Merge branch 'netkit-support-for-io_uring-zero-copy-and-af_xdp'

Daniel Borkmann says:

====================
netkit: Support for io_uring zero-copy and AF_XDP

Containers use virtual netdevs to route traffic from a physical netdev
in the host namespace. They do not have access to the physical netdev
in the host and thus can't use memory providers or AF_XDP that require
reconfiguring/restarting queues in the physical netdev.

This patchset adds the concept of queue leasing to virtual netdevs that
allow containers to use memory providers and AF_XDP at native speed.
Leased queues are bound to a real queue in a physical netdev and act
as a proxy.

Memory providers and AF_XDP operations take an ifindex and queue id,
so containers would pass in an ifindex for a virtual netdev and a queue
id of a leased queue, which then gets proxied to the underlying real
queue.

We have implemented support for this concept in netkit and tested the
latter against Nvidia ConnectX-6 (mlx5) as well as Broadcom BCM957504
(bnxt_en) 100G NICs. For more details see the individual patches.
====================

Link: https://patch.msgid.link/20260115082603.219152-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

7 files changed, 62 insertions, 7 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d99b0fbc1942..4d146c000e21 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3400,11 +3400,17 @@ static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
+
 static inline void unregister_netdevice(struct net_device *dev)
 {
 	unregister_netdevice_queue(dev, NULL);
 }
 
+static inline bool unregister_netdevice_queued(const struct net_device *dev)
+{
+	return !list_empty(&dev->unreg_list);
+}
+
 int netdev_refcnt_read(const struct net_device *dev);
 void free_netdev(struct net_device *dev);
 
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index b55d3b9cb9c2..81dc7cb2360c 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -130,6 +130,11 @@ void netdev_stat_queue_sum(struct net_device *netdev,
  * @ndo_queue_get_dma_dev: Get dma device for zero-copy operations to be used
  *			   for this queue. Return NULL on error.
  *
+ * @ndo_queue_create: Create a new RX queue which can be leased to another queue.
+ *		      Ops on this queue are redirected to the leased queue e.g.
+ *		      when opening a memory provider. Return the new queue id on
+ *		      success. Return negative error code on failure.
+ *
  * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while
  * the interface is closed. @ndo_queue_start and @ndo_queue_stop will only
  * be called for an interface which is open.
@@ -149,9 +154,12 @@ struct netdev_queue_mgmt_ops {
 						  int idx);
 	struct device *		(*ndo_queue_get_dma_dev)(struct net_device *dev,
 							 int idx);
+	int			(*ndo_queue_create)(struct net_device *dev);
 };
 
-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);
+bool netif_rxq_has_mp(struct net_device *dev, unsigned int rxq_idx);
+bool netif_rxq_is_leased(struct net_device *dev, unsigned int rxq_idx);
 
 /**
  * DOC: Lockless queue stopping / waking helpers.
@@ -340,5 +348,10 @@ 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, int idx,
+		       struct netlink_ext_ack *extack);
+#endif /* _LINUX_NET_QUEUES_H */
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index 8cdcd138b33f..508d11afaecb 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -28,6 +28,8 @@ struct netdev_rx_queue {
 #endif
 	struct napi_struct		*napi;
 	struct pp_memory_provider_params mp_params;
+	struct netdev_rx_queue		*lease;
+	netdevice_tracker		lease_tracker;
 } ____cacheline_aligned_in_smp;
 
 /*
@@ -57,5 +59,22 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
 }
 
 int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq);
+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);
+bool netif_rx_queue_lease_get_owner(struct net_device **dev, unsigned int *rxq);
 
-#endif
+enum netif_lease_dir {
+	NETIF_VIRT_TO_PHYS,
+	NETIF_PHYS_TO_VIRT,
+};
+
+struct netdev_rx_queue *
+__netif_get_rx_queue_lease(struct net_device **dev, unsigned int *rxq,
+			   enum netif_lease_dir dir);
+struct netdev_rx_queue *
+netif_get_rx_queue_lease_locked(struct net_device **dev, unsigned int *rxq);
+void netif_put_rx_queue_lease_locked(struct net_device *orig_dev,
+				     struct net_device *dev);
+#endif /* _LINUX_NETDEV_RX_QUEUE_H */
diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
index ada4f968960a..b6f811c3416b 100644
--- a/include/net/page_pool/memory_provider.h
+++ b/include/net/page_pool/memory_provider.h
@@ -23,12 +23,12 @@ bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr);
 void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov);
 void net_mp_niov_clear_page_pool(struct net_iov *niov);
 
-int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 		    struct pp_memory_provider_params *p);
 int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 		      const struct pp_memory_provider_params *p,
 		      struct netlink_ext_ack *extack);
-void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+void net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx,
 		      struct pp_memory_provider_params *old_p);
 void __net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx,
 			const struct pp_memory_provider_params *old_p);
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 242e34f771cc..c07cfb431eac 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -28,7 +28,7 @@ void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
 u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
 void xsk_tx_release(struct xsk_buff_pool *pool);
-struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+struct xsk_buff_pool *xsk_get_pool_from_qid(const struct net_device *dev,
 					    u16 queue_id);
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
 void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 3b491d96e52e..bbd565757298 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1296,6 +1296,11 @@ enum netkit_mode {
 	NETKIT_L3,
 };
 
+enum netkit_pairing {
+	NETKIT_DEVICE_PAIR,
+	NETKIT_DEVICE_SINGLE,
+};
+
 /* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
  * the BPF program if attached. This also means the latter can
  * consume the two fields if they were populated earlier.
@@ -1320,6 +1325,7 @@ enum {
 	IFLA_NETKIT_PEER_SCRUB,
 	IFLA_NETKIT_HEADROOM,
 	IFLA_NETKIT_TAILROOM,
+	IFLA_NETKIT_PAIRING,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index e0b579a1df4f..7df1056a35fd 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -160,6 +160,7 @@ enum {
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
 	NETDEV_A_QUEUE_XSK,
+	NETDEV_A_QUEUE_LEASE,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
@@ -203,6 +204,15 @@ enum {
 };
 
 enum {
+	NETDEV_A_LEASE_IFINDEX = 1,
+	NETDEV_A_LEASE_QUEUE,
+	NETDEV_A_LEASE_NETNS_ID,
+
+	__NETDEV_A_LEASE_MAX,
+	NETDEV_A_LEASE_MAX = (__NETDEV_A_LEASE_MAX - 1)
+};
+
+enum {
 	NETDEV_A_DMABUF_IFINDEX = 1,
 	NETDEV_A_DMABUF_QUEUES,
 	NETDEV_A_DMABUF_FD,
@@ -228,6 +238,7 @@ enum {
 	NETDEV_CMD_BIND_RX,
 	NETDEV_CMD_NAPI_SET,
 	NETDEV_CMD_BIND_TX,
+	NETDEV_CMD_QUEUE_CREATE,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)