linux-stable.git/drivers/net/netdevsim/netdevsim.h, branch linux-6.14.y Linux kernel stable tree netdevsim: call napi_schedule from a timer context 2025-05-29T09:13:14+00:00 Breno Leitao leitao@debian.org 2025-02-19T16:41:20+00:00 4ce005ddaac08e92e917dca7af901ba11ec8a5f8 [ Upstream commit bf3624cf1c3708284c53ed99a1c43f2e104dc2dd ] The netdevsim driver was experiencing NOHZ tick-stop errors during packet transmission due to pending softirq work when calling napi_schedule(). This issue was observed when running the netconsole selftest, which triggered the following error message: NOHZ tick-stop error: local softirq work is pending, handler #08!!! To fix this issue, introduce a timer that schedules napi_schedule() from a timer context instead of calling it directly from the TX path. Create an hrtimer for each queue and kick it from the TX path, which then schedules napi_schedule() from the timer context. Suggested-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Breno Leitao <leitao@debian.org> Link: https://patch.msgid.link/20250219-netdevsim-v3-1-811e2b8abc4c@debian.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit bf3624cf1c3708284c53ed99a1c43f2e104dc2dd ]

The netdevsim driver was experiencing NOHZ tick-stop errors during packet
transmission due to pending softirq work when calling napi_schedule().
This issue was observed when running the netconsole selftest, which
triggered the following error message:

  NOHZ tick-stop error: local softirq work is pending, handler #08!!!

To fix this issue, introduce a timer that schedules napi_schedule()
from a timer context instead of calling it directly from the TX path.

Create an hrtimer for each queue and kick it from the TX path,
which then schedules napi_schedule() from the timer context.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250219-netdevsim-v3-1-811e2b8abc4c@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
net: netdevsim: try to close UDP port harness races 2025-01-27T22:24:34+00:00 Jakub Kicinski kuba@kernel.org 2025-01-22T22:45:03+00:00 50bf398e1ceacb9a7f85bd3bdca065ebe5cb6159 syzbot discovered that we remove the debugfs files after we free the netdev. Try to clean up the relevant dir while the device is still around. Reported-by: syzbot+2e5de9e3ab986b71d2bf@syzkaller.appspotmail.com Fixes: 424be63ad831 ("netdevsim: add UDP tunnel port offload support") Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Link: https://patch.msgid.link/20250122224503.762705-1-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
syzbot discovered that we remove the debugfs files after we free
the netdev. Try to clean up the relevant dir while the device
is still around.

Reported-by: syzbot+2e5de9e3ab986b71d2bf@syzkaller.appspotmail.com
Fixes: 424be63ad831 ("netdevsim: add UDP tunnel port offload support")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250122224503.762705-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdevsim: add HDS feature 2025-01-15T22:42:12+00:00 Taehee Yoo ap420073@gmail.com 2025-01-14T14:28:51+00:00 f394d07b192b67a895dbed76253ce95dcbb5d17c HDS options(tcp-data-split, hds-thresh) have dependencies between other features like XDP. Basic dependencies are checked in the core API. netdevsim is very useful to check basic dependencies. The default tcp-data-split mode is UNKNOWN but netdevsim driver returns ENABLED when ethtool dumps tcp-data-split mode. The default value of HDS threshold is 0 and the maximum value is 1024. ethtool shows like this. ethtool -g eni1np1 Ring parameters for eni1np1: Pre-set maximums: ... HDS thresh: 1024 Current hardware settings: ... TCP data split: on HDS thresh: 0 ethtool -G eni1np1 tcp-data-split on hds-thresh 1024 ethtool -g eni1np1 Ring parameters for eni1np1: Pre-set maximums: ... HDS thresh: 1024 Current hardware settings: ... TCP data split: on HDS thresh: 1024 Signed-off-by: Taehee Yoo <ap420073@gmail.com> Link: https://patch.msgid.link/20250114142852.3364986-10-ap420073@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
HDS options(tcp-data-split, hds-thresh) have dependencies between other
features like XDP. Basic dependencies are checked in the core API.
netdevsim is very useful to check basic dependencies.

The default tcp-data-split mode is UNKNOWN but netdevsim driver
returns ENABLED when ethtool dumps tcp-data-split mode.
The default value of HDS threshold is 0 and the maximum value is 1024.

ethtool shows like this.

ethtool -g eni1np1
Ring parameters for eni1np1:
Pre-set maximums:
...
HDS thresh:             1024
Current hardware settings:
...
TCP data split:         on
HDS thresh:             0

ethtool -G eni1np1 tcp-data-split on hds-thresh 1024
ethtool -g eni1np1
Ring parameters for eni1np1:
Pre-set maximums:
...
HDS thresh:             1024
Current hardware settings:
...
TCP data split:         on
HDS thresh:             1024

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250114142852.3364986-10-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdevsim: add debugfs-triggered queue reset 2025-01-09T14:33:08+00:00 Jakub Kicinski kuba@kernel.org 2025-01-07T16:08:45+00:00 6917d207b469ee81e6dc7f8ccca29c234a16916d Support triggering queue reset via debugfs for an upcoming test. Reviewed-by: Willem de Bruijn <willemb@google.com> Acked-by: Stanislav Fomichev <sdf@fomichev.me> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Reviewed-by: Mina Almasry <almasrymina@google.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> 
Support triggering queue reset via debugfs for an upcoming test.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
netdevsim: add queue management API support 2025-01-09T14:33:08+00:00 Jakub Kicinski kuba@kernel.org 2025-01-07T16:08:44+00:00 5bc8e8dbef27b73bd7b6d1fd5108b4fd4c6d469f Add queue management API support. We need a way to reset queues to test NAPI reordering, the queue management API provides a handy scaffolding for that. Reviewed-by: Willem de Bruijn <willemb@google.com> Acked-by: Stanislav Fomichev <sdf@fomichev.me> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Reviewed-by: Mina Almasry <almasrymina@google.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> 
Add queue management API support. We need a way to reset queues
to test NAPI reordering, the queue management API provides a
handy scaffolding for that.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
netdevsim: allocate rqs individually 2025-01-09T14:33:08+00:00 Jakub Kicinski kuba@kernel.org 2025-01-07T16:08:42+00:00 915c82f842f955429e347a53ce005604ad421343 Make nsim->rqs an array of pointers and allocate them individually so that we can swap them out one by one. Reviewed-by: Willem de Bruijn <willemb@google.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Paolo Abeni <pabeni@redhat.com> 
Make nsim->rqs an array of pointers and allocate them individually
so that we can swap them out one by one.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
netdevsim: add NAPI support 2024-05-09T01:59:47+00:00 David Wei dw@davidwei.uk 2024-05-07T16:32:27+00:00 3762ec05a9fbda16aaaa2568df679ab8ad13f38d Add NAPI support to netdevim, similar to veth. * Add a nsim_rq rx queue structure to hold a NAPI instance and a skb queue. * During xmit, store the skb in the peer skb queue and schedule NAPI. * During napi_poll(), drain the skb queue and pass up the stack. * Add assoc between rxq and NAPI instance using netif_queue_set_napi(). Signed-off-by: David Wei <dw@davidwei.uk> Link: https://lore.kernel.org/r/20240507163228.2066817-2-dw@davidwei.uk Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Add NAPI support to netdevim, similar to veth.

* Add a nsim_rq rx queue structure to hold a NAPI instance and a skb
  queue.
* During xmit, store the skb in the peer skb queue and schedule NAPI.
* During napi_poll(), drain the skb queue and pass up the stack.
* Add assoc between rxq and NAPI instance using netif_queue_set_napi().

Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://lore.kernel.org/r/20240507163228.2066817-2-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: netdevsim: add some fake page pool use 2024-04-15T18:21:11+00:00 Jakub Kicinski kuba@kernel.org 2024-04-12T14:14:31+00:00 1580cbcbfe770b0a7fb76735c1a601483335c1c2 Add very basic page pool use so that we can exercise the netlink uAPI in a selftest. Page pool gets created on open, destroyed on close. But we control allocating of a single page thru debugfs. This page may survive past the page pool itself so that we can test orphaned page pools. Link: https://lore.kernel.org/r/20240412141436.828666-2-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Add very basic page pool use so that we can exercise
the netlink uAPI in a selftest.

Page pool gets created on open, destroyed on close.
But we control allocating of a single page thru debugfs.
This page may survive past the page pool itself so that
we can test orphaned page pools.

Link: https://lore.kernel.org/r/20240412141436.828666-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
netdevsim: forward skbs from one connected port to another 2024-03-01T10:43:10+00:00 David Wei dw@davidwei.uk 2024-02-28T23:22:50+00:00 9eb95228a74163e26d338913a5d61e571ea45307 Forward skbs sent from one netdevsim port to its connected netdevsim port using dev_forward_skb, in a spirit similar to veth. Add a tx_dropped variable to struct netdevsim, tracking the number of skbs that could not be forwarded using dev_forward_skb(). The xmit() function accessing the peer ptr is protected by an RCU read critical section. The rcu_read_lock() is functionally redundant as since v5.0 all softirqs are implicitly RCU read critical sections; but it is useful for human readers. If another CPU is concurrently in nsim_destroy(), then it will first set the peer ptr to NULL. This does not affect any existing readers that dereferenced a non-NULL peer. Then, in unregister_netdevice(), there is a synchronize_rcu() before the netdev is actually unregistered and freed. This ensures that any readers i.e. xmit() that got a non-NULL peer will complete before the netdev is freed. Any readers after the RCU_INIT_POINTER() but before synchronize_rcu() will dereference NULL, making it safe. The codepath to nsim_destroy() and nsim_create() takes both the newly added nsim_dev_list_lock and rtnl_lock. This makes it safe with concurrent calls to linking two netdevsims together. Signed-off-by: David Wei <dw@davidwei.uk> Reviewed-by: Maciek Machnikowski <maciek@machnikowski.net> Signed-off-by: David S. Miller <davem@davemloft.net> 
Forward skbs sent from one netdevsim port to its connected netdevsim
port using dev_forward_skb, in a spirit similar to veth.

Add a tx_dropped variable to struct netdevsim, tracking the number of
skbs that could not be forwarded using dev_forward_skb().

The xmit() function accessing the peer ptr is protected by an RCU read
critical section. The rcu_read_lock() is functionally redundant as since
v5.0 all softirqs are implicitly RCU read critical sections; but it is
useful for human readers.

If another CPU is concurrently in nsim_destroy(), then it will first set
the peer ptr to NULL. This does not affect any existing readers that
dereferenced a non-NULL peer. Then, in unregister_netdevice(), there is
a synchronize_rcu() before the netdev is actually unregistered and
freed. This ensures that any readers i.e. xmit() that got a non-NULL
peer will complete before the netdev is freed.

Any readers after the RCU_INIT_POINTER() but before synchronize_rcu()
will dereference NULL, making it safe.

The codepath to nsim_destroy() and nsim_create() takes both the newly
added nsim_dev_list_lock and rtnl_lock. This makes it safe with
concurrent calls to linking two netdevsims together.

Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Maciek Machnikowski <maciek@machnikowski.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
netdevsim: allow two netdevsim ports to be connected 2024-03-01T10:43:10+00:00 David Wei dw@davidwei.uk 2024-02-28T23:22:49+00:00 f532957d76de89b8ee2545cb6ad5265e1701d0ba Add two netdevsim bus attribute to sysfs: /sys/bus/netdevsim/link_device /sys/bus/netdevsim/unlink_device Writing "A M B N" to link_device will link netdevsim M in netnsid A with netdevsim N in netnsid B. Writing "A M" to unlink_device will unlink netdevsim M in netnsid A from its peer, if any. rtnl_lock is taken to ensure nothing changes during the linking. Signed-off-by: David Wei <dw@davidwei.uk> Reviewed-by: Maciek Machnikowski <maciek@machnikowski.net> Signed-off-by: David S. Miller <davem@davemloft.net> 
Add two netdevsim bus attribute to sysfs:
/sys/bus/netdevsim/link_device
/sys/bus/netdevsim/unlink_device

Writing "A M B N" to link_device will link netdevsim M in netnsid A with
netdevsim N in netnsid B.

Writing "A M" to unlink_device will unlink netdevsim M in netnsid A from
its peer, if any.

rtnl_lock is taken to ensure nothing changes during the linking.

Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Maciek Machnikowski <maciek@machnikowski.net>
Signed-off-by: David S. Miller <davem@davemloft.net>