In the following patch we want to read dev->allmulti
and dev->promiscuity locklessly from rtnl_fill_ifinfo()
In this patch I change __dev_set_promiscuity() and
__dev_set_allmulti() to write these fields (and dev->flags)
only if they succeed, with WRITE_ONCE() annotations.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
rtnl_fill_ifinfo() can read dev->tx_queue_len locklessly,
granted we add corresponding READ_ONCE()/WRITE_ONCE() annotations.
Add missing READ_ONCE(dev->tx_queue_len) in teql_enqueue()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
We will convert ioctl(SIOCGARP) to RCU, and then we need to copy
dev->name which is currently protected by rtnl_lock().
This patch does the following:
1) Add seqlock netdev_rename_lock to protect dev->name
2) Add netdev_copy_name() that copies dev->name to buffer
under netdev_rename_lock
3) Use netdev_copy_name() in netdev_get_name() and drop
devnet_rename_sem
Suggested-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/netdev/CANn89iJEWs7AYSJqGCUABeVqOCTkErponfZdT5kV-iD=-SajnQ@mail.gmail.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240430015813.71143-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sysctl_skb_defer_max is used in TCP fast path,
move it to net_hodata.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240429134025.1233626-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This came while reviewing commit c4e86b4363 ("net: add two more
call_rcu_hurry()").
Paolo asked if adding one synchronize_rcu() would help.
While synchronize_rcu() does not help, making sure to call
rcu_barrier() before msleep(wait) is definitely helping
to make sure lazy call_rcu() are completed.
Instead of waiting ~100 seconds in my tests, the ref_tracker
splats occurs one time only, and netdev_wait_allrefs_any()
latency is reduced to the strict minimum.
Ideally we should audit our call_rcu() users to make sure
no refcount (or cascading call_rcu()) is held too long,
because rcu_barrier() is quite expensive.
Fixes: 0e4be9e57e ("net: use exponential backoff in netdev_wait_allrefs")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/all/28bbf698-befb-42f6-b561-851c67f464aa@kernel.org/T/#m76d73ed6b03cd930778ac4d20a777f22a08d6824
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is impossible to use init_dummy_netdev together with alloc_netdev()
as the 'setup' argument.
This is because alloc_netdev() initializes some fields in the net_device
structure, and later init_dummy_netdev() memzero them all. This causes
some problems as reported here:
https://lore.kernel.org/all/20240322082336.49f110cc@kernel.org/
Split the init_dummy_netdev() function in two. Create a new function called
init_dummy_netdev_core() that does not memzero the net_device structure.
Then have init_dummy_netdev() memzero-ing and calling
init_dummy_netdev_core(), keeping the old behaviour.
init_dummy_netdev_core() is the new function that could be called as an
argument for alloc_netdev().
Also, create a helper to allocate and initialize dummy net devices,
leveraging init_dummy_netdev_core() as the setup argument. This function
basically simplify the allocation of dummy devices, by allocating and
initializing it. Freeing the device continue to be done through
free_netdev()
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For dummy devices, exit earlier at free_netdev() instead of executing
the whole function. This is necessary, because dummy devices are
special, and shouldn't have the second part of the function executed.
Otherwise reg_state, which is NETREG_DUMMY, will be overwritten and
there will be no way to identify that this is a dummy device. Also, this
device do not need the final put_device(), since dummy devices are not
registered (through register_netdevice()), where the device reference is
increased (at netdev_register_kobject()/device_add()).
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix bad grammar in description of init_dummy_netdev() function. This
topic showed up in the review of the "allocate dummy device dynamically"
patch set.
Suggested-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is the last member in struct rps_dev_flow which should be
protected locklessly. So finish it.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As we can see, rflow->filter can be written/read concurrently, so
lockless access is needed.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Removing one unnecessary reader protection and add another writer
protection to finish the locklessly proctection job.
Note: the removed READ_ONCE() is not needed because we only have to protect
the locklessly reader in the different context (rps_may_expire_flow()).
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the mirred action is used on a classful egress qdisc and a packet is
mirrored or redirected to self we hit a qdisc lock deadlock.
See trace below.
[..... other info removed for brevity....]
[ 82.890906]
[ 82.890906] ============================================
[ 82.890906] WARNING: possible recursive locking detected
[ 82.890906] 6.8.0-05205-g77fadd89fe2d-dirty #213 Tainted: G W
[ 82.890906] --------------------------------------------
[ 82.890906] ping/418 is trying to acquire lock:
[ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at:
__dev_queue_xmit+0x1778/0x3550
[ 82.890906]
[ 82.890906] but task is already holding lock:
[ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at:
__dev_queue_xmit+0x1778/0x3550
[ 82.890906]
[ 82.890906] other info that might help us debug this:
[ 82.890906] Possible unsafe locking scenario:
[ 82.890906]
[ 82.890906] CPU0
[ 82.890906] ----
[ 82.890906] lock(&sch->q.lock);
[ 82.890906] lock(&sch->q.lock);
[ 82.890906]
[ 82.890906] *** DEADLOCK ***
[ 82.890906]
[..... other info removed for brevity....]
Example setup (eth0->eth0) to recreate
tc qdisc add dev eth0 root handle 1: htb default 30
tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \
action mirred egress redirect dev eth0
Another example(eth0->eth1->eth0) to recreate
tc qdisc add dev eth0 root handle 1: htb default 30
tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \
action mirred egress redirect dev eth1
tc qdisc add dev eth1 root handle 1: htb default 30
tc filter add dev eth1 handle 1: protocol ip prio 2 matchall \
action mirred egress redirect dev eth0
We fix this by adding an owner field (CPU id) to struct Qdisc set after
root qdisc is entered. When the softirq enters it a second time, if the
qdisc owner is the same CPU, the packet is dropped to break the loop.
Reported-by: Mingshuai Ren <renmingshuai@huawei.com>
Closes: https://lore.kernel.org/netdev/20240314111713.5979-1-renmingshuai@huawei.com/
Fixes: 3bcb846ca4 ("net: get rid of spin_trylock() in net_tx_action()")
Fixes: e578d9c025 ("net: sched: use counter to break reclassify loops")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20240415210728.36949-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link topologies containing multiple network PHYs attached to the same
net_device can be found when using a PHY as a media converter for use
with an SFP connector, on which an SFP transceiver containing a PHY can
be used.
With the current model, the transceiver's PHY can't be used for
operations such as cable testing, timestamping, macsec offload, etc.
The reason being that most of the logic for these configuration, coming
from either ethtool netlink or ioctls tend to use netdev->phydev, which
in multi-phy systems will reference the PHY closest to the MAC.
Introduce a numbering scheme allowing to enumerate PHY devices that
belong to any netdev, which can in turn allow userspace to take more
precise decisions with regard to each PHY's configuration.
The numbering is maintained per-netdev, in a phy_device_list.
The numbering works similarly to a netdevice's ifindex, with
identifiers that are only recycled once INT_MAX has been reached.
This prevents races that could occur between PHY listing and SFP
transceiver removal/insertion.
The identifiers are assigned at phy_attach time, as the numbering
depends on the netdevice the phy is attached to. The PHY index can be
re-used for PHYs that are persistent.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
For systems that use CPU isolation (via nohz_full), creating or destroying
a socket with SO_TIMESTAMP, SO_TIMESTAMPNS or SO_TIMESTAMPING with flag
SOF_TIMESTAMPING_RX_SOFTWARE will cause a static key to be enabled/disabled.
This in turn causes undesired IPIs to isolated CPUs.
So enable the static key unconditionally, if CPU isolation is enabled,
thus avoiding the IPIs.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/ZgrUiLLtbEUf9SFn@tpad
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
process_backlog() can batch increments of sd->input_queue_head,
saving some memory bandwidth.
Also add READ_ONCE()/WRITE_ONCE() annotations around
sd->input_queue_head accesses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
input_queue_tail_incr_save() is incrementing the sd queue_tail
and save it in the flow last_qtail.
Two issues here :
- no lock protects the write on last_qtail, we should use appropriate
annotations.
- We can perform this write after releasing the per-cpu backlog lock,
to decrease this lock hold duration (move away the cache line miss)
Also move input_queue_head_incr() and rps helpers to include/net/rps.h,
while adding rps_ prefix to better reflect their role.
v2: Fixed a build issue (Jakub and kernel build bots)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can remove a goto and a label by reversing a condition.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If under extreme cpu backlog pressure enqueue_to_backlog() has
to drop a packet, it could do this without dirtying a cache line
and potentially slowing down the target cpu.
Move sd->dropped into a separate cache line, and make it atomic.
In non pressure mode, this field is not touched, no need to consume
valuable space in a hot cache line.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the device attached to the packet given to enqueue_to_backlog()
is not running, we drop the packet.
But we accidentally increase sd->dropped, giving false signals
to admins: sd->dropped should be reserved to cpu backlog pressure,
not to temporary glitches at device dismantles.
While we are at it, perform the netif_running() test before
we get the rps lock, and use REASON_DEV_READY
drop reason instead of NOT_SPECIFIED.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no reason to consume a full cacheline to store system_page_pool.
We can eventually move it to softnet_data later for full locality control.
Fixes: 2b0cfa6e49 ("net: add generic percpu page_pool allocator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lorenzo Bianconi <lorenzo@kernel.org>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20240328173448.2262593-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TC filters come in 3 variants:
- no flag (try to process in hardware, but fallback to software))
- skip_hw (do not process filter by hardware)
- skip_sw (do not process filter by software)
However skip_sw is implemented so that the skip_sw
flag can first be checked, after it has been matched.
IMHO it's common when using skip_sw, to use it on all rules.
So if all filters in a block is skip_sw filters, then
we can bail early, we can thus avoid having to match
the filters, just to check for the skip_sw flag.
This patch adds a bypass, for when only TC skip_sw rules
are used. The bypass is guarded by a static key, to avoid
harming other workloads.
There are 3 ways that a packet from a skip_sw ruleset, can
end up in the kernel path. Although the send packets to a
non-existent chain way is only improved a few percents, then
I believe it's worth optimizing the trap and fall-though
use-cases.
+----------------------------+--------+--------+--------+
| Test description | Pre- | Post- | Rel. |
| | kpps | kpps | chg. |
+----------------------------+--------+--------+--------+
| basic forwarding + notrack | 3589.3 | 3587.9 | 1.00x |
| switch to eswitch mode | 3081.8 | 3094.7 | 1.00x |
| add ingress qdisc | 3042.9 | 3063.6 | 1.01x |
| tc forward in hw / skip_sw |37024.7 |37028.4 | 1.00x |
| tc forward in sw / skip_hw | 3245.0 | 3245.3 | 1.00x |
+----------------------------+--------+--------+--------+
| tests with only skip_sw rules below: |
+----------------------------+--------+--------+--------+
| 1 non-matching rule | 2694.7 | 3058.7 | 1.14x |
| 1 n-m rule, match trap | 2611.2 | 3323.1 | 1.27x |
| 1 n-m rule, goto non-chain | 2886.8 | 2945.9 | 1.02x |
| 5 non-matching rules | 1958.2 | 3061.3 | 1.56x |
| 5 n-m rules, match trap | 1911.9 | 3327.0 | 1.74x |
| 5 n-m rules, goto non-chain| 2883.1 | 2947.5 | 1.02x |
| 10 non-matching rules | 1466.3 | 3062.8 | 2.09x |
| 10 n-m rules, match trap | 1444.3 | 3317.9 | 2.30x |
| 10 n-m rules,goto non-chain| 2883.1 | 2939.5 | 1.02x |
| 25 non-matching rules | 838.5 | 3058.9 | 3.65x |
| 25 n-m rules, match trap | 824.5 | 3323.0 | 4.03x |
| 25 n-m rules,goto non-chain| 2875.8 | 2944.7 | 1.02x |
| 50 non-matching rules | 488.1 | 3054.7 | 6.26x |
| 50 n-m rules, match trap | 484.9 | 3318.5 | 6.84x |
| 50 n-m rules,goto non-chain| 2884.1 | 2939.7 | 1.02x |
+----------------------------+--------+--------+--------+
perf top (25 n-m skip_sw rules - pre patch):
20.39% [kernel] [k] __skb_flow_dissect
16.43% [kernel] [k] rhashtable_jhash2
10.58% [kernel] [k] fl_classify
10.23% [kernel] [k] fl_mask_lookup
4.79% [kernel] [k] memset_orig
2.58% [kernel] [k] tcf_classify
1.47% [kernel] [k] __x86_indirect_thunk_rax
1.42% [kernel] [k] __dev_queue_xmit
1.36% [kernel] [k] nft_do_chain
1.21% [kernel] [k] __rcu_read_lock
perf top (25 n-m skip_sw rules - post patch):
5.12% [kernel] [k] __dev_queue_xmit
4.77% [kernel] [k] nft_do_chain
3.65% [kernel] [k] dev_gro_receive
3.41% [kernel] [k] check_preemption_disabled
3.14% [kernel] [k] mlx5e_skb_from_cqe_mpwrq_nonlinear
2.88% [kernel] [k] __netif_receive_skb_core.constprop.0
2.49% [kernel] [k] mlx5e_xmit
2.15% [kernel] [k] ip_forward
1.95% [kernel] [k] mlx5e_tc_restore_tunnel
1.92% [kernel] [k] vlan_gro_receive
Test setup:
DUT: Intel Xeon D-1518 (2.20GHz) w/ Nvidia/Mellanox ConnectX-6 Dx 2x100G
Data rate measured on switch (Extreme X690), and DUT connected as
a router on a stick, with pktgen and pktsink as VLANs.
Pktgen-dpdk was in range 36.6-37.7 Mpps 64B packets across all tests.
Full test data at https://files.fiberby.net/ast/2024/tc_skip_sw/v2_tests/
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
System page_pools are percpu and one instance can be used only on
one CPU.
%NUMA_NO_NODE is fine for allocating pages, as the PP core always
allocates local pages in this case. But for the struct &page_pool
itself, this node ID means they are allocated on the boot CPU,
which may belong to a different node than the target CPU.
Pin system page_pools to the corresponding nodes when creating,
so that all the allocated data will always be local. Use
cpu_to_mem() to account memless nodes.
Nodes != 0 win some Kpps when testing with xdp-trafficgen.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20240325160635.3215855-1-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The rps_lock.*() functions use the inner lock of a sk_buff_head for
locking. This lock is used if RPS is enabled, otherwise the list is
accessed lockless and disabling interrupts is enough for the
synchronisation because it is only accessed CPU local. Not only the list
is protected but also the NAPI state protected.
With the addition of backlog threads, the lock is also needed because of
the cross CPU access even without RPS. The clean up of the defer_list
list is also done via backlog threads (if enabled).
It has been suggested to rename the locking function since it is no
longer just RPS.
Rename the rps_lock*() functions to backlog_lock*().
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The defer_list is a per-CPU list which is used to free skbs outside of
the socket lock and on the CPU on which they have been allocated.
The list is processed during NAPI callbacks so ideally the list is
cleaned up.
Should the amount of skbs on the list exceed a certain water mark then
the softirq is triggered remotely on the target CPU by invoking a remote
function call. The raise of the softirqs via a remote function call
leads to waking the ksoftirqd on PREEMPT_RT which is undesired.
The backlog-NAPI threads already provide the infrastructure which can be
utilized to perform the cleanup of the defer_list.
The NAPI state is updated with the input_pkt_queue.lock acquired. It
order not to break the state, it is needed to also wake the backlog-NAPI
thread with the lock held. This requires to acquire the use the lock in
rps_lock_irq*() if the backlog-NAPI threads are used even with RPS
disabled.
Move the logic of remotely starting softirqs to clean up the defer_list
into kick_defer_list_purge(). Make sure a lock is held in
rps_lock_irq*() if backlog-NAPI threads are used. Schedule backlog-NAPI
for defer_list cleanup if backlog-NAPI is available.
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Backlog NAPI is a per-CPU NAPI struct only (with no device behind it)
used by drivers which don't do NAPI them self, RPS and parts of the
stack which need to avoid recursive deadlocks while processing a packet.
The non-NAPI driver use the CPU local backlog NAPI. If RPS is enabled
then a flow for the skb is computed and based on the flow the skb can be
enqueued on a remote CPU. Scheduling/ raising the softirq (for backlog's
NAPI) on the remote CPU isn't trivial because the softirq is only
scheduled on the local CPU and performed after the hardirq is done.
In order to schedule a softirq on the remote CPU, an IPI is sent to the
remote CPU which schedules the backlog-NAPI on the then local CPU.
On PREEMPT_RT interrupts are force-threaded. The soft interrupts are
raised within the interrupt thread and processed after the interrupt
handler completed still within the context of the interrupt thread. The
softirq is handled in the context where it originated.
With force-threaded interrupts enabled, ksoftirqd is woken up if a
softirq is raised from hardirq context. This is the case if it is raised
from an IPI. Additionally there is a warning on PREEMPT_RT if the
softirq is raised from the idle thread.
This was done for two reasons:
- With threaded interrupts the processing should happen in thread
context (where it originated) and ksoftirqd is the only thread for
this context if raised from hardirq. Using the currently running task
instead would "punish" a random task.
- Once ksoftirqd is active it consumes all further softirqs until it
stops running. This changed recently and is no longer the case.
Instead of keeping the backlog NAPI in ksoftirqd (in force-threaded/
PREEMPT_RT setups) I am proposing NAPI-threads for backlog.
The "proper" setup with threaded-NAPI is not doable because the threads
are not pinned to an individual CPU and can be modified by the user.
Additionally a dummy network device would have to be assigned. Also
CPU-hotplug has to be considered if additional CPUs show up.
All this can be probably done/ solved but the smpboot-threads already
provide this infrastructure.
Sending UDP packets over loopback expects that the packet is processed
within the call. Delaying it by handing it over to the thread hurts
performance. It is not beneficial to the outcome if the context switch
happens immediately after enqueue or after a while to process a few
packets in a batch.
There is no need to always use the thread if the backlog NAPI is
requested on the local CPU. This restores the loopback throuput. The
performance drops mostly to the same value after enabling RPS on the
loopback comparing the IPI and the tread result.
Create NAPI-threads for backlog if request during boot. The thread runs
the inner loop from napi_threaded_poll(), the wait part is different. It
checks for NAPI_STATE_SCHED (the backlog NAPI can not be disabled).
The NAPI threads for backlog are optional, it has to be enabled via the boot
argument "thread_backlog_napi". It is mandatory for PREEMPT_RT to avoid the
wakeup of ksoftirqd from the IPI.
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
A NAPI thread is scheduled by first setting NAPI_STATE_SCHED bit. If
successful (the bit was not yet set) then the NAPI_STATE_SCHED_THREADED
is set but only if thread's state is not TASK_INTERRUPTIBLE (is
TASK_RUNNING) followed by task wakeup.
If the task is idle (TASK_INTERRUPTIBLE) then the
NAPI_STATE_SCHED_THREADED bit is not set. The thread is no relying on
the bit but always leaving the wait-loop after returning from schedule()
because there must have been a wakeup.
The smpboot-threads implementation for per-CPU threads requires an
explicit condition and does not support "if we get out of schedule()
then there must be something to do".
Removing this optimisation simplifies the following integration.
Set NAPI_STATE_SCHED_THREADED unconditionally on wakeup and rely on it
in the wait path by removing the `woken' condition.
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
NAPI threads can keep polling packets under load. Currently it is only
calling cond_resched() before repolling, but it is not sufficient to
clear out the holdout of RCU tasks, which prevent BPF tracing programs
from detaching for long period. This can be reproduced easily with
following set up:
ip netns add test1
ip netns add test2
ip -n test1 link add veth1 type veth peer name veth2 netns test2
ip -n test1 link set veth1 up
ip -n test1 link set lo up
ip -n test2 link set veth2 up
ip -n test2 link set lo up
ip -n test1 addr add 192.168.1.2/31 dev veth1
ip -n test1 addr add 1.1.1.1/32 dev lo
ip -n test2 addr add 192.168.1.3/31 dev veth2
ip -n test2 addr add 2.2.2.2/31 dev lo
ip -n test1 route add default via 192.168.1.3
ip -n test2 route add default via 192.168.1.2
for i in `seq 10 210`; do
for j in `seq 10 210`; do
ip netns exec test2 iptables -I INPUT -s 3.3.$i.$j -p udp --dport 5201
done
done
ip netns exec test2 ethtool -K veth2 gro on
ip netns exec test2 bash -c 'echo 1 > /sys/class/net/veth2/threaded'
ip netns exec test1 ethtool -K veth1 tso off
Then run an iperf3 client/server and a bpftrace script can trigger it:
ip netns exec test2 iperf3 -s -B 2.2.2.2 >/dev/null&
ip netns exec test1 iperf3 -c 2.2.2.2 -B 1.1.1.1 -u -l 1500 -b 3g -t 100 >/dev/null&
bpftrace -e 'kfunc:__napi_poll{@=count();} interval:s:1{exit();}'
Report RCU quiescent states periodically will resolve the issue.
Fixes: 29863d41bb ("net: implement threaded-able napi poll loop support")
Reviewed-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Yan Zhai <yan@cloudflare.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/4c3b0d3f32d3b18949d75b18e5e1d9f13a24f025.1710877680.git.yan@cloudflare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev->state can be read in rx and tx fast paths.
netif_running() which needs dev->state is called from
- enqueue_to_backlog() [RX path]
- __dev_direct_xmit() [TX path]
Fixes: 43a71cd66b ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240314200845.3050179-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
rps_sock_flow_table and rps_cpu_mask are used in fast path.
Move them to net_hotdata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-19-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Move RPS related structures and helpers from include/linux/netdevice.h
and include/net/sock.h to a new include file.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-18-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev_rx_weight is read from process_backlog().
Move it to net_hotdata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-10-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev_tx_weight is used in tx fast path.
Move it to net_hotdata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-9-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdev_max_backlog is used in rx fat path.
Move it to net_hodata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ptype_all is used in rx/tx fast paths.
Move it to net_hotdata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdev_tstamp_prequeue is used in rx path.
Move it to net_hotdata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdev_budget and netdev_budget are used in rx path (net_rx_action())
Move them into net_hotdata for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240306160031.874438-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Older versions of GCC really want to know the full definition
of the type involved in rcu_assign_pointer().
struct dpll_pin is defined in a local header, net/core can't
reach it. Move all the netdev <> dpll code into dpll, where
the type is known. Otherwise we'd need multiple function calls
to jump between the compilation units.
This is the same problem the commit under fixes was trying to address,
but with rcu_assign_pointer() not rcu_dereference().
Some of the exports are not needed, networking core can't
be a module, we only need exports for the helpers used by
drivers.
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/all/35a869c8-52e8-177-1d4d-e57578b99b6@linux-m68k.org/
Fixes: 640f41ed33 ("dpll: fix build failure due to rcu_dereference_check() on unknown type")
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240305013532.694866-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In the following patch, inet_base_seq() will no longer be called
with RTNL held.
Add READ_ONCE()/WRITE_ONCE() annotations in dev_base_seq_inc()
and inet_base_seq().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the network driver is relying in the net core to do stats allocation,
then we want to dev_get_tstats64() instead of netdev_stats_to_stats64(),
since there are per-cpu stats that needs to be taken in consideration.
This will also simplify the drivers in regard to statistics. Once the
driver sets NETDEV_PCPU_STAT_TSTATS, it doesn't not need to allocate the
stacks, neither it needs to set `.ndo_get_stats64 = dev_get_tstats64`
for the generic stats collection function anymore.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
skb_defer_free_flush() is currently called from net_rx_action()
and napi_threaded_poll().
We should also call it from __napi_busy_loop() otherwise
there is the risk the percpu queue can grow until an IPI
is forced from skb_attempt_defer_free() adding a latency spike.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Samiullah Khawaja <skhawaja@google.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240227210105.3815474-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This fixes a possible UAF in if_nlmsg_size(),
which can run without RTNL.
Add rcu protection to "struct dpll_pin"
Move netdev_dpll_pin() from netdevice.h to dpll.h to
decrease name pollution.
Note: This looks possible to no longer acquire RTNL in
netdev_dpll_pin_assign() later in net-next.
v2: do not force rcu_read_lock() in rtnl_dpll_pin_size() (Jiri Pirko)
Fixes: 5f18426928 ("netdev: expose DPLL pin handle for netdevice")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240223123208.3543319-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We want to use RCU protection instead of RTNL
for inet6_fill_ifinfo().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We want to be able to run rtnl_fill_ifinfo() under RCU protection
instead of RTNL in the future.
This patch prepares dev_get_iflink() and nla_put_iflink()
to run either with RTNL or RCU held.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use global percpu page_pool_recycle_stats counter for system page_pool
allocator instead of allocating a separate percpu variable for each
(also percpu) page pool instance.
Reviewed-by: Toke Hoiland-Jorgensen <toke@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/87f572425e98faea3da45f76c3c68815c01a20ee.1708075412.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev_base_lock is not needed anymore, all remaining users also hold RTNL.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RTNL already protects writes to dev->reg_state, we no longer need to hold
dev_base_lock to protect the readers.
unlist_netdevice() second argument can be removed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using dev_base_lock is not preventing from reading garbage.
Use dev_addr_sem instead.
v4: place dev_addr_sem extern in net/core/dev.h (Jakub Kicinski)
Link: https://lore.kernel.org/netdev/20240212175845.10f6680a@kernel.org/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prepares things so that dev->reg_state reads can be lockless,
by adding WRITE_ONCE() on write side.
READ_ONCE()/WRITE_ONCE() do not support bitfields.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
name_assign_type_show() runs locklessly, we should annotate
accesses to dev->name_assign_type.
Alternative would be to grab devnet_rename_sem semaphore
from name_assign_type_show(), but this would not bring
more accuracy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to native xdp, do not always linearize the skb in
netif_receive_generic_xdp routine but create a non-linear xdp_buff to be
processed by the eBPF program. This allow to add multi-buffer support
for xdp running in generic mode.
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Toke Hoiland-Jorgensen <toke@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/1044d6412b1c3e95b40d34993fd5f37cd2f319fd.1707729884.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Rely on skb pointer reference instead of the skb pointer in do_xdp_generic
and netif_receive_generic_xdp routine signatures.
This is a preliminary patch to add multi-buff support for xdp running in
generic mode where we will need to reallocate the skb to avoid
linearization and we will need to make it visible to do_xdp_generic()
caller.
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Toke Hoiland-Jorgensen <toke@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/c09415b1f48c8620ef4d76deed35050a7bddf7c2.1707729884.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Introduce generic percpu page_pools allocator.
Moreover add page_pool_create_percpu() and cpuid filed in page_pool struct
in order to recycle the page in the page_pool "hot" cache if
napi_pp_put_page() is running on the same cpu.
This is a preliminary patch to add xdp multi-buff support for xdp running
in generic mode.
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Toke Hoiland-Jorgensen <toke@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/80bc4285228b6f4220cd03de1999d86e46e3fcbd.1707729884.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
rtnl_prop_list_size() can be called while alternative names
are added or removed concurrently.
if_nlmsg_size() / rtnl_calcit() can indeed be called
without RTNL held.
Use explicit RCU protection to avoid UAF.
Fixes: 88f4fb0c74 ("net: rtnetlink: put alternative names to getlink message")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240209181248.96637-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev_change_name() holds RTNL, we better use synchronize_net()
instead of plain synchronize_rcu().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
dev->lstats is notably used from loopback ndo_start_xmit()
and other virtual drivers.
Per cpu stats updates are dirtying per-cpu data,
but the pointer itself is read-only.
Fixes: 43a71cd66b ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Simon Horman <horms@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge netdev bits of io_uring busy polling support.
Jens Axboe says:
====================
io_uring: add napi busy polling support
I finally got around to testing this patchset in its current form, and
results look fine to me. It Works. Using the basic ping/pong test that's
part of the liburing addition, without enabling NAPI I get:
Stock settings, no NAPI, 100k packets:
rtt(us) min/avg/max/mdev = 31.730/37.006/87.960/0.497
and with -t10 -b enabled:
rtt(us) min/avg/max/mdev = 23.250/29.795/63.511/1.203
In short, this patchset enables per io_uring NAPI enablement, rather
than need to enable that globally. This allows targeted NAPI usage with
io_uring.
Here's Stefan's v15 posting, which predates this one:
https://lore.kernel.org/io-uring/20230608163839.2891748-1-shr@devkernel.io/
====================
Link: https://lore.kernel.org/r/20240206163422.646218-1-axboe@kernel.dk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This adds the napi_busy_loop_rcu() function. This function assumes that
the calling function is already holding the rcu read lock and
napi_busy_loop() does not need to take the rcu read lock. Add a
NAPI_F_NO_SCHED flag, which tells __napi_busy_loop() to abort if we
need to reschedule rather than drop the RCU read lock and reschedule.
Signed-off-by: Stefan Roesch <shr@devkernel.io>
Link: https://lore.kernel.org/r/20230608163839.2891748-3-shr@devkernel.io
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This splits off the key part of the napi_busy_poll function into its own
function, __napi_busy_poll, and changes the prefer_busy_poll bool to be
flag based to allow passing in more flags in the future.
This is done in preparation for an additional napi_busy_poll() function,
that doesn't take the rcu_read_lock(). The new function is introduced
in the next patch.
Signed-off-by: Stefan Roesch <shr@devkernel.io>
Link: https://lore.kernel.org/r/20230608163839.2891748-2-shr@devkernel.io
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
init_dummy_netdev() always returns zero and all the callers do not check
the returned value. Set the function to not return value, as it is not
really used today.
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240205103022.440946-1-amcohen@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We can use a global dev_unreg_count counter instead
of a per netns one.
As a bonus we can factorize the changes done on it
for bulk device removals.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We had to add another synchronize_rcu() in recent fix.
Bite the bullet and add an rcu_head to netdev_name_node,
free from RCU.
Note that name_node does not hold any reference on dev
to which it points, but there must be a synchronize_rcu()
on device removal path, so we should be fine.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mark reports a BUG() when a net namespace is removed.
kernel BUG at net/core/dev.c:11520!
Physical interfaces moved outside of init_net get "refunded"
to init_net when that namespace disappears. The main interface
name may get overwritten in the process if it would have
conflicted. We need to also discard all conflicting altnames.
Recent fixes addressed ensuring that altnames get moved
with the main interface, which surfaced this problem.
Reported-by: Марк Коренберг <socketpair@gmail.com>
Link: https://lore.kernel.org/all/CAEmTpZFZ4Sv3KwqFOY2WKDHeZYdi0O7N5H1nTvcGp=SAEavtDg@mail.gmail.com/
Fixes: 7663d52209 ("net: check for altname conflicts when changing netdev's netns")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
xdp_prog is used in receive path, both from XDP enabled drivers
and from netif_elide_gro().
This patch also removes two 4-bytes holes.
Fixes: 43a71cd66b ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240102162220.750823-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev->gso_partial_features is read from tx fast path for GSO packets.
Move it to appropriate section to avoid a cache line miss.
Fixes: 43a71cd66b ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: David Ahern <dsahern@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Link topologies containing multiple network PHYs attached to the same
net_device can be found when using a PHY as a media converter for use
with an SFP connector, on which an SFP transceiver containing a PHY can
be used.
With the current model, the transceiver's PHY can't be used for
operations such as cable testing, timestamping, macsec offload, etc.
The reason being that most of the logic for these configuration, coming
from either ethtool netlink or ioctls tend to use netdev->phydev, which
in multi-phy systems will reference the PHY closest to the MAC.
Introduce a numbering scheme allowing to enumerate PHY devices that
belong to any netdev, which can in turn allow userspace to take more
precise decisions with regard to each PHY's configuration.
The numbering is maintained per-netdev, in a phy_device_list.
The numbering works similarly to a netdevice's ifindex, with
identifiers that are only recycled once INT_MAX has been reached.
This prevents races that could occur between PHY listing and SFP
transceiver removal/insertion.
The identifiers are assigned at phy_attach time, as the numbering
depends on the netdevice the phy is attached to.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some drivers might misbehave if TSO packets get too big.
GVE for instance uses a 16bit field in its TX descriptor,
and will do bad things if a packet is bigger than 2^16 bytes.
Linux TCP stack honors dev->gso_max_size, but there are
other ways for too big packets to reach an ndo_start_xmit()
handler : virtio_net, af_packet, GRO...
Add a generic check in gso_features_check() and fallback
to GSO when needed.
gso_max_size was added in the blamed commit.
Fixes: 82cc1a7a56 ("[NET]: Add per-connection option to set max TSO frame size")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231219125331.4127498-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Incrementing on Daniel's patch[1], make tc-related drop reason more
flexible for remaining qdiscs - that is, all qdiscs aside from clsact.
In essence, the drop reason will be set by cls_api and act_api in case
any error occurred in the data path. With that, we can give the user more
detailed information so that they can distinguish between a policy drop
or an error drop.
[1] https://lore.kernel.org/all/20231009092655.22025-1-daniel@iogearbox.net
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move drop_reason from struct tcf_result to skb cb - more specifically to
struct tc_skb_cb. With that, we'll be able to also set the drop reason for
the remaining qdiscs (aside from clsact) that do not have access to
tcf_result when time comes to set the skb drop reason.
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are multiple ways to query for the carrier state: through
rtnetlink, sysfs, and (possibly) ethtool. Synchronize linkwatch
work before these operations so that we don't have a situation
where userspace queries the carrier state between the driver's
carrier off->on transition and linkwatch running and expects it
to work, when really (at least) TX cannot work until linkwatch
has run.
I previously posted a longer explanation of how this applies to
wireless [1] but with this wireless can simply query the state
before sending data, to ensure the kernel is ready for it.
[1] https://lore.kernel.org/all/346b21d87c69f817ea3c37caceb34f1f56255884.camel@sipsolutions.net/
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231204214706.303c62768415.I1caedccae72ee5a45c9085c5eb49c145ce1c0dd5@changeid
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reorganize fast path variables on tx-txrx-rx order
Fastpath variables end after npinfo.
Below data generated with pahole on x86 architecture.
Fast path variables span cache lines before change: 12
Fast path variables span cache lines after change: 4
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231204201232.520025-2-lixiaoyan@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Implement the netdev netlink framework functions for
napi support. The netdev structure tracks all the napi
instances and napi fields. The napi instances and associated
parameters can be retrieved this way.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147333637.5260.14807433239805550815.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add the napi pointer in netdev queue for tracking the napi
instance for each queue. This achieves the queue<->napi mapping.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147331483.5260.15723438819994285695.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Networking supports changing netdevice's netns and name
at the same time. This allows avoiding name conflicts
and having to rename the interface in multiple steps.
E.g. netns1={eth0, eth1}, netns2={eth1} - we want
to move netns1:eth1 to netns2 and call it eth0 there.
If we can't rename "in flight" we'd need to (1) rename
eth1 -> $tmp, (2) change netns, (3) rename $tmp -> eth0.
To rename the underlying struct device we have to call
device_rename(). The rename()'s MOVE event, however, doesn't
"belong" to either the old or the new namespace.
If there are conflicts on both sides it's actually impossible
to issue a real MOVE (old name -> new name) without confusing
user space. And Daniel reports that such confusions do in fact
happen for systemd, in real life.
Since we already issue explicit REMOVE and ADD events
manually - suppress the MOVE event completely. Move
the ADD after the rename, so that the REMOVE uses
the old name, and the ADD the new one.
If there is no rename this changes the picture as follows:
Before:
old ns | KERNEL[213.399289] remove /devices/virtual/net/eth0 (net)
new ns | KERNEL[213.401302] add /devices/virtual/net/eth0 (net)
new ns | KERNEL[213.401397] move /devices/virtual/net/eth0 (net)
After:
old ns | KERNEL[266.774257] remove /devices/virtual/net/eth0 (net)
new ns | KERNEL[266.774509] add /devices/virtual/net/eth0 (net)
If there is a rename and a conflict (using the exact eth0/eth1
example explained above) we get this:
Before:
old ns | KERNEL[224.316833] remove /devices/virtual/net/eth1 (net)
new ns | KERNEL[224.318551] add /devices/virtual/net/eth1 (net)
new ns | KERNEL[224.319662] move /devices/virtual/net/eth0 (net)
After:
old ns | KERNEL[333.033166] remove /devices/virtual/net/eth1 (net)
new ns | KERNEL[333.035098] add /devices/virtual/net/eth0 (net)
Note that "in flight" rename is only performed when needed.
If there is no conflict for old name in the target netns -
the rename will be performed separately by dev_change_name(),
as if the rename was a different command, and there will still
be a MOVE event for the rename:
Before:
old ns | KERNEL[194.416429] remove /devices/virtual/net/eth0 (net)
new ns | KERNEL[194.418809] add /devices/virtual/net/eth0 (net)
new ns | KERNEL[194.418869] move /devices/virtual/net/eth0 (net)
new ns | KERNEL[194.420866] move /devices/virtual/net/eth1 (net)
After:
old ns | KERNEL[71.917520] remove /devices/virtual/net/eth0 (net)
new ns | KERNEL[71.919155] add /devices/virtual/net/eth0 (net)
new ns | KERNEL[71.920729] move /devices/virtual/net/eth1 (net)
If deleting the MOVE event breaks some user space we should insert
an explicit kobject_uevent(MOVE) after the ADD, like this:
@@ -11192,6 +11192,12 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
netdev_adjacent_add_links(dev);
+ /* User space wants an explicit MOVE event, issue one unless
+ * dev_change_name() will get called later and issue one.
+ */
+ if (!pat || new_name[0])
+ kobject_uevent(&dev->dev.kobj, KOBJ_MOVE);
+
/* Adapt owner in case owning user namespace of target network
* namespace is different from the original one.
*/
Reported-by: Daniel Gröber <dxld@darkboxed.org>
Link: https://lore.kernel.org/all/20231010121003.x3yi6fihecewjy4e@House.clients.dxld.at/
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/all/20231120184140.578375-1-kuba@kernel.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Traffic redirected by bpf_redirect_peer() (used by recent CNIs like Cilium)
is not accounted for in the RX stats of supported devices (that is, veth
and netkit), confusing user space metrics collectors such as cAdvisor [0],
as reported by Youlun.
Fix it by calling dev_sw_netstats_rx_add() in skb_do_redirect(), to update
RX traffic counters. Devices that support ndo_get_peer_dev _must_ use the
@tstats per-CPU counters (instead of @lstats, or @dstats).
To make this more fool-proof, error out when ndo_get_peer_dev is set but
@tstats are not selected.
[0] Specifically, the "container_network_receive_{byte,packet}s_total"
counters are affected.
Fixes: 9aa1206e8f ("bpf: Add redirect_peer helper")
Reported-by: Youlun Zhang <zhangyoulun@bytedance.com>
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20231114004220.6495-6-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Move {l,t,d}stats allocation to the core and let netdevs pick the stats
type they need. That way the driver doesn't have to bother with error
handling (allocation failure checking, making sure free happens in the
right spot, etc) - all happening in the core.
Co-developed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Cc: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231114004220.6495-3-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Revert following commits:
commit acec05fb78 ("net_tstamp: Add TIMESTAMPING SOFTWARE and HARDWARE mask")
commit 11d55be06d ("net: ethtool: Add a command to expose current time stamping layer")
commit bb8645b00c ("netlink: specs: Introduce new netlink command to get current timestamp")
commit d905f9c753 ("net: ethtool: Add a command to list available time stamping layers")
commit aed5004ee7 ("netlink: specs: Introduce new netlink command to list available time stamping layers")
commit 51bdf3165f ("net: Replace hwtstamp_source by timestamping layer")
commit 0f7f463d48 ("net: Change the API of PHY default timestamp to MAC")
commit 091fab1228 ("net: ethtool: ts: Update GET_TS to reply the current selected timestamp")
commit 152c75e1d0 ("net: ethtool: ts: Let the active time stamping layer be selectable")
commit ee60ea6be0 ("netlink: specs: Introduce time stamping set command")
They need more time for reviews.
Link: https://lore.kernel.org/all/20231118183529.6e67100c@kernel.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Change the API to select MAC default time stamping instead of the PHY.
Indeed the PHY is closer to the wire therefore theoretically it has less
delay than the MAC timestamping but the reality is different. Due to lower
time stamping clock frequency, latency in the MDIO bus and no PHC hardware
synchronization between different PHY, the PHY PTP is often less precise
than the MAC. The exception is for PHY designed specially for PTP case but
these devices are not very widespread. For not breaking the compatibility I
introduce a default_timestamp flag in phy_device that is set by the phy
driver to know we are using the old API behavior.
The phy_set_timestamp function is called at each call of phy_attach_direct.
In case of MAC driver using phylink this function is called when the
interface is turned up. Then if the interface goes down and up again the
last choice of timestamp will be overwritten by the default choice.
A solution could be to cache the timestamp status but it can bring other
issues. In case of SFP, if we change the module, it doesn't make sense to
blindly re-set the timestamp back to PHY, if the new module has a PHY with
mediocre timestamping capabilities.
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cited commit removed the strscpy() call and kept the snprintf() only.
It is common to use 'dev->name' as the format string before a netdev is
registered, this results in 'res' and 'name' pointers being equal.
According to POSIX, if copying takes place between objects that overlap
as a result of a call to sprintf() or snprintf(), the results are
undefined.
Add back the strscpy() and use 'buf' as an intermediate buffer.
Fixes: 7ad17b04dc ("net: trust the bitmap in __dev_alloc_name()")
Cc: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCZTp12QAKCRDbK58LschI
g8BrAQDifqp5liEEdXV8jdReBwJtqInjrL5tzy5LcyHUMQbTaAEA6Ph3Ct3B+3oA
mFnIW/y6UJiJrby0Xz4+vV5BXI/5WQg=
=pLCV
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-10-26
We've added 51 non-merge commits during the last 10 day(s) which contain
a total of 75 files changed, 5037 insertions(+), 200 deletions(-).
The main changes are:
1) Add open-coded task, css_task and css iterator support.
One of the use cases is customizable OOM victim selection via BPF,
from Chuyi Zhou.
2) Fix BPF verifier's iterator convergence logic to use exact states
comparison for convergence checks, from Eduard Zingerman,
Andrii Nakryiko and Alexei Starovoitov.
3) Add BPF programmable net device where bpf_mprog defines the logic
of its xmit routine. It can operate in L3 and L2 mode,
from Daniel Borkmann and Nikolay Aleksandrov.
4) Batch of fixes for BPF per-CPU kptr and re-enable unit_size checking
for global per-CPU allocator, from Hou Tao.
5) Fix libbpf which eagerly assumed that SHT_GNU_verdef ELF section
was going to be present whenever a binary has SHT_GNU_versym section,
from Andrii Nakryiko.
6) Fix BPF ringbuf correctness to fold smp_mb__before_atomic() into
atomic_set_release(), from Paul E. McKenney.
7) Add a warning if NAPI callback missed xdp_do_flush() under
CONFIG_DEBUG_NET which helps checking if drivers were missing
the former, from Sebastian Andrzej Siewior.
8) Fix missed RCU read-lock in bpf_task_under_cgroup() which was throwing
a warning under sleepable programs, from Yafang Shao.
9) Avoid unnecessary -EBUSY from htab_lock_bucket by disabling IRQ before
checking map_locked, from Song Liu.
10) Make BPF CI linked_list failure test more robust,
from Kumar Kartikeya Dwivedi.
11) Enable samples/bpf to be built as PIE in Fedora, from Viktor Malik.
12) Fix xsk starving when multiple xsk sockets were associated with
a single xsk_buff_pool, from Albert Huang.
13) Clarify the signed modulo implementation for the BPF ISA standardization
document that it uses truncated division, from Dave Thaler.
14) Improve BPF verifier's JEQ/JNE branch taken logic to also consider
signed bounds knowledge, from Andrii Nakryiko.
15) Add an option to XDP selftests to use multi-buffer AF_XDP
xdp_hw_metadata and mark used XDP programs as capable to use frags,
from Larysa Zaremba.
16) Fix bpftool's BTF dumper wrt printing a pointer value and another
one to fix struct_ops dump in an array, from Manu Bretelle.
* tag 'for-netdev' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (51 commits)
netkit: Remove explicit active/peer ptr initialization
selftests/bpf: Fix selftests broken by mitigations=off
samples/bpf: Allow building with custom bpftool
samples/bpf: Fix passing LDFLAGS to libbpf
samples/bpf: Allow building with custom CFLAGS/LDFLAGS
bpf: Add more WARN_ON_ONCE checks for mismatched alloc and free
selftests/bpf: Add selftests for netkit
selftests/bpf: Add netlink helper library
bpftool: Extend net dump with netkit progs
bpftool: Implement link show support for netkit
libbpf: Add link-based API for netkit
tools: Sync if_link uapi header
netkit, bpf: Add bpf programmable net device
bpf: Improve JEQ/JNE branch taken logic
bpf: Fold smp_mb__before_atomic() into atomic_set_release()
bpf: Fix unnecessary -EBUSY from htab_lock_bucket
xsk: Avoid starving the xsk further down the list
bpf: print full verifier states on infinite loop detection
selftests/bpf: test if state loops are detected in a tricky case
bpf: correct loop detection for iterators convergence
...
====================
Link: https://lore.kernel.org/r/20231026150509.2824-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Remove unnecessary else clauses after return.
I copied this if / else construct from somewhere,
it makes the code harder to read.
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231023152346.3639749-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Prior to restructuring __dev_alloc_name() handled both printf
and non-printf names. In a clever attempt at code reuse it
always prints the name into a buffer and checks if it's
a duplicate.
Trust the bitmap, and return an error if its full.
This shrinks the possible ID space by one from 32K to 32K - 1,
as previously the max value would have been tried as a valid ID.
It seems very unlikely that anyone would care as we heard
no requests to increase the max beyond 32k.
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231023152346.3639749-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
All callers of __dev_valid_name() go thru dev_prep_valid_name()
which handles the non-printf case. Focus __dev_alloc_name() on
the sprintf case, remove the indentation level.
Minor functional change of returning -EINVAL if % is not found,
which should now never happen.
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231023152346.3639749-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
__dev_alloc_name() handles both the sprintf and non-sprintf
target names. This complicates the code.
dev_prep_valid_name() already handles the non-sprintf case,
before calling __dev_alloc_name(), make the only other caller
also go thru dev_prep_valid_name(). This way we can drop
the non-sprintf handling in __dev_alloc_name() in one of
the next changes.
commit 55a5ec9b77 ("Revert "net: core: dev_get_valid_name is now the same as dev_alloc_name_ns"") and
commit 029b6d1405 ("Revert "net: core: maybe return -EEXIST in __dev_alloc_name"")
tell us that we can't start returning -EEXIST from dev_alloc_name()
on name duplicates. Bite the bullet and pass the expected errno to
dev_prep_valid_name().
dev_prep_valid_name() must now propagate out the allocated id
for printf names.
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231023152346.3639749-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Callers of __dev_alloc_name() want to pass dev->name as
the output buffer. Make __dev_alloc_name() not clobber
that buffer on failure, and remove the workarounds
in callers.
dev_alloc_name_ns() is now completely unnecessary.
The extra strscpy() added here will be gone by the end
of the patch series.
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231023152346.3639749-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The altname nodes are currently not moved to the new netns
when netdevice itself moves:
[ ~]# ip netns add test
[ ~]# ip -netns test link add name eth0 type dummy
[ ~]# ip -netns test link property add dev eth0 altname some-name
[ ~]# ip -netns test link show dev some-name
2: eth0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/ether 1e:67:ed:19:3d:24 brd ff:ff:ff:ff:ff:ff
altname some-name
[ ~]# ip -netns test link set dev eth0 netns 1
[ ~]# ip link
...
3: eth0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/ether 02:40:88:62:ec:b8 brd ff:ff:ff:ff:ff:ff
altname some-name
[ ~]# ip li show dev some-name
Device "some-name" does not exist.
Remove them from the hash table when device is unlisted
and add back when listed again.
Fixes: 36fbf1e52b ("net: rtnetlink: add linkprop commands to add and delete alternative ifnames")
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Altnames are accessed under RCU (dev_get_by_name_rcu())
but freed by kfree() with no synchronization point.
Each node has one or two allocations (node and a variable-size
name, sometimes the name is netdev->name). Adding rcu_heads
here is a bit tedious. Besides most code which unlists the names
already has rcu barriers - so take the simpler approach of adding
synchronize_rcu(). Note that the one on the unregistration path
(which matters more) is removed by the next fix.
Fixes: ff92741270 ("net: introduce name_node struct to be used in hashlist")
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
It's currently possible to create an altname conflicting
with an altname or real name of another device by creating
it in another netns and moving it over:
[ ~]$ ip link add dev eth0 type dummy
[ ~]$ ip netns add test
[ ~]$ ip -netns test link add dev ethX netns test type dummy
[ ~]$ ip -netns test link property add dev ethX altname eth0
[ ~]$ ip -netns test link set dev ethX netns 1
[ ~]$ ip link
...
3: eth0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/ether 02:40:88:62:ec:b8 brd ff:ff:ff:ff:ff:ff
...
5: ethX: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/ether 26:b7:28:78:38:0f brd ff:ff:ff:ff:ff:ff
altname eth0
Create a macro for walking the altnames, this hopefully makes
it clearer that the list we walk contains only altnames.
Which is otherwise not entirely intuitive.
Fixes: 36fbf1e52b ("net: rtnetlink: add linkprop commands to add and delete alternative ifnames")
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
dev_get_valid_name() overwrites the netdev's name on success.
This makes it hard to use in prepare-commit-like fashion,
where we do validation first, and "commit" to the change
later.
Factor out a helper which lets us save the new name to a buffer.
Use it to fix the problem of notification on netns move having
incorrect name:
5: eth0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default
link/ether be:4d:58:f9:d5:40 brd ff:ff:ff:ff:ff:ff
6: eth1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default
link/ether 1e:4a:34:36:e3:cd brd ff:ff:ff:ff:ff:ff
[ ~]# ip link set dev eth0 netns 1 name eth1
ip monitor inside netns:
Deleted inet eth0
Deleted inet6 eth0
Deleted 5: eth1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default
link/ether be:4d:58:f9:d5:40 brd ff:ff:ff:ff:ff:ff new-netnsid 0 new-ifindex 7
Name is reported as eth1 in old netns for ifindex 5, already renamed.
Fixes: d90310243f ("net: device name allocation cleanups")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
We currently have napi_if_scheduled_mark_missed that can be used to
check if napi is scheduled but that does more thing than simply checking
it and return a bool. Some driver already implement custom function to
check if napi is scheduled.
Drop these custom function and introduce napi_is_scheduled that simply
check if napi is scheduled atomically.
Update any driver and code that implement a similar check and instead
use this new helper.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
A few drivers were missing a xdp_do_flush() invocation after
XDP_REDIRECT.
Add three helper functions each for one of the per-CPU lists. Return
true if the per-CPU list is non-empty and flush the list.
Add xdp_do_check_flushed() which invokes each helper functions and
creates a warning if one of the functions had a non-empty list.
Hide everything behind CONFIG_DEBUG_NET.
Suggested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20231016125738.Yt79p1uF@linutronix.de
Currently, the kfree_skb_reason() in sch_handle_{ingress,egress}() can only
express a basic SKB_DROP_REASON_TC_INGRESS or SKB_DROP_REASON_TC_EGRESS reason.
Victor kicked-off an initial proposal to make this more flexible by disambiguating
verdict from return code by moving the verdict into struct tcf_result and
letting tcf_classify() return a negative error. If hit, then two new drop
reasons were added in the proposal, that is SKB_DROP_REASON_TC_INGRESS_ERROR
as well as SKB_DROP_REASON_TC_EGRESS_ERROR. Further analysis of the actual
error codes would have required to attach to tcf_classify via kprobe/kretprobe
to more deeply debug skb and the returned error.
In order to make the kfree_skb_reason() in sch_handle_{ingress,egress}() more
extensible, it can be addressed in a more straight forward way, that is: Instead
of placing the verdict into struct tcf_result, we can just put the drop reason
in there, which does not require changes throughout various classful schedulers
given the existing verdict logic can stay as is.
Then, SKB_DROP_REASON_TC_ERROR{,_*} can be added to the enum skb_drop_reason
to disambiguate between an error or an intentional drop. New drop reason error
codes can be added successively to the tc code base.
For internal error locations which have not yet been annotated with a
SKB_DROP_REASON_TC_ERROR{,_*}, the fallback is SKB_DROP_REASON_TC_INGRESS and
SKB_DROP_REASON_TC_EGRESS, respectively. Generic errors could be marked with a
SKB_DROP_REASON_TC_ERROR code until they are converted to more specific ones
if it is found that they would be useful for troubleshooting.
While drop reasons have infrastructure for subsystem specific error codes which
are currently used by mac80211 and ovs, Jakub mentioned that it is preferred
for tc to use the enum skb_drop_reason core codes given it is a better fit and
currently the tooling support is better, too.
With regards to the latter:
[...] I think Alastair (bpftrace) is working on auto-prettifying enums when
bpftrace outputs maps. So we can do something like:
$ bpftrace -e 'tracepoint:skb:kfree_skb { @[args->reason] = count(); }'
Attaching 1 probe...
^C
@[SKB_DROP_REASON_TC_INGRESS]: 2
@[SKB_CONSUMED]: 34
^^^^^^^^^^^^ names!!
Auto-magically. [...]
Add a small helper tcf_set_drop_reason() which can be used to set the drop reason
into the tcf_result.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Victor Nogueira <victor@mojatatu.com>
Link: https://lore.kernel.org/netdev/20231006063233.74345d36@kernel.org
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231009092655.22025-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR.
No conflicts.
Adjacent changes:
kernel/bpf/verifier.c
829955981c ("bpf: Fix verifier log for async callback return values")
a923819fb2 ("bpf: Treat first argument as return value for bpf_throw")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Although there is a kfree_skb_reason() helper function that can be used to
find the reason why this skb is dropped, but most callers didn't increase
one of rx_dropped, tx_dropped, rx_nohandler and rx_otherhost_dropped.
For the users, people are more concerned about why the dropped in ip
is increasing.
Introduce netdev_core_stats_inc() for trace the caller of
dev_core_stats_*_inc().
Also, add __code to netdev_core_stats_alloc(), as it's called with small
probability. And add noinline make sure netdev_core_stats_inc was never
inlined.
Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
syzbot uses panic_on_warn.
This means that the skb_dump() I added in the blamed commit are
not even called.
Rewrite this so that we get the needed skb dump before syzbot crashes.
Fixes: eeee4b77dc ("net: add more debug info in skb_checksum_help()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20231006173355.2254983-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In case netdevice represents a SyncE port, the user needs to understand
the connection between netdevice and associated DPLL pin. There might me
multiple netdevices pointing to the same pin, in case of VF/SF
implementation.
Add a IFLA Netlink attribute to nest the DPLL pin handle, similar to
how it is implemented for devlink port. Add a struct dpll_pin pointer
to netdev and protect access to it by RTNL. Expose netdev_dpll_pin_set()
and netdev_dpll_pin_clear() helpers to the drivers so they can set/clear
the DPLL pin relationship to netdev.
Note that during the lifetime of struct dpll_pin the pin handle does not
change. Therefore it is save to access it lockless. It is drivers
responsibility to call netdev_dpll_pin_clear() before dpll_pin_put().
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use bitmap_zalloc() and bitmap_free() instead of hand-writing them.
It is less verbose and it improves the type checking and semantic.
While at it, add missing header inclusion (should be bitops.h,
but with the above change it becomes bitmap.h).
Suggested-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230911154534.4174265-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While looking at TC_ACT_* handling, the TC_ACT_CONSUMED is only handled in
sch_handle_ingress but not sch_handle_egress. This was added via cd11b16407
("net/tc: introduce TC_ACT_REINSERT.") and e5cf1baf92 ("act_mirred: use
TC_ACT_REINSERT when possible") and later got renamed into TC_ACT_CONSUMED
via 720f22fed8 ("net: sched: refactor reinsert action").
The initial work was targeted for ovs back then and only needed on ingress,
and the mirred action module also restricts it to only that. However, given
it's an API contract it would still make sense to make this consistent to
sch_handle_ingress and handle it on egress side in the same way, that is,
setting return code to "success" and returning NULL back to the caller as
otherwise an action module sitting on egress returning TC_ACT_CONSUMED could
lead to an UAF when untreated.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix a memory leak for the tc egress path with TC_ACT_{STOLEN,QUEUED,TRAP}:
[...]
unreferenced object 0xffff88818bcb4f00 (size 232):
comm "softirq", pid 0, jiffies 4299085078 (age 134.028s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 80 70 61 81 88 ff ff 00 41 31 14 81 88 ff ff ..pa.....A1.....
backtrace:
[<ffffffff9991b938>] kmem_cache_alloc_node+0x268/0x400
[<ffffffff9b3d9231>] __alloc_skb+0x211/0x2c0
[<ffffffff9b3f0c7e>] alloc_skb_with_frags+0xbe/0x6b0
[<ffffffff9b3bf9a9>] sock_alloc_send_pskb+0x6a9/0x870
[<ffffffff9b6b3f00>] __ip_append_data+0x14d0/0x3bf0
[<ffffffff9b6ba24e>] ip_append_data+0xee/0x190
[<ffffffff9b7e1496>] icmp_push_reply+0xa6/0x470
[<ffffffff9b7e4030>] icmp_reply+0x900/0xa00
[<ffffffff9b7e42e3>] icmp_echo.part.0+0x1a3/0x230
[<ffffffff9b7e444d>] icmp_echo+0xcd/0x190
[<ffffffff9b7e9566>] icmp_rcv+0x806/0xe10
[<ffffffff9b699bd1>] ip_protocol_deliver_rcu+0x351/0x3d0
[<ffffffff9b699f14>] ip_local_deliver_finish+0x2b4/0x450
[<ffffffff9b69a234>] ip_local_deliver+0x174/0x1f0
[<ffffffff9b69a4b2>] ip_sublist_rcv_finish+0x1f2/0x420
[<ffffffff9b69ab56>] ip_sublist_rcv+0x466/0x920
[...]
I was able to reproduce this via:
ip link add dev dummy0 type dummy
ip link set dev dummy0 up
tc qdisc add dev eth0 clsact
tc filter add dev eth0 egress protocol ip prio 1 u32 match ip protocol 1 0xff action mirred egress redirect dev dummy0
ping 1.1.1.1
<stolen>
After the fix, there are no kmemleak reports with the reproducer. This is
in line with what is also done on the ingress side, and from debugging the
skb_unref(skb) on dummy xmit and sch_handle_egress() side, it is visible
that these are two different skbs with both skb_unref(skb) as true. The two
seen skbs are due to mirred doing a skb_clone() internally as use_reinsert
is false in tcf_mirred_act() for egress. This was initially reported by Gal.
Fixes: e420bed025 ("bpf: Add fd-based tcx multi-prog infra with link support")
Reported-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/bdfc2640-8f65-5b56-4472-db8e2b161aab@nvidia.com
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since the xarray changes we mix returning valid ifindex and negative
errno in a single int returned from dev_index_reserve(). This depends
on the fact that ifindexes can't be negative. Otherwise we may insert
into the xarray and return a very large negative value. This in turn
may break ERR_PTR().
OvS is susceptible to this problem and lacking validation (fix posted
separately for net).
Reject negative ifindex explicitly. Add a warning because the input
validation is better handled by the caller.
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230814205627.2914583-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQRdM/uy1Ege0+EN1fNar9k/UBDW4wUCZMvevwAKCRBar9k/UBDW
42Z0AP90hLZ9OmoghYAlALHLl8zqXuHCV8OeFXR5auqG+kkcCwEAx6h99vnh4zgP
Tngj6Yid60o39/IZXXblhV37HfSiyQ8=
=/kVE
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Martin KaFai Lau says:
====================
pull-request: bpf-next 2023-08-03
We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 84 files changed, 4026 insertions(+), 562 deletions(-).
The main changes are:
1) Add SO_REUSEPORT support for TC bpf_sk_assign from Lorenz Bauer,
Daniel Borkmann
2) Support new insns from cpu v4 from Yonghong Song
3) Non-atomically allocate freelist during prefill from YiFei Zhu
4) Support defragmenting IPv(4|6) packets in BPF from Daniel Xu
5) Add tracepoint to xdp attaching failure from Leon Hwang
6) struct netdev_rx_queue and xdp.h reshuffling to reduce
rebuild time from Jakub Kicinski
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
net: invert the netdevice.h vs xdp.h dependency
net: move struct netdev_rx_queue out of netdevice.h
eth: add missing xdp.h includes in drivers
selftests/bpf: Add testcase for xdp attaching failure tracepoint
bpf, xdp: Add tracepoint to xdp attaching failure
selftests/bpf: fix static assert compilation issue for test_cls_*.c
bpf: fix bpf_probe_read_kernel prototype mismatch
riscv, bpf: Adapt bpf trampoline to optimized riscv ftrace framework
libbpf: fix typos in Makefile
tracing: bpf: use struct trace_entry in struct syscall_tp_t
bpf, devmap: Remove unused dtab field from bpf_dtab_netdev
bpf, cpumap: Remove unused cmap field from bpf_cpu_map_entry
netfilter: bpf: Only define get_proto_defrag_hook() if necessary
bpf: Fix an array-index-out-of-bounds issue in disasm.c
net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
docs/bpf: Fix malformed documentation
bpf: selftests: Add defrag selftests
bpf: selftests: Support custom type and proto for client sockets
bpf: selftests: Support not connecting client socket
netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link
...
====================
Link: https://lore.kernel.org/r/20230803174845.825419-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
struct netdev_rx_queue is touched in only a few places
and having it defined in netdevice.h brings in the dependency
on xdp.h, because struct xdp_rxq_info gets embedded in
struct netdev_rx_queue.
In prep for removal of xdp.h from netdevice.h move all
the netdev_rx_queue stuff to a new header.
We could technically break the new header up to avoid
the sysfs.h include but it's so rarely included it
doesn't seem to be worth it at this point.
Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230803010230.1755386-3-kuba@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
When error happens in dev_xdp_attach(), it should have a way to tell
users the error message like the netlink approach.
To avoid breaking uapi, adding a tracepoint in bpf_xdp_link_attach() is
an appropriate way to notify users the error message.
Hence, bpf libraries are able to retrieve the error message by this
tracepoint, and then report the error message to users.
Signed-off-by: Leon Hwang <hffilwlqm@gmail.com>
Link: https://lore.kernel.org/r/20230801142621.7925-2-hffilwlqm@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Iterating over the netdev hash table for netlink dumps is hard.
Dumps are done in "chunks" so we need to save the position
after each chunk, so we know where to restart from. Because
netdevs are stored in a hash table we remember which bucket
we were in and how many devices we dumped.
Since we don't hold any locks across the "chunks" - devices may
come and go while we're dumping. If that happens we may miss
a device (if device is deleted from the bucket we were in).
We indicate to user space that this may have happened by setting
NLM_F_DUMP_INTR. User space is supposed to dump again (I think)
if it sees that. Somehow I doubt most user space gets this right..
To illustrate let's look at an example:
System state:
start: # [A, B, C]
del: B # [A, C]
with the hash table we may dump [A, B], missing C completely even
tho it existed both before and after the "del B".
Add an xarray and use it to allocate ifindexes. This way we
can iterate ifindexes in order, without the worry that we'll
skip one. We may still generate a dump of a state which "never
existed", for example for a set of values and sequence of ops:
System state:
start: # [A, B]
add: C # [A, C, B]
del: B # [A, C]
we may generate a dump of [A], if C got an index between A and B.
System has never been in such state. But I'm 90% sure that's perfectly
fine, important part is that we can't _miss_ devices which exist before
and after. User space which wants to mirror kernel's state subscribes
to notifications and does periodic dumps so it will know that C exists
from the notification about its creation or from the next dump
(next dump is _guaranteed_ to include C, if it doesn't get removed).
To avoid any perf regressions keep the hash table for now. Most
net namespaces have very few devices and microbenchmarking 1M lookups
on Skylake I get the following results (not counting loopback
to number of devs):
#devs | hash | xa | delta
2 | 18.3 | 20.1 | + 9.8%
16 | 18.3 | 20.1 | + 9.5%
64 | 18.3 | 26.3 | +43.8%
128 | 20.4 | 26.3 | +28.6%
256 | 20.0 | 26.4 | +32.1%
1024 | 26.6 | 26.7 | + 0.2%
8192 |541.3 | 33.5 | -93.8%
No surprises since the hash table has 256 entries.
The microbenchmark scans indexes in order, if the pattern is more
random xa starts to win at 512 devices already. But that's a lot
of devices, in practice.
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230726185530.2247698-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
There are currently two paths that call remove_xps_queue():
1. __netif_set_xps_queue -> remove_xps_queue
2. clean_xps_maps -> remove_xps_queue_cpu -> remove_xps_queue
There is no need to check dev_maps in remove_xps_queue() because
dev_maps has been checked on these two paths.
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Link: https://lore.kernel.org/r/20230724023735.2751602-1-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This work refactors and adds a lightweight extension ("tcx") to the tc BPF
ingress and egress data path side for allowing BPF program management based
on fds via bpf() syscall through the newly added generic multi-prog API.
The main goal behind this work which we also presented at LPC [0] last year
and a recent update at LSF/MM/BPF this year [3] is to support long-awaited
BPF link functionality for tc BPF programs, which allows for a model of safe
ownership and program detachment.
Given the rise in tc BPF users in cloud native environments, this becomes
necessary to avoid hard to debug incidents either through stale leftover
programs or 3rd party applications accidentally stepping on each others toes.
As a recap, a BPF link represents the attachment of a BPF program to a BPF
hook point. The BPF link holds a single reference to keep BPF program alive.
Moreover, hook points do not reference a BPF link, only the application's
fd or pinning does. A BPF link holds meta-data specific to attachment and
implements operations for link creation, (atomic) BPF program update,
detachment and introspection. The motivation for BPF links for tc BPF programs
is multi-fold, for example:
- From Meta: "It's especially important for applications that are deployed
fleet-wide and that don't "control" hosts they are deployed to. If such
application crashes and no one notices and does anything about that, BPF
program will keep running draining resources or even just, say, dropping
packets. We at FB had outages due to such permanent BPF attachment
semantics. With fd-based BPF link we are getting a framework, which allows
safe, auto-detachable behavior by default, unless application explicitly
opts in by pinning the BPF link." [1]
- From Cilium-side the tc BPF programs we attach to host-facing veth devices
and phys devices build the core datapath for Kubernetes Pods, and they
implement forwarding, load-balancing, policy, EDT-management, etc, within
BPF. Currently there is no concept of 'safe' ownership, e.g. we've recently
experienced hard-to-debug issues in a user's staging environment where
another Kubernetes application using tc BPF attached to the same prio/handle
of cls_bpf, accidentally wiping all Cilium-based BPF programs from underneath
it. The goal is to establish a clear/safe ownership model via links which
cannot accidentally be overridden. [0,2]
BPF links for tc can co-exist with non-link attachments, and the semantics are
in line also with XDP links: BPF links cannot replace other BPF links, BPF
links cannot replace non-BPF links, non-BPF links cannot replace BPF links and
lastly only non-BPF links can replace non-BPF links. In case of Cilium, this
would solve mentioned issue of safe ownership model as 3rd party applications
would not be able to accidentally wipe Cilium programs, even if they are not
BPF link aware.
Earlier attempts [4] have tried to integrate BPF links into core tc machinery
to solve cls_bpf, which has been intrusive to the generic tc kernel API with
extensions only specific to cls_bpf and suboptimal/complex since cls_bpf could
be wiped from the qdisc also. Locking a tc BPF program in place this way, is
getting into layering hacks given the two object models are vastly different.
We instead implemented the tcx (tc 'express') layer which is an fd-based tc BPF
attach API, so that the BPF link implementation blends in naturally similar to
other link types which are fd-based and without the need for changing core tc
internal APIs. BPF programs for tc can then be successively migrated from classic
cls_bpf to the new tc BPF link without needing to change the program's source
code, just the BPF loader mechanics for attaching is sufficient.
For the current tc framework, there is no change in behavior with this change
and neither does this change touch on tc core kernel APIs. The gist of this
patch is that the ingress and egress hook have a lightweight, qdisc-less
extension for BPF to attach its tc BPF programs, in other words, a minimal
entry point for tc BPF. The name tcx has been suggested from discussion of
earlier revisions of this work as a good fit, and to more easily differ between
the classic cls_bpf attachment and the fd-based one.
For the ingress and egress tcx points, the device holds a cache-friendly array
with program pointers which is separated from control plane (slow-path) data.
Earlier versions of this work used priority to determine ordering and expression
of dependencies similar as with classic tc, but it was challenged that for
something more future-proof a better user experience is required. Hence this
resulted in the design and development of the generic attach/detach/query API
for multi-progs. See prior patch with its discussion on the API design. tcx is
the first user and later we plan to integrate also others, for example, one
candidate is multi-prog support for XDP which would benefit and have the same
'look and feel' from API perspective.
The goal with tcx is to have maximum compatibility to existing tc BPF programs,
so they don't need to be rewritten specifically. Compatibility to call into
classic tcf_classify() is also provided in order to allow successive migration
or both to cleanly co-exist where needed given its all one logical tc layer and
the tcx plus classic tc cls/act build one logical overall processing pipeline.
tcx supports the simplified return codes TCX_NEXT which is non-terminating (go
to next program) and terminating ones with TCX_PASS, TCX_DROP, TCX_REDIRECT.
The fd-based API is behind a static key, so that when unused the code is also
not entered. The struct tcx_entry's program array is currently static, but
could be made dynamic if necessary at a point in future. The a/b pair swap
design has been chosen so that for detachment there are no allocations which
otherwise could fail.
The work has been tested with tc-testing selftest suite which all passes, as
well as the tc BPF tests from the BPF CI, and also with Cilium's L4LB.
Thanks also to Nikolay Aleksandrov and Martin Lau for in-depth early reviews
of this work.
[0] https://lpc.events/event/16/contributions/1353/
[1] https://lore.kernel.org/bpf/CAEf4BzbokCJN33Nw_kg82sO=xppXnKWEncGTWCTB9vGCmLB6pw@mail.gmail.com
[2] https://colocatedeventseu2023.sched.com/event/1Jo6O/tales-from-an-ebpf-programs-murder-mystery-hemanth-malla-guillaume-fournier-datadog
[3] http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf
[4] https://lore.kernel.org/bpf/20210604063116.234316-1-memxor@gmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230719140858.13224-3-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Introduce new netlink attribute NETDEV_A_DEV_XDP_ZC_MAX_SEGS that will
carry maximum fragments that underlying ZC driver is able to handle on
TX side. It is going to be included in netlink response only when driver
supports ZC. Any value higher than 1 implies multi-buffer ZC support on
underlying device.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-11-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
We have for some time the assign_bit() API to replace open coded
if (foo)
set_bit(n, bar);
else
clear_bit(n, bar);
Use this API in the code. No functional change intended.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Message-ID: <20230710100830.89936-1-andriy.shevchenko@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Commit ad72c4a06a introduced optimization to return from function
quickly if the MAC address is not changing at all. It was reported
that such change causes dev->addr_assign_type to not change
to NET_ADDR_SET from _PERM or _RANDOM.
Restore the old behavior and skip only call to ndo_set_mac_address.
Fixes: ad72c4a06a ("net: add check for current MAC address in dev_set_mac_address")
Reported-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Piotr Gardocki <piotrx.gardocki@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230621132106.991342-1-piotrx.gardocki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In some cases it is possible for kernel to come with request
to change primary MAC address to the address that is already
set on the given interface.
Add proper check to return fast from the function in these cases.
An example of such case is adding an interface to bonding
channel in balance-alb mode:
modprobe bonding mode=balance-alb miimon=100 max_bonds=1
ip link set bond0 up
ifenslave bond0 <eth>
Signed-off-by: Piotr Gardocki <piotrx.gardocki@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
New users of dev_get_by_index() and dev_get_by_name() keep
getting added and it would be nice to steer them towards
the APIs with reference tracking.
Add variants of those calls which allocate the reference
tracker and use them in a couple of places.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move declarations into include/net/gso.h and code into net/core/gso.c
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230608191738.3947077-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR.
Conflicts:
net/sched/sch_taprio.c
d636fc5dd6 ("net: sched: add rcu annotations around qdisc->qdisc_sleeping")
dced11ef84 ("net/sched: taprio: don't overwrite "sch" variable in taprio_dump_class_stats()")
net/ipv4/sysctl_net_ipv4.c
e209fee411 ("net/ipv4: ping_group_range: allow GID from 2147483648 to 4294967294")
ccce324dab ("tcp: make the first N SYN RTO backoffs linear")
https://lore.kernel.org/all/20230605100816.08d41a7b@canb.auug.org.au/
No adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add READ_ONCE()/WRITE_ONCE() on accesses to the sock flow table.
This also prevents a (smart ?) compiler to remove the condition in:
if (table->ents[index] != newval)
table->ents[index] = newval;
We need the condition to avoid dirtying a shared cache line.
Fixes: fec5e652e5 ("rfs: Receive Flow Steering")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrzej Hajda says:
====================
drm/i915: use ref_tracker library for tracking wakerefs
This is reviewed series of ref_tracker patches, ready to merge
via network tree, rebased on net-next/main.
i915 patches will be merged later via intel-gfx tree.
====================
Merge on top of an -rc tag in case it's needed in another tree.
Link: https://lore.kernel.org/r/20230224-track_gt-v9-0-5b47a33f55d1@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In case the library is tracking busy subsystem, simply
printing stack for every active reference will spam log
with long, hard to read, redundant stack traces. To improve
readabilty following changes have been made:
- reports are printed per stack_handle - log is more compact,
- added display name for ref_tracker_dir - it will differentiate
multiple subsystems,
- stack trace is printed indented, in the same printk call,
- info about dropped references is printed as well.
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
If PREEMPT_RT is set, then assume that the user focuses on minimum
latency. Therefore don't set sw irq coalescing defaults.
This affects the defaults only, users can override these settings
via sysfs.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/f9439c7f-c92c-4c2c-703e-110f96d841b7@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Busy polling is currently not allowed on PREEMPT_RT, because it disables
preemption while invoking the NAPI callback. It is not possible to acquire
sleeping locks with disabled preemption. For details see commit
20ab39d13e ("net/core: disable NET_RX_BUSY_POLL on PREEMPT_RT").
However, strict cyclic and/or low latency network applications may prefer busy
polling e.g., using AF_XDP instead of interrupt driven communication.
The preempt_disable() is used in order to prevent the poll_owner and NAPI owner
to be preempted while owning the resource to ensure progress. Netpoll performs
busy polling in order to acquire the lock. NAPI is locked by setting the
NAPIF_STATE_SCHED flag. There is no busy polling if the flag is set and the
"owner" is preempted. Worst case is that the task owning NAPI gets preempted and
NAPI processing stalls. This is can be prevented by properly prioritising the
tasks within the system.
Allow RX_BUSY_POLL on PREEMPT_RT if NETPOLL is disabled. Don't disable
preemption on PREEMPT_RT within the busy poll loop.
Tested on x86 hardware with v6.1-RT and v6.3-RT on Intel i225 (igc) with
AF_XDP/ZC sockets configured to run in busy polling mode.
Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
We use napi_threaded_poll() in order to reduce our softirq dependency.
We can add a followup of 821eba962d ("net: optimize napi_schedule_rps()")
to further remove the need of firing NET_RX_SOFTIRQ whenever
RPS/RFS are used.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If we call skb_defer_free_flush() from napi_threaded_poll(),
we can avoid to raise IPI from skb_attempt_defer_free()
when the list becomes too big.
This allows napi_threaded_poll() to rely less on softirqs,
and lowers latency caused by a too big list.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We plan using skb_defer_free_flush() from napi_threaded_poll()
in the following patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
kfree_skb() can be called from hard irq handlers,
but skb_attempt_defer_free() is meant to be used
from process or BH contexts, and skb_defer_free_flush()
is meant to be called from BH contexts.
Not having to mask hard irq can save some cycles.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
__kfree_skb_defer() uses the old naming where "defer" meant
slab bulk free/alloc APIs. In the meantime we also made
__kfree_skb_defer() feed the per-NAPI skb cache, which
implies bulk APIs. So take away the 'defer' and add 'napi'.
While at it add a drop reason. This only matters on the
tx_action path, if the skb has a frag_list. But getting
rid of a SKB_DROP_REASON_NOT_SPECIFIED seems like a net
benefit so why not.
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20230420020005.815854-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
SCTP is not universally deployed, allow hiding its bit
from the skb.
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Recent patches to mlx5 mentioned a regression when moving from
driver local page pool to only using the generic page pool code.
Page pool has two recycling paths (1) direct one, which runs in
safe NAPI context (basically consumer context, so producing
can be lockless); and (2) via a ptr_ring, which takes a spin
lock because the freeing can happen from any CPU; producer
and consumer may run concurrently.
Since the page pool code was added, Eric introduced a revised version
of deferred skb freeing. TCP skbs are now usually returned to the CPU
which allocated them, and freed in softirq context. This places the
freeing (producing of pages back to the pool) enticingly close to
the allocation (consumer).
If we can prove that we're freeing in the same softirq context in which
the consumer NAPI will run - lockless use of the cache is perfectly fine,
no need for the lock.
Let drivers link the page pool to a NAPI instance. If the NAPI instance
is scheduled on the same CPU on which we're freeing - place the pages
in the direct cache.
With that and patched bnxt (XDP enabled to engage the page pool, sigh,
bnxt really needs page pool work :() I see a 2.6% perf boost with
a TCP stream test (app on a different physical core than softirq).
The CPU use of relevant functions decreases as expected:
page_pool_refill_alloc_cache 1.17% -> 0%
_raw_spin_lock 2.41% -> 0.98%
Only consider lockless path to be safe when NAPI is scheduled
- in practice this should cover majority if not all of steady state
workloads. It's usually the NAPI kicking in that causes the skb flush.
The main case we'll miss out on is when application runs on the same
CPU as NAPI. In that case we don't use the deferred skb free path.
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The commits referenced below allows userspace to use the NLM_F_ECHO flag
for RTM_NEW/DELLINK operations to receive unicast notifications for the
affected link. Prior to these changes, applications may have relied on
multicast notifications to learn the same information without specifying
the NLM_F_ECHO flag.
For such applications, the mentioned commits changed the behavior for
requests not using NLM_F_ECHO. Multicast notifications are still received,
but now use the portid of the requester and the sequence number of the
request instead of zero values used previously. For the application, this
message may be unexpected and likely handled as a response to the
NLM_F_ACKed request, especially if it uses the same socket to handle
requests and notifications.
To fix existing applications relying on the old notification behavior,
set the portid and sequence number in the notification only if the
request included the NLM_F_ECHO flag. This restores the old behavior
for applications not using it, but allows unicasted notifications for
others.
Fixes: f3a63cce1b ("rtnetlink: Honour NLM_F_ECHO flag in rtnl_delete_link")
Fixes: d88e136cab ("rtnetlink: Honour NLM_F_ECHO flag in rtnl_newlink_create")
Signed-off-by: Martin Willi <martin@strongswan.org>
Acked-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20230411074319.24133-1-martin@strongswan.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
There was a sort of rush surrounding commit 88c0a6b503 ("net: create a
netdev notifier for DSA to reject PTP on DSA master"), due to a desire
to convert DSA's attempt to deny TX timestamping on a DSA master to
something that doesn't block the kernel-wide API conversion from
ndo_eth_ioctl() to ndo_hwtstamp_set().
What was required was a mechanism that did not depend on ndo_eth_ioctl(),
and what was provided was a mechanism that did not depend on
ndo_eth_ioctl(), while at the same time introducing something that
wasn't absolutely necessary - a new netdev notifier.
There have been objections from Jakub Kicinski that using notifiers in
general when they are not absolutely necessary creates complications to
the control flow and difficulties to maintainers who look at the code.
So there is a desire to not use notifiers.
In addition to that, the notifier chain gets called even if there is no
DSA in the system and no one is interested in applying any restriction.
Take the model of udp_tunnel_nic_ops and introduce a stub mechanism,
through which net/core/dev_ioctl.c can call into DSA even when
CONFIG_NET_DSA=m.
Compared to the code that existed prior to the notifier conversion, aka
what was added in commits:
- 4cfab35667 ("net: dsa: Add wrappers for overloaded ndo_ops")
- 3369afba1e ("net: Call into DSA netdevice_ops wrappers")
this is different because we are not overloading any struct
net_device_ops of the DSA master anymore, but rather, we are exposing a
rather specific functionality which is orthogonal to which API is used
to enable it - ndo_eth_ioctl() or ndo_hwtstamp_set().
Also, what is similar is that both approaches use function pointers to
get from built-in code to DSA.
There is no point in replicating the function pointers towards
__dsa_master_hwtstamp_validate() once for every CPU port (dev->dsa_ptr).
Instead, it is sufficient to introduce a singleton struct dsa_stubs,
built into the kernel, which contains a single function pointer to
__dsa_master_hwtstamp_validate().
I find this approach preferable to what we had originally, because
dev->dsa_ptr->netdev_ops->ndo_do_ioctl() used to require going through
struct dsa_port (dev->dsa_ptr), and so, this was incompatible with any
attempts to add any data encapsulation and hide DSA data structures from
the outside world.
Link: https://lore.kernel.org/netdev/20230403083019.120b72fd@kernel.org/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
assume the following setup on a single machine:
1. An openvswitch instance with one bridge and default flows
2. two network namespaces "server" and "client"
3. two ovs interfaces "server" and "client" on the bridge
4. for each ovs interface a veth pair with a matching name and 32 rx and
tx queues
5. move the ends of the veth pairs to the respective network namespaces
6. assign ip addresses to each of the veth ends in the namespaces (needs
to be the same subnet)
7. start some http server on the server network namespace
8. test if a client in the client namespace can reach the http server
when following the actions below the host has a chance of getting a cpu
stuck in a infinite loop:
1. send a large amount of parallel requests to the http server (around
3000 curls should work)
2. in parallel delete the network namespace (do not delete interfaces or
stop the server, just kill the namespace)
there is a low chance that this will cause the below kernel cpu stuck
message. If this does not happen just retry.
Below there is also the output of bpftrace for the functions mentioned
in the output.
The series of events happening here is:
1. the network namespace is deleted calling
`unregister_netdevice_many_notify` somewhere in the process
2. this sets first `NETREG_UNREGISTERING` on both ends of the veth and
then runs `synchronize_net`
3. it then calls `call_netdevice_notifiers` with `NETDEV_UNREGISTER`
4. this is then handled by `dp_device_event` which calls
`ovs_netdev_detach_dev` (if a vport is found, which is the case for
the veth interface attached to ovs)
5. this removes the rx_handlers of the device but does not prevent
packages to be sent to the device
6. `dp_device_event` then queues the vport deletion to work in
background as a ovs_lock is needed that we do not hold in the
unregistration path
7. `unregister_netdevice_many_notify` continues to call
`netdev_unregister_kobject` which sets `real_num_tx_queues` to 0
8. port deletion continues (but details are not relevant for this issue)
9. at some future point the background task deletes the vport
If after 7. but before 9. a packet is send to the ovs vport (which is
not deleted at this point in time) which forwards it to the
`dev_queue_xmit` flow even though the device is unregistering.
In `skb_tx_hash` (which is called in the `dev_queue_xmit`) path there is
a while loop (if the packet has a rx_queue recorded) that is infinite if
`dev->real_num_tx_queues` is zero.
To prevent this from happening we update `do_output` to handle devices
without carrier the same as if the device is not found (which would
be the code path after 9. is done).
Additionally we now produce a warning in `skb_tx_hash` if we will hit
the infinite loop.
bpftrace (first word is function name):
__dev_queue_xmit server: real_num_tx_queues: 1, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 1
netdev_core_pick_tx server: addr: 0xffff9f0a46d4a000 real_num_tx_queues: 1, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 1
dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 2, reg_state: 1
synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024
synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024
synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024
synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024
dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 6, reg_state: 2
ovs_netdev_detach_dev server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, reg_state: 2
netdev_rx_handler_unregister server: real_num_tx_queues: 1, cpu: 9, pid: 21024, tid: 21024, reg_state: 2
synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024
netdev_rx_handler_unregister ret server: real_num_tx_queues: 1, cpu: 9, pid: 21024, tid: 21024, reg_state: 2
dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 27, reg_state: 2
dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 22, reg_state: 2
dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 18, reg_state: 2
netdev_unregister_kobject: real_num_tx_queues: 1, cpu: 9, pid: 21024, tid: 21024
synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024
ovs_vport_send server: real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 2
__dev_queue_xmit server: real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 2
netdev_core_pick_tx server: addr: 0xffff9f0a46d4a000 real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 2
broken device server: real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024
ovs_dp_detach_port server: real_num_tx_queues: 0 cpu 9, pid: 9124, tid: 9124, reg_state: 2
synchronize_rcu_expedited: cpu 9, pid: 33604, tid: 33604
stuck message:
watchdog: BUG: soft lockup - CPU#5 stuck for 26s! [curl:1929279]
Modules linked in: veth pktgen bridge stp llc ip_set_hash_net nft_counter xt_set nft_compat nf_tables ip_set_hash_ip ip_set nfnetlink_cttimeout nfnetlink openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 tls binfmt_misc nls_iso8859_1 input_leds joydev serio_raw dm_multipath scsi_dh_rdac scsi_dh_emc scsi_dh_alua sch_fq_codel drm efi_pstore virtio_rng ip_tables x_tables autofs4 btrfs blake2b_generic zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear hid_generic usbhid hid crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel virtio_net ahci net_failover crypto_simd cryptd psmouse libahci virtio_blk failover
CPU: 5 PID: 1929279 Comm: curl Not tainted 5.15.0-67-generic #74-Ubuntu
Hardware name: OpenStack Foundation OpenStack Nova, BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:netdev_pick_tx+0xf1/0x320
Code: 00 00 8d 48 ff 0f b7 c1 66 39 ca 0f 86 e9 01 00 00 45 0f b7 ff 41 39 c7 0f 87 5b 01 00 00 44 29 f8 41 39 c7 0f 87 4f 01 00 00 <eb> f2 0f 1f 44 00 00 49 8b 94 24 28 04 00 00 48 85 d2 0f 84 53 01
RSP: 0018:ffffb78b40298820 EFLAGS: 00000246
RAX: 0000000000000000 RBX: ffff9c8773adc2e0 RCX: 000000000000083f
RDX: 0000000000000000 RSI: ffff9c8773adc2e0 RDI: ffff9c870a25e000
RBP: ffffb78b40298858 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff9c870a25e000
R13: ffff9c870a25e000 R14: ffff9c87fe043480 R15: 0000000000000000
FS: 00007f7b80008f00(0000) GS:ffff9c8e5f740000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f7b80f6a0b0 CR3: 0000000329d66000 CR4: 0000000000350ee0
Call Trace:
<IRQ>
netdev_core_pick_tx+0xa4/0xb0
__dev_queue_xmit+0xf8/0x510
? __bpf_prog_exit+0x1e/0x30
dev_queue_xmit+0x10/0x20
ovs_vport_send+0xad/0x170 [openvswitch]
do_output+0x59/0x180 [openvswitch]
do_execute_actions+0xa80/0xaa0 [openvswitch]
? kfree+0x1/0x250
? kfree+0x1/0x250
? kprobe_perf_func+0x4f/0x2b0
? flow_lookup.constprop.0+0x5c/0x110 [openvswitch]
ovs_execute_actions+0x4c/0x120 [openvswitch]
ovs_dp_process_packet+0xa1/0x200 [openvswitch]
? ovs_ct_update_key.isra.0+0xa8/0x120 [openvswitch]
? ovs_ct_fill_key+0x1d/0x30 [openvswitch]
? ovs_flow_key_extract+0x2db/0x350 [openvswitch]
ovs_vport_receive+0x77/0xd0 [openvswitch]
? __htab_map_lookup_elem+0x4e/0x60
? bpf_prog_680e8aff8547aec1_kfree+0x3b/0x714
? trace_call_bpf+0xc8/0x150
? kfree+0x1/0x250
? kfree+0x1/0x250
? kprobe_perf_func+0x4f/0x2b0
? kprobe_perf_func+0x4f/0x2b0
? __mod_memcg_lruvec_state+0x63/0xe0
netdev_port_receive+0xc4/0x180 [openvswitch]
? netdev_port_receive+0x180/0x180 [openvswitch]
netdev_frame_hook+0x1f/0x40 [openvswitch]
__netif_receive_skb_core.constprop.0+0x23d/0xf00
__netif_receive_skb_one_core+0x3f/0xa0
__netif_receive_skb+0x15/0x60
process_backlog+0x9e/0x170
__napi_poll+0x33/0x180
net_rx_action+0x126/0x280
? ttwu_do_activate+0x72/0xf0
__do_softirq+0xd9/0x2e7
? rcu_report_exp_cpu_mult+0x1b0/0x1b0
do_softirq+0x7d/0xb0
</IRQ>
<TASK>
__local_bh_enable_ip+0x54/0x60
ip_finish_output2+0x191/0x460
__ip_finish_output+0xb7/0x180
ip_finish_output+0x2e/0xc0
ip_output+0x78/0x100
? __ip_finish_output+0x180/0x180
ip_local_out+0x5e/0x70
__ip_queue_xmit+0x184/0x440
? tcp_syn_options+0x1f9/0x300
ip_queue_xmit+0x15/0x20
__tcp_transmit_skb+0x910/0x9c0
? __mod_memcg_state+0x44/0xa0
tcp_connect+0x437/0x4e0
? ktime_get_with_offset+0x60/0xf0
tcp_v4_connect+0x436/0x530
__inet_stream_connect+0xd4/0x3a0
? kprobe_perf_func+0x4f/0x2b0
? aa_sk_perm+0x43/0x1c0
inet_stream_connect+0x3b/0x60
__sys_connect_file+0x63/0x70
__sys_connect+0xa6/0xd0
? setfl+0x108/0x170
? do_fcntl+0xe8/0x5a0
__x64_sys_connect+0x18/0x20
do_syscall_64+0x5c/0xc0
? __x64_sys_fcntl+0xa9/0xd0
? exit_to_user_mode_prepare+0x37/0xb0
? syscall_exit_to_user_mode+0x27/0x50
? do_syscall_64+0x69/0xc0
? __sys_setsockopt+0xea/0x1e0
? exit_to_user_mode_prepare+0x37/0xb0
? syscall_exit_to_user_mode+0x27/0x50
? __x64_sys_setsockopt+0x1f/0x30
? do_syscall_64+0x69/0xc0
? irqentry_exit+0x1d/0x30
? exc_page_fault+0x89/0x170
entry_SYSCALL_64_after_hwframe+0x61/0xcb
RIP: 0033:0x7f7b8101c6a7
Code: 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2a 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 18 89 54 24 0c 48 89 34 24 89
RSP: 002b:00007ffffd6b2198 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7b8101c6a7
RDX: 0000000000000010 RSI: 00007ffffd6b2360 RDI: 0000000000000005
RBP: 0000561f1370d560 R08: 00002795ad21d1ac R09: 0030312e302e302e
R10: 00007ffffd73f080 R11: 0000000000000246 R12: 0000561f1370c410
R13: 0000000000000000 R14: 0000000000000005 R15: 0000000000000000
</TASK>
Fixes: 7f8a436eaa ("openvswitch: Add conntrack action")
Co-developed-by: Luca Czesla <luca.czesla@mail.schwarz>
Signed-off-by: Luca Czesla <luca.czesla@mail.schwarz>
Signed-off-by: Felix Huettner <felix.huettner@mail.schwarz>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/ZC0pBXBAgh7c76CA@kernel-bug-kernel-bug
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The fact that PTP 2-step TX timestamping is broken on DSA switches if
the master also timestamps the same packets is documented by commit
f685e609a3 ("net: dsa: Deny PTP on master if switch supports it").
We attempt to help the users avoid shooting themselves in the foot by
making DSA reject the timestamping ioctls on an interface that is a DSA
master, and the switch tree beneath it contains switches which are aware
of PTP.
The only problem is that there isn't an established way of intercepting
ndo_eth_ioctl calls, so DSA creates avoidable burden upon the network
stack by creating a struct dsa_netdevice_ops with overlaid function
pointers that are manually checked from the relevant call sites. There
used to be 2 such dsa_netdevice_ops, but now, ndo_eth_ioctl is the only
one left.
There is an ongoing effort to migrate driver-visible hardware timestamping
control from the ndo_eth_ioctl() based API to a new ndo_hwtstamp_set()
model, but DSA actively prevents that migration, since dsa_master_ioctl()
is currently coded to manually call the master's legacy ndo_eth_ioctl(),
and so, whenever a network device driver would be converted to the new
API, DSA's restrictions would be circumvented, because any device could
be used as a DSA master.
The established way for unrelated modules to react on a net device event
is via netdevice notifiers. So we create a new notifier which gets
called whenever there is an attempt to change hardware timestamping
settings on a device.
Finally, there is another reason why a netdev notifier will be a good
idea, besides strictly DSA, and this has to do with PHY timestamping.
With ndo_eth_ioctl(), all MAC drivers must manually call
phy_has_hwtstamp() before deciding whether to act upon SIOCSHWTSTAMP,
otherwise they must pass this ioctl to the PHY driver via
phy_mii_ioctl().
With the new ndo_hwtstamp_set() API, it will be desirable to simply not
make any calls into the MAC device driver when timestamping should be
performed at the PHY level.
But there exist drivers, such as the lan966x switch, which need to
install packet traps for PTP regardless of whether they are the layer
that provides the hardware timestamps, or the PHY is. That would be
impossible to support with the new API.
The proposal there, too, is to introduce a netdev notifier which acts as
a better cue for switching drivers to add or remove PTP packet traps,
than ndo_hwtstamp_set(). The one introduced here "almost" works there as
well, except for the fact that packet traps should only be installed if
the PHY driver succeeded to enable hardware timestamping, whereas here,
we need to deny hardware timestamping on the DSA master before it
actually gets enabled. This is why this notifier is called "PRE_", and
the notifier that would get used for PHY timestamping and packet traps
would be called NETDEV_CHANGE_HWTSTAMP. This isn't a new concept, for
example NETDEV_CHANGEUPPER and NETDEV_PRECHANGEUPPER do the same thing.
In expectation of future netlink UAPI, we also pass a non-NULL extack
pointer to the netdev notifier, and we make DSA populate it with an
informative reason for the rejection. To avoid making it go to waste, we
make the ioctl-based dev_set_hwtstamp() create a fake extack and print
the message to the kernel log.
Link: https://lore.kernel.org/netdev/20230401191215.tvveoi3lkawgg6g4@skbuf/
Link: https://lore.kernel.org/netdev/20230310164451.ls7bbs6pdzs4m6pw@skbuf/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
____napi_schedule() adds a napi into current cpu softnet_data poll_list,
then raises NET_RX_SOFTIRQ to make sure net_rx_action() will process it.
Idea of this patch is to not raise NET_RX_SOFTIRQ when being called indirectly
from net_rx_action(), because we can process poll_list from this point,
without going to full softirq loop.
This needs a change in net_rx_action() to make sure we restart
its main loop if sd->poll_list was updated without NET_RX_SOFTIRQ
being raised.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Based on initial patch from Jason Xing.
Idea is to not raise NET_RX_SOFTIRQ from napi_schedule_rps()
when we queued a packet into another cpu backlog.
We can do this only in the context of us being called indirectly
from net_rx_action(), to have the guarantee our rps_ipi_list
will be processed before we exit from net_rx_action().
Link: https://lore.kernel.org/lkml/20230325152417.5403-1-kerneljasonxing@gmail.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
We want to make two optimizations in napi_schedule_rps() and
____napi_schedule() which require to know if these helpers are
called from net_rx_action(), instead of being called from
other contexts.
sd.in_net_rx_action is only read/written by the owning cpu.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
napi_schedule_rps() return value is ignored, remove it.
Change the comment to clarify the intent.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
We want to remove our use of skb_mac_header() in tx paths,
eg remove skb_reset_mac_header() from __dev_queue_xmit().
Idea is that ndo_start_xmit() can get the mac header
simply looking at skb->data.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When setting the XPS value of a TX queue, warn the user once if the
index of the queue is greater than the number of allocated TX queues.
Previously, this scenario went uncaught. In the best case, it resulted
in unnecessary allocations. In the worst case, it resulted in
out-of-bounds memory references through calls to `netdev_get_tx_queue(
dev, index)`. Therefore, it is important to inform the user but not
worth returning an error and risk downing the netdevice.
Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Reviewed-by: Piotr Raczynski <piotr.raczynski@intel.com>
Link: https://lore.kernel.org/r/20230321150725.127229-1-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
enum skb_drop_reason is more generic, we can adopt it instead.
Provide dev_kfree_skb_irq_reason() and dev_kfree_skb_any_reason().
This means drivers can use more precise drop reasons if they want to.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Link: https://lore.kernel.org/r/20230306204313.10492-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dev_kfree_skb() is aliased to consume_skb().
When a driver is dropping a packet by calling dev_kfree_skb_any()
we should propagate the drop reason instead of pretending
the packet was consumed.
Note: Now we have enum skb_drop_reason we could remove
enum skb_free_reason (for linux-6.4)
v2: added an unlikely(), suggested by Yunsheng Lin.
Fixes: e6247027e5 ("net: introduce dev_consume_skb_any()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cited commit changed devlink to register its netdev notifier block on
the global netdev notifier chain instead of on the per network namespace
one.
However, when changing the network namespace of the devlink instance,
devlink still tries to unregister its notifier block from the chain of
the old namespace and register it on the chain of the new namespace.
This results in corruption of the notifier chains, as the same notifier
block is registered on two different chains: The global one and the per
network namespace one. In turn, this causes other problems such as the
inability to dismantle namespaces due to netdev reference count issues.
Fix by preventing devlink from moving its notifier block between
namespaces.
Reproducer:
# echo "10 1" > /sys/bus/netdevsim/new_device
# ip netns add test123
# devlink dev reload netdevsim/netdevsim10 netns test123
# ip netns del test123
[ 71.935619] unregister_netdevice: waiting for lo to become free. Usage count = 2
[ 71.938348] leaked reference.
Fixes: 565b4824c3 ("devlink: change port event netdev notifier from per-net to global")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230215073139.1360108-1-idosch@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The kernel stack can be more consistent by printing the IFF_PROMISC
aka promiscuous enable/disable messages with the standard netdev_info
message which can include bus and driver info as well as the device.
typical command usage from user space looks like:
ip link set eth0 promisc <on|off>
But lots of utilities such as bridge, tcpdump, etc put the interface into
promiscuous mode.
old message:
[ 406.034418] device eth0 entered promiscuous mode
[ 408.424703] device eth0 left promiscuous mode
new message:
[ 406.034431] ice 0000:17:00.0 eth0: entered promiscuous mode
[ 408.424715] ice 0000:17:00.0 eth0: left promiscuous mode
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When the user sets or clears the IFF_ALLMULTI flag in the netdev, there are
no log messages printed to the kernel log to indicate anything happened.
This is inexplicably different from most other dev->flags changes, and
could suprise the user.
Typically this occurs from user-space when a user:
ip link set eth0 allmulticast <on|off>
However, other devices like bridge set allmulticast as well, and many
other flows might trigger entry into allmulticast as well.
The new message uses the standard netdev_info print and looks like:
[ 413.246110] ixgbe 0000:17:00.0 eth0: entered allmulticast mode
[ 415.977184] ixgbe 0000:17:00.0 eth0: left allmulticast mode
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When converting net_device_stats to rtnl_link_stats64 sign extension
is triggered on ILP32 machines as 6c1c509778 changed the previous
"ulong -> u64" conversion to "long -> u64" by accessing the
net_device_stats fields through a (signed) atomic_long_t.
This causes for example the received bytes counter to jump to 16EiB after
having received 2^31 bytes. Casting the atomic value to "unsigned long"
beforehand converting it into u64 avoids this.
Fixes: 6c1c509778 ("net: add atomic_long_t to net_device_stats fields")
Signed-off-by: Felix Riemann <felix.riemann@sma.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCY+bZrwAKCRDbK58LschI
gzi4AP4+TYo0jnSwwkrOoN9l4f5VO9X8osmj3CXfHBv7BGWVxAD/WnvA3TDZyaUd
agIZTkRs6BHF9He8oROypARZxTeMLwM=
=nO1C
-----END PGP SIGNATURE-----
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-02-11
We've added 96 non-merge commits during the last 14 day(s) which contain
a total of 152 files changed, 4884 insertions(+), 962 deletions(-).
There is a minor conflict in drivers/net/ethernet/intel/ice/ice_main.c
between commit 5b246e533d ("ice: split probe into smaller functions")
from the net-next tree and commit 66c0e13ad2 ("drivers: net: turn on
XDP features") from the bpf-next tree. Remove the hunk given ice_cfg_netdev()
is otherwise there a 2nd time, and add XDP features to the existing
ice_cfg_netdev() one:
[...]
ice_set_netdev_features(netdev);
netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
NETDEV_XDP_ACT_XSK_ZEROCOPY;
ice_set_ops(netdev);
[...]
Stephen's merge conflict mail:
https://lore.kernel.org/bpf/20230207101951.21a114fa@canb.auug.org.au/
The main changes are:
1) Add support for BPF trampoline on s390x which finally allows to remove many
test cases from the BPF CI's DENYLIST.s390x, from Ilya Leoshkevich.
2) Add multi-buffer XDP support to ice driver, from Maciej Fijalkowski.
3) Add capability to export the XDP features supported by the NIC.
Along with that, add a XDP compliance test tool,
from Lorenzo Bianconi & Marek Majtyka.
4) Add __bpf_kfunc tag for marking kernel functions as kfuncs,
from David Vernet.
5) Add a deep dive documentation about the verifier's register
liveness tracking algorithm, from Eduard Zingerman.
6) Fix and follow-up cleanups for resolve_btfids to be compiled
as a host program to avoid cross compile issues,
from Jiri Olsa & Ian Rogers.
7) Batch of fixes to the BPF selftest for xdp_hw_metadata which resulted
when testing on different NICs, from Jesper Dangaard Brouer.
8) Fix libbpf to better detect kernel version code on Debian, from Hao Xiang.
9) Extend libbpf to add an option for when the perf buffer should
wake up, from Jon Doron.
10) Follow-up fix on xdp_metadata selftest to just consume on TX
completion, from Stanislav Fomichev.
11) Extend the kfuncs.rst document with description on kfunc
lifecycle & stability expectations, from David Vernet.
12) Fix bpftool prog profile to skip attaching to offline CPUs,
from Tonghao Zhang.
====================
Link: https://lore.kernel.org/r/20230211002037.8489-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a Netlink spec-compatible family for netdevs.
This is a very simple implementation without much
thought going into it.
It allows us to reap all the benefits of Netlink specs,
one can use the generic client to issue the commands:
$ ./cli.py --spec netdev.yaml --dump dev_get
[{'ifindex': 1, 'xdp-features': set()},
{'ifindex': 2, 'xdp-features': {'basic', 'ndo-xmit', 'redirect'}},
{'ifindex': 3, 'xdp-features': {'rx-sg'}}]
the generic python library does not have flags-by-name
support, yet, but we also don't have to carry strings
in the messages, as user space can get the names from
the spec.
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/327ad9c9868becbe1e601b580c962549c8cd81f2.1675245258.git.lorenzo@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch introduces gso_ipv4_max_size and gro_ipv4_max_size
per device and adds netlink attributes for them, so that IPV4
BIG TCP can be guarded by a separate tunable in the next patch.
To not break the old application using "gso/gro_max_size" for
IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size"
in netif_set_gso/gro_max_size() if the new size isn't greater
than GSO_LEGACY_MAX_SIZE, so that nothing will change even if
userspace doesn't realize the new netlink attributes.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCY9RqJgAKCRDbK58LschI
gw2IAP9G5uhFO5abBzYLupp6SY3T5j97MUvPwLfFqUEt7EXmuwEA2lCUEWeW0KtR
QX+QmzCa6iHxrW7WzP4DUYLue//FJQY=
=yYqA
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
bpf-next 2023-01-28
We've added 124 non-merge commits during the last 22 day(s) which contain
a total of 124 files changed, 6386 insertions(+), 1827 deletions(-).
The main changes are:
1) Implement XDP hints via kfuncs with initial support for RX hash and
timestamp metadata kfuncs, from Stanislav Fomichev and
Toke Høiland-Jørgensen.
Measurements on overhead: https://lore.kernel.org/bpf/875yellcx6.fsf@toke.dk
2) Extend libbpf's bpf_tracing.h support for tracing arguments of
kprobes/uprobes and syscall as a special case, from Andrii Nakryiko.
3) Significantly reduce the search time for module symbols by livepatch
and BPF, from Jiri Olsa and Zhen Lei.
4) Enable cpumasks to be used as kptrs, which is useful for tracing
programs tracking which tasks end up running on which CPUs
in different time intervals, from David Vernet.
5) Fix several issues in the dynptr processing such as stack slot liveness
propagation, missing checks for PTR_TO_STACK variable offset, etc,
from Kumar Kartikeya Dwivedi.
6) Various performance improvements, fixes, and introduction of more
than just one XDP program to XSK selftests, from Magnus Karlsson.
7) Big batch to BPF samples to reduce deprecated functionality,
from Daniel T. Lee.
8) Enable struct_ops programs to be sleepable in verifier,
from David Vernet.
9) Reduce pr_warn() noise on BTF mismatches when they are expected under
the CONFIG_MODULE_ALLOW_BTF_MISMATCH config anyway, from Connor O'Brien.
10) Describe modulo and division by zero behavior of the BPF runtime
in BPF's instruction specification document, from Dave Thaler.
11) Several improvements to libbpf API documentation in libbpf.h,
from Grant Seltzer.
12) Improve resolve_btfids header dependencies related to subcmd and add
proper support for HOSTCC, from Ian Rogers.
13) Add ipip6 and ip6ip decapsulation support for bpf_skb_adjust_room()
helper along with BPF selftests, from Ziyang Xuan.
14) Simplify the parsing logic of structure parameters for BPF trampoline
in the x86-64 JIT compiler, from Pu Lehui.
15) Get BTF working for kernels with CONFIG_RUST enabled by excluding
Rust compilation units with pahole, from Martin Rodriguez Reboredo.
16) Get bpf_setsockopt() working for kTLS on top of TCP sockets,
from Kui-Feng Lee.
17) Disable stack protection for BPF objects in bpftool given BPF backends
don't support it, from Holger Hoffstätte.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (124 commits)
selftest/bpf: Make crashes more debuggable in test_progs
libbpf: Add documentation to map pinning API functions
libbpf: Fix malformed documentation formatting
selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata
selftests/bpf: Calls bpf_setsockopt() on a ktls enabled socket.
bpf: Check the protocol of a sock to agree the calls to bpf_setsockopt().
bpf/selftests: Verify struct_ops prog sleepable behavior
bpf: Pass const struct bpf_prog * to .check_member
libbpf: Support sleepable struct_ops.s section
bpf: Allow BPF_PROG_TYPE_STRUCT_OPS programs to be sleepable
selftests/bpf: Fix vmtest static compilation error
tools/resolve_btfids: Alter how HOSTCC is forced
tools/resolve_btfids: Install subcmd headers
bpf/docs: Document the nocast aliasing behavior of ___init
bpf/docs: Document how nested trusted fields may be defined
bpf/docs: Document cpumask kfuncs in a new file
selftests/bpf: Add selftest suite for cpumask kfuncs
selftests/bpf: Add nested trust selftests suite
bpf: Enable cpumasks to be queried and used as kptrs
bpf: Disallow NULLable pointers for trusted kfuncs
...
====================
Link: https://lore.kernel.org/r/20230128004827.21371-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The spin_lock irqsave/restore API variant in skb_defer_free_flush can
be replaced with the faster spin_lock irq variant, which doesn't need
to read and restore the CPU flags.
Using the unconditional irq "disable/enable" API variant is safe,
because the skb_defer_free_flush() function is only called during
NAPI-RX processing in net_rx_action(), where it is known the IRQs
are enabled.
Expected gain is 14 cycles from avoiding reading and restoring CPU
flags in a spin_lock_irqsave/restore operation, measured via a
microbencmark kernel module[1] on CPU E5-1650 v4 @ 3.60GHz.
Microbenchmark overhead of spin_lock+unlock:
- spin_lock_unlock_irq cost: 34 cycles(tsc) 9.486 ns
- spin_lock_unlock_irqsave cost: 48 cycles(tsc) 13.567 ns
We don't expect to see a measurable packet performance gain, as
skb_defer_free_flush() is called infrequently once per NIC device NAPI
bulk cycle and conditionally only if SKBs have been deferred by other
CPUs via skb_attempt_defer_free().
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/lib/time_bench_sample.c
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/r/167421646327.1321776.7390743166998776914.stgit@firesoul
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
New flag BPF_F_XDP_DEV_BOUND_ONLY plus all the infra to have a way
to associate a netdev with a BPF program at load time.
netdevsim checks are dropped in favor of generic check in dev_xdp_attach.
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: Alexander Lobakin <alexandr.lobakin@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@gmail.com>
Cc: Maryam Tahhan <mtahhan@redhat.com>
Cc: xdp-hints@xdp-project.net
Cc: netdev@vger.kernel.org
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230119221536.3349901-6-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
BPF offloading infra will be reused to implement
bound-but-not-offloaded bpf programs. Rename existing
helpers for clarity. No functional changes.
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: Alexander Lobakin <alexandr.lobakin@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@gmail.com>
Cc: Maryam Tahhan <mtahhan@redhat.com>
Cc: xdp-hints@xdp-project.net
Cc: netdev@vger.kernel.org
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230119221536.3349901-3-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
unregister_netdevice_notifier_net() is used for unregister a notifier
registered by register_netdevice_notifier_net(). Also s/into/from/.
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a helper for drivers wanting to set SW IRQ coalescing
by default. The related sysfs attributes can be used to
override the default values.
Follow Jakub's suggestion and put this functionality into
net core so that drivers wanting to use software interrupt
coalescing per default don't have to open-code it.
Note that this function needs to be called before the
netdevice is registered.
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dan reported a new warning after my recent patch:
New smatch warnings:
net/core/dev.c:6409 napi_disable() error: uninitialized symbol 'new'.
Indeed, we must first wait for STATE_SCHED and STATE_NPSVC to be cleared,
to make sure @new variable has been initialized properly.
Fixes: 4ffa1d1c68 ("net: adopt try_cmpxchg() in napi_{enable|disable}()")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Long standing KCSAN issues are caused by data-race around
some dev->stats changes.
Most performance critical paths already use per-cpu
variables, or per-queue ones.
It is reasonable (and more correct) to use atomic operations
for the slow paths.
This patch adds an union for each field of net_device_stats,
so that we can convert paths that are not yet protected
by a spinlock or a mutex.
netdev_stats_to_stats64() no longer has an #if BITS_PER_LONG==64
Note that the memcpy() we were using on 64bit arches
had no provision to avoid load-tearing,
while atomic_long_read() is providing the needed protection
at no cost.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adopting atomic_try_cmpxchg() makes the code cleaner.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, net_dev() netdev notifier variant follows the netdev with
per-net notifier from namespace to namespace. This is implemented
by move_netdevice_notifiers_dev_net() helper.
For devlink it is needed to re-register per-net notifier during
devlink reload. Introduce a new helper called
move_netdevice_notifier_net() and share the unregister/register code
with existing move_netdevice_notifiers_dev_net() helper.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Allow a network interface to be renamed when the interface
is up.
As described in the netconsole documentation [1], when netconsole is
used as a built-in, it will bring up the specified interface as soon as
possible. As a result, user space will not be able to rename the
interface since the kernel disallows renaming of interfaces that are
administratively up unless the 'IFF_LIVE_RENAME_OK' private flag was set
by the kernel.
The original solution [2] to this problem was to add a new parameter to
the netconsole configuration parameters that allows renaming of
the interface used by netconsole while it is administratively up.
However, during the discussion that followed, it became apparent that we
have no reason to keep the current restriction and instead we should
allow user space to rename interfaces regardless of their administrative
state:
1. The restriction was put in place over 20 years ago when renaming was
only possible via IOCTL and before rtnetlink started notifying user
space about such changes like it does today.
2. The 'IFF_LIVE_RENAME_OK' flag was added over 3 years ago in version
5.2 and no regressions were reported.
3. In-kernel listeners to 'NETDEV_CHANGENAME' do not seem to care about
the administrative state of interface.
Therefore, allow user space to rename running interfaces by removing the
restriction and the associated 'IFF_LIVE_RENAME_OK' flag. Help in
possible triage by emitting a message to the kernel log that an
interface was renamed while UP.
[1] https://www.kernel.org/doc/Documentation/networking/netconsole.rst
[2] https://lore.kernel.org/netdev/20221102002420.2613004-1-andy.ren@getcruise.com/
Signed-off-by: Andy Ren <andy.ren@getcruise.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, ethernet drivers are using devlink_port_type_eth_set() and
devlink_port_type_clear() to set devlink port type and link to related
netdev.
Instead of calling them directly, let the driver use
SET_NETDEV_DEVLINK_PORT macro to assign devlink_port pointer and let
devlink to track it. Note the devlink port pointer is static during
the time netdevice is registered.
In devlink code, use per-namespace netdev notifier to track
the netdevices with devlink_port assigned and change the internal
devlink_port type and related type pointer accordingly.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add new helper unregister_netdevice_many_notify(), pass netlink message
header and portid, which could be used to notify userspace when flag
NLM_F_ECHO is set.
Make the unregister_netdevice_many() as a wrapper of new function
unregister_netdevice_many_notify().
Suggested-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch pass netlink message header and portid to rtnl_configure_link()
All the functions in this call chain need to add the parameters so we can
use them in the last call rtnl_notify(), and notify the userspace about
the new link info if NLM_F_ECHO flag is set.
- rtnl_configure_link()
- __dev_notify_flags()
- rtmsg_ifinfo()
- rtmsg_ifinfo_event()
- rtmsg_ifinfo_build_skb()
- rtmsg_ifinfo_send()
- rtnl_notify()
Also move __dev_notify_flags() declaration to net/core/dev.h, as Jakub
suggested.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Now that the 32bit UP oddity is gone and 32bit uses always a sequence
count, there is no need for the fetch_irq() variants anymore.
Convert to the regular interface.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
One of the worst offenders of "fake flexible arrays" is struct sockaddr,
as it is the classic example of why GCC and Clang have been traditionally
forced to treat all trailing arrays as fake flexible arrays: in the
distant misty past, sa_data became too small, and code started just
treating it as a flexible array, even though it was fixed-size. The
special case by the compiler is specifically that sizeof(sa->sa_data)
and FORTIFY_SOURCE (which uses __builtin_object_size(sa->sa_data, 1))
do not agree (14 and -1 respectively), which makes FORTIFY_SOURCE treat
it as a flexible array.
However, the coming -fstrict-flex-arrays compiler flag will remove
these special cases so that FORTIFY_SOURCE can gain coverage over all
the trailing arrays in the kernel that are _not_ supposed to be treated
as a flexible array. To deal with this change, convert sa_data to a true
flexible array. To keep the structure size the same, move sa_data into
a union with a newly introduced sa_data_min with the original size. The
result is that FORTIFY_SOURCE can continue to have no idea how large
sa_data may actually be, but anything using sizeof(sa->sa_data) must
switch to sizeof(sa->sa_data_min).
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Cc: David Ahern <dsahern@kernel.org>
Cc: Dylan Yudaken <dylany@fb.com>
Cc: Yajun Deng <yajun.deng@linux.dev>
Cc: Petr Machata <petrm@nvidia.com>
Cc: Hangbin Liu <liuhangbin@gmail.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: syzbot <syzkaller@googlegroups.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221018095503.never.671-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently qdisc ingress handling (sch_handle_ingress()) doesn't
set a return value and it is left to the old return value of
the caller (__netif_receive_skb_core()) which is RX drop, so if
the packet is consumed, caller will stop and return this value
as if the packet was dropped.
This causes a problem in the kernel tcp stack when having a
egress tc rule forwarding to a ingress tc rule.
The tcp stack sending packets on the device having the egress rule
will see the packets as not successfully transmitted (although they
actually were), will not advance it's internal state of sent data,
and packets returning on such tcp stream will be dropped by the tcp
stack with reason ack-of-unsent-data. See reproduction in [0] below.
Fix that by setting the return value to RX success if
the packet was handled successfully.
[0] Reproduction steps:
$ ip link add veth1 type veth peer name peer1
$ ip link add veth2 type veth peer name peer2
$ ifconfig peer1 5.5.5.6/24 up
$ ip netns add ns0
$ ip link set dev peer2 netns ns0
$ ip netns exec ns0 ifconfig peer2 5.5.5.5/24 up
$ ifconfig veth2 0 up
$ ifconfig veth1 0 up
#ingress forwarding veth1 <-> veth2
$ tc qdisc add dev veth2 ingress
$ tc qdisc add dev veth1 ingress
$ tc filter add dev veth2 ingress prio 1 proto all flower \
action mirred egress redirect dev veth1
$ tc filter add dev veth1 ingress prio 1 proto all flower \
action mirred egress redirect dev veth2
#steal packet from peer1 egress to veth2 ingress, bypassing the veth pipe
$ tc qdisc add dev peer1 clsact
$ tc filter add dev peer1 egress prio 20 proto ip flower \
action mirred ingress redirect dev veth1
#run iperf and see connection not running
$ iperf3 -s&
$ ip netns exec ns0 iperf3 -c 5.5.5.6 -i 1
#delete egress rule, and run again, now should work
$ tc filter del dev peer1 egress
$ ip netns exec ns0 iperf3 -c 5.5.5.6 -i 1
Fixes: f697c3e8b3 ("[NET]: Avoid unnecessary cloning for ingress filtering")
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 3226b158e6 ("net: avoid 32 x truesize under-estimation
for tiny skbs") we are observing 10-20% regressions in performance
tests with small packets. The perf trace points to high pressure on
the slab allocator.
This change tries to improve the allocation schema for small packets
using an idea originally suggested by Eric: a new per CPU page frag is
introduced and used in __napi_alloc_skb to cope with small allocation
requests.
To ensure that the above does not lead to excessive truesize
underestimation, the frag size for small allocation is inflated to 1K
and all the above is restricted to build with 4K page size.
Note that we need to update accordingly the run-time check introduced
with commit fd9ea57f4e ("net: add napi_get_frags_check() helper").
Alex suggested a smart page refcount schema to reduce the number
of atomic operations and deal properly with pfmemalloc pages.
Under small packet UDP flood, I measure a 15% peak tput increases.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Alexander H Duyck <alexanderduyck@fb.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/6b6f65957c59f86a353fc09a5127e83a32ab5999.1664350652.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
While reading netdev_unregister_timeout_secs, it can be changed
concurrently. Thus, we need to add READ_ONCE() to its reader.
Fixes: 5aa3afe107 ("net: make unregister netdev warning timeout configurable")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading netdev_budget_usecs, it can be changed concurrently.
Thus, we need to add READ_ONCE() to its reader.
Fixes: 7acf8a1e8a ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading netdev_budget, it can be changed concurrently.
Thus, we need to add READ_ONCE() to its reader.
Fixes: 51b0bdedb8 ("[NET]: Separate two usages of netdev_max_backlog.")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading netdev_tstamp_prequeue, it can be changed concurrently.
Thus, we need to add READ_ONCE() to its readers.
Fixes: 3b098e2d7c ("net: Consistent skb timestamping")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading netdev_max_backlog, it can be changed concurrently.
Thus, we need to add READ_ONCE() to its readers.
While at it, we remove the unnecessary spaces in the doc.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading weight_p, it can be changed concurrently. Thus, we need
to add READ_ONCE() to its reader.
Also, dev_[rt]x_weight can be read/written at the same time. So, we
need to use READ_ONCE() and WRITE_ONCE() for its access. Moreover, to
use the same weight_p while changing dev_[rt]x_weight, we add a mutex
in proc_do_dev_weight().
Fixes: 3d48b53fb2 ("net: dev_weight: TX/RX orthogonality")
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
DECnet is an obsolete network protocol that receives more attention
from kernel janitors than users. It belongs in computer protocol
history museum not in Linux kernel.
It has been "Orphaned" in kernel since 2010. The iproute2 support
for DECnet was dropped in 5.0 release. The documentation link on
Sourceforge says it is abandoned there as well.
Leave the UAPI alone to keep userspace programs compiling.
This means that there is still an empty neighbour table
for AF_DECNET.
The table of /proc/sys/net entries was updated to match
current directories and reformatted to be alphabetical.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Ahern <dsahern@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
bpf-next 2022-07-22
We've added 73 non-merge commits during the last 12 day(s) which contain
a total of 88 files changed, 3458 insertions(+), 860 deletions(-).
The main changes are:
1) Implement BPF trampoline for arm64 JIT, from Xu Kuohai.
2) Add ksyscall/kretsyscall section support to libbpf to simplify tracing kernel
syscalls through kprobe mechanism, from Andrii Nakryiko.
3) Allow for livepatch (KLP) and BPF trampolines to attach to the same kernel
function, from Song Liu & Jiri Olsa.
4) Add new kfunc infrastructure for netfilter's CT e.g. to insert and change
entries, from Kumar Kartikeya Dwivedi & Lorenzo Bianconi.
5) Add a ksym BPF iterator to allow for more flexible and efficient interactions
with kernel symbols, from Alan Maguire.
6) Bug fixes in libbpf e.g. for uprobe binary path resolution, from Dan Carpenter.
7) Fix BPF subprog function names in stack traces, from Alexei Starovoitov.
8) libbpf support for writing custom perf event readers, from Jon Doron.
9) Switch to use SPDX tag for BPF helper man page, from Alejandro Colomar.
10) Fix xsk send-only sockets when in busy poll mode, from Maciej Fijalkowski.
11) Reparent BPF maps and their charging on memcg offlining, from Roman Gushchin.
12) Multiple follow-up fixes around BPF lsm cgroup infra, from Stanislav Fomichev.
13) Use bootstrap version of bpftool where possible to speed up builds, from Pu Lehui.
14) Cleanup BPF verifier's check_func_arg() handling, from Joanne Koong.
15) Make non-prealloced BPF map allocations low priority to play better with
memcg limits, from Yafang Shao.
16) Fix BPF test runner to reject zero-length data for skbs, from Zhengchao Shao.
17) Various smaller cleanups and improvements all over the place.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (73 commits)
bpf: Simplify bpf_prog_pack_[size|mask]
bpf: Support bpf_trampoline on functions with IPMODIFY (e.g. livepatch)
bpf, x64: Allow to use caller address from stack
ftrace: Allow IPMODIFY and DIRECT ops on the same function
ftrace: Add modify_ftrace_direct_multi_nolock
bpf/selftests: Fix couldn't retrieve pinned program in xdp veth test
bpf: Fix build error in case of !CONFIG_DEBUG_INFO_BTF
selftests/bpf: Fix test_verifier failed test in unprivileged mode
selftests/bpf: Add negative tests for new nf_conntrack kfuncs
selftests/bpf: Add tests for new nf_conntrack kfuncs
selftests/bpf: Add verifier tests for trusted kfunc args
net: netfilter: Add kfuncs to set and change CT status
net: netfilter: Add kfuncs to set and change CT timeout
net: netfilter: Add kfuncs to allocate and insert CT
net: netfilter: Deduplicate code in bpf_{xdp,skb}_ct_lookup
bpf: Add documentation for kfuncs
bpf: Add support for forcing kfunc args to be trusted
bpf: Switch to new kfunc flags infrastructure
tools/resolve_btfids: Add support for 8-byte BTF sets
bpf: Introduce 8-byte BTF set
...
====================
Link: https://lore.kernel.org/r/20220722221218.29943-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The byte queue limits (BQL) mechanism is intended to move queuing from
the driver to the network stack in order to reduce latency caused by
excessive queuing in hardware. However, when transmitting or redirecting
a packet using generic XDP, the qdisc layer is bypassed and there are no
additional queues. Since netif_xmit_stopped() also takes BQL limits into
account, but without having any alternative queuing, packets are
silently dropped.
This patch modifies the drop condition to only consider cases when the
driver itself cannot accept any more packets. This is analogous to the
condition in __dev_direct_xmit(). Dropped packets are also counted on
the device.
Bypassing the qdisc layer in the generic XDP TX path means that XDP
packets are able to starve other packets going through a qdisc, and
DDOS attacks will be more effective. In-driver-XDP use dedicated TX
queues, so they do not have this starvation issue.
Signed-off-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220705082345.2494312-1-johan.almbladh@anyfinetworks.com
This is a follow up of commit 3226b158e6
("net: avoid 32 x truesize under-estimation for tiny skbs")
When/if we increase MAX_SKB_FRAGS, we better make sure
the old bug will not come back.
Adding a check in napi_get_frags() would be costly,
even if using DEBUG_NET_WARN_ON_ONCE().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
One check in dev_loopback_xmit() has not caught issues
in the past.
Keep it for CONFIG_DEBUG_NET=y builds only.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As explained in commit 316580b69d ("u64_stats: provide u64_stats_t type")
we should use u64_stats_t and related accessors to avoid load/store tearing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Netdev reference helpers have a dev_ prefix for historic
reasons. Renaming the old helpers would be too much churn
but we can rename the tracking ones which are relatively
recent and should be the default for new code.
Rename:
dev_hold_track() -> netdev_hold()
dev_put_track() -> netdev_put()
dev_replace_track() -> netdev_ref_replace()
Link: https://lore.kernel.org/r/20220608043955.919359-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Core
----
- Support TCPv6 segmentation offload with super-segments larger than
64k bytes using the IPv6 Jumbogram extension header (AKA BIG TCP).
- Generalize skb freeing deferral to per-cpu lists, instead of
per-socket lists.
- Add a netdev statistic for packets dropped due to L2 address
mismatch (rx_otherhost_dropped).
- Continue work annotating skb drop reasons.
- Accept alternative netdev names (ALT_IFNAME) in more netlink
requests.
- Add VLAN support for AF_PACKET SOCK_RAW GSO.
- Allow receiving skb mark from the socket as a cmsg.
- Enable memcg accounting for veth queues, sysctl tables and IPv6.
BPF
---
- Add libbpf support for User Statically-Defined Tracing (USDTs).
- Speed up symbol resolution for kprobes multi-link attachments.
- Support storing typed pointers to referenced and unreferenced
objects in BPF maps.
- Add support for BPF link iterator.
- Introduce access to remote CPU map elements in BPF per-cpu map.
- Allow middle-of-the-road settings for the
kernel.unprivileged_bpf_disabled sysctl.
- Implement basic types of dynamic pointers e.g. to allow for
dynamically sized ringbuf reservations without extra memory copies.
Protocols
---------
- Retire port only listening_hash table, add a second bind table
hashed by port and address. Avoid linear list walk when binding
to very popular ports (e.g. 443).
- Add bridge FDB bulk flush filtering support allowing user space
to remove all FDB entries matching a condition.
- Introduce accept_unsolicited_na sysctl for IPv6 to implement
router-side changes for RFC9131.
- Support for MPTCP path manager in user space.
- Add MPTCP support for fallback to regular TCP for connections
that have never connected additional subflows or transmitted
out-of-sequence data (partial support for RFC8684 fallback).
- Avoid races in MPTCP-level window tracking, stabilize and improve
throughput.
- Support lockless operation of GRE tunnels with seq numbers enabled.
- WiFi support for host based BSS color collision detection.
- Add support for SO_TXTIME/SCM_TXTIME on CAN sockets.
- Support transmission w/o flow control in CAN ISOTP (ISO 15765-2).
- Support zero-copy Tx with TLS 1.2 crypto offload (sendfile).
- Allow matching on the number of VLAN tags via tc-flower.
- Add tracepoint for tcp_set_ca_state().
Driver API
----------
- Improve error reporting from classifier and action offload.
- Add support for listing line cards in switches (devlink).
- Add helpers for reporting page pool statistics with ethtool -S.
- Add support for reading clock cycles when using PTP virtual clocks,
instead of having the driver convert to time before reporting.
This makes it possible to report time from different vclocks.
- Support configuring low-latency Tx descriptor push via ethtool.
- Separate Clause 22 and Clause 45 MDIO accesses more explicitly.
New hardware / drivers
----------------------
- Ethernet:
- Marvell's Octeon NIC PCI Endpoint support (octeon_ep)
- Sunplus SP7021 SoC (sp7021_emac)
- Add support for Renesas RZ/V2M (in ravb)
- Add support for MediaTek mt7986 switches (in mtk_eth_soc)
- Ethernet PHYs:
- ADIN1100 industrial PHYs (w/ 10BASE-T1L and SQI reporting)
- TI DP83TD510 PHY
- Microchip LAN8742/LAN88xx PHYs
- WiFi:
- Driver for pureLiFi X, XL, XC devices (plfxlc)
- Driver for Silicon Labs devices (wfx)
- Support for WCN6750 (in ath11k)
- Support Realtek 8852ce devices (in rtw89)
- Mobile:
- MediaTek T700 modems (Intel 5G 5000 M.2 cards)
- CAN:
- ctucanfd: add support for CTU CAN FD open-source IP core
from Czech Technical University in Prague
Drivers
-------
- Delete a number of old drivers still using virt_to_bus().
- Ethernet NICs:
- intel: support TSO on tunnels MPLS
- broadcom: support multi-buffer XDP
- nfp: support VF rate limiting
- sfc: use hardware tx timestamps for more than PTP
- mlx5: multi-port eswitch support
- hyper-v: add support for XDP_REDIRECT
- atlantic: XDP support (including multi-buffer)
- macb: improve real-time perf by deferring Tx processing to NAPI
- High-speed Ethernet switches:
- mlxsw: implement basic line card information querying
- prestera: add support for traffic policing on ingress and egress
- Embedded Ethernet switches:
- lan966x: add support for packet DMA (FDMA)
- lan966x: add support for PTP programmable pins
- ti: cpsw_new: enable bc/mc storm prevention
- Qualcomm 802.11ax WiFi (ath11k):
- Wake-on-WLAN support for QCA6390 and WCN6855
- device recovery (firmware restart) support
- support setting Specific Absorption Rate (SAR) for WCN6855
- read country code from SMBIOS for WCN6855/QCA6390
- enable keep-alive during WoWLAN suspend
- implement remain-on-channel support
- MediaTek WiFi (mt76):
- support Wireless Ethernet Dispatch offloading packet movement
between the Ethernet switch and WiFi interfaces
- non-standard VHT MCS10-11 support
- mt7921 AP mode support
- mt7921 IPv6 NS offload support
- Ethernet PHYs:
- micrel: ksz9031/ksz9131: cabletest support
- lan87xx: SQI support for T1 PHYs
- lan937x: add interrupt support for link detection
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=Wjii
-----END PGP SIGNATURE-----
Merge tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core
----
- Support TCPv6 segmentation offload with super-segments larger than
64k bytes using the IPv6 Jumbogram extension header (AKA BIG TCP).
- Generalize skb freeing deferral to per-cpu lists, instead of
per-socket lists.
- Add a netdev statistic for packets dropped due to L2 address
mismatch (rx_otherhost_dropped).
- Continue work annotating skb drop reasons.
- Accept alternative netdev names (ALT_IFNAME) in more netlink
requests.
- Add VLAN support for AF_PACKET SOCK_RAW GSO.
- Allow receiving skb mark from the socket as a cmsg.
- Enable memcg accounting for veth queues, sysctl tables and IPv6.
BPF
---
- Add libbpf support for User Statically-Defined Tracing (USDTs).
- Speed up symbol resolution for kprobes multi-link attachments.
- Support storing typed pointers to referenced and unreferenced
objects in BPF maps.
- Add support for BPF link iterator.
- Introduce access to remote CPU map elements in BPF per-cpu map.
- Allow middle-of-the-road settings for the
kernel.unprivileged_bpf_disabled sysctl.
- Implement basic types of dynamic pointers e.g. to allow for
dynamically sized ringbuf reservations without extra memory copies.
Protocols
---------
- Retire port only listening_hash table, add a second bind table
hashed by port and address. Avoid linear list walk when binding to
very popular ports (e.g. 443).
- Add bridge FDB bulk flush filtering support allowing user space to
remove all FDB entries matching a condition.
- Introduce accept_unsolicited_na sysctl for IPv6 to implement
router-side changes for RFC9131.
- Support for MPTCP path manager in user space.
- Add MPTCP support for fallback to regular TCP for connections that
have never connected additional subflows or transmitted
out-of-sequence data (partial support for RFC8684 fallback).
- Avoid races in MPTCP-level window tracking, stabilize and improve
throughput.
- Support lockless operation of GRE tunnels with seq numbers enabled.
- WiFi support for host based BSS color collision detection.
- Add support for SO_TXTIME/SCM_TXTIME on CAN sockets.
- Support transmission w/o flow control in CAN ISOTP (ISO 15765-2).
- Support zero-copy Tx with TLS 1.2 crypto offload (sendfile).
- Allow matching on the number of VLAN tags via tc-flower.
- Add tracepoint for tcp_set_ca_state().
Driver API
----------
- Improve error reporting from classifier and action offload.
- Add support for listing line cards in switches (devlink).
- Add helpers for reporting page pool statistics with ethtool -S.
- Add support for reading clock cycles when using PTP virtual clocks,
instead of having the driver convert to time before reporting. This
makes it possible to report time from different vclocks.
- Support configuring low-latency Tx descriptor push via ethtool.
- Separate Clause 22 and Clause 45 MDIO accesses more explicitly.
New hardware / drivers
----------------------
- Ethernet:
- Marvell's Octeon NIC PCI Endpoint support (octeon_ep)
- Sunplus SP7021 SoC (sp7021_emac)
- Add support for Renesas RZ/V2M (in ravb)
- Add support for MediaTek mt7986 switches (in mtk_eth_soc)
- Ethernet PHYs:
- ADIN1100 industrial PHYs (w/ 10BASE-T1L and SQI reporting)
- TI DP83TD510 PHY
- Microchip LAN8742/LAN88xx PHYs
- WiFi:
- Driver for pureLiFi X, XL, XC devices (plfxlc)
- Driver for Silicon Labs devices (wfx)
- Support for WCN6750 (in ath11k)
- Support Realtek 8852ce devices (in rtw89)
- Mobile:
- MediaTek T700 modems (Intel 5G 5000 M.2 cards)
- CAN:
- ctucanfd: add support for CTU CAN FD open-source IP core from
Czech Technical University in Prague
Drivers
-------
- Delete a number of old drivers still using virt_to_bus().
- Ethernet NICs:
- intel: support TSO on tunnels MPLS
- broadcom: support multi-buffer XDP
- nfp: support VF rate limiting
- sfc: use hardware tx timestamps for more than PTP
- mlx5: multi-port eswitch support
- hyper-v: add support for XDP_REDIRECT
- atlantic: XDP support (including multi-buffer)
- macb: improve real-time perf by deferring Tx processing to NAPI
- High-speed Ethernet switches:
- mlxsw: implement basic line card information querying
- prestera: add support for traffic policing on ingress and egress
- Embedded Ethernet switches:
- lan966x: add support for packet DMA (FDMA)
- lan966x: add support for PTP programmable pins
- ti: cpsw_new: enable bc/mc storm prevention
- Qualcomm 802.11ax WiFi (ath11k):
- Wake-on-WLAN support for QCA6390 and WCN6855
- device recovery (firmware restart) support
- support setting Specific Absorption Rate (SAR) for WCN6855
- read country code from SMBIOS for WCN6855/QCA6390
- enable keep-alive during WoWLAN suspend
- implement remain-on-channel support
- MediaTek WiFi (mt76):
- support Wireless Ethernet Dispatch offloading packet movement
between the Ethernet switch and WiFi interfaces
- non-standard VHT MCS10-11 support
- mt7921 AP mode support
- mt7921 IPv6 NS offload support
- Ethernet PHYs:
- micrel: ksz9031/ksz9131: cabletest support
- lan87xx: SQI support for T1 PHYs
- lan937x: add interrupt support for link detection"
* tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1809 commits)
ptp: ocp: Add firmware header checks
ptp: ocp: fix PPS source selector debugfs reporting
ptp: ocp: add .init function for sma_op vector
ptp: ocp: vectorize the sma accessor functions
ptp: ocp: constify selectors
ptp: ocp: parameterize input/output sma selectors
ptp: ocp: revise firmware display
ptp: ocp: add Celestica timecard PCI ids
ptp: ocp: Remove #ifdefs around PCI IDs
ptp: ocp: 32-bit fixups for pci start address
Revert "net/smc: fix listen processing for SMC-Rv2"
ath6kl: Use cc-disable-warning to disable -Wdangling-pointer
selftests/bpf: Dynptr tests
bpf: Add dynptr data slices
bpf: Add bpf_dynptr_read and bpf_dynptr_write
bpf: Dynptr support for ring buffers
bpf: Add bpf_dynptr_from_mem for local dynptrs
bpf: Add verifier support for dynptrs
bpf: Suppress 'passing zero to PTR_ERR' warning
bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack
...
-----BEGIN PGP SIGNATURE-----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=SUr3
-----END PGP SIGNATURE-----
Merge tag 'random-5.19-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random
Pull random number generator updates from Jason Donenfeld:
"These updates continue to refine the work began in 5.17 and 5.18 of
modernizing the RNG's crypto and streamlining and documenting its
code.
New for 5.19, the updates aim to improve entropy collection methods
and make some initial decisions regarding the "premature next" problem
and our threat model. The cloc utility now reports that random.c is
931 lines of code and 466 lines of comments, not that basic metrics
like that mean all that much, but at the very least it tells you that
this is very much a manageable driver now.
Here's a summary of the various updates:
- The random_get_entropy() function now always returns something at
least minimally useful. This is the primary entropy source in most
collectors, which in the best case expands to something like RDTSC,
but prior to this change, in the worst case it would just return 0,
contributing nothing. For 5.19, additional architectures are wired
up, and architectures that are entirely missing a cycle counter now
have a generic fallback path, which uses the highest resolution
clock available from the timekeeping subsystem.
Some of those clocks can actually be quite good, despite the CPU
not having a cycle counter of its own, and going off-core for a
stamp is generally thought to increase jitter, something positive
from the perspective of entropy gathering. Done very early on in
the development cycle, this has been sitting in next getting some
testing for a while now and has relevant acks from the archs, so it
should be pretty well tested and fine, but is nonetheless the thing
I'll be keeping my eye on most closely.
- Of particular note with the random_get_entropy() improvements is
MIPS, which, on CPUs that lack the c0 count register, will now
combine the high-speed but short-cycle c0 random register with the
lower-speed but long-cycle generic fallback path.
- With random_get_entropy() now always returning something useful,
the interrupt handler now collects entropy in a consistent
construction.
- Rather than comparing two samples of random_get_entropy() for the
jitter dance, the algorithm now tests many samples, and uses the
amount of differing ones to determine whether or not jitter entropy
is usable and how laborious it must be. The problem with comparing
only two samples was that if the cycle counter was extremely slow,
but just so happened to be on the cusp of a change, the slowness
wouldn't be detected. Taking many samples fixes that to some
degree.
This, combined with the other improvements to random_get_entropy(),
should make future unification of /dev/random and /dev/urandom
maybe more possible. At the very least, were we to attempt it again
today (we're not), it wouldn't break any of Guenter's test rigs
that broke when we tried it with 5.18. So, not today, but perhaps
down the road, that's something we can revisit.
- We attempt to reseed the RNG immediately upon waking up from system
suspend or hibernation, making use of the various timestamps about
suspend time and such available, as well as the usual inputs such
as RDRAND when available.
- Batched randomness now falls back to ordinary randomness before the
RNG is initialized. This provides more consistent guarantees to the
types of random numbers being returned by the various accessors.
- The "pre-init injection" code is now gone for good. I suspect you
in particular will be happy to read that, as I recall you
expressing your distaste for it a few months ago. Instead, to avoid
a "premature first" issue, while still allowing for maximal amount
of entropy availability during system boot, the first 128 bits of
estimated entropy are used immediately as it arrives, with the next
128 bits being buffered. And, as before, after the RNG has been
fully initialized, it winds up reseeding anyway a few seconds later
in most cases. This resulted in a pretty big simplification of the
initialization code and let us remove various ad-hoc mechanisms
like the ugly crng_pre_init_inject().
- The RNG no longer pretends to handle the "premature next" security
model, something that various academics and other RNG designs have
tried to care about in the past. After an interesting mailing list
thread, these issues are thought to be a) mainly academic and not
practical at all, and b) actively harming the real security of the
RNG by delaying new entropy additions after a potential compromise,
making a potentially bad situation even worse. As well, in the
first place, our RNG never even properly handled the premature next
issue, so removing an incomplete solution to a fake problem was
particularly nice.
This allowed for numerous other simplifications in the code, which
is a lot cleaner as a consequence. If you didn't see it before,
https://lore.kernel.org/lkml/YmlMGx6+uigkGiZ0@zx2c4.com/ may be a
thread worth skimming through.
- While the interrupt handler received a separate code path years ago
that avoids locks by using per-cpu data structures and a faster
mixing algorithm, in order to reduce interrupt latency, input and
disk events that are triggered in hardirq handlers were still
hitting locks and more expensive algorithms. Those are now
redirected to use the faster per-cpu data structures.
- Rather than having the fake-crypto almost-siphash-based random32
implementation be used right and left, and in many places where
cryptographically secure randomness is desirable, the batched
entropy code is now fast enough to replace that.
- As usual, numerous code quality and documentation cleanups. For
example, the initialization state machine now uses enum symbolic
constants instead of just hard coding numbers everywhere.
- Since the RNG initializes once, and then is always initialized
thereafter, a pretty heavy amount of code used during that
initialization is never used again. It is now completely cordoned
off using static branches and it winds up in the .text.unlikely
section so that it doesn't reduce cache compactness after the RNG
is ready.
- A variety of functions meant for waiting on the RNG to be
initialized were only used by vsprintf, and in not a particularly
optimal way. Replacing that usage with a more ordinary setup made
it possible to remove those functions.
- A cleanup of how we warn userspace about the use of uninitialized
/dev/urandom and uninitialized get_random_bytes() usage.
Interestingly, with the change you merged for 5.18 that attempts to
use jitter (but does not block if it can't), the majority of users
should never see those warnings for /dev/urandom at all now, and
the one for in-kernel usage is mainly a debug thing.
- The file_operations struct for /dev/[u]random now implements
.read_iter and .write_iter instead of .read and .write, allowing it
to also implement .splice_read and .splice_write, which makes
splice(2) work again after it was broken here (and in many other
places in the tree) during the set_fs() removal. This was a bit of
a last minute arrival from Jens that hasn't had as much time to
bake, so I'll be keeping my eye on this as well, but it seems
fairly ordinary. Unfortunately, read_iter() is around 3% slower
than read() in my tests, which I'm not thrilled about. But Jens and
Al, spurred by this observation, seem to be making progress in
removing the bottlenecks on the iter paths in the VFS layer in
general, which should remove the performance gap for all drivers.
- Assorted other bug fixes, cleanups, and optimizations.
- A small SipHash cleanup"
* tag 'random-5.19-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random: (49 commits)
random: check for signals after page of pool writes
random: wire up fops->splice_{read,write}_iter()
random: convert to using fops->write_iter()
random: convert to using fops->read_iter()
random: unify batched entropy implementations
random: move randomize_page() into mm where it belongs
random: remove mostly unused async readiness notifier
random: remove get_random_bytes_arch() and add rng_has_arch_random()
random: move initialization functions out of hot pages
random: make consistent use of buf and len
random: use proper return types on get_random_{int,long}_wait()
random: remove extern from functions in header
random: use static branch for crng_ready()
random: credit architectural init the exact amount
random: handle latent entropy and command line from random_init()
random: use proper jiffies comparison macro
random: remove ratelimiting for in-kernel unseeded randomness
random: move initialization out of reseeding hot path
random: avoid initializing twice in credit race
random: use symbolic constants for crng_init states
...
random32.c has two random number generators in it: one that is meant to
be used deterministically, with some predefined seed, and one that does
the same exact thing as random.c, except does it poorly. The first one
has some use cases. The second one no longer does and can be replaced
with calls to random.c's proper random number generator.
The relatively recent siphash-based bad random32.c code was added in
response to concerns that the prior random32.c was too deterministic.
Out of fears that random.c was (at the time) too slow, this code was
anonymously contributed. Then out of that emerged a kind of shadow
entropy gathering system, with its own tentacles throughout various net
code, added willy nilly.
Stop👏making👏bespoke👏random👏number👏generators👏.
Fortunately, recent advances in random.c mean that we can stop playing
with this sketchiness, and just use get_random_u32(), which is now fast
enough. In micro benchmarks using RDPMC, I'm seeing the same median
cycle count between the two functions, with the mean being _slightly_
higher due to batches refilling (which we can optimize further need be).
However, when doing *real* benchmarks of the net functions that actually
use these random numbers, the mean cycles actually *decreased* slightly
(with the median still staying the same), likely because the additional
prandom code means icache misses and complexity, whereas random.c is
generally already being used by something else nearby.
The biggest benefit of this is that there are many users of prandom who
probably should be using cryptographically secure random numbers. This
makes all of those accidental cases become secure by just flipping a
switch. Later on, we can do a tree-wide cleanup to remove the static
inline wrapper functions that this commit adds.
There are also some low-ish hanging fruits for making this even faster
in the future: a get_random_u16() function for use in the networking
stack will give a 2x performance boost there, using SIMD for ChaCha20
will let us compute 4 or 8 or 16 blocks of output in parallel, instead
of just one, giving us large buffers for cheap, and introducing a
get_random_*_bh() function that assumes irqs are already disabled will
shave off a few cycles for ordinary calls. These are things we can chip
away at down the road.
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
When calling dev_fill_forward_path on a pppoe device, the provided destination
address is invalid. In order for the bridge fdb lookup to succeed, the pppoe
code needs to update ctx->daddr to the correct value.
Fix this by storing the address inside struct net_device_path_ctx
Fixes: f6efc675c9 ("net: ppp: resolve forwarding path for bridge pppoe devices")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
skb_defer_free_flush() can consume cpu cycles,
it seems better to call it in the inner loop:
- Potentially frees page/skb that will be reallocated while hot.
- Account for the cpu cycles in the @time_limit determination.
- Keep softnet_data.defer_count small to reduce chances for
skb_attempt_defer_free() to send an IPI.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit 68822bdf76 ("net: generalize skb freeing
deferral to per-cpu lists") added another per-cpu
cache of skbs. It was expected to be small,
and an IPI was forced whenever the list reached 128
skbs.
We might need to be able to control more precisely
queue capacity and added latency.
An IPI is generated whenever queue reaches half capacity.
Default value of the new limit is 64.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_defer_free_flush() runs from softirq context,
we have the opportunity to refill the napi_alloc_cache,
and/or use kmem_cache_free_bulk() when this cache is full.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A cpu can observe sd->defer_count reaching 128,
and call smp_call_function_single_async()
Problem is that the remote CPU can clear sd->defer_count
before the IPI is run/acknowledged.
Other cpus can queue more packets and also decide
to call smp_call_function_single_async() while the pending
IPI was not yet delivered.
This is a common issue with smp_call_function_single_async().
Callers must ensure correct synchronization and serialization.
I triggered this issue while experimenting smaller threshold.
Performing the call to smp_call_function_single_async()
under sd->defer_lock protection did not solve the problem.
Commit 5a18ceca63 ("smp: Allow smp_call_function_single_async()
to insert locked csd") replaced an informative WARN_ON_ONCE()
with a return of -EBUSY, which is often ignored.
Test of CSD_FLAG_LOCK presence is racy anyway.
Fixes: 68822bdf76 ("net: generalize skb freeing deferral to per-cpu lists")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow the gro_max_size to exceed a value larger than 65536.
There weren't really any external limitations that prevented this other
than the fact that IPv4 only supports a 16 bit length field. Since we have
the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to
exceed this value and for IPv4 and non-TCP flows we can cap things at 65536
via a constant rather than relying on gro_max_size.
[edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The code for gso_max_size was added originally to allow for debugging and
workaround of buggy devices that couldn't support TSO with blocks 64K in
size. The original reason for limiting it to 64K was because that was the
existing limits of IPv4 and non-jumbogram IPv6 length fields.
With the addition of Big TCP we can remove this limit and allow the value
to potentially go up to UINT_MAX and instead be limited by the tso_max_size
value.
So in order to support this we need to go through and clean up the
remaining users of the gso_max_size value so that the values will cap at
64K for non-TCPv6 flows. In addition we can clean up the GSO_MAX_SIZE value
so that 64K becomes GSO_LEGACY_MAX_SIZE and UINT_MAX will now be the upper
limit for GSO_MAX_SIZE.
v6: (edumazet) fixed a compile error if CONFIG_IPV6=n,
in a new sk_trim_gso_size() helper.
netif_set_tso_max_size() caps the requested TSO size
with GSO_MAX_SIZE.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a followup of previous patch.
Dumping the stack trace is a good start, but printing
basic skb information is probably better.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I have a syzbot report that managed to get a crash in skb_checksum_help()
If syzbot can trigger these BUG(), it makes sense to replace
them with more friendly WARN_ON_ONCE() since skb_checksum_help()
can instead return an error code.
Note that syzbot will still crash there, until real bug is fixed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers should call the TSO setting helper, GSO is controllable
by user space.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Up until commit 46e6b992c2 ("rtnetlink: allow GSO maximums to
be set on device creation") the gso_max_segs and gso_max_size
of a device were not controlled from user space.
The quoted commit added the ability to control them because of
the following setup:
netns A | netns B
veth<->veth eth0
If eth0 has TSO limitations and user wants to efficiently forward
traffic between eth0 and the veths they should copy the TSO
limitations of eth0 onto the veths. This would happen automatically
for macvlans or ipvlan but veth users are not so lucky (given the
loose coupling).
Unfortunately the commit in question allowed users to also override
the limits on real HW devices.
It may be useful to control the max GSO size and someone may be using
that ability (not that I know of any user), so create a separate set
of knobs to reliably record the TSO limitations. Validate the user
requests.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
To make later patches smaller create a helper for inheriting
the TSO limitations of a lower device. The TSO in the name
is not an accident, subsequent patches will replace GSO
with TSO in more names.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most drivers should not have to worry about selecting the right
weight for their NAPI instances and pass NAPI_POLL_WEIGHT.
It'd be best if we didn't require the argument at all and selected
the default internally.
This change prepares the ground for such reshuffling, allowing
for a smooth transition. The following API should remain after
the next release cycle:
netif_napi_add()
netif_napi_add_weight()
netif_napi_add_tx()
netif_napi_add_tx_weight()
Where the _weight() variants take an explicit weight argument.
I opted for a _weight() suffix rather than a __ prefix, because
we use __ in places to mean that caller needs to also issue a
synchronize_net() call.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20220502232703.396351-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Inline dev_queue_xmit() and dev_queue_xmit_accel(), they both are small
proxy functions doing nothing but redirecting the control flow to
__dev_queue_xmit().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I missed a stray return; in net_rx_action(), which very well
is taken whenever trigger_rx_softirq() has been called on
a cpu that is no longer receiving network packets,
or receiving too few of them.
Fixes: 68822bdf76 ("net: generalize skb freeing deferral to per-cpu lists")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://lore.kernel.org/r/20220427204147.1310161-1-eric.dumazet@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The macro dev_core_stats_##FIELD##_inc() disables preemption and invokes
netdev_core_stats_alloc() to return a per-CPU pointer.
netdev_core_stats_alloc() will allocate memory on its first invocation
which breaks on PREEMPT_RT because it requires non-atomic context for
memory allocation.
This can be avoided by enabling preemption in netdev_core_stats_alloc()
assuming the caller always disables preemption.
It might be better to replace local_inc() with this_cpu_inc() now that
dev_core_stats_##FIELD##_inc() gained a preempt-disable section and does
not rely on already disabled preemption. This results in less
instructions on x86-64:
local_inc:
| incl %gs:__preempt_count(%rip) # __preempt_count
| movq 488(%rdi), %rax # _1->core_stats, _22
| testq %rax, %rax # _22
| je .L585 #,
| add %gs:this_cpu_off(%rip), %rax # this_cpu_off, tcp_ptr__
| .L586:
| testq %rax, %rax # _27
| je .L587 #,
| incq (%rax) # _6->a.counter
| .L587:
| decl %gs:__preempt_count(%rip) # __preempt_count
this_cpu_inc(), this patch:
| movq 488(%rdi), %rax # _1->core_stats, _5
| testq %rax, %rax # _5
| je .L591 #,
| .L585:
| incq %gs:(%rax) # _18->rx_dropped
Use unsigned long as type for the counter. Use this_cpu_inc() to
increment the counter. Use a plain read of the counter.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/YmbO0pxgtKpCw4SY@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Logic added in commit f35f821935 ("tcp: defer skb freeing after socket
lock is released") helped bulk TCP flows to move the cost of skbs
frees outside of critical section where socket lock was held.
But for RPC traffic, or hosts with RFS enabled, the solution is far from
being ideal.
For RPC traffic, recvmsg() has to return to user space right after
skb payload has been consumed, meaning that BH handler has no chance
to pick the skb before recvmsg() thread. This issue is more visible
with BIG TCP, as more RPC fit one skb.
For RFS, even if BH handler picks the skbs, they are still picked
from the cpu on which user thread is running.
Ideally, it is better to free the skbs (and associated page frags)
on the cpu that originally allocated them.
This patch removes the per socket anchor (sk->defer_list) and
instead uses a per-cpu list, which will hold more skbs per round.
This new per-cpu list is drained at the end of net_action_rx(),
after incoming packets have been processed, to lower latencies.
In normal conditions, skbs are added to the per-cpu list with
no further action. In the (unlikely) cases where the cpu does not
run net_action_rx() handler fast enough, we use an IPI to raise
NET_RX_SOFTIRQ on the remote cpu.
Also, we do not bother draining the per-cpu list from dev_cpu_dead()
This is because skbs in this list have no requirement on how fast
they should be freed.
Note that we can add in the future a small per-cpu cache
if we see any contention on sd->defer_lock.
Tested on a pair of hosts with 100Gbit NIC, RFS enabled,
and /proc/sys/net/ipv4/tcp_rmem[2] tuned to 16MB to work around
page recycling strategy used by NIC driver (its page pool capacity
being too small compared to number of skbs/pages held in sockets
receive queues)
Note that this tuning was only done to demonstrate worse
conditions for skb freeing for this particular test.
These conditions can happen in more general production workload.
10 runs of one TCP_STREAM flow
Before:
Average throughput: 49685 Mbit.
Kernel profiles on cpu running user thread recvmsg() show high cost for
skb freeing related functions (*)
57.81% [kernel] [k] copy_user_enhanced_fast_string
(*) 12.87% [kernel] [k] skb_release_data
(*) 4.25% [kernel] [k] __free_one_page
(*) 3.57% [kernel] [k] __list_del_entry_valid
1.85% [kernel] [k] __netif_receive_skb_core
1.60% [kernel] [k] __skb_datagram_iter
(*) 1.59% [kernel] [k] free_unref_page_commit
(*) 1.16% [kernel] [k] __slab_free
1.16% [kernel] [k] _copy_to_iter
(*) 1.01% [kernel] [k] kfree
(*) 0.88% [kernel] [k] free_unref_page
0.57% [kernel] [k] ip6_rcv_core
0.55% [kernel] [k] ip6t_do_table
0.54% [kernel] [k] flush_smp_call_function_queue
(*) 0.54% [kernel] [k] free_pcppages_bulk
0.51% [kernel] [k] llist_reverse_order
0.38% [kernel] [k] process_backlog
(*) 0.38% [kernel] [k] free_pcp_prepare
0.37% [kernel] [k] tcp_recvmsg_locked
(*) 0.37% [kernel] [k] __list_add_valid
0.34% [kernel] [k] sock_rfree
0.34% [kernel] [k] _raw_spin_lock_irq
(*) 0.33% [kernel] [k] __page_cache_release
0.33% [kernel] [k] tcp_v6_rcv
(*) 0.33% [kernel] [k] __put_page
(*) 0.29% [kernel] [k] __mod_zone_page_state
0.27% [kernel] [k] _raw_spin_lock
After patch:
Average throughput: 73076 Mbit.
Kernel profiles on cpu running user thread recvmsg() looks better:
81.35% [kernel] [k] copy_user_enhanced_fast_string
1.95% [kernel] [k] _copy_to_iter
1.95% [kernel] [k] __skb_datagram_iter
1.27% [kernel] [k] __netif_receive_skb_core
1.03% [kernel] [k] ip6t_do_table
0.60% [kernel] [k] sock_rfree
0.50% [kernel] [k] tcp_v6_rcv
0.47% [kernel] [k] ip6_rcv_core
0.45% [kernel] [k] read_tsc
0.44% [kernel] [k] _raw_spin_lock_irqsave
0.37% [kernel] [k] _raw_spin_lock
0.37% [kernel] [k] native_irq_return_iret
0.33% [kernel] [k] __inet6_lookup_established
0.31% [kernel] [k] ip6_protocol_deliver_rcu
0.29% [kernel] [k] tcp_rcv_established
0.29% [kernel] [k] llist_reverse_order
v2: kdoc issue (kernel bots)
do not defer if (alloc_cpu == smp_processor_id()) (Paolo)
replace the sk_buff_head with a single-linked list (Jakub)
add a READ_ONCE()/WRITE_ONCE() for the lockless read of sd->defer_list
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20220422201237.416238-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch fixes issue:
* If we install tc filters with act_skbedit in clsact hook.
It doesn't work, because netdev_core_pick_tx() overwrites
queue_mapping.
$ tc filter ... action skbedit queue_mapping 1
And this patch is useful:
* We can use FQ + EDT to implement efficient policies. Tx queues
are picked by xps, ndo_select_queue of netdev driver, or skb hash
in netdev_core_pick_tx(). In fact, the netdev driver, and skb
hash are _not_ under control. xps uses the CPUs map to select Tx
queues, but we can't figure out which task_struct of pod/containter
running on this cpu in most case. We can use clsact filters to classify
one pod/container traffic to one Tx queue. Why ?
In containter networking environment, there are two kinds of pod/
containter/net-namespace. One kind (e.g. P1, P2), the high throughput
is key in these applications. But avoid running out of network resource,
the outbound traffic of these pods is limited, using or sharing one
dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods
(e.g. Pn), the low latency of data access is key. And the traffic is not
limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc.
This choice provides two benefits. First, contention on the HTB/FQ Qdisc
lock is significantly reduced since fewer CPUs contend for the same queue.
More importantly, Qdisc contention can be eliminated completely if each
CPU has its own FIFO Qdisc for the second kind of pods.
There must be a mechanism in place to support classifying traffic based on
pods/container to different Tx queues. Note that clsact is outside of Qdisc
while Qdisc can run a classifier to select a sub-queue under the lock.
In general recording the decision in the skb seems a little heavy handed.
This patch introduces a per-CPU variable, suggested by Eric.
The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit().
- Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag
is set in qdisc->enqueue() though tx queue has been selected in
netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared
firstly in __dev_queue_xmit(), is useful:
- Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev
in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy:
For example, eth0, macvlan in pod, which root Qdisc install skbedit
queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of
eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping
because there is no filters in clsact or tx Qdisc of this netdev.
Same action taked in eth0, ixgbe in Host.
- Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue
in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it
in __dev_queue_xmit when processing next packets.
For performance reasons, use the static key. If user does not config the NET_EGRESS,
the patch will not be compiled.
+----+ +----+ +----+
| P1 | | P2 | | Pn |
+----+ +----+ +----+
| | |
+-----------+-----------+
|
| clsact/skbedit
| MQ
v
+-----------+-----------+
| q0 | q1 | qn
v v v
HTB/FQ HTB/FQ ... FIFO
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Talal Ahmad <talalahmad@google.com>
Cc: Kevin Hao <haokexin@gmail.com>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Antoine Tenart <atenart@kernel.org>
Cc: Wei Wang <weiwan@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
As David Ahern suggested, the reasons for skb drops should be more
general and not be code based.
Therefore, rename SKB_DROP_REASON_PTYPE_ABSENT to
SKB_DROP_REASON_UNHANDLED_PROTO, which is used for the cases of no
L3 protocol handler, no L4 protocol handler, version extensions, etc.
From previous discussion, now we have the aim to make these reasons
more abstract and users based, avoiding code based.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Increment rx_otherhost_dropped counter when packet dropped due to
mismatched dest MAC addr.
An example when this drop can occur is when manually crafting raw
packets that will be consumed by a user space application via a tap
device. For testing purposes local traffic was generated using trafgen
for the client and netcat to start a server
Tested: Created 2 netns, sent 1 packet using trafgen from 1 to the other
with "{eth(daddr=$INCORRECT_MAC...}", verified that iproute2 showed the
counter was incremented. (Also had to modify iproute2 to show the stat,
additional patch for that coming next.)
Signed-off-by: Jeffrey Ji <jeffreyji@google.com>
Reviewed-by: Brian Vazquez <brianvv@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20220406172600.1141083-1-jeffreyjilinux@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
There's a number of functions and static variables used
under net/core/ but not from the outside. We currently
dump most of them into netdevice.h. That bad for many
reasons:
- netdevice.h is very cluttered, hard to figure out
what the APIs are;
- netdevice.h is very long;
- we have to touch netdevice.h more which causes expensive
incremental builds.
Create a header under net/core/ and move some declarations.
The new header is also a bit of a catch-all but that's
fine, if we create more specific headers people will
likely over-think where their declaration fit best.
And end up putting them in netdevice.h, again.
More work should be done on splitting netdevice.h into more
targeted headers, but that'd be more time consuming so small
steps.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We have a bunch of functions which are only used under
net/core/ yet they get exported. Remove the exports.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This allows hardware flow offloading from Ethernet to WLAN on MT7622 SoC
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
In [1], Will raised a potential issue that the cfg80211 code,
which does (from a locking perspective)
rtnl_lock()
wiphy_lock()
rtnl_unlock()
might be suspectible to ABBA deadlocks, because rtnl_unlock()
calls netdev_run_todo(), which might end up calling rtnl_lock()
again, which could then deadlock (see the comment in the code
added here for the scenario).
Some back and forth and thinking ensued, but clearly this can't
happen if the net_todo_list is empty at the rtnl_unlock() here.
Clearly, the code here cannot actually put an entry on it, and
all other users of rtnl_unlock() will empty it since that will
always go through netdev_run_todo(), emptying the list.
So the only other way to get there would be to add to the list
and then unlock the RTNL without going through rtnl_unlock(),
which is only possible through __rtnl_unlock(). However, this
isn't exported and not used in many places, and none of them
seem to be able to unregister before using it.
Therefore, add a WARN_ON() in the code to ensure this invariant
won't be broken, so that the cfg80211 (or any similar) code
stays safe.
[1] https://lore.kernel.org/r/Yjzpo3TfZxtKPMAG@google.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20220404113847.0ee02e4a70da.Ic73d206e217db20fd22dcec14fe5442ca732804b@changeid
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The lockdep annotation lockdep_assert_softirq_will_run() expects that
either hard or soft interrupts are disabled because both guaranty that
the "raised" soft-interrupts will be processed once the context is left.
This triggers in flush_smp_call_function_from_idle() but it this case it
explicitly calls do_softirq() in case of pending softirqs.
Revert the "softirq will run" annotation in ____napi_schedule() and move
the check back to __netif_rx() as it was. Keep the IRQ-off assert in
____napi_schedule() because this is always required.
Fixes: fbd9a2ceba ("net: Add lockdep asserts to ____napi_schedule().")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Jason A. Donenfeld <Jason@zx2c4.com>
Link: https://lore.kernel.org/r/YjhD3ZKWysyw8rc6@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Network drivers can call to netif_get_num_default_rss_queues to get the
default number of receive queues to use. Right now, this default number
is min(8, num_online_cpus()).
Instead, as suggested by Jakub, use the number of physical cores divided
by 2 as a way to avoid wasting CPU resources and to avoid using both CPU
threads, but still allowing to scale for high-end processors with many
cores.
As an exception, select 2 queues for processors with 2 cores, because
otherwise it won't take any advantage of RSS despite being SMP capable.
Tested: Processor Intel Xeon E5-2620 (2 sockets, 6 cores/socket, 2
threads/core). NIC Broadcom NetXtreme II BCM57810 (10GBps). Ran some
tests with `perf stat iperf3 -R`, with parallelisms of 1, 8 and 24,
getting the following results:
- Number of queues: 6 (instead of 8)
- Network throughput: not affected
- CPU usage: utilized 0.05-0.12 CPUs more than before (having 24 CPUs
this is only 0.2-0.5% higher)
- Reduced the number of context switches by 7-50%, being more noticeable
when using a higher number of parallel threads.
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Íñigo Huguet <ihuguet@redhat.com>
Link: https://lore.kernel.org/r/20220315091832.13873-1-ihuguet@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
____napi_schedule() needs to be invoked with disabled interrupts due to
__raise_softirq_irqoff (in order not to corrupt the per-CPU list).
____napi_schedule() needs also to be invoked from an interrupt context
so that the raised-softirq is processed while the interrupt context is
left.
Add lockdep asserts for both conditions.
While this is the second time the irq/softirq check is needed, provide a
generic lockdep_assert_softirq_will_run() which is used by both caller.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before adding yet another possibly contended atomic_long_t,
it is time to add per-cpu storage for existing ones:
dev->tx_dropped, dev->rx_dropped, and dev->rx_nohandler
Because many devices do not have to increment such counters,
allocate the per-cpu storage on demand, so that dev_get_stats()
does not have to spend considerable time folding zero counters.
Note that some drivers have abused these counters which
were supposed to be only used by core networking stack.
v4: should use per_cpu_ptr() in dev_get_stats() (Jakub)
v3: added a READ_ONCE() in netdev_core_stats_alloc() (Paolo)
v2: add a missing include (reported by kernel test robot <lkp@intel.com>)
Change in netdev_core_stats_alloc() (Jakub)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: jeffreyji <jeffreyji@google.com>
Reviewed-by: Brian Vazquez <brianvv@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20220311051420.2608812-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdev_name_node_alt_create() and netdev_name_node_alt_destroy()
are only called by rtnetlink, so no need for exports.
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20220310223952.558779-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add reason for skb drops to __netif_receive_skb_core() when packet_type
not found to handle the skb. For this purpose, the drop reason
SKB_DROP_REASON_PTYPE_ABSENT is introduced. Take ether packets for
example, this case mainly happens when L3 protocol is not supported.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace kfree_skb() used in sch_handle_ingress() with
kfree_skb_reason(). Following drop reasons are introduced:
SKB_DROP_REASON_TC_INGRESS
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace kfree_skb() used in do_xdp_generic() with kfree_skb_reason().
The drop reason SKB_DROP_REASON_XDP is introduced for this case.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace kfree_skb() used in enqueue_to_backlog() with
kfree_skb_reason(). The skb rop reason SKB_DROP_REASON_CPU_BACKLOG is
introduced for the case of failing to enqueue the skb to the per CPU
backlog queue. The further reason can be backlog queue full or RPS
flow limition, and I think we needn't to make further distinctions.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add reasons for skb drops to __dev_xmit_skb() by replacing
kfree_skb_list() with kfree_skb_list_reason(). The drop reason of
SKB_DROP_REASON_QDISC_DROP is introduced for qdisc enqueue fails.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace kfree_skb() used in sch_handle_egress() with kfree_skb_reason().
The drop reason SKB_DROP_REASON_TC_EGRESS is introduced. Considering
the code path of tc egerss, we make it distinct with the drop reason
of SKB_DROP_REASON_QDISC_DROP in the next commit.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since commit
baebdf48c3 ("net: dev: Makes sure netif_rx() can be invoked in any context.")
the function netif_rx() can be used in preemptible/thread context as
well as in interrupt context.
Use netif_rx().
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
The previous patches handled the delivery_time in the ingress path
before the routing decision is made. This patch can postpone clearing
delivery_time in a skb until knowing it is delivered locally and also
set the (rcv) timestamp if needed. This patch moves the
skb_clear_delivery_time() from dev.c to ip_local_deliver_finish()
and ip6_input_finish().
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The previous patches handled the delivery_time before sch_handle_ingress().
This patch can now set the skb->mono_delivery_time to flag the skb->tstamp
is used as the mono delivery_time (EDT) instead of the (rcv) timestamp
and also clear it with skb_clear_delivery_time() after
sch_handle_ingress(). This will make the bpf_redirect_*()
to keep the mono delivery_time and used by a qdisc (fq) of
the egress-ing interface.
A latter patch will postpone the skb_clear_delivery_time() until the
stack learns that the skb is being delivered locally and that will
make other kernel forwarding paths (ip[6]_forward) able to keep
the delivery_time also. Thus, like the previous patches on using
the skb->mono_delivery_time bit, calling skb_clear_delivery_time()
is not limited within the CONFIG_NET_INGRESS to avoid too many code
churns among this set.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In __skb_tstamp_tx(), it may clone the egress skb and queues the clone to
the sk_error_queue. The outgoing skb may have the mono delivery_time
while the (rcv) timestamp is expected for the clone, so the
skb->mono_delivery_time bit needs to be cleared from the clone.
This patch adds the skb->mono_delivery_time clearing to the existing
__net_timestamp() and use it in __skb_tstamp_tx().
The __net_timestamp() fast path usage in dev.c is changed to directly
call ktime_get_real() since the mono_delivery_time bit is not set at
that point.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A latter patch will set the skb->mono_delivery_time to flag the skb->tstamp
is used as the mono delivery_time (EDT) instead of the (rcv) timestamp.
skb_clear_tstamp() will then keep this delivery_time during forwarding.
This patch is to make the network tapping (with af_packet) to handle
the delivery_time stored in skb->tstamp.
Regardless of tapping at the ingress or egress, the tapped skb is
received by the af_packet socket, so it is ingress to the af_packet
socket and it expects the (rcv) timestamp.
When tapping at egress, dev_queue_xmit_nit() is used. It has already
expected skb->tstamp may have delivery_time, so it does
skb_clone()+net_timestamp_set() to ensure the cloned skb has
the (rcv) timestamp before passing to the af_packet sk.
This patch only adds to clear the skb->mono_delivery_time
bit in net_timestamp_set().
When tapping at ingress, it currently expects the skb->tstamp is either 0
or the (rcv) timestamp. Meaning, the tapping at ingress path
has already expected the skb->tstamp could be 0 and it will get
the (rcv) timestamp by ktime_get_real() when needed.
There are two cases for tapping at ingress:
One case is af_packet queues the skb to its sk_receive_queue.
The skb is either not shared or new clone created. The newly
added skb_clear_delivery_time() is called to clear the
delivery_time (if any) and set the (rcv) timestamp if
needed before the skb is queued to the sk_receive_queue.
Another case, the ingress skb is directly copied to the rx_ring
and tpacket_get_timestamp() is used to get the (rcv) timestamp.
The newly added skb_tstamp() is used in tpacket_get_timestamp()
to check the skb->mono_delivery_time bit before returning skb->tstamp.
As mentioned earlier, the tapping@ingress has already expected
the skb may not have the (rcv) timestamp (because no sk has asked
for it) and has handled this case by directly calling ktime_get_real().
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
