When sk_alloc() allocates a socket, mem_cgroup_sk_alloc() sets
sk->sk_memcg based on the current task.
MPTCP subflow socket creation is triggered from userspace or
an in-kernel worker.
In the latter case, sk->sk_memcg is not what we want. So, we fix
it up from the parent socket's sk->sk_memcg in mptcp_attach_cgroup().
Although the code is placed under #ifdef CONFIG_MEMCG, it is buried
under #ifdef CONFIG_SOCK_CGROUP_DATA.
The two configs are orthogonal. If CONFIG_MEMCG is enabled without
CONFIG_SOCK_CGROUP_DATA, the subflow's memory usage is not charged
correctly.
Let's move the code out of the wrong ifdef guard.
Note that sk->sk_memcg is freed in sk_prot_free() and the parent
sk holds the refcnt of memcg->css here, so we don't need to use
css_tryget().
Fixes: 3764b0c565 ("mptcp: attach subflow socket to parent cgroup")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Link: https://patch.msgid.link/20250815201712.1745332-2-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Oleksij Rempel says:
====================
stmmac: stop silently dropping bad checksum packets
this series reworks how stmmac handles receive checksum offload
(CoE) errors on dwmac4.
At present, when CoE is enabled, the hardware silently discards any
frame that fails checksum validation. These packets never reach the
driver and are not accounted in the generic drop statistics. They are
only visible in the stmmac-specific counters as "payload error" or
"header error" packets, which makes it harder to debug or monitor
network issues.
Following discussion [1], the driver is reworked to propagate checksum
error information up to the stack. With these changes, CoE stays
enabled, but frames that fail hardware validation are no longer dropped
in hardware. Instead, the driver marks them with CHECKSUM_NONE so the
network stack can validate, drop, and properly account them in the
standard drop statistics.
[1] https://lore.kernel.org/all/20250625132117.1b3264e8@kernel.org/
====================
Link: https://patch.msgid.link/20250818090217.2789521-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Tell the MAC not to discard frames that fail TCP/IP checksum
validation.
By default, when the hardware checksum engine (CoE) is enabled,
dwmac4 silently drops any packet where the offload engine detects
a checksum error. These frames are not reported to the driver and
are not counted in any statistics as dropped packets.
Set the MTL_OP_MODE_DIS_TCP_EF bit when initializing the Rx channel so
that all packets are delivered, even if they failed hardware checksum
validation. CoE remains enabled, but instead of dropping such frames,
the driver propagates the error status and marks the skb with
CHECKSUM_NONE. This allows the stack to verify and drop the packet
while updating statistics.
This change follows the decision made in the discussion:
Link: https://lore.kernel.org/all/20250625132117.1b3264e8@kernel.org/
It depends on the previous patches that added proper error propagation
in the Rx path.
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250818090217.2789521-4-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Propagate hardware checksum failures from the descriptor parser to the
caller.
Currently, dwmac4_wrback_get_rx_status() updates stats when the Rx
descriptor signals an IP header or payload checksum error, but it does
not reflect this in its return value. The higher-level stmmac_rx() code
therefore cannot tell that hardware checksum validation failed.
Set the csum_none flag in the returned status when either
RDES1_IP_HDR_ERROR or RDES1_IP_PAYLOAD_ERROR is present. This aligns
dwmac4 with enh_desc_coe_rdes0() and lets stmmac_rx() mark the skb as
CHECKSUM_NONE for software verification.
This is a preparatory step for disabling the hardware filter that drops
frames which do not pass checksum validation.
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250818090217.2789521-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The stmmac_rx function would previously set skb->ip_summed to
CHECKSUM_UNNECESSARY if hardware checksum offload (CoE) was enabled
and the packet was of a known IP ethertype.
However, this logic failed to check if the hardware had actually
reported a checksum error. The hardware status, indicating a header or
payload checksum failure, was being ignored at this stage. This could
cause corrupt packets to be passed up the network stack as valid.
This patch corrects the logic by checking the `csum_none` status flag,
which is set when the hardware reports a checksum error. If this flag
is set, skb->ip_summed is now correctly set to CHECKSUM_NONE,
ensuring the kernel's network stack will perform its own validation and
properly handle the corrupt packet.
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250818090217.2789521-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
hclge_only_alloc_priv_buff() only return true or false,
So, change the function return type from integer to boolean.
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Link: https://patch.msgid.link/20250815100414.949752-3-shaojijie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The RTL8226-CG can make use of the serdes option mode feature to
dynamically switch between SGMII and 2500base-X. From what is
known the setup sequence is much simpler with no magic values.
Convert the exiting config_init() into a helper that configures
the PHY depending on generation 1 or 2. Call the helper from two
separated new config_init() functions.
Finally convert the phy_driver specs of the RTL8226-CG to make
use of the new configuration and switch over to the extended
read_status() function to dynamically change the interface
according to the serdes mode.
Remark! The logic could be simpler if the serdes mode could be
set before all other generation 2 magic values. Due to missing
RTL8221B test hardware the mmd command order was kept.
Tested on Zyxel XGS1210-12.
Signed-off-by: Markus Stockhausen <markus.stockhausen@gmx.de>
Link: https://patch.msgid.link/20250815082009.3678865-1-markus.stockhausen@gmx.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Replace the strcpy() call that copies the device name into
tunnel->parms.name with strscpy(), to avoid potential overflow
and guarantee NULL termination. This uses the two-argument
form of strscpy(), where the destination size is inferred
from the array type.
Destination is tunnel->parms.name (size IFNAMSIZ).
Tested in QEMU (Alpine rootfs):
- Created IPv6 GRE tunnels over loopback
- Assigned overlay IPv6 addresses
- Verified bidirectional ping through the tunnel
- Changed tunnel parameters at runtime (`ip -6 tunnel change`)
Signed-off-by: Miguel García <miguelgarciaroman8@gmail.com>
Link: https://patch.msgid.link/20250818220203.899338-1-miguelgarciaroman8@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stanislav Fomichev says:
====================
net: Convert to skb_dstref_steal and skb_dstref_restore
To diagnose and prevent issues similar to [0], emit warning
(CONFIG_DEBUG_NET) from skb_dst_set and skb_dst_set_noref when
overwriting non-null reference-counted entry. Two new helpers
are added to handle special cases where the entry needs to be
reset and restored: skb_dstref_steal/skb_dstref_restore. The bulk of
the patches in the series converts manual _skb_refst manipulations
to these new helpers.
0: https://lore.kernel.org/netdev/20250723224625.1340224-1-sdf@fomichev.me/T/#u
====================
Link: https://patch.msgid.link/20250818154032.3173645-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Going forward skb_dst_set will assert that skb dst_entry
is empty during skb_dst_set. skb_dstref_steal is added to reset
existing entry without doing refcnt. Chelsio driver is
doing extra dst management via skb_dst_set(NULL). Replace
these calls with skb_dstref_steal.
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250818154032.3173645-7-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Instead of doing dst_release and skb_dst_set, do skb_dst_drop which
should do the right thing.
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250818154032.3173645-6-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Going forward skb_dst_set will assert that skb dst_entry
is empty during skb_dst_set. skb_dstref_steal is added to reset
existing entry without doing refcnt. skb_dstref_restore should
be used to restore the previous entry. Convert icmp_route_lookup
and ip_options_rcv_srr to these helpers. Add extra call to
skb_dstref_reset to icmp_route_lookup to clear the ip_route_input
entry.
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250818154032.3173645-5-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Going forward skb_dst_set will assert that skb dst_entry
is empty during skb_dst_set. skb_dstref_steal is added to reset
existing entry without doing refcnt. Switch to skb_dstref_steal
in ip[6]_route_me_harder and add a comment on why it's safe
to skip skb_dstref_restore.
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250818154032.3173645-4-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Going forward skb_dst_set will assert that skb dst_entry
is empty during skb_dst_set. skb_dstref_steal is added to reset
existing entry without doing refcnt. Switch to skb_dstref_steal
in __xfrm_route_forward and add a comment on why it's safe
to skip skb_dstref_restore.
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250818154032.3173645-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Going forward skb_dst_set will assert that skb dst_entry
is empty during skb_dst_set to prevent potential leaks. There
are few places that still manually manage dst_entry not using
the helpers. Convert them to the following new helpers:
- skb_dstref_steal that resets dst_entry and returns previous dst_entry
value
- skb_dstref_restore that restores dst_entry previously reset via
skb_dstref_steal
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250818154032.3173645-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When removing a nexthop, commit
90f33bffa3 ("nexthops: don't modify published nexthop groups") added a
call to synchronize_rcu() (later changed to _net()) to make sure
everyone sees the new nexthop-group before the rtnl-lock is released.
When one wants to delete a large number of groups and nexthops, it is
fastest to first flush the groups (ip nexthop flush groups) and then
flush the nexthops themselves (ip -6 nexthop flush). As that way the
groups don't need to be rebalanced.
However, `ip -6 nexthop flush` will still take a long time if there is
a very large number of nexthops because of the call to
synchronize_net(). Now, if there are no more groups, there is no point
in calling synchronize_net(). So, let's skip that entirely by checking
if nh->grp_list is empty.
This gives us a nice speedup:
BEFORE:
=======
$ time sudo ip -6 nexthop flush
Dump was interrupted and may be inconsistent.
Flushed 2097152 nexthops
real 1m45.345s
user 0m0.001s
sys 0m0.005s
$ time sudo ip -6 nexthop flush
Dump was interrupted and may be inconsistent.
Flushed 4194304 nexthops
real 3m10.430s
user 0m0.002s
sys 0m0.004s
AFTER:
======
$ time sudo ip -6 nexthop flush
Dump was interrupted and may be inconsistent.
Flushed 2097152 nexthops
real 0m17.545s
user 0m0.003s
sys 0m0.003s
$ time sudo ip -6 nexthop flush
Dump was interrupted and may be inconsistent.
Flushed 4194304 nexthops
real 0m35.823s
user 0m0.002s
sys 0m0.004s
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250816-nexthop_dump-v2-2-491da3462118@openai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When we have a (very) large number of nexthops, they do not fit within a
single message. rtm_dump_walk_nexthops() thus will be called repeatedly
and ctx->idx is used to avoid dumping the same nexthops again.
The approach in which we avoid dumping the same nexthops is by basically
walking the entire nexthop rb-tree from the left-most node until we find
a node whose id is >= s_idx. That does not scale well.
Instead of this inefficient approach, rather go directly through the
tree to the nexthop that should be dumped (the one whose nh_id >=
s_idx). This allows us to find the relevant node in O(log(n)).
We have quite a nice improvement with this:
Before:
=======
--> ~1M nexthops:
$ time ~/libnl/src/nl-nh-list | wc -l
1050624
real 0m21.080s
user 0m0.666s
sys 0m20.384s
--> ~2M nexthops:
$ time ~/libnl/src/nl-nh-list | wc -l
2101248
real 1m51.649s
user 0m1.540s
sys 1m49.908s
After:
======
--> ~1M nexthops:
$ time ~/libnl/src/nl-nh-list | wc -l
1050624
real 0m1.157s
user 0m0.926s
sys 0m0.259s
--> ~2M nexthops:
$ time ~/libnl/src/nl-nh-list | wc -l
2101248
real 0m2.763s
user 0m2.042s
sys 0m0.776s
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250816-nexthop_dump-v2-1-491da3462118@openai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ncdevmem tests that the kernel correctly rejects attempts
to deactivate queues with MPs bound.
Make the configure_channels() test support combined channels.
Currently it tries to set the queue counts to rx N tx N-1,
which only makes sense for devices which have IRQs per ring
type. Most modern devices used combined IRQs/channels with
both Rx and Tx queues. Since the math is total Rx == combined+Rx
setting Rx when combined is non-zero will be increasing the total
queue count, not decreasing as the test intends.
Note that the test would previously also try to set the Tx
ring count to Rx - 1, for some reason. Which would be 0
if the device has only 2 queues configured.
With this change (device with 2 queues):
setting channel count rx:1 tx:1
YNL set channels: Kernel error: 'requested channel counts are too low for existing memory provider setting (2)'
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250815231513.381652-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We see quite a few flakes during the TSO test against virtualized
devices in NIPA. There's often 10-30 retransmissions during the
test. Sometimes as many as 100. Set the retransmission threshold
at 1/4th of the wire frame target.
Link: https://patch.msgid.link/20250815224100.363438-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
For external phy, clk_phy should be optional, and some external phy
need the clock input from clk_phy. This patch adds support for setting
clk_phy for external phy.
Signed-off-by: David Wu <david.wu@rock-chips.com>
Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Link: https://patch.msgid.link/20250815023515.114-1-kernel@airkyi.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Test that threaded state (in the persistent NAPI config) gets updated
even when NAPI with given ID is not allocated at the time.
This test is validating commit ccba9f6baa ("net: update NAPI threaded
config even for disabled NAPIs").
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20250815013314.2237512-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This patch enhances RX buffer handling in the mana driver by allocating
pages from a page pool and slicing them into MTU-sized fragments, rather
than dedicating a full page per packet. This approach is especially
beneficial on systems with large base page sizes like 64KB.
Key improvements:
- Proper integration of page pool for RX buffer allocations.
- MTU-sized buffer slicing to improve memory utilization.
- Reduce overall per Rx queue memory footprint.
- Automatic fallback to full-page buffers when:
* Jumbo frames are enabled (MTU > PAGE_SIZE / 2).
* The XDP path is active, to avoid complexities with fragment reuse.
Testing on VMs with 64KB pages shows around 200% throughput improvement.
Memory efficiency is significantly improved due to reduced wastage in page
allocations. Example: We are now able to fit 35 rx buffers in a single 64kb
page for MTU size of 1500, instead of 1 rx buffer per page previously.
Tested:
- iperf3, iperf2, and nttcp benchmarks.
- Jumbo frames with MTU 9000.
- Native XDP programs (XDP_PASS, XDP_DROP, XDP_TX, XDP_REDIRECT) for
testing the XDP path in driver.
- Memory leak detection (kmemleak).
- Driver load/unload, reboot, and stress scenarios.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Link: https://patch.msgid.link/20250814140410.GA22089@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The 'exclude_qbv' bit in the designcfg_debug1 register varies across
MACB/GEM IP revisions, making direct probing unreliable for detecting
QBV support. This patch introduces a capability-based approach for
consistent QBV feature identification across the IP family.
Platform support updates:
- Establish foundation for QBV detection in TAPRIO implementation
- Enable MACB_CAPS_QBV for Xilinx Versal platform configuration
- Fix capability line wrapping, ensuring code stays within 80 columns
Signed-off-by: Vineeth Karumanchi <vineeth.karumanchi@amd.com>
Link: https://patch.msgid.link/20250814071058.3062453-3-vineeth.karumanchi@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support to collect XDP stats via ethtool API. We record
packets and bytes sent, and packets dropped on the XDP_TX path.
ethtool -S eth0 | grep xdp | grep -v "0"
xdp_tx_queue_13_packets: 2
xdp_tx_queue_13_bytes: 16126
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-10-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support for XDP statistics collection and reporting via rtnl_link
and netdev_queue API.
For XDP programs without frags support, fbnic requires MTU to be less
than the HDS threshold. If an over-sized frame is received, the frame
is dropped and recorded as rx_length_errors reported via ip stats to
highlight that this is an error.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-9-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support for XDP_TX action and cleaning the associated work.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-8-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support for allocating XDP_TX queues and configuring ring support.
FBNIC has been designed with XDP support in mind. Each Tx queue has 2
submission queues and one completion queue, with the expectation that
one of the submission queues will be used by the stack, and the other
by XDP. XDP queues are populated by XDP_TX and start from index 128
in the TX queue array.
The support for XDP_TX is added in the next patch.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-7-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add basic support for attaching an XDP program to the device and support
for PASS/DROP/ABORT actions. In fbnic, buffers are always mapped as
DMA_BIDIRECTIONAL.
The BPF program pointer can be read either on a per-packet basis or on a
per-NAPI poll basis. Both approaches are functionally equivalent, in the
current code. Stick to per-packet as it limits number of arguments we need
to pass around.
On the XDP hot path, check that packets with fragments are only allowed
when multi-buffer support is enabled for the XDP program. Ideally, this
check should not be necessary because ndo_bpf verifies that for XDP
programs without multi-buff support, MTU is less than the hds_thresh.
However, the MTU currently does not enforce the receive size which would
require cleaning up the data path and bouncing the link. For practical
reasons, prioritize the ability to enter and exit BPF mode with different
MTU sizes without requiring a full reconfig.
Testing:
Hook a simple XDP program that passes all the packets destined for a
specific port
iperf3 -c 192.168.1.10 -P 5 -p 12345
Connecting to host 192.168.1.10, port 12345
[ 5] local 192.168.1.9 port 46702 connected to 192.168.1.10 port 12345
[ ID] Interval Transfer Bitrate Retr Cwnd
- - - - - - - - - - - - - - - - - - - - - - - - -
[SUM] 1.00-2.00 sec 3.86 GBytes 33.2 Gbits/sec 0
XDP_DROP:
Hook an XDP program that drops packets destined for a specific port
iperf3 -c 192.168.1.10 -P 5 -p 12345
^C- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[SUM] 0.00-0.00 sec 0.00 Bytes 0.00 bits/sec 0 sender
[SUM] 0.00-0.00 sec 0.00 Bytes 0.00 bits/sec receiver
iperf3: interrupt - the client has terminated
XDP with HDS:
- Validate XDP attachment failure when HDS is low
~] ethtool -G eth0 hds-thresh 512
~] sudo ip link set eth0 xdpdrv obj xdp_pass_12345.o sec xdp
~] Error: fbnic: MTU too high, or HDS threshold is too low for single
buffer XDP.
- Validate successful XDP attachment when HDS threshold is appropriate
~] ethtool -G eth0 hds-thresh 1536
~] sudo ip link set eth0 xdpdrv obj xdp_pass_12345.o sec xdp
- Validate when the XDP program is attached, changing HDS thresh to a
lower value fails
~] ethtool -G eth0 hds-thresh 512
~] netlink error: fbnic: Use higher HDS threshold or multi-buf capable
program
- Validate HDS thresh does not matter when xdp frags support is
available
~] ethtool -G eth0 hds-thresh 512
~] sudo ip link set eth0 xdpdrv obj xdp_pass_mb_12345.o sec xdp.frags
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-6-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Issue a prefetch for the start of the buffer on Rx to try to avoid cache
miss on packet headers.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-5-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Remove local fields that track frags state and instead store this
information directly in the shinfo struct. This change is necessary
because the current implementation can lead to inaccuracies in certain
scenarios, such as when using XDP multi-buff support. Specifically, the
XDP program may update nr_frags without updating the local variables,
resulting in an inconsistent state.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-4-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fbnic currently reserves a minimum of 64B headroom, but this is
insufficient for inserting additional headers (e.g., IPV6) via XDP, as
only 24 bytes are available for adjustment. To address this limitation,
increase the headroom to a larger value while ensuring better page use.
Although the resulting headroom (192B) is smaller than the recommended
value (256B), forcing the headroom to 256B would require aligning to
256B (as opposed to the current 128B), which can push the max headroom
to 511B.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-3-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support for configuring the header data split threshold.
For fbnic, the tcp data split support is enabled all the time.
Fbnic supports a maximum buffer size of 4KB. However, the reservation
for the headroom, tailroom, and padding reduce the max header size
accordingly.
ethtool_hds -g eth0
Ring parameters for eth0:
Pre-set maximums:
...
HDS thresh: 3584
Current hardware settings:
...
HDS thresh: 1536
Verify hds tests in ksft-net-drv are passing
ksft-net-drv]# ./drivers/net/hds.py
TAP version 13
1..13
ok 1 hds.get_hds
ok 2 hds.get_hds_thresh
ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by ...
...
...
ok 12 hds.ioctl_set_xdp
ok 13 hds.ioctl_enabled_set_xdp
\# Totals: pass:12 fail:0 xfail:0 xpass:0 skip:1 error:0
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250813221319.3367670-2-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Russell King says:
====================
net: stmmac: EEE and WoL cleanups
This series contains a series of cleanup patches for the EEE and WoL
code in stmmac, prompted by issues raised during the last three weeks.
====================
Link: https://patch.msgid.link/aJ8avIp8DBAckgMc@shell.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The call to phylink_speed_down() looks odd on the face of it. Add a
comment to explain why this call is there. phylink_speed_up() is
always called in __stmmac_open(), and already has a comment.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1umsfV-008vKv-1O@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add two helpers to abstract the WoL enable status at the PHY and MAC to
make the code easier to read.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1umsfP-008vKp-U1@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The PM core provides management of wake IRQs along side setting the
device wake enable state. In order to use this, we need to register
the interrupt used to wakeup the system using devm_pm_set_wake_irq()
or dev_pm_set_wake_irq(). The core will then enable or disable IRQ
wake state on this interrupt as appropriate, depending on the
device_set_wakeup_enable() state. device_set_wakeup_enable() does not
care about having balanced enable/disable calls.
Make use of this functionality, rather than explicitly managing the
IRQ enable state in the set_wol() ethtool op. This removes the IRQ
wake state management from stmmac.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1umsfK-008vKj-Pw@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Printing "stmmac: wakeup enable" to the kernel log isn't useful - it
doesn't identify the adapter, and is effectively nothing more than a
debugging print. This information can be discovered by looking at
/sys/device.../power/wakeup as the device_set_wakeup_enable() call
updates this sysfs file.
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1umsfF-008vKc-Kt@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The core ethtool API validates the WoL options passed from userspace
against the support which the driver reports from its get_wol() method,
returning EINVAL if an unsupported mode is requested.
Therefore, there is no need for stmmac to implement its own validation.
Remove this unnecessary code.
See ethnl_set_wol() in net/ethtool/wol.c and ethtool_set_wol() in
net/ethtool/ioctl.c.
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1umsfA-008vKW-H1@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
mac_device_info->pmt is only ever written, nothing reads it. Remove
this struct member.
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1umsf5-008vKQ-DT@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Phylink will check whether the MAC supports the LPI methods in
struct phylink_mac_ops, and return -EOPNOTSUPP if the LPI capabilities
are not provided. stmmac doesn't provide LPI capabilities if
priv->dma_cap.eee is not set.
Therefore, checking the state of priv->dma_cap.eee in the ethtool ops
and returning -EOPNOTSUPP is redundant - let phylink handle this.
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1umsf0-008vKK-A3@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Ethtool has advanced with additional configurable options, but the
current driver does not support tx-usecs configuration using Ethtool.
Add support to configure and retrieve 'tx-usecs' using ethtool, which
specifies the wait time before servicing an interrupt for Tx coalescing.
Signed-off-by: Vishal Badole <Vishal.Badole@amd.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://patch.msgid.link/20250816141941.126054-1-Vishal.Badole@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
