Commit d04686d9 authored by Daniel Borkmann's avatar Daniel Borkmann Committed by Jakub Kicinski
Browse files

net: Implement netdev_nl_queue_create_doit 



Implement netdev_nl_queue_create_doit which creates a new rx queue in a
virtual netdev and then leases it to a rx queue in a physical netdev.

Example with ynl client:

  # ynl --family netdev --output-json --do queue-create \
        --json '{"ifindex": 8, "type": "rx", "lease": {"ifindex": 4, "queue": {"type": "rx", "id": 15}}}'
  {'id': 1}

Note that the netdevice locking order is always from the virtual to
the physical device.

Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Co-developed-by: default avatarDavid Wei <dw@davidwei.uk>
Signed-off-by: default avatarDavid Wei <dw@davidwei.uk>
Reviewed-by: default avatarNikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-3-daniel@iogearbox.net


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 7789c6bb

Documentation/networking/netdevices.rst

+6 −0
Original line number Diff line number Diff line
@@ -329,6 +329,12 @@ by setting ``request_ops_lock`` to true. Code comments and docs refer 
to drivers which have ops called under the instance lock as "ops locked".

See also the documentation of the ``lock`` member of struct net_device.



There is also a case of taking two per-netdev locks in sequence when netdev

queues are leased, that is, the netdev-scope lock is taken for both the

virtual and the physical device. To prevent deadlocks, the virtual device's

lock must always be acquired before the physical device's (see

``netdev_nl_queue_create_doit``).



In the future, there will be an option for individual

drivers to opt out of using ``rtnl_lock`` and instead perform their control

operations directly under the netdev instance lock.

include/linux/netdevice.h

+8 −1
Original line number Diff line number Diff line
@@ -2561,7 +2561,14 @@ struct net_device { 
	 * Also protects some fields in:

	 *	struct napi_struct, struct netdev_queue, struct netdev_rx_queue

	 *

	 * Ordering: take after rtnl_lock.

	 * Ordering:

	 *

	 * - take after rtnl_lock

	 *

	 * - for the case of netdev queue leasing, the netdev-scope lock is

	 *   taken for both the virtual and the physical device; to prevent

	 *   deadlocks, the virtual device's lock must always be acquired

	 *   before the physical device's (see netdev_nl_queue_create_doit)

	 */

	struct mutex		lock;

include/net/netdev_queues.h

+16 −3
Original line number Diff line number Diff line
@@ -150,6 +150,11 @@ enum { 
 *			When NIC-wide config is changed the callback will

 *			be invoked for all queues.

 *

 * @ndo_queue_create:	Create a new RX queue on a virtual device that will

 *			be paired with a physical device's queue via leasing.

 *			Return the new queue id on success, negative error

 *			on failure.

 *

 * @supported_params:	Bitmask of supported parameters, see QCFG_*.

 *

 * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while
@@ -178,6 +183,8 @@ struct netdev_queue_mgmt_ops { 
				     struct netlink_ext_ack *extack);

	struct device *	(*ndo_queue_get_dma_dev)(struct net_device *dev,

						 int idx);

	int	(*ndo_queue_create)(struct net_device *dev,

				    struct netlink_ext_ack *extack);



	unsigned int supported_params;

};
@@ -185,7 +192,7 @@ struct netdev_queue_mgmt_ops { 
void netdev_queue_config(struct net_device *dev, int rxq,

			 struct netdev_queue_config *qcfg);



bool netif_rxq_has_unreadable_mp(struct net_device *dev, int idx);

bool netif_rxq_has_unreadable_mp(struct net_device *dev, unsigned int rxq_idx);



/**

 * DOC: Lockless queue stopping / waking helpers.
@@ -374,5 +381,11 @@ static inline unsigned int netif_xmit_timeout_ms(struct netdev_queue *txq) 
	})



struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx);



#endif
 
bool netdev_can_create_queue(const struct net_device *dev,

			     struct netlink_ext_ack *extack);

bool netdev_can_lease_queue(const struct net_device *dev,

			    struct netlink_ext_ack *extack);

bool netdev_queue_busy(struct net_device *dev, unsigned int idx,

		       enum netdev_queue_type type,

		       struct netlink_ext_ack *extack);

#endif /* _LINUX_NET_QUEUES_H */

include/net/netdev_rx_queue.h

+13 −2
Original line number Diff line number Diff line
@@ -31,6 +31,14 @@ struct netdev_rx_queue { 
	struct napi_struct		*napi;

	struct netdev_queue_config	qcfg;

	struct pp_memory_provider_params mp_params;



	/* If a queue is leased, then the lease pointer is always

	 * valid. From the physical device it points to the virtual

	 * queue, and from the virtual device it points to the

	 * physical queue.

	 */

	struct netdev_rx_queue		*lease;

	netdevice_tracker		lease_tracker;

} ____cacheline_aligned_in_smp;



/*
@@ -60,5 +68,8 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) 
}



int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq);



#endif
 
void netdev_rx_queue_lease(struct netdev_rx_queue *rxq_dst,

			   struct netdev_rx_queue *rxq_src);

void netdev_rx_queue_unlease(struct netdev_rx_queue *rxq_dst,

			     struct netdev_rx_queue *rxq_src);

#endif /* _LINUX_NETDEV_RX_QUEUE_H */

net/core/dev.c

+8 −0
Original line number Diff line number Diff line
@@ -1121,6 +1121,14 @@ netdev_get_by_index_lock_ops_compat(struct net *net, int ifindex) 
	return __netdev_put_lock_ops_compat(dev, net);

}



struct net_device *

netdev_put_lock(struct net_device *dev, struct net *net,

		netdevice_tracker *tracker)

{

	netdev_tracker_free(dev, tracker);

	return __netdev_put_lock(dev, net);

}



struct net_device *

netdev_xa_find_lock(struct net *net, struct net_device *dev,

		    unsigned long *index)