linux.git/net/core/netpoll.c, branch v6.16

net: netpoll: Initialize UDP checksum field before checksumming

2025-06-23T20:14:51+00:00

commit f1fce08e63fe ("netpoll: Eliminate redundant assignment") removed
the initialization of the UDP checksum, which was wrong and broke
netpoll IPv6 transmission due to bad checksumming.

udph->check needs to be set before calling csum_ipv6_magic().

Fixes: f1fce08e63fe ("netpoll: Eliminate redundant assignment")
Signed-off-by: Breno Leitao 
Reviewed-by: Simon Horman 
Link: https://patch.msgid.link/20250620-netpoll_fix-v1-1-f9f0b82bc059@debian.org
Signed-off-by: Jakub Kicinski

netpoll: Eliminate redundant assignment

2025-03-24T20:42:53+00:00

The assignment of zero to udph->check is unnecessary as it is
immediately overwritten in the subsequent line. Remove the redundant
assignment.

Signed-off-by: Breno Leitao 
Reviewed-by: Joe Damato 
Link: https://patch.msgid.link/20250319-netpoll_nit-v1-1-a7faac5cbd92@debian.org
Signed-off-by: Jakub Kicinski

netconsole: allow selection of egress interface via MAC address

2025-03-19T18:17:58+00:00

Currently, netconsole has two methods of configuration - module
parameter and configfs. The former interface allows for netconsole
activation earlier during boot (by specifying the module parameter on
the kernel command line), so it is preferred for debugging issues which
arise before userspace is up/the configfs interface can be used. The
module parameter syntax requires specifying the egress interface name.
This requirement makes it hard to use for a couple reasons:
- The egress interface name can be hard or impossible to predict. For
  example, installing a new network card in a system can change the
  interface names assigned by the kernel.
- When constructing the module parameter, one may have trouble
  determining the original (kernel-assigned) name of the interface
  (which is the name that should be given to netconsole) if some stable
  interface naming scheme is in effect. A human can usually look at
  kernel logs to determine the original name, but this is very painful
  if automation is constructing the parameter.

For these reasons, allow selection of the egress interface via MAC
address when configuring netconsole using the module parameter. Update
the netconsole documentation with an example of the new syntax.
Selection of egress interface by MAC address via configfs is far less
interesting (since when this interface can be used, one should be able
to easily convert between MAC address and interface name), so it is left
unimplemented.

Signed-off-by: Uday Shankar 
Reviewed-by: Breno Leitao 
Tested-by: Breno Leitao 
Reviewed-by: Simon Horman 
Link: https://patch.msgid.link/20250312-netconsole-v6-2-3437933e79b8@purestorage.com
Signed-off-by: Paolo Abeni

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2025-03-13T22:08:11+00:00

Cross-merge networking fixes after downstream PR (net-6.14-rc6).

Conflicts:

tools/testing/selftests/drivers/net/ping.py
  75cc19c8ff89 ("selftests: drv-net: add xdp cases for ping.py")
  de94e8697405 ("selftests: drv-net: store addresses in dict indexed by ipver")
https://lore.kernel.org/netdev/20250311115758.17a1d414@canb.auug.org.au/

net/core/devmem.c
  a70f891e0fa0 ("net: devmem: do not WARN conditionally after netdev_rx_queue_restart()")
  1d22d3060b9b ("net: drop rtnl_lock for queue_mgmt operations")
https://lore.kernel.org/netdev/20250313114929.43744df1@canb.auug.org.au/

Adjacent changes:

tools/testing/selftests/net/Makefile
  6f50175ccad4 ("selftests: Add IPv6 link-local address generation tests for GRE devices.")
  2e5584e0f913 ("selftests/net: expand cmsg_ipv6.sh with ipv4")

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  661958552eda ("eth: bnxt: do not use BNXT_VNIC_NTUPLE unconditionally in queue restart logic")
  fe96d717d38e ("bnxt_en: Extend queue stop/start for TX rings")

Signed-off-by: Paolo Abeni

netpoll: hold rcu read lock in __netpoll_send_skb()

2025-03-08T03:57:33+00:00

The function __netpoll_send_skb() is being invoked without holding the
RCU read lock. This oversight triggers a warning message when
CONFIG_PROVE_RCU_LIST is enabled:

	net/core/netpoll.c:330 suspicious rcu_dereference_check() usage!

	 netpoll_send_skb
	 netpoll_send_udp
	 write_ext_msg
	 console_flush_all
	 console_unlock
	 vprintk_emit

To prevent npinfo from disappearing unexpectedly, ensure that
__netpoll_send_skb() is protected with the RCU read lock.

Fixes: 2899656b494dcd1 ("netpoll: take rcu_read_lock_bh() in netpoll_send_skb_on_dev()")
Signed-off-by: Breno Leitao 
Reviewed-by: Simon Horman 
Link: https://patch.msgid.link/20250306-netpoll_rcu_v2-v2-1-bc4f5c51742a@debian.org
Signed-off-by: Jakub Kicinski

netpoll: Optimize skb refilling on critical path

2025-03-08T03:55:40+00:00

netpoll tries to refill the skb queue on every packet send, independently
if packets are being consumed from the pool or not. This was
particularly problematic while being called from printk(), where the
operation would be done while holding the console lock.

Introduce a more intelligent approach to skb queue management. Instead
of constantly attempting to refill the queue, the system now defers
refilling to a work queue and only triggers the workqueue when a buffer
is actually dequeued. This change significantly reduces operations with
the lock held.

Add a work_struct to the netpoll structure for asynchronous refilling,
updating find_skb() to schedule refill work only when necessary (skb is
dequeued).

These changes have demonstrated a 15% reduction in time spent during
netpoll_send_msg operations, especially when no SKBs are not consumed
from consumed from pool.

When SKBs are being dequeued, the improvement is even better, around
70%, mainly because refilling the SKB pool is now happening outside of
the critical patch (with console_owner lock held).

Signed-off-by: Breno Leitao 
Reviewed-by: Simon Horman 
Link: https://patch.msgid.link/20250304-netpoll_refill_v2-v1-1-06e2916a4642@debian.org
Signed-off-by: Jakub Kicinski

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2025-01-16T18:34:59+00:00

Cross-merge networking fixes after downstream PR (net-6.13-rc8).

Conflicts:

drivers/net/ethernet/realtek/r8169_main.c
  1f691a1fc4be ("r8169: remove redundant hwmon support")
  152d00a91396 ("r8169: simplify setting hwmon attribute visibility")
https://lore.kernel.org/20250115122152.760b4e8d@canb.auug.org.au

Adjacent changes:

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  152f4da05aee ("bnxt_en: add support for rx-copybreak ethtool command")
  f0aa6a37a3db ("eth: bnxt: always recalculate features after XDP clearing, fix null-deref")

drivers/net/ethernet/intel/ice/ice_type.h
  50327223a8bb ("ice: add lock to protect low latency interface")
  dc26548d729e ("ice: Fix quad registers read on E825")

Signed-off-by: Jakub Kicinski

net: netpoll: ensure skb_pool list is always initialized

2025-01-15T01:45:14+00:00

When __netpoll_setup() is called directly, instead of through
netpoll_setup(), the np->skb_pool list head isn't initialized.
If skb_pool_flush() is later called, then we hit a NULL pointer
in skb_queue_purge_reason().  This can be seen with this repro,
when CONFIG_NETCONSOLE is enabled as a module:

    ip tuntap add mode tap tap0
    ip link add name br0 type bridge
    ip link set dev tap0 master br0
    modprobe netconsole netconsole=4444@10.0.0.1/br0,9353@10.0.0.2/
    rmmod netconsole

The backtrace is:

    BUG: kernel NULL pointer dereference, address: 0000000000000008
    #PF: supervisor write access in kernel mode
    #PF: error_code(0x0002) - not-present page
    ... ... ...
    Call Trace:
     
     __netpoll_free+0xa5/0xf0
     br_netpoll_cleanup+0x43/0x50 [bridge]
     do_netpoll_cleanup+0x43/0xc0
     netconsole_netdev_event+0x1e3/0x300 [netconsole]
     unregister_netdevice_notifier+0xd9/0x150
     cleanup_module+0x45/0x920 [netconsole]
     __se_sys_delete_module+0x205/0x290
     do_syscall_64+0x70/0x150
     entry_SYSCALL_64_after_hwframe+0x76/0x7e

Move the skb_pool list setup and initial skb fill into __netpoll_setup().

Fixes: 221a9c1df790 ("net: netpoll: Individualize the skb pool")
Signed-off-by: John Sperbeck 
Reviewed-by: Breno Leitao 
Link: https://patch.msgid.link/20250114011354.2096812-1-jsperbeck@google.com
Signed-off-by: Jakub Kicinski

netpoll: Make netpoll_send_udp return status instead of void

2024-12-05T03:15:38+00:00

netpoll_send_udp can return if send was successful.
It will allow client code to be aware of the send status.

Possible return values are the result of __netpoll_send_skb (cast to int)
and -ENOMEM. This doesn't cover the case when TX was not successful
instantaneously and was scheduled for later, __netpoll__send_skb returns
success in that case.

Signed-off-by: Maksym Kutsevol 
Link: https://patch.msgid.link/20241202-netcons-add-udp-send-fail-statistics-to-netconsole-v5-1-70e82239f922@kutsevol.com
Signed-off-by: Jakub Kicinski

netpoll: Use rtnl_dereference() for npinfo pointer access

2024-12-05T02:41:37+00:00

In the __netpoll_setup() function, when accessing the device's npinfo
pointer, replace rcu_access_pointer() with rtnl_dereference(). This
change is more appropriate, as suggested by Herbert Xu[1].

The function is called with the RTNL mutex held, and the pointer is
being dereferenced later, so, dereference earlier and just reuse the
pointer for the if/else.

The replacement ensures correct pointer access while maintaining
the existing locking and RCU semantics of the netpoll subsystem.

Link: https://lore.kernel.org/lkml/Zz1cKZYt1e7elibV@gondor.apana.org.au/ [1]
Suggested-by: Herbert Xu 
Signed-off-by: Breno Leitao 
Reviewed-by: Jacob Keller 
Acked-by: Herbert Xu 
Link: https://patch.msgid.link/20241202-netpoll_rcu_herbet_fix-v2-1-2b9d58edc76a@debian.org
Signed-off-by: Jakub Kicinski