Add dumpit handler for resource-dump command to iterate over all devlink
devices and show their resources.
$ devlink resource show
pci/0000:08:00.0:
name local_max_SFs size 508 unit entry
name external_max_SFs size 508 unit entry
pci/0000:08:00.1:
name local_max_SFs size 508 unit entry
name external_max_SFs size 508 unit entry
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260407194107.148063-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The device-level "resource show" displays max_local_SFs and
max_external_SFs without indicating which port each resource belongs
to. Users cannot determine the controller number and pfnum associated
with each SF pool.
Register max_SFs resource on the host PF representor port to expose
per-port SF limits. Users can correlate the port resource with the
controller number and pfnum shown in 'devlink port show'.
Future patches will introduce an ECPF that manages multiple PFs,
where each PF has its own SF pool.
Example usage:
$ devlink resource show pci/0000:03:00.0/196608
pci/0000:03:00.0/196608:
name max_SFs size 20 unit entry
$ devlink port show pci/0000:03:00.0/196608
pci/0000:03:00.0/196608: type eth netdev pf0hpf flavour pcipf
controller 1 pfnum 0 external true splittable false
function:
hw_addr b8:3f:d2:e1:8f:dc roce enable max_io_eqs 120
We can create up to 20 SFs over devlink port pci/0000:03:00.0/196608,
with pfnum 0 and controller 1.
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260407194107.148063-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The current devlink resource infrastructure supports only device-level
resources. Some hardware resources are associated with specific ports
rather than the entire device, and today we have no way to show resource
per-port.
Add support for registering resources at the port level.
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260407194107.148063-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently the resource functions take devlink pointer as parameter
and take the resource list from there.
Allow resource functions to work with other resource lists that will
be added in next patches and not only with the devlink's resource list.
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260407194107.148063-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In "bpf: Disallow freplace on XDP with mismatched xdp_has_frags values" [1],
this XDP test is suggested to add to xdp.py.
1. Verify the failure of updating frag-capable prog with non-frag-capable
prog, when the frag-capable prog attaches to mtu=9k driver.
The test has been verified against Mellanox CX6 and Intel 82599ES NICs.
With dropping other tests, here is the test log.
# ethtool -i eth0
driver: mlx5_core
version: 6.19.0-061900-generic
# NETIF=eth0 python3 xdp.py
TAP version 13
1..1
ok 1 xdp.test_xdp_native_update_mb_to_sb
# Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
# ethtool -i eth0
driver: ixgbe
version: 6.19.0-061900-generic
# NETIF=eth0 python3 xdp.py
TAP version 13
1..1
# CMD: ip link set dev eth0 xdpdrv obj /path/to/tools/testing/selftests/net/lib/xdp_dummy.bpf.o sec xdp.frags
# EXIT: 2
# STDERR: RTNETLINK answers: Invalid argument
ok 1 xdp.test_xdp_native_update_mb_to_sb # SKIP device does not support multi-buffer XDP
# Totals: pass:0 fail:0 xfail:0 xpass:0 skip:1 error:0
Signed-off-by: Leon Hwang <leon.huangfu@shopee.com>
Link: https://patch.msgid.link/20260406072655.368173-1-leon.huangfu@shopee.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean says:
====================
dsa_loop and platform_data cleanups
While working to add some new features to dsa_loop, I gathered a number
of cleanup patches. They mostly remove some data structures that became
unused after the multi-switch platforms were migrated to the modern DT
bindings.
====================
Link: https://patch.msgid.link/20260406212158.721806-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This has accumulated some fields which are no longer parsed by the core
or set by any driver. Remove them.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260406212158.721806-3-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Matthieu Baerts says:
====================
mptcp: autotune related improvement
Here are two patches from Paolo that have been crafted a couple of
months ago, but needed more validation because they were indirectly
causing instabilities in the sefltests. The root cause has been fixed in
'net' recently in commit 8c09412e58 ("selftests: mptcp: more stable
simult_flows tests").
These patches refactor the receive space and RTT estimator, overall
making DRS more correct while avoiding receive buffer drifting to
tcp_rmem[2], which in turn makes the throughput more stable and less
bursty, especially with high bandwidth and low delay environments.
Note that the first patch addresses a very old issue. 'net-next' is
targeted because the change is quite invasive and based on a recent
backlog refactor. The 'Fixes' tag is then there more as a FYI, because
backporting this patch will quickly be blocked due to large conflicts.
====================
Link: https://patch.msgid.link/20260407-net-next-mptcp-reduce-rbuf-v2-0-0d1d135bf6f6@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This is the MPTCP counter-part of commit ea33537d82 ("tcp: add receive
queue awareness in tcp_rcv_space_adjust()").
Prior to this commit:
ESTAB 33165568 0 192.168.255.2:5201 192.168.255.1:53380 \
skmem:(r33076416,rb33554432,t0,tb91136,f448,w0,o0,bl0,d0)
After:
ESTAB 3279168 0 192.168.255.2:5201 192.168.255.1]:53042 \
skmem:(r3190912,rb3719956,t0,tb91136,f1536,w0,o0,bl0,d0)
Same throughput.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260407-net-next-mptcp-reduce-rbuf-v2-2-0d1d135bf6f6@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The current MPTCP-level RTT estimator has several issues. On high speed
links, the MPTCP-level receive buffer auto-tuning happens with a
frequency well above the TCP-level's one. That in turn can cause
excessive/unneeded receive buffer increase.
On such links, the initial rtt_us value is considerably higher than the
actual delay, and the current mptcp_rcv_space_adjust() updates
msk->rcvq_space.rtt_us with a period equal to the such field previous
value. If the initial rtt_us is 40ms, its first update will happen after
40ms, even if the subflows see actual RTT orders of magnitude lower.
Additionally:
- setting the msk RTT to the maximum among all the subflows RTTs makes
DRS constantly overshooting the rcvbuf size when a subflow has
considerable higher latency than the other(s).
- during unidirectional bulk transfers with multiple active subflows,
the TCP-level RTT estimator occasionally sees considerably higher
value than the real link delay, i.e. when the packet scheduler reacts
to an incoming ACK on given subflow pushing data on a different
subflow.
- currently inactive but still open subflows (i.e. switched to backup
mode) are always considered when computing the msk-level RTT.
Address the all the issues above with a more accurate RTT estimation
strategy: the MPTCP-level RTT is set to the minimum of all the subflows
actually feeding data into the MPTCP receive buffer, using a small
sliding window.
While at it, also use EWMA to compute the msk-level scaling_ratio, to
that MPTCP can avoid traversing the subflow list is
mptcp_rcv_space_adjust().
Use some care to avoid updating msk and ssk level fields too often.
Fixes: a6b118febb ("mptcp: add receive buffer auto-tuning")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260407-net-next-mptcp-reduce-rbuf-v2-1-0d1d135bf6f6@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sk_clone() initializes sk_tx_queue_mapping via sk_tx_queue_clear()
but does not initialize sk_rx_queue_mapping. Since this field is in
the sk_dontcopy region, it is neither copied from the parent socket
by sock_copy() nor zeroed by sk_prot_alloc() (called without
__GFP_ZERO from sk_clone).
Commit 03cfda4fa6 ("tcp: fix another uninit-value
(sk_rx_queue_mapping)") attempted to fix this by introducing
sk_mark_napi_id_set() with force_set=true in tcp_child_process().
However, sk_mark_napi_id_set() -> sk_rx_queue_set() only writes
when skb_rx_queue_recorded(skb) is true. If the 3-way handshake
ACK arrives through a device that does not record rx_queue (e.g.
loopback or veth), sk_rx_queue_mapping remains uninitialized.
When a subsequent data packet arrives with a recorded rx_queue,
sk_mark_napi_id() -> sk_rx_queue_update() reads the uninitialized
field for comparison (force_set=false path), triggering KMSAN.
This was reproduced by establishing a TCP connection over loopback
(which does not call skb_record_rx_queue), then attaching a BPF TC
program on lo ingress to set skb->queue_mapping on data packets:
BUG: KMSAN: uninit-value in tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1875)
tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1875)
tcp_v4_rcv (net/ipv4/tcp_ipv4.c:2287)
ip_protocol_deliver_rcu (net/ipv4/ip_input.c:207)
ip_local_deliver_finish (net/ipv4/ip_input.c:242)
ip_local_deliver (net/ipv4/ip_input.c:262)
ip_rcv (net/ipv4/ip_input.c:573)
__netif_receive_skb (net/core/dev.c:6294)
process_backlog (net/core/dev.c:6646)
__napi_poll (net/core/dev.c:7710)
net_rx_action (net/core/dev.c:7929)
handle_softirqs (kernel/softirq.c:623)
do_softirq (kernel/softirq.c:523)
__local_bh_enable_ip (kernel/softirq.c:?)
__dev_queue_xmit (net/core/dev.c:?)
ip_finish_output2 (net/ipv4/ip_output.c:237)
ip_output (net/ipv4/ip_output.c:438)
__ip_queue_xmit (net/ipv4/ip_output.c:534)
__tcp_transmit_skb (net/ipv4/tcp_output.c:1693)
tcp_write_xmit (net/ipv4/tcp_output.c:3064)
tcp_sendmsg_locked (net/ipv4/tcp.c:?)
tcp_sendmsg (net/ipv4/tcp.c:1465)
inet_sendmsg (net/ipv4/af_inet.c:865)
sock_write_iter (net/socket.c:1195)
vfs_write (fs/read_write.c:688)
...
Uninit was created at:
kmem_cache_alloc_noprof (mm/slub.c:4873)
sk_prot_alloc (net/core/sock.c:2239)
sk_alloc (net/core/sock.c:2301)
inet_create (net/ipv4/af_inet.c:334)
__sock_create (net/socket.c:1605)
__sys_socket (net/socket.c:1747)
Fix this at the root by adding sk_rx_queue_clear() alongside
sk_tx_queue_clear() in sk_clone().
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260407084219.95718-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The piece of code which processes the command line arguments and
populates NETIFS based on them is really unobvious. Rewrite it so that
the intention is clear and the code is easy to follow.
Suggested-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20260407102058.867279-1-ioana.ciornei@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This shows an improvement of 1.9% in reducing the CPU cycles and data
cache misses.
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Nicolai Buchwitz <nb@tipi-net.de>
Link: https://patch.msgid.link/20260408001813.635679-1-florian.fainelli@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ipvlan and macvlan use queues to process broadcast/multicast packets
from a work queue.
Under attack these queues can drop packets.
Add MACVLAN_BROADCAST_BACKLOG drop_reason for macvlan broadcast queue.
Add IPVLAN_MULTICAST_BACKLOG drop_reason for ipvlan multicast queue.
Use different reasons as some deployments use both ipvlan and macvlan.
Also change ipvlan_rcv_frame() to use SKB_DROP_REASON_DEV_READY
when the device is not UP.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260407150710.1640747-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
codel_dump_stats() only runs with RTNL held,
reading fields that can be changed in qdisc fast path.
Add READ_ONCE()/WRITE_ONCE() annotations.
Alternative would be to acquire the qdisc spinlock, but our long-term
goal is to make qdisc dump operations lockless as much as we can.
tc_codel_xstats fields don't need to be latched atomically,
otherwise this bug would have been caught earlier.
No change in kernel size:
$ scripts/bloat-o-meter -t vmlinux.0 vmlinux
add/remove: 0/0 grow/shrink: 1/1 up/down: 3/-1 (2)
Function old new delta
codel_qdisc_dequeue 2462 2465 +3
codel_dump_stats 250 249 -1
Total: Before=29739919, After=29739921, chg +0.00%
Fixes: 76e3cc126b ("codel: Controlled Delay AQM")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260407143053.1570620-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Replace the magic numbers with defines. Register names were obtained from
publicly available documentation[1]. This should make it clear what's going
on in the code.
1. RTL8201F/RTL8201FL/RTL8201FN Rev. 1.4 Datasheet
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Nicolai Buchwitz nb@tipi-net.de
Link: https://patch.msgid.link/20260406201222.1043396-1-olek2@wp.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since commit 2884bf72fb ("net: bonding: fix use-after-free in
bond_xmit_broadcast()"), bond_is_last_slave() was only used in
bond_xmit_broadcast(). After the recent fix replaced that usage with
a simple index comparison, bond_is_last_slave() has no remaining
callers. bond_is_first_slave() likewise has no callers.
Remove both unused macros.
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Link: https://patch.msgid.link/20260404220412.444753-1-xmei5@asu.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reword the reviewer guidance based on behavior we see on the list.
Steer folks:
- towards sending tags
- away from process issues.
Reviewed-by: Joe Damato <joe@dama.to>
Reviewed-by: Nicolai Buchwitz <nb@tipi-net.de>
Link: https://patch.msgid.link/20260406175334.3153451-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=T6NA
-----END PGP SIGNATURE-----
Merge tag 'nf-next-26-04-08' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next
Florian Westphal says:
====================
netfilter: updates for net-next
1) Fix ancient sparse warnings in nf conntrack nat modules, from
Sun Jian.
2) Fix typo in enum description, from Jelle van der Waa.
3) remove redundant refetch of netns pointer in nf_conntrack_sip.
4) add a deprecation warning for dccp match.
We can extend the deadline later if needed, but plan atm is to
remove the feature.
5) remove nf_conntrack_h323 debug code that can read out-of-bounds
with malformed messages. This code was commented out, but better
remove this.
6+7) add more netlink policy validations in netfilter.
This could theoretically cause issues when a client sends e.g.
unsupported feature flags that were previously ignored, so we
may have to relax some changes. For now, try to be stricter and
reject upfront.
8+9) minor code cleanup in nft_set_pipapo (an nftables set backend).
10) Add nftables matching support fro double-tagged vlan and pppoe
frames, from Pablo Neira Ayuso.
11) Fix up indentation of debug messages in nf_conntrack_h323 conntrack
helper, from David Laight.
12) Add a helper to iterate to next flow action and bail out if the
maximum number of actions is reached, also from Pablo.
* tag 'nf-next-26-04-08' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
netfilter: nf_tables_offload: add nft_flow_action_entry_next() and use it
netfilter: nf_conntrack_h323: Correct indentation when H323_TRACE defined
netfilter: nft_meta: add double-tagged vlan and pppoe support
netfilter: nft_set_pipapo_avx2: remove redundant loop in lookup_slow
netfilter: nft_set_pipapo: increment data in one step
netfilter: nf_tables: add netlink policy based cap on registers
netfilter: add more netlink-based policy range checks
netfilter: nf_conntrack_h323: remove unreliable debug code in decode_octstr
netfilter: add deprecation warning for dccp support
netfilter: nf_conntrack_sip: remove net variable shadowing
netfilter: nf_tables: Fix typo in enum description
netfilter: use function typedefs for __rcu NAT helper hook pointers
====================
Link: https://patch.msgid.link/20260408060419.25258-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQIzBAABCgAdFiEEH7ZpcWbFyOOp6OJbrB3Eaf9PW7cFAmnWIe8ACgkQrB3Eaf9P
W7dDqRAAho59mSQlQAaoj6lkPlBCR8/TZrEHWXeTZvWzzyILiE8GJGdkMoUOk47S
QR2YJ7xTg/eAALJFFPCKj82k5GOt2CjOo30BS901zdBhSZbN/H+tW57QfYRegR3o
BFZ0eBCDc5FHQYRl8QbCi2XtF4Sqr8erLIvNwfaOiuoPCZmoehD2kyMpPhb/w9qQ
DD0OsYWjZuhBP+MwHGCsmtMBoesVKI/86HV0LpeyH7uU+928Tf+TcACJzkLMrUcE
AwrvTL3Mvp2ljsm9mw6mElyiAqemQHM87yg8BrR7NoXlahAEOJx8UWchKpAgGXv5
bO8ng0Y8lNcuG+tN7rVk4/KeyjGNSW6ubRKfZbast6aoj5LfUhOIxxMTyYOEU5rH
wKbIX00ilONs8S+kK/S4D0/1EdszOB/WVUTN5yEH1+FxkpvMGs3LUfhEjzfk9Lnz
sT1ZF65YNwR0qa1SaIU4kYM543mlr/CrFgoPx5VOu0+jG+xCVWiC8fy+/SD688ht
VTQGf8Y6gGX0yRMYJeauHHCBeMwbF7WEu7MYSi+4+7uUCYexh700QpOjaYLrTpgS
NLpT9JPvuyWQ389DjJ+h5cpTqIsLrNs6+SXo+mZ6nkubGe+HRKZnLFwXj+41p3hE
tUv+EcZTKDa+YVGymVcjORC5JjqvJXXklqQFeROuoamdJF0M96c=
=0E3L
-----END PGP SIGNATURE-----
Merge tag 'ipsec-next-2026-04-08' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next
Steffen Klassert says:
====================
pull request (net-next): ipsec-next 2026-04-08
1) Update outdated comment in xfrm_dst_check().
From kexinsun.
2) Drop support for HMAC-RIPEMD-160 from IPsec.
From Eric Biggers.
* tag 'ipsec-next-2026-04-08' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next:
xfrm: Drop support for HMAC-RIPEMD-160
xfrm: update outdated comment
====================
Link: https://patch.msgid.link/20260408094258.148555-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a new helper function to retrieve the next action entry in flow
rule, check if the maximum number of actions is reached, bail out in
such case.
Replace existing opencoded iteration on the action array by this
helper function.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
The trace lines are indented using PRINT("%*.s", xx, " ").
Userspace will treat this as "%*.0s" and will output no characters
when 'xx' is zero, the kernel treats it as "%*s" and will output
a single ' ' - which is probably what is intended.
Change all the formats to "%*s" removing the default precision.
This gives a single space indent when level is zero.
Signed-off-by: David Laight <david.laight.linux@gmail.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Currently:
add rule netdev x y ip saddr 1.1.1.1
does not work with neither double-tagged vlan nor pppoe packets. This is
because the network and transport header offset are not pointing to the
IP and transport protocol headers in the stack.
This patch expands NFT_META_PROTOCOL and NFT_META_L4PROTO to parse
double-tagged vlan and pppoe packets so matching network and transport
header fields becomes possible with the existing userspace generated
bytecode. Note that this parser only supports double-tagged vlan which
is composed of vlan offload + vlan header in the skb payload area for
simplicity.
NFT_META_PROTOCOL is used by bridge and netdev family as an implicit
dependency in the bytecode to match on network header fields.
Similarly, there is also NFT_META_L4PROTO, which is also used as an
implicit dependency when matching on the transport protocol header
fields.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
nft_pipapo_avx2_lookup_slow will never be used in reality, because the
common sizes are handled by avx2 optimized versions.
However, nft_pipapo_avx2_lookup_slow loops over the data just like the
avx2 functions. However, _slow doesn't need to do that.
As-is, first loop sets all the right result bits and the next iterations
boil down to 'x = x & x'. Remove the loop.
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Since commit e807b13cb3 ("nft_set_pipapo: Generalise group size for buckets")
there is no longer a need to increment the data pointer in two steps.
Switch to a single invocation of NFT_PIPAPO_GROUPS_PADDED_SIZE() helper,
like the avx2 implementation.
[ Stefano: Improve commit message ]
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Should have no effect in practice; all of these use the
nft_parse_register_load/store apis which is mandatory anyway due
to the need to further validate the register load/store, e.g.
that the size argument doesn't result in out-of-bounds load/store.
OTOH this is a simple method to reject obviously wrong input
at earlier stage.
Signed-off-by: Florian Westphal <fw@strlen.de>
These spots either already check the attribute range manually
before use or the consuming functions tolerate unexpected values.
Nevertheless, add more range checks via netlink policy so we gain
more users and avoid possible re-use in other places that might
not have the required manual checks. This also improves error
reporting: netlink core can generate extack errors.
Signed-off-by: Florian Westphal <fw@strlen.de>
The debug code (not enabled in any build) reads up to 6 octets of
the inpt buffer, but does so without bound checks. Zap this.
Signed-off-by: Florian Westphal <fw@strlen.de>
net is already set, derived from nf_conn.
I don't see how the device could be living in a different netns
than the conntrack entry.
Remove the extra variable and re-use existing one.
Signed-off-by: Florian Westphal <fw@strlen.de>
After commit 07919126ec ("netfilter: annotate NAT helper hook pointers
with __rcu"), sparse can warn about type/address-space mismatches when
RCU-dereferencing NAT helper hook function pointers.
The hooks are __rcu-annotated and accessed via rcu_dereference(), but the
combination of complex function pointer declarators and the WRITE_ONCE()
machinery used by RCU_INIT_POINTER()/rcu_assign_pointer() can confuse
sparse and trigger false positives.
Introduce typedefs for the NAT helper function types, so __rcu applies to
a simple "fn_t __rcu *" pointer form. Also replace local typeof(hook)
variables with "fn_t *" to avoid propagating __rcu address space into
temporaries.
No functional change intended.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202603022359.3dGE9fwI-lkp@intel.com/
Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Eric Dumazet says:
====================
net: pull gso packet headers in core stack
Most ndo_start_xmit() methods expects headers of gso packets
to be already in skb->head.
net/core/tso.c users are particularly at risk, because tso_build_hdr()
does a memcpy(hdr, skb->data, hdr_len);
qdisc_pkt_len_segs_init() already does a dissection of gso packets.
Use pskb_may_pull() instead of skb_header_pointer() to make
sure drivers do not have to reimplement this.
First patch is a small cleanup to ease second patch review.
====================
Link: https://patch.msgid.link/20260403221540.3297753-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Most ndo_start_xmit() methods expects headers of gso packets
to be already in skb->head.
net/core/tso.c users are particularly at risk, because tso_build_hdr()
does a memcpy(hdr, skb->data, hdr_len);
qdisc_pkt_len_segs_init() already does a dissection of gso packets.
Use pskb_may_pull() instead of skb_header_pointer() to make
sure drivers do not have to reimplement this.
Some malicious packets could be fed, detect them so that we can
drop them sooner with a new SKB_DROP_REASON_SKB_BAD_GSO drop_reason.
Fixes: e876f208af ("net: Add a software TSO helper API")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260403221540.3297753-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reduce indentation level by returning early if the transport header
was not set.
Add an unlikely() clause as this is not the common case.
No functional change.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260403221540.3297753-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
socat v1.8.1.0 now defaults to shut-null, it sends an extra
0-length UDP packet when sender disconnects. This breaks
our tests which expect the exact packet sequence.
Add shut-none which was the old default where necessary.
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Joe Damato <joe@dama.to>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20260404230103.2719103-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
On PRP protocol, when deleting the port the MAC address change
notification was missing. In addition to that, make sure to only perform
the MAC address change on slave2 deletion and PRP protocol as the
operation isn't necessary for HSR nor slave1.
Note that the eth_hw_addr_set() is correct on PRP context as the slaves
are either in promiscuous mode or forward offload enabled.
Reported-by: Luka Gejak <luka.gejak@linux.dev>
Closes: https://lore.kernel.org/netdev/DHFCZEM93FTT.1RWFBIE32K7OT@linux.dev/
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Felix Maurer <fmaurer@redhat.com>
Link: https://patch.msgid.link/20260403123928.4249-2-fmancera@suse.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tariq Toukan says:
====================
net/mlx5e: XDP, Add support for multi-packet per page
This series removes the limitation of having one packet per page in XDP
mode. This has the following implications:
- XDP in Striding RQ mode can now be used on 64K page systems.
- XDP in Legacy RQ mode was using a single packet per page which on 64K
page systems is quite inefficient. The improvement can be observed
with an XDP_DROP test when running in Legacy RQ mode on a ARM
Neoverse-N1 system with a 64K page size:
+-----------------------------------------------+
| MTU | baseline | this change | improvement |
|------+------------+-------------+-------------|
| 1500 | 15.55 Mpps | 18.99 Mpps | 22.0 % |
| 9000 | 15.53 Mpps | 18.24 Mpps | 17.5 % |
+-----------------------------------------------+
After lifting this limitation, the series switches to using fragments
for the side page in non-linear mode. This small improvement is at most
visible for XDP_DROP tests with small 64B packets and a large enough MTU
for Striding RQ to be in non-linear mode:
+----------------------------------------------------------------------+
| System | MTU | baseline | this change | improvement |
|----------------------+------+------------+-------------+-------------|
| 4K page x86_64 [1] | 9000 | 26.30 Mpps | 30.45 Mpps | 15.80 % |
| 64K page aarch64 [2] | 9000 | 15.27 Mpps | 20.10 Mpps | 31.62 % |
+----------------------------------------------------------------------+
This series does not cover the xsk (AF_XDP) paths for 64K page systems.
[1] https://lore.kernel.org/all/20260324024235.929875-1-kuba@kernel.org/
====================
Link: https://patch.msgid.link/20260403090927.139042-1-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently in XDP multi-buffer mode for striding rq a whole page is
allocated for the linear part of the XDP buffer. This is wasteful,
especially on systems with larger page sizes.
This change splits the page into fixed sized fragments. The page is
replenished when the maximum number of allowed fragments is reached.
When a fragment is not used, it will be simply recycled on next packet.
This is great for XDP_DROP as the fragment can be recycled for the next
packet. In the most extreme case (XDP_DROP everything), there will be 0
fragments used => only one linear page allocation for the lifetime of
the XDP program.
The previous page_pool size increase was too conservative (doubling the
size) and now there are much fewer allocations (1/8 for a 4K page). So
drop the page_pool size extension altogether when the linear side page
is used.
This small improvement is at most visible for XDP_DROP tests with small
64B packets and a large enough MTU for Striding RQ to be in non-linear
mode:
+----------------------------------------------------------------------+
| System | MTU | baseline | this change | improvement |
|----------------------+------+------------+-------------+-------------|
| 4K page x86_64 [1] | 9000 | 26.30 Mpps | 30.45 Mpps | 15.80 % |
| 64K page aarch64 [2] | 9000 | 15.27 Mpps | 20.10 Mpps | 31.62 % |
+----------------------------------------------------------------------+
[1] Intel Xeon Platinum 8580
[2] ARM Neoverse-N1
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260403090927.139042-6-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently in striding rq there is one mlx5e_frag_page member per WQE for
the linear page. This linear page is used only in XDP multi-buffer mode.
This is wasteful because only one linear page is needed per rq: the page
gets refreshed on every packet, regardless of WQE. Furthermore, it is
not needed in other modes (non-XDP, XDP single-buffer).
This change moves the linear page into its own structure (struct
mlx5_mpw_linear_info) and allocates it only when necessary.
A special structure is created because an upcoming patch will extend
this structure to support fragmentation of the linear page.
This patch has no functional changes.
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260403090927.139042-5-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently XDP mode always uses PAGE_SIZE strides. This limitation
existed because page fragment counting was not implemented when XDP was
added. Furthermore, due to this limitation there were other issues as
well on system with larger pages (e.g. 64K):
- XDP for Striding RQ was effectively disabled on such systems.
- Legacy RQ allows the configuration but uses a fixed scheme of one XDP
buffer per page which is inefficient.
As fragment counting was added during the driver conversion to
page_pool and the support for XDP multi-buffer, it is now possible
to remove this stride size limitation. This patch does just that.
Now it is possible to use XDP on systems with higher page sizes (e.g.
64K):
- For Striding RQ, loading the program is no longer blocked.
Although a 64K page can fit any packet, MTUs that result in
stride > 8K will still make the RQ in non-linear mode. That's
because the HW doesn't support a higher than 8K stride.
- For Legacy RQ, the stride size was PAGE_SIZE which was very
inefficient. Now the stride size will be calculated relative to MTU.
Legacy RQ will always be in linear mode for larger system pages.
This can be observed with an XDP_DROP test [1] when running
in Legacy RQ mode on a ARM Neoverse-N1 system with a 64K
page size:
+-----------------------------------------------+
| MTU | baseline | this change | improvement |
|------+------------+-------------+-------------|
| 1500 | 15.55 Mpps | 18.99 Mpps | 22.0 % |
| 9000 | 15.53 Mpps | 18.24 Mpps | 17.5 % |
+-----------------------------------------------+
There are performance benefits for Striding RQ mode as well:
- Striding RQ non-linear mode now uses 256B strides, just like
non-XDP mode.
- Striding RQ linear mode can now fit a number of XDP buffers per page
that is relative to the MTU size. That means that on 4K page systems
and a small enough MTU, 2 XDP buffers can fit in one page.
The above benefits for Striding RQ can be observed with an
XDP_DROP test [1] when running on a 4K page x86_64 system
(Intel Xeon Platinum 8580):
+-----------------------------------------------+
| MTU | baseline | this change | improvement |
|------+------------+-------------+-------------|
| 1000 | 28.36 Mpps | 33.98 Mpps | 19.82 % |
| 9000 | 20.76 Mpps | 26.30 Mpps | 26.70 % |
+-----------------------------------------------+
[1] Test description:
- xdp-bench with XDP_DROP
- RX: single queue
- TX: sends 64B packets to saturate CPU on RX side
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260403090927.139042-4-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When calculating the dma address of the linear part of an XDP frame, the
formula assumes that there is a single XDP buffer per page. Extend the
formula to allow multiple XDP buffers per page by calculating the data
offset in the page.
This is a preparation for the upcoming removal of a single XDP buffer
per page limitation when the formula will no longer be correct.
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260403090927.139042-3-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When 64K pages are used, chunk_size can take the 64K value
which doesn't fit in u16. This results in overflows that
are detected in mlx5e_mpwrq_log_wqe_sz().
Increase the type to u32 to fix this.
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260403090927.139042-2-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Drop support for HMAC-RIPEMD-160 from IPsec to reduce the UAPI surface
and simplify future maintenance. It's almost certainly unused.
RIPEMD-160 received some attention in the early 2000s when SHA-* weren't
quite as well established. But it never received much adoption outside
of certain niches such as Bitcoin.
It's actually unclear that Linux + IPsec + HMAC-RIPEMD-160 has *ever*
been used, even historically. When support for it was added in 2003, it
was done so in a "cleanup" commit without any justification [1]. It
didn't actually work until someone happened to fix it 5 years later [2].
That person didn't use or test it either [3]. Finally, also note that
"hmac(rmd160)" is by far the slowest of the algorithms in aalg_list[].
Of course, today IPsec is usually used with an AEAD, such as AES-GCM.
But even for IPsec users still using a dedicated auth algorithm, they
almost certainly aren't using, and shouldn't use, HMAC-RIPEMD-160.
Thus, let's just drop support for it. Note: no kconfig update is
needed, since CRYPTO_RMD160 wasn't actually being selected anyway.
References:
[1] linux-history commit d462985fc1941a47
("[IPSEC]: Clean up key manager algorithm handling.")
[2] linux commit a13366c632
("xfrm: xfrm_algo: correct usage of RIPEMD-160")
[3] https://lore.kernel.org/all/1212340578-15574-1-git-send-email-rueegsegger@swiss-it.ch
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Matthieu Baerts says:
====================
mptcp: support MSG_EOR and small cleanups
This series contains various unrelated patches:
- Patches 1 & 2: support MSG_EOR instead of ignoring it.
- Patch 3: avoid duplicated code in TCP and MPTCP by using a new helper.
- Patch 4: adapt test to reproduce bug and increase code coverage.
====================
Link: https://patch.msgid.link/20260403-net-next-mptcp-msg_eor-misc-v1-0-b0b33bea3fed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
