options_received rx_opt; /* 2604 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2628 0 */
/* XXX 4 bytes hole, try to pack */
[...]
/* size: 3200, cachelines: 50, members: 167 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-4-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Accurate ECN negotiation parts based on the specification:
https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
Accurate ECN is negotiated using ECE, CWR and AE flags in the
TCP header. TCP falls back into using RFC3168 ECN if one of the
ends supports only RFC3168-style ECN.
The AccECN negotiation includes reflecting IP ECN field value
seen in SYN and SYNACK back using the same bits as negotiation
to allow responding to SYN CE marks and to detect ECN field
mangling. CE marks should not occur currently because SYN=1
segments are sent with Non-ECT in IP ECN field (but proposal
exists to remove this restriction).
Reflecting SYN IP ECN field in SYNACK is relatively simple.
Reflecting SYNACK IP ECN field in the final/third ACK of
the handshake is more challenging. Linux TCP code is not well
prepared for using the final/third ACK a signalling channel
which makes things somewhat complicated here.
tcp_ecn sysctl can be used to select the highest ECN variant
(Accurate ECN, ECN, No ECN) that is attemped to be negotiated and
requested for incoming connection and outgoing connection:
TCP_ECN_IN_NOECN_OUT_NOECN, TCP_ECN_IN_ECN_OUT_ECN,
TCP_ECN_IN_ECN_OUT_NOECN, TCP_ECN_IN_ACCECN_OUT_ACCECN,
TCP_ECN_IN_ACCECN_OUT_ECN, and TCP_ECN_IN_ACCECN_OUT_NOECN.
After this patch, the size of tcp_request_sock remains unchanged
and no new holes are added. Below are the pahole outcomes before
and after this patch:
[BEFORE THIS PATCH]
struct tcp_request_sock {
[...]
u32 rcv_nxt; /* 352 4 */
u8 syn_tos; /* 356 1 */
/* size: 360, cachelines: 6, members: 16 */
}
[AFTER THIS PATCH]
struct tcp_request_sock {
[...]
u32 rcv_nxt; /* 352 4 */
u8 syn_tos; /* 356 1 */
bool accecn_ok; /* 357 1 */
u8 syn_ect_snt:2; /* 358: 0 1 */
u8 syn_ect_rcv:2; /* 358: 2 1 */
u8 accecn_fail_mode:4; /* 358: 4 1 */
/* size: 360, cachelines: 6, members: 20 */
}
After this patch, the size of tcp_sock remains unchanged and no new
holes are added. Also, 4 bits of the existing 2-byte hole are exploited.
Below are the pahole outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u8 dup_ack_counter:2; /* 2761: 0 1 */
u8 tlp_retrans:1; /* 2761: 2 1 */
u8 unused:5; /* 2761: 3 1 */
u8 thin_lto:1; /* 2762: 0 1 */
u8 fastopen_connect:1; /* 2762: 1 1 */
u8 fastopen_no_cookie:1; /* 2762: 2 1 */
u8 fastopen_client_fail:2; /* 2762: 3 1 */
u8 frto:1; /* 2762: 5 1 */
/* XXX 2 bits hole, try to pack */
[...]
u8 keepalive_probes; /* 2765 1 */
/* XXX 2 bytes hole, try to pack */
[...]
/* size: 3200, cachelines: 50, members: 164 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u8 dup_ack_counter:2; /* 2761: 0 1 */
u8 tlp_retrans:1; /* 2761: 2 1 */
u8 syn_ect_snt:2; /* 2761: 3 1 */
u8 syn_ect_rcv:2; /* 2761: 5 1 */
u8 thin_lto:1; /* 2761: 7 1 */
u8 fastopen_connect:1; /* 2762: 0 1 */
u8 fastopen_no_cookie:1; /* 2762: 1 1 */
u8 fastopen_client_fail:2; /* 2762: 2 1 */
u8 frto:1; /* 2762: 4 1 */
/* XXX 3 bits hole, try to pack */
[...]
u8 keepalive_probes; /* 2765 1 */
u8 accecn_fail_mode:4; /* 2766: 0 1 */
/* XXX 4 bits hole, try to pack */
/* XXX 1 byte hole, try to pack */
[...]
/* size: 3200, cachelines: 50, members: 166 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Co-developed-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-3-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This change implements Accurate ECN without negotiation and
AccECN Option (that will be added by later changes). Based on
AccECN specifications:
https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
Accurate ECN allows feeding back the number of CE (congestion
experienced) marks accurately to the sender in contrast to
RFC3168 ECN that can only signal one marks-seen-yes/no per RTT.
Congestion control algorithms can take advantage of the accurate
ECN information to fine-tune their congestion response to avoid
drastic rate reduction when only mild congestion is encountered.
With Accurate ECN, tp->received_ce (r.cep in AccECN spec) keeps
track of how many segments have arrived with a CE mark. Accurate
ECN uses ACE field (ECE, CWR, AE) to communicate the value back
to the sender which updates tp->delivered_ce (s.cep) based on the
feedback. This signalling channel is lossy when ACE field overflow
occurs.
Conservative strategy is selected here to deal with the ACE
overflow, however, some strategies using the AccECN option later
in the overall patchset mitigate against false overflows detected.
The ACE field values on the wire are offset by
TCP_ACCECN_CEP_INIT_OFFSET. Delivered_ce/received_ce count the
real CE marks rather than forcing all downstream users to adapt
to the wire offset.
This patch uses the first 1-byte hole and the last 4-byte hole of
the tcp_sock_write_txrx for 'received_ce_pending' and 'received_ce'.
Also, the group size of tcp_sock_write_txrx is increased from
91 + 4 to 95 + 4 due to the new u32 received_ce member. Below are
the trimmed pahole outcomes before and after this patch.
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2521 0 */
u8 nonagle:4; /* 2521: 0 1 */
u8 rate_app_limited:1; /* 2521: 4 1 */
/* XXX 3 bits hole, try to pack */
/* XXX 2 bytes hole, try to pack */
[...]
u32 delivered_ce; /* 2576 4 */
u32 app_limited; /* 2580 4 */
u32 rcv_wnd; /* 2684 4 */
struct tcp_options_received rx_opt; /* 2688 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2612 0 */
/* XXX 4 bytes hole, try to pack */
[...]
/* size: 3200, cachelines: 50, members: 161 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2521 0 */
u8 nonagle:4; /* 2521: 0 1 */
u8 rate_app_limited:1; /* 2521: 4 1 */
/* XXX 3 bits hole, try to pack */
/* Force alignment to the next boundary: */
u8 :0;
u8 received_ce_pending:4;/* 2522: 0 1 */
u8 unused2:4; /* 2522: 4 1 */
/* XXX 1 byte hole, try to pack */
[...]
u32 delivered_ce; /* 2576 4 */
u32 received_ce; /* 2580 4 */
u32 app_limited; /* 2584 4 */
u32 rcv_wnd; /* 2588 4 */
struct tcp_options_received rx_opt; /* 2592 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2616 0 */
[...]
/* size: 3200, cachelines: 50, members: 164 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Co-developed-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-2-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
During recent testing with the netem qdisc to inject delays into TCP
traffic, we observed that our CLS BPF program failed to function correctly
due to incorrect classid retrieval from task_get_classid(). The issue
manifests in the following call stack:
bpf_get_cgroup_classid+5
cls_bpf_classify+507
__tcf_classify+90
tcf_classify+217
__dev_queue_xmit+798
bond_dev_queue_xmit+43
__bond_start_xmit+211
bond_start_xmit+70
dev_hard_start_xmit+142
sch_direct_xmit+161
__qdisc_run+102 <<<<< Issue location
__dev_xmit_skb+1015
__dev_queue_xmit+637
neigh_hh_output+159
ip_finish_output2+461
__ip_finish_output+183
ip_finish_output+41
ip_output+120
ip_local_out+94
__ip_queue_xmit+394
ip_queue_xmit+21
__tcp_transmit_skb+2169
tcp_write_xmit+959
__tcp_push_pending_frames+55
tcp_push+264
tcp_sendmsg_locked+661
tcp_sendmsg+45
inet_sendmsg+67
sock_sendmsg+98
sock_write_iter+147
vfs_write+786
ksys_write+181
__x64_sys_write+25
do_syscall_64+56
entry_SYSCALL_64_after_hwframe+100
The problem occurs when multiple tasks share a single qdisc. In such cases,
__qdisc_run() may transmit skbs created by different tasks. Consequently,
task_get_classid() retrieves an incorrect classid since it references the
current task's context rather than the skb's originating task.
Given that dev_queue_xmit() always executes with bh disabled, we can use
softirq_count() instead to obtain the correct classid.
The simple steps to reproduce this issue:
1. Add network delay to the network interface:
such as: tc qdisc add dev bond0 root netem delay 1.5ms
2. Build two distinct net_cls cgroups, each with a network-intensive task
3. Initiate parallel TCP streams from both tasks to external servers.
Under this specific condition, the issue reliably occurs. The kernel
eventually dequeues an SKB that originated from Task-A while executing in
the context of Task-B.
It is worth noting that it will change the established behavior for a
slightly different scenario:
<sock S is created by task A>
<class ID for task A is changed>
<skb is created by sock S xmit and classified>
prior to this patch the skb will be classified with the 'new' task A
classid, now with the old/original one. The bpf_get_cgroup_classid_curr()
function is a more appropriate choice for this case.
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250902062933.30087-1-laoar.shao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Hosts under DOS attack can suffer from false sharing
in enqueue_to_backlog() : atomic_inc(&sd->dropped).
This is because sd->dropped can be touched from many cpus,
possibly residing on different NUMA nodes.
Generalize the sk_drop_counters infrastucture
added in commit c51613fa27 ("net: add sk->sk_drop_counters")
and use it to replace softnet_data.dropped
with NUMA friendly softnet_data.drop_counters.
This adds 64 bytes per cpu, maybe more in the future
if we increase the number of counters (currently 2)
per 'struct numa_drop_counters'.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250909121942.1202585-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Now that the destruction of info/keys is delayed until the socket
destructor, it's safe to use kfree() without an RCU callback.
The socket is in TCP_CLOSE state either because it never left it,
or it's already closed and the refcounter is zero. In any way,
no one can discover it anymore, it's safe to release memory
straight away.
Similar thing was possible for twsk already.
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://patch.msgid.link/20250909-b4-tcp-ao-md5-rst-finwait2-v5-2-9ffaaaf8b236@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently there are a couple of minor issues with destroying the keys
tcp_v4_destroy_sock():
1. The socket is yet in TCP bind buckets, making it reachable for
incoming segments [on another CPU core], potentially available to send
late FIN/ACK/RST replies.
2. There is at least one code path, where tcp_done() is called before
sending RST [kudos to Bob for investigation]. This is a case of
a server, that finished sending its data and just called close().
The socket is in TCP_FIN_WAIT2 and has RCV_SHUTDOWN (set by
__tcp_close())
tcp_v4_do_rcv()/tcp_v6_do_rcv()
tcp_rcv_state_process() /* LINUX_MIB_TCPABORTONDATA */
tcp_reset()
tcp_done_with_error()
tcp_done()
inet_csk_destroy_sock() /* Destroys AO/MD5 keys */
/* tcp_rcv_state_process() returns SKB_DROP_REASON_TCP_ABORT_ON_DATA */
tcp_v4_send_reset() /* Sends an unsigned RST segment */
tcpdump:
> 22:53:15.399377 00:00:b2:1f:00:00 > 00:00:01:01:00:00, ethertype IPv4 (0x0800), length 74: (tos 0x0, ttl 64, id 33929, offset 0, flags [DF], proto TCP (6), length 60)
> 1.0.0.1.34567 > 1.0.0.2.49848: Flags [F.], seq 2185658590, ack 3969644355, win 502, options [nop,nop,md5 valid], length 0
> 22:53:15.399396 00:00:01:01:00:00 > 00:00:b2:1f:00:00, ethertype IPv4 (0x0800), length 86: (tos 0x0, ttl 64, id 51951, offset 0, flags [DF], proto TCP (6), length 72)
> 1.0.0.2.49848 > 1.0.0.1.34567: Flags [.], seq 3969644375, ack 2185658591, win 128, options [nop,nop,md5 valid,nop,nop,sack 1 {2185658590:2185658591}], length 0
> 22:53:16.429588 00:00:b2:1f:00:00 > 00:00:01:01:00:00, ethertype IPv4 (0x0800), length 60: (tos 0x0, ttl 64, id 0, offset 0, flags [DF], proto TCP (6), length 40)
> 1.0.0.1.34567 > 1.0.0.2.49848: Flags [R], seq 2185658590, win 0, length 0
> 22:53:16.664725 00:00:b2:1f:00:00 > 00:00:01:01:00:00, ethertype IPv4 (0x0800), length 74: (tos 0x0, ttl 64, id 0, offset 0, flags [DF], proto TCP (6), length 60)
> 1.0.0.1.34567 > 1.0.0.2.49848: Flags [R], seq 2185658591, win 0, options [nop,nop,md5 valid], length 0
> 22:53:17.289832 00:00:b2:1f:00:00 > 00:00:01:01:00:00, ethertype IPv4 (0x0800), length 74: (tos 0x0, ttl 64, id 0, offset 0, flags [DF], proto TCP (6), length 60)
> 1.0.0.1.34567 > 1.0.0.2.49848: Flags [R], seq 2185658591, win 0, options [nop,nop,md5 valid], length 0
Note the signed RSTs later in the dump - those are sent by the server
when the fin-wait socket gets removed from hash buckets, by
the listener socket.
Instead of destroying AO/MD5 info and their keys in inet_csk_destroy_sock(),
slightly delay it until the actual socket .sk_destruct(). As shutdown'ed
socket can yet send non-data replies, they should be signed in order for
the peer to process them. Now it also matches how AO/MD5 gets destructed
for TIME-WAIT sockets (in tcp_twsk_destructor()).
This seems optimal for TCP-MD5, while for TCP-AO it seems to have an
open problem: once RST get sent and socket gets actually destructed,
there is no information on the initial sequence numbers. So, in case
this last RST gets lost in the network, the server's listener socket
won't be able to properly sign another RST. Nothing in RFC 1122
prescribes keeping any local state after non-graceful reset.
Luckily, BGP are known to use keep alive(s).
While the issue is quite minor/cosmetic, these days monitoring network
counters is a common practice and getting invalid signed segments from
a trusted BGP peer can get customers worried.
Investigated-by: Bob Gilligan <gilligan@arista.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://patch.msgid.link/20250909-b4-tcp-ao-md5-rst-finwait2-v5-1-9ffaaaf8b236@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Johannes Berg says:
====================
Plenty of things going on, notably:
- iwlwifi: major cleanups/rework
- brcmfmac: gets AP isolation support
- mac80211: gets more S1G support
* tag 'wireless-next-2025-09-11' of https://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next: (94 commits)
wifi: mwifiex: fix endianness handling in mwifiex_send_rgpower_table
wifi: cfg80211: Remove the redundant wiphy_dev
wifi: mac80211: fix incorrect comment
wifi: cfg80211: update the time stamps in hidden ssid
wifi: mac80211: Fix HE capabilities element check
wifi: mac80211: add tx_handlers_drop statistics to ethtool
wifi: mac80211: fix reporting of all valid links in sta_set_sinfo()
wifi: iwlwifi: mld: CHANNEL_SURVEY_NOTIF is always supported
wifi: iwlwifi: mld: remove support of iwl_esr_mode_notif version 1
wifi: iwlwifi: mld: remove support from of sta cmd version 1
wifi: iwlwifi: mld: remove support of roc cmd version 5
wifi: iwlwifi: mld: remove support of mac cmd ver 2
wifi: iwlwifi: mld: don't consider phy cmd version 5
wifi: iwlwifi: implement wowlan status notification API update
wifi: iwlwifi: fw: Add ASUS to PPAG and TAS list
wifi: iwlwifi: add kunit tests for nvm parse
wifi: iwlwifi: api: add a flag to iwl_link_ctx_modify_flags
wifi: iwlwifi: pcie: move ltr_enabled to the specific transport
wifi: iwlwifi: pcie: move pm_support to the specific transport
wifi: iwlwifi: rename iwl_finish_nic_init
...
====================
Link: https://patch.msgid.link/20250911100854.20445-3-johannes@sipsolutions.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR (net-6.17-rc6).
Conflicts:
net/netfilter/nft_set_pipapo.c
net/netfilter/nft_set_pipapo_avx2.c
c4eaca2e10 ("netfilter: nft_set_pipapo: don't check genbit from packetpath lookups")
84c1da7b38 ("netfilter: nft_set_pipapo: use avx2 algorithm for insertions too")
Only trivial adjacent changes (in a doc and a Makefile).
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
__icmp_send() is used to generate ICMP error messages in response to
various situations such as MTU errors (i.e., "Fragmentation Required")
and too many hops (i.e., "Time Exceeded").
The skb that generated the error does not necessarily come from the IPv4
layer and does not always have a valid IPv4 control block in skb->cb.
Therefore, commit 9ef6b42ad6 ("net: Add __icmp_send helper.") changed
the function to take the IP options structure as argument instead of
deriving it from the skb's control block. Some callers of this function
such as icmp_send() pass the IP options structure from the skb's control
block as in these call paths the control block is known to be valid, but
other callers simply pass a zeroed structure.
A subsequent patch will need __icmp_send() to access more information
from the IPv4 control block (specifically, the ifindex of the input
interface). As a preparation for this change, change the function to
take the IPv4 control block structure as an argument instead of the IP
options structure. This makes the function similar to its IPv6
counterpart that already takes the IPv6 control block structure as an
argument.
No functional changes intended.
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250908073238.119240-3-idosch@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
xdp_update_skb_shared_info() needs to update skb state which
was maintained in xdp_buff / frame. Pass full flags into it,
instead of breaking it out bit by bit. We will need to add
a bit for unreadable frags (even tho XDP doesn't support
those the driver paths may be common), at which point almost
all call sites would become:
xdp_update_skb_shared_info(skb, num_frags,
sinfo->xdp_frags_size,
MY_PAGE_SIZE * num_frags,
xdp_buff_is_frag_pfmemalloc(xdp),
xdp_buff_is_frag_unreadable(xdp));
Keep a helper for accessing the flags, in case we need to
transform them somehow in the future (e.g. to cover up xdp_buff
vs xdp_frame differences).
While we are touching call callers - rename the helper to
xdp_update_skb_frags_info(), previous name may have implied that
it's shinfo that's updated. We are updating flags in struct sk_buff
based on frags that got attched.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://patch.msgid.link/20250905221539.2930285-2-kuba@kernel.org
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This function was added for retpoline mitigation and is replaced by a
static inline helper if mitigations are not enabled.
Enable this helper function unconditionally so next patch can add a lookup
restart mechanism to fix possible false negatives while transactions are
in progress.
Adding lookup restarts in nft_lookup_eval doesn't work as nft_objref would
then need the same copypaste loop.
This patch is separate to ease review of the actual bug fix.
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
This will soon be read from packet path around same time as the gencursor.
Both gencursor and base_seq get incremented almost at the same time, so
it makes sense to place them in the same structure.
This doesn't increase struct net size on 64bit due to padding.
Signed-off-by: Florian Westphal <fw@strlen.de>
NICs are typically configured with total_vfs=0, forcing users to rely
on external tools to enable SR-IOV (a widely used and essential feature).
Add total_vfs parameter to devlink for SR-IOV max VF configurability.
Enables standard kernel tools to manage SR-IOV, addressing the need for
flexible VF configuration.
Signed-off-by: Vlad Dumitrescu <vdumitrescu@nvidia.com>
Tested-by: Kamal Heib <kheib@redhat.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250907012953.301746-2-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Tony Nguyen says:
====================
idpf: add XDP support
Alexander Lobakin says:
Add XDP support (w/o XSk for now) to the idpf driver using the libeth_xdp
sublib. All possible verdicts, .ndo_xdp_xmit(), multi-buffer etc. are here.
In general, nothing outstanding comparing to ice, except performance --
let's say, up to 2x for .ndo_xdp_xmit() on certain platforms and
scenarios.
idpf doesn't support VLAN Rx offload, so only the hash hint is
available for now.
Patches 1-7 are prereqs, without which XDP would either not work at all
or work slower/worse/...
* '200GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
idpf: add XDP RSS hash hint
idpf: add support for .ndo_xdp_xmit()
idpf: add support for XDP on Rx
idpf: use generic functions to build xdp_buff and skb
idpf: implement XDP_SETUP_PROG in ndo_bpf for splitq
idpf: prepare structures to support XDP
idpf: add support for nointerrupt queues
idpf: remove SW marker handling from NAPI
idpf: add 4-byte completion descriptor definition
idpf: link NAPIs to queues
idpf: use a saner limit for default number of queues to allocate
idpf: fix Rx descriptor ready check barrier in splitq
xdp, libeth: make the xdp_init_buff() micro-optimization generic
====================
Link: https://patch.msgid.link/20250908195748.1707057-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a new ad_select policy 'port_priority' that uses the per-port
actor priority values (set via ad_actor_port_prio) to determine
aggregator selection.
This allows administrators to influence which ports are preferred
for aggregation by assigning different priority values, providing
more flexible load balancing control in LACP configurations.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250902064501.360822-3-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Introduce a new netlink attribute 'actor_port_prio' to allow setting
the LACP actor port priority on a per-slave basis. This extends the
existing bonding infrastructure to support more granular control over
LACP negotiations.
The priority value is embedded in LACPDU packets and will be used by
subsequent patches to influence aggregator selection policies.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250902064501.360822-2-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Often times the compilers are not able to expand two consecutive 32-bit
writes into one 64-bit on the corresponding architectures. This applies
to xdp_init_buff() called for every received frame (or at least once
per each 64 frames when the frag size is fixed).
Move the not-so-pretty hack from libeth_xdp straight to xdp_init_buff(),
but using a proper union around ::frame_sz and ::flags.
The optimization is limited to LE architectures due to the structure
layout.
One simple example from idpf with the XDP series applied (Clang 22-git,
CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE => -O2):
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-27 (-27)
Function old new delta
idpf_vport_splitq_napi_poll 5076 5049 -27
The perf difference with XDP_DROP is around +0.8-1% which I see as more
than satisfying.
Suggested-by: Simon Horman <horms@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The so-called fullmac devices rely on firmware functionality and/or API to
change BSS parameters. Today there are limited drivers supporting the
nl80211 primitive, but they only handle a subset of the bss parameters
passed if any. The mac80211 driver does handle all parameters and stores
their configured values. Some of the BSS parameters were already conditional
by wiphy->features. For these the wiphy->bss_param_support and wiphy->features
fields are silently aligned in wiphy_register(). Maybe better to issue a warning
instead when they are misaligned.
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20250817190435.1495094-2-arend.vanspriel@broadcom.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
If a valid radio index is not found, the function returns -ENOENT. If the
channel argument itself is invalid, it returns -EINVAL. However, since the
caller only checks for < 0, the distinction between these error codes is
not utilized much. Also, handling these two distinct error codes throughout
the codebase adds complexity, as both cases must be addressed separately. A
subsequent change aims to simplify this by using a single error code for
all invalid cases, making error handling more consistent and streamlined.
To support this change, update the return value to -EINVAL when a valid
radio index is not found. This is still appropriate because, even if the
channel argument is structurally valid, the absence of a corresponding
radio index implies that the argument is effectively invalid—otherwise, a
valid index would have been found.
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250812-fix_scan_ap_flag_requirement_during_mlo-v4-1-383ffb6da213@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
An exchange with a NFC target must complete within NCI_DATA_TIMEOUT.
A delay of 700 ms is not sufficient for cryptographic operations on smart
cards. CardOS 6.0 may need up to 1.3 seconds to perform 256-bit ECDH
or 3072-bit RSA. To prevent brute-force attacks, passports and similar
documents introduce even longer delays into access control protocols
(BAC/PACE).
The timeout should be higher, but not too much. The expiration allows
us to detect that a NFC target has disappeared.
Signed-off-by: Juraj Šarinay <juraj@sarinay.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250902113630.62393-1-juraj@sarinay.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Florian Westphal says:
====================
netfilter: updates for net-next
1) prefer vmalloc_array in ebtables, from Qianfeng Rong.
2) Use csum_replace4 instead of open-coding it, from Christophe Leroy.
3+4) Get rid of GFP_ATOMIC in transaction object allocations, those
cause silly failures with large sets under memory pressure, from
myself.
5) Remove test for AVX cpu feature in nftables pipapo set type,
testing for AVX2 feature is sufficient.
6) Unexport a few function in nf_reject infra: no external callers.
7) Extend payload offset to u16, this was restricted to values <=255
so far, from Fernando Fernandez Mancera.
* tag 'nf-next-25-09-02' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
netfilter: nft_payload: extend offset to 65535 bytes
netfilter: nf_reject: remove unneeded exports
netfilter: nft_set_pipapo: remove redundant test for avx feature bit
netfilter: nf_tables: all transaction allocations can now sleep
netfilter: nf_tables: allow iter callbacks to sleep
netfilter: nft_payload: Use csum_replace4() instead of opencoding
netfilter: ebtables: Use vmalloc_array() to improve code
====================
Link: https://patch.msgid.link/20250902133549.15945-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a helper to check if RFS is needed or not. Allows to make the code a
bit cleaner and the next patch to have MPTCP use this helper to decide
whether or not to iterate over the subflows.
tun_flow_update() was calling sock_rps_record_flow_hash() regardless of
the state of rfs_needed. This was not really a bug as sock_flow_table
simply ends up being NULL and thus everything will be fine.
This commit here thus also implicitly makes tun_flow_update() respect
the state of rfs_needed.
Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250902-net-next-mptcp-misc-feat-6-18-v2-3-fa02bb3188b1@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Remove the implementation of use_carrier, the link monitoring
method that utilizes ethtool or ioctl to determine the link state of an
interface in a bond. Bonding will always behaves as if use_carrier=1,
which relies on netif_carrier_ok() to determine the link state of
interfaces.
To avoid acquiring RTNL many times per second, bonding inspects
link state under RCU, but not under RTNL. However, ethtool
implementations in drivers may sleep, and therefore this strategy is
unsuitable for use with calls into driver ethtool functions.
The use_carrier option was introduced in 2003, to provide
backwards compatibility for network device drivers that did not support
the then-new netif_carrier_ok/on/off system. Device drivers are now
expected to support netif_carrier_*, and the use_carrier backwards
compatibility logic is no longer necessary.
The option itself remains, but when queried always returns 1,
and may only be set to 1.
Link: https://lore.kernel.org/000000000000eb54bf061cfd666a@google.com
Link: https://lore.kernel.org/20240718122017.d2e33aaac43a.I10ab9c9ded97163aef4e4de10985cd8f7de60d28@changeid
Signed-off-by: Jay Vosburgh <jv@jvosburgh.net>
Reported-by: syzbot+b8c48ea38ca27d150063@syzkaller.appspotmail.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/2029487.1756512517@famine
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In some situations 255 bytes offset is not enough to match or manipulate
the desired packet field. Increase the offset limit to 65535 or U16_MAX.
In addition, the nla policy maximum value is not set anymore as it is
limited to s16. Instead, the maximum value is checked during the payload
expression initialization function.
Tested with the nft command line tool.
table ip filter {
chain output {
@nh,2040,8 set 0xff
@nh,524280,8 set 0xff
@nh,524280,8 0xff
@nh,2040,8 0xff
}
}
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Quoting Sven Auhagen:
we do see on occasions that we get the following error message, more so on
x86 systems than on arm64:
Error: Could not process rule: Cannot allocate memory delete table inet filter
It is not a consistent error and does not happen all the time.
We are on Kernel 6.6.80, seems to me like we have something along the lines
of the nf_tables: allow clone callbacks to sleep problem using GFP_ATOMIC.
As hinted at by Sven, this is because of GFP_ATOMIC allocations during
set flush.
When set is flushed, all elements are deactivated. This triggers a set
walk and each element gets added to the transaction list.
The rbtree and rhashtable sets don't allow the iter callback to sleep:
rbtree walk acquires read side of an rwlock with bh disabled, rhashtable
walk happens with rcu read lock held.
Rbtree is simple enough to resolve:
When the walk context is ITER_READ, no change is needed (the iter
callback must not deactivate elements; we're not in a transaction).
When the iter type is ITER_UPDATE, the rwlock isn't needed because the
caller holds the transaction mutex, this prevents any and all changes to
the ruleset, including add/remove of set elements.
Rhashtable is slightly more complex.
When the iter type is ITER_READ, no change is needed, like rbtree.
For ITER_UPDATE, we hold transaction mutex which prevents elements from
getting free'd, even outside of rcu read lock section.
So build a temporary list of all elements while doing the rcu iteration
and then call the iterator in a second pass.
The disadvantage is the need to iterate twice, but this cost comes with
the benefit to allow the iter callback to use GFP_KERNEL allocations in
a followup patch.
The new list based logic makes it necessary to catch recursive calls to
the same set earlier.
Such walk -> iter -> walk recursion for the same set can happen during
ruleset validation in case userspace gave us a bogus (cyclic) ruleset
where verdict map m jumps to chain that sooner or later also calls
"vmap @m".
Before the new ->in_update_walk test, the ruleset is rejected because the
infinite recursion causes ctx->level to exceed the allowed maximum.
But with the new logic added here, elements would get skipped:
nft_rhash_walk_update would see elements that are on the walk_list of
an older stack frame.
As all recursive calls into same map results in -EMLINK, we can avoid this
problem by using the new in_update_walk flag and reject immediately.
Next patch converts the problematic GFP_ATOMIC allocations.
Reported-by: Sven Auhagen <Sven.Auhagen@belden.com>
Closes: https://lore.kernel.org/netfilter-devel/BY1PR18MB5874110CAFF1ED098D0BC4E7E07BA@BY1PR18MB5874.namprd18.prod.outlook.com/
Signed-off-by: Florian Westphal <fw@strlen.de>
