linux.git/Documentation/networking, branch v6.6.131

tcp: Set pingpong threshold via sysctl

2026-03-04T12:20:22+00:00

[ Upstream commit 562b1fdf061bff9394ccd884456ed1173c224fdc ]

TCP pingpong threshold is 1 by default. But some applications, like SQL DB
may prefer a higher pingpong threshold to activate delayed acks in quick
ack mode for better performance.

The pingpong threshold and related code were changed to 3 in the year
2019 in:
  commit 4a41f453bedf ("tcp: change pingpong threshold to 3")
And reverted to 1 in the year 2022 in:
  commit 4d8f24eeedc5 ("Revert "tcp: change pingpong threshold to 3"")

There is no single value that fits all applications.
Add net.ipv4.tcp_pingpong_thresh sysctl tunable, so it can be tuned for
optimal performance based on the application needs.

Signed-off-by: Haiyang Zhang 
Reviewed-by: Simon Horman 
Reviewed-by: Eric Dumazet 
Acked-by: Neal Cardwell 
Reviewed-by: Kuniyuki Iwashima 
Link: https://lore.kernel.org/r/1697056244-21888-1-git-send-email-haiyangz@microsoft.com
Signed-off-by: Jakub Kicinski 
Stable-dep-of: 87b08913a9ae ("inet: move icmp_global_{credit,stamp} to a separate cache line")
Signed-off-by: Sasha Levin

tcp: defer regular ACK while processing socket backlog

2026-03-04T12:20:22+00:00

[ Upstream commit 133c4c0d37175f510a10fa9bed51e223936073fc ]

This idea came after a particular workload requested
the quickack attribute set on routes, and a performance
drop was noticed for large bulk transfers.

For high throughput flows, it is best to use one cpu
running the user thread issuing socket system calls,
and a separate cpu to process incoming packets from BH context.
(With TSO/GRO, bottleneck is usually the 'user' cpu)

Problem is the user thread can spend a lot of time while holding
the socket lock, forcing BH handler to queue most of incoming
packets in the socket backlog.

Whenever the user thread releases the socket lock, it must first
process all accumulated packets in the backlog, potentially
adding latency spikes. Due to flood mitigation, having too many
packets in the backlog increases chance of unexpected drops.

Backlog processing unfortunately shifts a fair amount of cpu cycles
from the BH cpu to the 'user' cpu, thus reducing max throughput.

This patch takes advantage of the backlog processing,
and the fact that ACK are mostly cumulative.

The idea is to detect we are in the backlog processing
and defer all eligible ACK into a single one,
sent from tcp_release_cb().

This saves cpu cycles on both sides, and network resources.

Performance of a single TCP flow on a 200Gbit NIC:

- Throughput is increased by 20% (100Gbit -> 120Gbit).
- Number of generated ACK per second shrinks from 240,000 to 40,000.
- Number of backlog drops per second shrinks from 230 to 0.

Benchmark context:
- Regular netperf TCP_STREAM (no zerocopy)
- Intel(R) Xeon(R) Platinum 8481C (Saphire Rapids)
- MAX_SKB_FRAGS = 17 (~60KB per GRO packet)

This feature is guarded by a new sysctl, and enabled by default:
/proc/sys/net/ipv4/tcp_backlog_ack_defer

Signed-off-by: Eric Dumazet
Acked-by: Yuchung Cheng
Acked-by: Neal Cardwell
Acked-by: Soheil Hassas Yeganeh
Acked-by: Dave Taht
Signed-off-by: Paolo Abeni
Stable-dep-of: 87b08913a9ae ("inet: move icmp_global_{credit,stamp} to a separate cache line")
Signed-off-by: Sasha Levin

octeon_ep: support Octeon CN10K devices

2026-03-04T12:19:55+00:00

[ Upstream commit 0807dc76f3bf500f9a22465eedd2290da7357efb ]

Add PCI Endpoint NIC support for Octeon CN10K devices.
CN10K devices are part of Octeon 10 family products with
similar PCI NIC characteristics. These include:
- CN10KA
- CNF10KA
- CNF10KB
- CN10KB

Update supported device list in Documentation

Signed-off-by: Shinas Rasheed 
Link: https://lore.kernel.org/r/20231117103817.2468176-1-srasheed@marvell.com
Signed-off-by: Paolo Abeni 
Stable-dep-of: 73e6ffa37ceb ("octeon_ep: disable per ring interrupts")
Signed-off-by: Sasha Levin

doc: fix seg6_flowlabel path

2025-10-23T14:16:30+00:00

[ Upstream commit 0b4b77eff5f8cd9be062783a1c1e198d46d0a753 ]

This sysctl is not per interface; it's global per netns.

Fixes: 292ecd9f5a94 ("doc: move seg6_flowlabel to seg6-sysctl.rst")
Reported-by: Philippe Guibert 
Signed-off-by: Nicolas Dichtel 
Reviewed-by: Simon Horman 
Signed-off-by: David S. Miller 
Signed-off-by: Sasha Levin

docs: networking: can: change bcm_msg_head frames member to support flexible array

2025-09-19T14:32:06+00:00

[ Upstream commit 641427d5bf90af0625081bf27555418b101274cd ]

The documentation of the 'bcm_msg_head' struct does not match how
it is defined in 'bcm.h'. Changed the frames member to a flexible array,
matching the definition in the header file.

See commit 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with
flexible-array members")

Signed-off-by: Alex Tran 
Acked-by: Oliver Hartkopp 
Link: https://patch.msgid.link/20250904031709.1426895-1-alex.t.tran@gmail.com
Fixes: 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217783
Signed-off-by: Marc Kleine-Budde 
Signed-off-by: Sasha Levin

bonding: Add independent control state machine

2025-08-28T14:28:49+00:00

[ Upstream commit 240fd405528bbf7fafa0559202ca7aa524c9cd96 ]

Add support for the independent control state machine per IEEE
802.1AX-2008 5.4.15 in addition to the existing implementation of the
coupled control state machine.

Introduces two new states, AD_MUX_COLLECTING and AD_MUX_DISTRIBUTING in
the LACP MUX state machine for separated handling of an initial
Collecting state before the Collecting and Distributing state. This
enables a port to be in a state where it can receive incoming packets
while not still distributing. This is useful for reducing packet loss when
a port begins distributing before its partner is able to collect.

Added new functions such as bond_set_slave_tx_disabled_flags and
bond_set_slave_rx_enabled_flags to precisely manage the port's collecting
and distributing states. Previously, there was no dedicated method to
disable TX while keeping RX enabled, which this patch addresses.

Note that the regular flow process in the kernel's bonding driver remains
unaffected by this patch. The extension requires explicit opt-in by the
user (in order to ensure no disruptions for existing setups) via netlink
support using the new bonding parameter coupled_control. The default value
for coupled_control is set to 1 so as to preserve existing behaviour.

Signed-off-by: Aahil Awatramani
Reviewed-by: Hangbin Liu
Link: https://lore.kernel.org/r/20240202175858.1573852-1-aahila@google.com
Signed-off-by: Paolo Abeni
Stable-dep-of: 0599640a21e9 ("bonding: send LACPDUs periodically in passive mode after receiving partner's LACPDU")
Signed-off-by: Sasha Levin

mptcp: disable add_addr retransmission when timeout is 0

2025-08-28T14:28:44+00:00

commit f5ce0714623cffd00bf2a83e890d09c609b7f50a upstream.

When add_addr_timeout was set to 0, this caused the ADD_ADDR to be
retransmitted immediately, which looks like a buggy behaviour. Instead,
interpret 0 as "no retransmissions needed".

The documentation is updated to explicitly state that setting the timeout
to 0 disables retransmission.

Fixes: 93f323b9cccc ("mptcp: add a new sysctl add_addr_timeout")
Cc: stable@vger.kernel.org
Suggested-by: Matthieu Baerts 
Signed-off-by: Geliang Tang 
Reviewed-by: Matthieu Baerts (NGI0) 
Signed-off-by: Matthieu Baerts (NGI0) 
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-5-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski 
[ Before commit e4c28e3d5c09 ("mptcp: pm: move generic PM helpers to
  pm.c"), mptcp_pm_alloc_anno_list() was in pm_netlink.c. The same patch
  can be applied there without conflicts. ]
Signed-off-by: Matthieu Baerts (NGI0) 
Signed-off-by: Greg Kroah-Hartman

strparser: Add read_sock callback

2025-02-27T12:10:50+00:00

[ Upstream commit 0532a79efd68a4d9686b0385e4993af4b130ff82 ]

Added a new read_sock handler, allowing users to customize read operations
instead of relying on the native socket's read_sock.

Signed-off-by: Jiayuan Chen 
Signed-off-by: Martin KaFai Lau 
Reviewed-by: Jakub Sitnicki 
Acked-by: John Fastabend 
Link: https://patch.msgid.link/20250122100917.49845-2-mrpre@163.com
Stable-dep-of: 36b62df5683c ("bpf: Fix wrong copied_seq calculation")
Signed-off-by: Sasha Levin

can: j1939: fix error in J1939 documentation.

2024-12-09T09:31:38+00:00

[ Upstream commit b6ec62e01aa4229bc9d3861d1073806767ea7838 ]

The description of PDU1 format usage mistakenly referred to PDU2 format.

Signed-off-by: Alexander Hölzl 
Acked-by: Oleksij Rempel 
Acked-by: Vincent Mailhol 
Link: https://patch.msgid.link/20241023145257.82709-1-alexander.hoelzl@gmx.net
Signed-off-by: Marc Kleine-Budde 
Signed-off-by: Sasha Levin

net: ena: Move XDP code to its new files

2024-04-17T09:19:32+00:00

[ Upstream commit d000574d02870710c62751148cbfe22993222b98 ]

XDP system has a very large footprint in the driver's overall code.
makes the whole driver's code much harder to read.

Moving XDP code to dedicated files.

This patch doesn't make any changes to the code itself and only
cut-pastes the code into ena_xdp.c and ena_xdp.h files so the change
is purely cosmetic.

Signed-off-by: Shay Agroskin 
Signed-off-by: David Arinzon 
Link: https://lore.kernel.org/r/20240101190855.18739-2-darinzon@amazon.com
Signed-off-by: Jakub Kicinski 
Stable-dep-of: 36a1ca01f045 ("net: ena: Set tx_info->xdpf value to NULL")
Signed-off-by: Sasha Levin