Preserve sockets bindings; this includes both resulting from an explicit
bind() and those implicitly bound through autobind during connect().
Prevents socket unbinding during a transport reassignment, which fixes a
use-after-free:
1. vsock_create() (refcnt=1) calls vsock_insert_unbound() (refcnt=2)
2. transport->release() calls vsock_remove_bound() without checking if
sk was bound and moved to bound list (refcnt=1)
3. vsock_bind() assumes sk is in unbound list and before
__vsock_insert_bound(vsock_bound_sockets()) calls
__vsock_remove_bound() which does:
list_del_init(&vsk->bound_table); // nop
sock_put(&vsk->sk); // refcnt=0
BUG: KASAN: slab-use-after-free in __vsock_bind+0x62e/0x730
Read of size 4 at addr ffff88816b46a74c by task a.out/2057
dump_stack_lvl+0x68/0x90
print_report+0x174/0x4f6
kasan_report+0xb9/0x190
__vsock_bind+0x62e/0x730
vsock_bind+0x97/0xe0
__sys_bind+0x154/0x1f0
__x64_sys_bind+0x6e/0xb0
do_syscall_64+0x93/0x1b0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Allocated by task 2057:
kasan_save_stack+0x1e/0x40
kasan_save_track+0x10/0x30
__kasan_slab_alloc+0x85/0x90
kmem_cache_alloc_noprof+0x131/0x450
sk_prot_alloc+0x5b/0x220
sk_alloc+0x2c/0x870
__vsock_create.constprop.0+0x2e/0xb60
vsock_create+0xe4/0x420
__sock_create+0x241/0x650
__sys_socket+0xf2/0x1a0
__x64_sys_socket+0x6e/0xb0
do_syscall_64+0x93/0x1b0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Freed by task 2057:
kasan_save_stack+0x1e/0x40
kasan_save_track+0x10/0x30
kasan_save_free_info+0x37/0x60
__kasan_slab_free+0x4b/0x70
kmem_cache_free+0x1a1/0x590
__sk_destruct+0x388/0x5a0
__vsock_bind+0x5e1/0x730
vsock_bind+0x97/0xe0
__sys_bind+0x154/0x1f0
__x64_sys_bind+0x6e/0xb0
do_syscall_64+0x93/0x1b0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 7 PID: 2057 at lib/refcount.c:25 refcount_warn_saturate+0xce/0x150
RIP: 0010:refcount_warn_saturate+0xce/0x150
__vsock_bind+0x66d/0x730
vsock_bind+0x97/0xe0
__sys_bind+0x154/0x1f0
__x64_sys_bind+0x6e/0xb0
do_syscall_64+0x93/0x1b0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
refcount_t: underflow; use-after-free.
WARNING: CPU: 7 PID: 2057 at lib/refcount.c:28 refcount_warn_saturate+0xee/0x150
RIP: 0010:refcount_warn_saturate+0xee/0x150
vsock_remove_bound+0x187/0x1e0
__vsock_release+0x383/0x4a0
vsock_release+0x90/0x120
__sock_release+0xa3/0x250
sock_close+0x14/0x20
__fput+0x359/0xa80
task_work_run+0x107/0x1d0
do_exit+0x847/0x2560
do_group_exit+0xb8/0x250
__x64_sys_exit_group+0x3a/0x50
x64_sys_call+0xfec/0x14f0
do_syscall_64+0x93/0x1b0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Fixes: c0cfa2d8a7 ("vsock: add multi-transports support")
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://patch.msgid.link/20250128-vsock-transport-vs-autobind-v3-1-1cf57065b770@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The sanity check that both source and destination are set when symmetric
RSS hash is requested is only relevant for ETHTOOL_SRXFH (rx-flow-hash),
it should not be performed on any other commands (e.g.
ETHTOOL_SRXCLSRLINS/ETHTOOL_SRXCLSRLDEL).
This resolves accessing uninitialized 'info.data' field, and fixes false
errors in rule insertion:
# ethtool --config-ntuple eth2 flow-type ip4 dst-ip 255.255.255.255 action -1 loc 0
rmgr: Cannot insert RX class rule: Invalid argument
Cannot insert classification rule
Fixes: 13e59344fb ("net: ethtool: add support for symmetric-xor RSS hash")
Cc: Ahmed Zaki <ahmed.zaki@intel.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250126191845.316589-1-gal@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Steffen Klassert says:
====================
pull request (net): ipsec 2025-01-27
1) Fix incrementing the upper 32 bit sequence numbers for GSO skbs.
From Jianbo Liu.
2) Fix an out-of-bounds read on xfrm state lookup.
From Florian Westphal.
3) Fix secpath handling on packet offload mode.
From Alexandre Cassen.
4) Fix the usage of skb->sk in the xfrm layer.
5) Don't disable preemption while looking up cache state
to fix PREEMPT_RT.
From Sebastian Sewior.
* tag 'ipsec-2025-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
xfrm: Don't disable preemption while looking up cache state.
xfrm: Fix the usage of skb->sk
xfrm: delete intermediate secpath entry in packet offload mode
xfrm: state: fix out-of-bounds read during lookup
xfrm: replay: Fix the update of replay_esn->oseq_hi for GSO
====================
Link: https://patch.msgid.link/20250127060757.3946314-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In its address list, afs now retains pointers to and refs on one or more
rxrpc_peer objects. The address list is freed under RCU and at this time,
it puts the refs on those peers.
Now, when an rxrpc_peer object runs out of refs, it gets removed from the
peer hash table and, for that, rxrpc has to take a spinlock. However, it
is now being called from afs's RCU cleanup, which takes place in BH
context - but it is just taking an ordinary spinlock.
The put may also be called from non-BH context, and so there exists the
possibility of deadlock if the BH-based RCU cleanup happens whilst the hash
spinlock is held. This led to the attached lockdep complaint.
Fix this by changing spinlocks of rxnet->peer_hash_lock back to
BH-disabling locks.
================================
WARNING: inconsistent lock state
6.13.0-rc5-build2+ #1223 Tainted: G E
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
swapper/1/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
ffff88810babe228 (&rxnet->peer_hash_lock){+.?.}-{3:3}, at: rxrpc_put_peer+0xcb/0x180
{SOFTIRQ-ON-W} state was registered at:
mark_usage+0x164/0x180
__lock_acquire+0x544/0x990
lock_acquire.part.0+0x103/0x280
_raw_spin_lock+0x2f/0x40
rxrpc_peer_keepalive_worker+0x144/0x440
process_one_work+0x486/0x7c0
process_scheduled_works+0x73/0x90
worker_thread+0x1c8/0x2a0
kthread+0x19b/0x1b0
ret_from_fork+0x24/0x40
ret_from_fork_asm+0x1a/0x30
irq event stamp: 972402
hardirqs last enabled at (972402): [<ffffffff8244360e>] _raw_spin_unlock_irqrestore+0x2e/0x50
hardirqs last disabled at (972401): [<ffffffff82443328>] _raw_spin_lock_irqsave+0x18/0x60
softirqs last enabled at (972300): [<ffffffff810ffbbe>] handle_softirqs+0x3ee/0x430
softirqs last disabled at (972313): [<ffffffff810ffc54>] __irq_exit_rcu+0x44/0x110
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&rxnet->peer_hash_lock);
<Interrupt>
lock(&rxnet->peer_hash_lock);
*** DEADLOCK ***
1 lock held by swapper/1/0:
#0: ffffffff83576be0 (rcu_callback){....}-{0:0}, at: rcu_lock_acquire+0x7/0x30
stack backtrace:
CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Tainted: G E 6.13.0-rc5-build2+ #1223
Tainted: [E]=UNSIGNED_MODULE
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Call Trace:
<IRQ>
dump_stack_lvl+0x57/0x80
print_usage_bug.part.0+0x227/0x240
valid_state+0x53/0x70
mark_lock_irq+0xa5/0x2f0
mark_lock+0xf7/0x170
mark_usage+0xe1/0x180
__lock_acquire+0x544/0x990
lock_acquire.part.0+0x103/0x280
_raw_spin_lock+0x2f/0x40
rxrpc_put_peer+0xcb/0x180
afs_free_addrlist+0x46/0x90 [kafs]
rcu_do_batch+0x2d2/0x640
rcu_core+0x2f7/0x350
handle_softirqs+0x1ee/0x430
__irq_exit_rcu+0x44/0x110
irq_exit_rcu+0xa/0x30
sysvec_apic_timer_interrupt+0x7f/0xa0
</IRQ>
Fixes: 72904d7b9b ("rxrpc, afs: Allow afs to pin rxrpc_peer objects")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/2095618.1737622752@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Page ppol tried to cache the NAPI ID in page pool info to avoid
having a dependency on the life cycle of the NAPI instance.
Since commit under Fixes the NAPI ID is not populated until
napi_enable() and there's a good chance that page pool is
created before NAPI gets enabled.
Protect the NAPI pointer with the existing page pool mutex,
the reading path already holds it. napi_id itself we need
to READ_ONCE(), it's protected by netdev_lock() which are
not holding in page pool.
Before this patch napi IDs were missing for mlx5:
# ./cli.py --spec netlink/specs/netdev.yaml --dump page-pool-get
[{'id': 144, 'ifindex': 2, 'inflight': 3072, 'inflight-mem': 12582912},
{'id': 143, 'ifindex': 2, 'inflight': 5568, 'inflight-mem': 22806528},
{'id': 142, 'ifindex': 2, 'inflight': 5120, 'inflight-mem': 20971520},
{'id': 141, 'ifindex': 2, 'inflight': 4992, 'inflight-mem': 20447232},
...
After:
[{'id': 144, 'ifindex': 2, 'inflight': 3072, 'inflight-mem': 12582912,
'napi-id': 565},
{'id': 143, 'ifindex': 2, 'inflight': 4224, 'inflight-mem': 17301504,
'napi-id': 525},
{'id': 142, 'ifindex': 2, 'inflight': 4288, 'inflight-mem': 17563648,
'napi-id': 524},
...
Fixes: 86e25f40aa ("net: napi: Add napi_config")
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20250123231620.1086401-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Copy of the rationale from 790071347a:
Change ndo_set_mac_address to dev_set_mac_address because
dev_set_mac_address provides a way to notify network layer about MAC
change. In other case, services may not aware about MAC change and keep
using old one which set from network adapter driver.
As example, DHCP client from systemd do not update MAC address without
notification from net subsystem which leads to the problem with acquiring
the right address from DHCP server.
Since dev_set_mac_address requires RTNL lock the operation can not be
performed directly in the response handler, see
9e2bbab94b.
The way of selecting the first suitable MAC address from the list is
changed, instead of having the driver check it this patch just assumes
any valid MAC should be good.
Fixes: b8291cf3d1 ("net/ncsi: Add NC-SI 1.2 Get MC MAC Address command")
Signed-off-by: Paul Fertser <fercerpav@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For the state cache lookup xfrm_input_state_lookup() first disables
preemption, to remain on the CPU and then retrieves a per-CPU pointer.
Within the preempt-disable section it also acquires
netns_xfrm::xfrm_state_lock, a spinlock_t. This lock must not be
acquired with explicit disabled preemption (such as by get_cpu())
because this lock becomes a sleeping lock on PREEMPT_RT.
To remain on the same CPU is just an optimisation for the CPU local
lookup. The actual modification of the per-CPU variable happens with
netns_xfrm::xfrm_state_lock acquired.
Remove get_cpu() and use the state_cache_input on the current CPU.
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Closes: https://lore.kernel.org/all/CAADnVQKkCLaj=roayH=Mjiiqz_svdf1tsC3OE4EC0E=mAD+L1A@mail.gmail.com/
Fixes: 81a331a0e7 ("xfrm: Add an inbound percpu state cache.")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
The NCSI state machine as it's currently implemented assumes that
transition to the next logical state is performed either explicitly by
calling `schedule_work(&ndp->work)` to re-queue itself or implicitly
after processing the predefined (ndp->pending_req_num) number of
replies. Thus to avoid the configuration FSM from advancing prematurely
and getting out of sync with the process it's essential to not skip
waiting for a reply.
This patch makes the code wait for reception of the Deselect Package
response for the last package probed before proceeding to channel
configuration.
Thanks go to Potin Lai and Cosmo Chou for the initial investigation and
testing.
Fixes: 8e13f70be0 ("net/ncsi: Probe single packages to avoid conflict")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Fertser <fercerpav@gmail.com>
Link: https://patch.msgid.link/20250116152900.8656-1-fercerpav@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pull networking updates from Paolo Abeni:
"This is slightly smaller than usual, with the most interesting work
being still around RTNL scope reduction.
Core:
- More core refactoring to reduce the RTNL lock contention, including
preparatory work for the per-network namespace RTNL lock, replacing
RTNL lock with a per device-one to protect NAPI-related net device
data and moving synchronize_net() calls outside such lock.
- Extend drop reasons usage, adding net scheduler, AF_UNIX, bridge
and more specific TCP coverage.
- Reduce network namespace tear-down time by removing per-subsystems
synchronize_net() in tipc and sched.
- Add flow label selector support for fib rules, allowing traffic
redirection based on such header field.
Netfilter:
- Do not remove netdev basechain when last device is gone, allowing
netdev basechains without devices.
- Revisit the flowtable teardown strategy, dealing better with fin,
reset and re-open events.
- Scale-up IP-vs connection dumping by avoiding linear search on each
restart.
Protocols:
- A significant XDP socket refactor, consolidating and optimizing
several helpers into the core
- Better scaling of ICMP rate-limiting, by removing false-sharing in
inet peers handling.
- Introduces netlink notifications for multicast IPv4 and IPv6
address changes.
- Add ipsec support for IP-TFS/AggFrag encapsulation, allowing
aggregation and fragmentation of the inner IP.
- Add sysctl to configure TIME-WAIT reuse delay for TCP sockets, to
avoid local port exhaustion issues when the average connection
lifetime is very short.
- Support updating keys (re-keying) for connections using kernel TLS
(for TLS 1.3 only).
- Support ipv4-mapped ipv6 address clients in smc-r v2.
- Add support for jumbo data packet transmission in RxRPC sockets,
gluing multiple data packets in a single UDP packet.
- Support RxRPC RACK-TLP to manage packet loss and retransmission in
conjunction with the congestion control algorithm.
Driver API:
- Introduce a unified and structured interface for reporting PHY
statistics, exposing consistent data across different H/W via
ethtool.
- Make timestamping selectable, allow the user to select the desired
hwtstamp provider (PHY or MAC) administratively.
- Add support for configuring a header-data-split threshold (HDS)
value via ethtool, to deal with partial or buggy H/W
implementation.
- Consolidate DSA drivers Energy Efficiency Ethernet support.
- Add EEE management to phylink, making use of the phylib
implementation.
- Add phylib support for in-band capabilities negotiation.
- Simplify how phylib-enabled mac drivers expose the supported
interfaces.
Tests and tooling:
- Make the YNL tool package-friendly to make it easier to deploy it
separately from the kernel.
- Increase TCP selftest coverage importing several packetdrill
test-cases.
- Regenerate the ethtool uapi header from the YNL spec, to ease
maintenance and future development.
- Add YNL support for decoding the link types used in net self-tests,
allowing a single build to run both net and drivers/net.
Drivers:
- Ethernet high-speed NICs:
- nVidia/Mellanox (mlx5):
- add cross E-Switch QoS support
- add SW Steering support for ConnectX-8
- implement support for HW-Managed Flow Steering, improving the
rule deletion/insertion rate
- support for multi-host LAG
- Intel (ixgbe, ice, igb):
- ice: add support for devlink health events
- ixgbe: add initial support for E610 chipset variant
- igb: add support for AF_XDP zero-copy
- Meta:
- add support for basic RSS config
- allow changing the number of channels
- add hardware monitoring support
- Broadcom (bnxt):
- implement TCP data split and HDS threshold ethtool support,
enabling Device Memory TCP.
- Marvell Octeon:
- implement egress ipsec offload support for the cn10k family
- Hisilicon (HIBMC):
- implement unicast MAC filtering
- Ethernet NICs embedded and virtual:
- Convert UDP tunnel drivers to NETDEV_PCPU_STAT_DSTATS, avoiding
contented atomic operations for drop counters
- Freescale:
- quicc: phylink conversion
- enetc: support Tx and Rx checksum offload and improve TSO
performances
- MediaTek:
- airoha: introduce support for ETS and HTB Qdisc offload
- Microchip:
- lan78XX USB: preparation work for phylink conversion
- Synopsys (stmmac):
- support DWMAC IP on NXP Automotive SoCs S32G2xx/S32G3xx/S32R45
- refactor EEE support to leverage the new driver API
- optimize DMA and cache access to increase raw RX performances
by 40%
- TI:
- icssg-prueth: add multicast filtering support for VLAN
interface
- netkit:
- add ability to configure head/tailroom
- VXLAN:
- accepts packets with user-defined reserved bit
- Ethernet switches:
- Microchip:
- lan969x: add RGMII support
- lan969x: improve TX and RX performance using the FDMA engine
- nVidia/Mellanox:
- move Tx header handling to PCI driver, to ease XDP support
- Ethernet PHYs:
- Texas Instruments DP83822:
- add support for GPIO2 clock output
- Realtek:
- 8169: add support for RTL8125D rev.b
- rtl822x: add hwmon support for the temperature sensor
- Microchip:
- add support for RDS PTP hardware
- consolidate periodic output signal generation
- CAN:
- several DT-bindings to DT schema conversions
- tcan4x5x:
- add HW standby support
- support nWKRQ voltage selection
- kvaser:
- allowing Bus Error Reporting runtime configuration
- WiFi:
- the on-going Multi-Link Operation (MLO) effort continues,
affecting both the stack and in drivers
- mac80211/cfg80211:
- Emergency Preparedness Communication Services (EPCS) station
mode support
- support for adding and removing station links for MLO
- add support for WiFi 7/EHT mesh over 320 MHz channels
- report Tx power info for each link
- RealTek (rtw88):
- enable USB Rx aggregation and USB 3 to improve performance
- LED support
- RealTek (rtw89):
- refactor power save to support Multi-Link Operations
- add support for RTL8922AE-VS variant
- MediaTek (mt76):
- single wiphy multiband support (preparation for MLO)
- p2p device support
- add TP-Link TXE50UH USB adapter support
- Qualcomm (ath10k):
- support for the QCA6698AQ IP core
- Qualcomm (ath12k):
- enable MLO for QCN9274
- Bluetooth:
- Allow sysfs to trigger hdev reset, to allow recovering devices
not responsive from user-space
- MediaTek: add support for MT7922, MT7925, MT7921e devices
- Realtek: add support for RTL8851BE devices
- Qualcomm: add support for WCN785x devices
- ISO: allow BIG re-sync"
* tag 'net-next-6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1386 commits)
net/rose: prevent integer overflows in rose_setsockopt()
net: phylink: fix regression when binding a PHY
net: ethernet: ti: am65-cpsw: streamline TX queue creation and cleanup
net: ethernet: ti: am65-cpsw: streamline RX queue creation and cleanup
net: ethernet: ti: am65-cpsw: ensure proper channel cleanup in error path
ipv6: Convert inet6_rtm_deladdr() to per-netns RTNL.
ipv6: Convert inet6_rtm_newaddr() to per-netns RTNL.
ipv6: Move lifetime validation to inet6_rtm_newaddr().
ipv6: Set cfg.ifa_flags before device lookup in inet6_rtm_newaddr().
ipv6: Pass dev to inet6_addr_add().
ipv6: Convert inet6_ioctl() to per-netns RTNL.
ipv6: Hold rtnl_net_lock() in addrconf_init() and addrconf_cleanup().
ipv6: Hold rtnl_net_lock() in addrconf_dad_work().
ipv6: Hold rtnl_net_lock() in addrconf_verify_work().
ipv6: Convert net.ipv6.conf.${DEV}.XXX sysctl to per-netns RTNL.
ipv6: Add __in6_dev_get_rtnl_net().
net: stmmac: Drop redundant skb_mark_for_recycle() for SKB frags
net: mii: Fix the Speed display when the network cable is not connected
sysctl net: Remove macro checks for CONFIG_SYSCTL
eth: bnxt: update header sizing defaults
...
Pull lsm updates from Paul Moore:
- Improved handling of LSM "secctx" strings through lsm_context struct
The LSM secctx string interface is from an older time when only one
LSM was supported, migrate over to the lsm_context struct to better
support the different LSMs we now have and make it easier to support
new LSMs in the future.
These changes explain the Rust, VFS, and networking changes in the
diffstat.
- Only build lsm_audit.c if CONFIG_SECURITY and CONFIG_AUDIT are
enabled
Small tweak to be a bit smarter about when we build the LSM's common
audit helpers.
- Check for absurdly large policies from userspace in SafeSetID
SafeSetID policies rules are fairly small, basically just "UID:UID",
it easy to impose a limit of KMALLOC_MAX_SIZE on policy writes which
helps quiet a number of syzbot related issues. While work is being
done to address the syzbot issues through other mechanisms, this is a
trivial and relatively safe fix that we can do now.
- Various minor improvements and cleanups
A collection of improvements to the kernel selftests, constification
of some function parameters, removing redundant assignments, and
local variable renames to improve readability.
* tag 'lsm-pr-20250121' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm:
lockdown: initialize local array before use to quiet static analysis
safesetid: check size of policy writes
net: corrections for security_secid_to_secctx returns
lsm: rename variable to avoid shadowing
lsm: constify function parameters
security: remove redundant assignment to return variable
lsm: Only build lsm_audit.c if CONFIG_SECURITY and CONFIG_AUDIT are set
selftests: refactor the lsm `flags_overset_lsm_set_self_attr` test
binder: initialize lsm_context structure
rust: replace lsm context+len with lsm_context
lsm: secctx provider check on release
lsm: lsm_context in security_dentry_init_security
lsm: use lsm_context in security_inode_getsecctx
lsm: replace context+len with lsm_context
lsm: ensure the correct LSM context releaser
Pull kthread updates from Frederic Weisbecker:
"Kthreads affinity follow either of 4 existing different patterns:
1) Per-CPU kthreads must stay affine to a single CPU and never
execute relevant code on any other CPU. This is currently handled
by smpboot code which takes care of CPU-hotplug operations.
Affinity here is a correctness constraint.
2) Some kthreads _have_ to be affine to a specific set of CPUs and
can't run anywhere else. The affinity is set through
kthread_bind_mask() and the subsystem takes care by itself to
handle CPU-hotplug operations. Affinity here is assumed to be a
correctness constraint.
3) Per-node kthreads _prefer_ to be affine to a specific NUMA node.
This is not a correctness constraint but merely a preference in
terms of memory locality. kswapd and kcompactd both fall into this
category. The affinity is set manually like for any other task and
CPU-hotplug is supposed to be handled by the relevant subsystem so
that the task is properly reaffined whenever a given CPU from the
node comes up. Also care should be taken so that the node affinity
doesn't cross isolated (nohz_full) cpumask boundaries.
4) Similar to the previous point except kthreads have a _preferred_
affinity different than a node. Both RCU boost kthreads and RCU
exp kworkers fall into this category as they refer to "RCU nodes"
from a distinctly distributed tree.
Currently the preferred affinity patterns (3 and 4) have at least 4
identified users, with more or less success when it comes to handle
CPU-hotplug operations and CPU isolation. Each of which do it in its
own ad-hoc way.
This is an infrastructure proposal to handle this with the following
API changes:
- kthread_create_on_node() automatically affines the created kthread
to its target node unless it has been set as per-cpu or bound with
kthread_bind[_mask]() before the first wake-up.
- kthread_affine_preferred() is a new function that can be called
right after kthread_create_on_node() to specify a preferred
affinity different than the specified node.
When the preferred affinity can't be applied because the possible
targets are offline or isolated (nohz_full), the kthread is affine to
the housekeeping CPUs (which means to all online CPUs most of the time
or only the non-nohz_full CPUs when nohz_full= is set).
kswapd, kcompactd, RCU boost kthreads and RCU exp kworkers have been
converted, along with a few old drivers.
Summary of the changes:
- Consolidate a bunch of ad-hoc implementations of
kthread_run_on_cpu()
- Introduce task_cpu_fallback_mask() that defines the default last
resort affinity of a task to become nohz_full aware
- Add some correctness check to ensure kthread_bind() is always
called before the first kthread wake up.
- Default affine kthread to its preferred node.
- Convert kswapd / kcompactd and remove their halfway working ad-hoc
affinity implementation
- Implement kthreads preferred affinity
- Unify kthread worker and kthread API's style
- Convert RCU kthreads to the new API and remove the ad-hoc affinity
implementation"
* tag 'kthread-for-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks:
kthread: modify kernel-doc function name to match code
rcu: Use kthread preferred affinity for RCU exp kworkers
treewide: Introduce kthread_run_worker[_on_cpu]()
kthread: Unify kthread_create_on_cpu() and kthread_create_worker_on_cpu() automatic format
rcu: Use kthread preferred affinity for RCU boost
kthread: Implement preferred affinity
mm: Create/affine kswapd to its preferred node
mm: Create/affine kcompactd to its preferred node
kthread: Default affine kthread to its preferred NUMA node
kthread: Make sure kthread hasn't started while binding it
sched,arm64: Handle CPU isolation on last resort fallback rq selection
arm64: Exclude nohz_full CPUs from 32bits el0 support
lib: test_objpool: Use kthread_run_on_cpu()
kallsyms: Use kthread_run_on_cpu()
soc/qman: test: Use kthread_run_on_cpu()
arm/bL_switcher: Use kthread_run_on_cpu()
In case of possible unpredictably large arguments passed to
rose_setsockopt() and multiplied by extra values on top of that,
integer overflows may occur.
Do the safest minimum and fix these issues by checking the
contents of 'opt' and returning -EINVAL if they are too large. Also,
switch to unsigned int and remove useless check for negative 'opt'
in ROSE_IDLE case.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://patch.msgid.link/20250115164220.19954-1-n.zhandarovich@fintech.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
inet6_addr_add() and inet6_addr_modify() have the same code to validate
IPv6 lifetime that is done under RTNL.
Let's factorise it out to inet6_rtm_newaddr() so that we can validate
the lifetime without RTNL later.
Note that inet6_addr_add() is called from addrconf_add_ifaddr(), but the
lifetime is INFINITY_LIFE_TIME in the path, so expires and flags are 0.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250115080608.28127-10-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We will convert inet6_rtm_newaddr() to per-netns RTNL.
Except for IFA_F_OPTIMISTIC, cfg.ifa_flags can be set before
__dev_get_by_index().
Let's move ifa_flags setup before __dev_get_by_index() so that
we can set ifa_flags without RTNL.
Also, now it's moved before tb[IFA_CACHEINFO] in preparing for
the next patch.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250115080608.28127-9-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
inet6_addr_add() is called from inet6_rtm_newaddr() and
addrconf_add_ifaddr().
inet6_addr_add() looks up dev by __dev_get_by_index(), but
it's already done in inet6_rtm_newaddr().
Let's move the 2nd lookup to addrconf_add_ifaddr() and pass
dev to inet6_addr_add().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250115080608.28127-8-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
These functions are called from inet6_ioctl() with a socket's netns
and hold RTNL.
* SIOCSIFADDR : addrconf_add_ifaddr()
* SIOCDIFADDR : addrconf_del_ifaddr()
* SIOCSIFDSTADDR : addrconf_set_dstaddr()
Let's use rtnl_net_lock().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250115080608.28127-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following batch contains Netfilter updates for net-next:
1) Unbreak set size settings for rbtree set backend, intervals in
rbtree are represented as two elements, this detailed is leaked
to userspace leading to bogus ENOSPC from control plane.
2) Remove dead code in br_netfilter's br_nf_pre_routing_finish()
due to never matching error when looking up for route,
from Antoine Tenart.
3) Simplify check for device already in use in flowtable,
from Phil Sutter.
4) Three patches to restore interface name field in struct nft_hook
and use it, this is to prepare for wildcard interface support.
From Phil Sutter.
5) Do not remove netdev basechain when last device is gone, this is
for consistency with the flowtable behaviour. This allows for netdev
basechains without devices. Another patch to simplify netdev event
notifier after this update. Also from Phil.
6) Two patches to add missing spinlock when flowtable updates TCP
state flags, from Florian Westphal.
7) Simplify __nf_ct_refresh_acct() by removing skbuff parameter,
also from Florian.
8) Flowtable gc now extends ct timeout for offloaded flow. This
is to address a possible race that leads to handing over flow
to classic path with long ct timeouts.
9) Tear down flow if cached rt_mtu is stale, before this patch,
packet is handed over to classic path but flow entry still remained
in place.
10) Revisit the flowtable teardown strategy, which was originally
designed to release flowtable hardware entries early. Add a new
CLOSING flag that still allows hardware to release entries when
fin/rst is seen, but keeps the flow entry in place when the
TCP connection is closed. Release flow after timeout or when a new
syn packet is seen for TCP reopen scenario.
* tag 'nf-next-25-01-19' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
netfilter: flowtable: add CLOSING state
netfilter: flowtable: teardown flow if cached mtu is stale
netfilter: conntrack: rework offload nf_conn timeout extension logic
netfilter: conntrack: remove skb argument from nf_ct_refresh
netfilter: nft_flow_offload: update tcp state flags under lock
netfilter: nft_flow_offload: clear tcp MAXACK flag before moving to slowpath
netfilter: nf_tables: Simplify chain netdev notifier
netfilter: nf_tables: Tolerate chains with no remaining hooks
netfilter: nf_tables: Compare netdev hooks based on stored name
netfilter: nf_tables: Use stored ifname in netdev hook dumps
netfilter: nf_tables: Store user-defined hook ifname
netfilter: nf_tables: Flowtable hook's pf value never varies
netfilter: br_netfilter: remove unused conditional and dead code
netfilter: nf_tables: fix set size with rbtree backend
====================
Link: https://patch.msgid.link/20250119172051.8261-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This is a follow-up of commit d460b04bc4 ("af_unix: Clean up
error paths in unix_stream_sendmsg().").
If we initialise skb with NULL in unix_stream_sendmsg(), we can
reuse the existing out_pipe label for the SEND_SHUTDOWN check.
Let's rename it and adjust the existing label as out_pipe_lock.
While at it, size and data_len are moved to the while loop scope.
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250116053441.5758-9-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
unix_dgram_disconnected() is called from two places:
1. when a connect()ed socket dis-connect()s or re-connect()s to
another socket
2. when sendmsg() fails because the peer socket that the client
has connect()ed to has been close()d
Then, the client's recv queue is purged to remove all messages from
the old peer socket.
Let's define a new drop reason for that case.
# echo 1 > /sys/kernel/tracing/events/skb/kfree_skb/enable
# python3
>>> from socket import *
>>>
>>> # s1 has a message from s2
>>> s1, s2 = socketpair(AF_UNIX, SOCK_DGRAM)
>>> s2.send(b'hello world')
>>>
>>> # re-connect() drops the message from s2
>>> s3 = socket(AF_UNIX, SOCK_DGRAM)
>>> s3.bind('')
>>> s1.connect(s3.getsockname())
# cat /sys/kernel/tracing/trace_pipe
python3-250 ... kfree_skb: ... location=skb_queue_purge_reason+0xdc/0x110 reason: UNIX_DISCONNECT
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250116053441.5758-8-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
unix_stream_read_skb() is called when BPF SOCKMAP reads some data
from a socket in the map.
SOCKMAP does not support MSG_OOB, and reading OOB results in a drop.
Let's set drop reasons respectively.
* SOCKET_CLOSE : the socket in SOCKMAP was close()d
* UNIX_SKIP_OOB : OOB was read from the socket in SOCKMAP
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250116053441.5758-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
AF_UNIX SOCK_STREAM socket supports MSG_OOB.
When OOB data is sent to a socket, recv() will break at that point.
If the next recv() does not have MSG_OOB, the normal data following
the OOB data is returned.
Then, the OOB skb is dropped.
Let's define a new drop reason for that case in manage_oob().
# echo 1 > /sys/kernel/tracing/events/skb/kfree_skb/enable
# python3
>>> from socket import *
>>> s1, s2 = socketpair(AF_UNIX)
>>> s1.send(b'a', MSG_OOB)
>>> s1.send(b'b')
>>> s2.recv(2)
b'b'
# cat /sys/kernel/tracing/trace_pipe
...
python3-223 ... kfree_skb: ... location=unix_stream_read_generic+0x59e/0xc20 reason: UNIX_SKIP_OOB
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250116053441.5758-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Inflight file descriptors by SCM_RIGHTS hold references to the
struct file.
AF_UNIX sockets could hold references to each other, forming
reference cycles.
Once such sockets are close()d without the fd recv()ed, they
will be unaccessible from userspace but remain in kernel.
__unix_gc() garbage-collects skb with the dead file descriptors
and frees them by __skb_queue_purge().
Let's set SKB_DROP_REASON_SOCKET_CLOSE there.
# echo 1 > /sys/kernel/tracing/events/skb/kfree_skb/enable
# python3
>>> from socket import *
>>> from array import array
>>>
>>> # Create a reference cycle
>>> s1 = socket(AF_UNIX, SOCK_DGRAM)
>>> s1.bind('')
>>> s1.sendmsg([b"nop"], [(SOL_SOCKET, SCM_RIGHTS, array("i", [s1.fileno()]))], 0, s1.getsockname())
>>> s1.close()
>>>
>>> # Trigger GC
>>> s2 = socket(AF_UNIX)
>>> s2.close()
# cat /sys/kernel/tracing/trace_pipe
...
kworker/u16:2-42 ... kfree_skb: ... location=__unix_gc+0x4ad/0x580 reason: SOCKET_CLOSE
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250116053441.5758-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
unix_release_sock() is called when the last refcnt of struct file
is released.
Let's define a new drop reason SKB_DROP_REASON_SOCKET_CLOSE and
set it for kfree_skb() in unix_release_sock().
# echo 1 > /sys/kernel/tracing/events/skb/kfree_skb/enable
# python3
>>> from socket import *
>>> s1, s2 = socketpair(AF_UNIX)
>>> s1.send(b'hello world')
>>> s2.close()
# cat /sys/kernel/tracing/trace_pipe
...
python3-280 ... kfree_skb: ... protocol=0 location=unix_release_sock+0x260/0x420 reason: SOCKET_CLOSE
To be precise, unix_release_sock() is also called for a new child
socket in unix_stream_connect() when something fails, but the new
sk does not have skb in the recv queue then and no event is logged.
Note that only tcp_inbound_ao_hash() uses a similar drop reason,
SKB_DROP_REASON_TCP_CLOSE, and this can be generalised later.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250116053441.5758-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
I noticed that HyStart incorrectly marks the start of rounds,
leading to inaccurate measurements of ACK train lengths and
resetting the `ca->sample_cnt` variable. This inaccuracy can impact
HyStart's functionality in terminating exponential cwnd growth during
Slow-Start, potentially degrading TCP performance.
The issue arises because the changes introduced in commit 4e1fddc98d
("tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows")
moved the caller of the `bictcp_hystart_reset` function inside the `hystart_update` function.
This modification added an additional condition for triggering the caller,
requiring that (tcp_snd_cwnd(tp) >= hystart_low_window) must also
be satisfied before invoking `bictcp_hystart_reset`.
This fix ensures that `bictcp_hystart_reset` is correctly called
at the start of a new round, regardless of the congestion window size.
This is achieved by moving the condition
(tcp_snd_cwnd(tp) >= hystart_low_window)
from before calling `bictcp_hystart_reset` to after it.
I tested with a client and a server connected through two Linux software routers.
In this setup, the minimum RTT was 150 ms, the bottleneck bandwidth was 50 Mbps,
and the bottleneck buffer size was 1 BDP, calculated as (50M / 1514 / 8) * 0.150 = 619 packets.
I conducted the test twice, transferring data from the server to the client for 1.5 seconds.
Before the patch was applied, HYSTART-DELAY stopped the exponential growth of cwnd when
cwnd = 516, and the bottleneck link was not yet saturated (516 < 619).
After the patch was applied, HYSTART-ACK-TRAIN stopped the exponential growth of cwnd when
cwnd = 632, and the bottleneck link was saturated (632 > 619).
In this test, applying the patch resulted in 300 KB more data delivered.
Fixes: 4e1fddc98d ("tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows")
Signed-off-by: Mahdi Arghavani <ma.arghavani@yahoo.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Haibo Zhang <haibo.zhang@otago.ac.nz>
Cc: David Eyers <david.eyers@otago.ac.nz>
Cc: Abbas Arghavani <abbas.arghavani@mdu.se>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On a 32bit system the "keylen + sizeof(struct tipc_aead_key)" math could
have an integer wrapping issue. It doesn't matter because the "keylen"
is checked on the next line, but just to make life easier for static
analysis tools, let's re-order these conditions and avoid the integer
overflow.
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
aarp_send_probe_phase1() used to work by calling ndo_do_ioctl of
appletalk drivers ltpc or cops, but these two drivers have been removed
since the following commits:
commit 03dcb90dbf ("net: appletalk: remove Apple/Farallon LocalTalk PC
support")
commit 00f3696f75 ("net: appletalk: remove cops support")
Thus aarp_send_probe_phase1() no longer works, so drop it. (found by
code inspection)
Signed-off-by: 谢致邦 (XIE Zhibang) <Yeking@Red54.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch addresses issues with filter counting in block (tcf_block),
particularly for software bypass scenarios, by introducing a more
accurate mechanism using useswcnt.
Previously, filtercnt and skipswcnt were introduced by:
Commit 2081fd3445 ("net: sched: cls_api: add filter counter") and
Commit f631ef39d8 ("net: sched: cls_api: add skip_sw counter")
filtercnt tracked all tp (tcf_proto) objects added to a block, and
skipswcnt counted tp objects with the skipsw attribute set.
The problem is: a single tp can contain multiple filters, some with skipsw
and others without. The current implementation fails in the case:
When the first filter in a tp has skipsw, both skipswcnt and filtercnt
are incremented, then adding a second filter without skipsw to the same
tp does not modify these counters because tp->counted is already set.
This results in bypass software behavior based solely on skipswcnt
equaling filtercnt, even when the block includes filters without
skipsw. Consequently, filters without skipsw are inadvertently bypassed.
To address this, the patch introduces useswcnt in block to explicitly count
tp objects containing at least one filter without skipsw. Key changes
include:
Whenever a filter without skipsw is added, its tp is marked with usesw
and counted in useswcnt. tc_run() now uses useswcnt to determine software
bypass, eliminating reliance on filtercnt and skipswcnt.
This refined approach prevents software bypass for blocks containing
mixed filters, ensuring correct behavior in tc_run().
Additionally, as atomic operations on useswcnt ensure thread safety and
tp->lock guards access to tp->usesw and tp->counted, the broader lock
down_write(&block->cb_lock) is no longer required in tc_new_tfilter(),
and this resolves a performance regression caused by the filter counting
mechanism during parallel filter insertions.
The improvement can be demonstrated using the following script:
# cat insert_tc_rules.sh
tc qdisc add dev ens1f0np0 ingress
for i in $(seq 16); do
taskset -c $i tc -b rules_$i.txt &
done
wait
Each of rules_$i.txt files above includes 100000 tc filter rules to a
mlx5 driver NIC ens1f0np0.
Without this patch:
# time sh insert_tc_rules.sh
real 0m50.780s
user 0m23.556s
sys 4m13.032s
With this patch:
# time sh insert_tc_rules.sh
real 0m17.718s
user 0m7.807s
sys 3m45.050s
Fixes: 047f340b36 ("net: sched: make skip_sw actually skip software")
Reported-by: Shuang Li <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Tested-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
xfrm assumed to always have a full socket at skb->sk.
This is not always true, so fix it by converting to a
full socket before it is used.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
