From: David Wei Add a ynl netdev family operation called bind-queue that creates a new rx queue in a virtual netdev (i.e. netkit or veth) and binds it to an rx queue in a real netdev. This forms a queue pair, where the peer queue of the pair in the virtual netdev acts as a proxy for the peer queue in the real netdev. Thus, the peer queue in the virtual netdev can be used by processes running in a container to use both memory providers (io_uring zero-copy rx and devmem) and AF_XDP. An early implementation had only driver-specific integration [0], but in order for other virtual devices to reuse, it makes sense to have this as a generic API. src-ifindex and src-queue-id is the real netdev and its rx queue id respectively. dst-ifindex is the virtual netdev. Note that this op doesn't take dst-queue-id because a new rx queue is created. The virtual netdev must have real_num_rx_queues less than num_rx_queues at the time of calling bind-queue. The queue-type must be rx as only rx queues are supported for now. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0] --- Documentation/netlink/specs/netdev.yaml | 61 +++++++++++++++++++++++++ include/uapi/linux/netdev.h | 12 +++++ net/core/netdev-genl-gen.c | 25 ++++++++++ net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 5 ++ tools/include/uapi/linux/netdev.h | 12 +++++ 6 files changed, 116 insertions(+) diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index e00d3fa1c152..1e24c7f76de0 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -561,6 +561,46 @@ attribute-sets: type: u32 checks: min: 1 + - + name: queue-pair + attributes: + - + name: queue-type + doc: | + Queue type as rx, tx, for src-queue-id and dst-queue-id. + Currently only pairing queues of type rx is supported. + type: u32 + enum: queue-type + - + name: src-ifindex + doc: | + Specifies the netdev ifindex of the physical device to pair + src-queue-id from. + type: u32 + checks: + min: 1 + max: s32-max + - + name: src-queue-id + doc: | + Specifies the netdev queue id of the physical device with + src-ifindex to pair a queue from. + type: u32 + - + name: dst-ifindex + doc: | + Specifies the netdev ifindex of the virtual device to pair + a new queue with the src-queue-id from src-ifindex. + type: u32 + checks: + min: 1 + max: s32-max + - + name: dst-queue-id + doc: | + Specifies the new netdev queue id of the virtual device after + a successful pairing operation. + type: u32 operations: list: @@ -772,6 +812,27 @@ operations: attributes: - id + - + name: bind-queue + doc: | + Bind a physical netdevice queue to a virtual one. The binding + creates a queue pair, where a queue can reference its peer queue. + This is useful for memory providers and AF_XDP operations which + take an ifindex and queue id to allow auch applications to bind + against virtual devices in containers. + attribute-set: queue-pair + flags: [admin-perm] + do: + request: + attributes: + - queue-type + - src-ifindex + - src-queue-id + - dst-ifindex + reply: + attributes: + - dst-queue-id + kernel-family: headers: ["net/netdev_netlink.h"] sock-priv: struct netdev_nl_sock diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 48eb49aa03d4..4ef04d0bc412 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -210,6 +210,17 @@ enum { NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) }; +enum { + NETDEV_A_QUEUE_PAIR_QUEUE_TYPE = 1, + NETDEV_A_QUEUE_PAIR_SRC_IFINDEX, + NETDEV_A_QUEUE_PAIR_SRC_QUEUE_ID, + NETDEV_A_QUEUE_PAIR_DST_IFINDEX, + NETDEV_A_QUEUE_PAIR_DST_QUEUE_ID, + + __NETDEV_A_QUEUE_PAIR_MAX, + NETDEV_A_QUEUE_PAIR_MAX = (__NETDEV_A_QUEUE_PAIR_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -226,6 +237,7 @@ enum { NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, NETDEV_CMD_BIND_TX, + NETDEV_CMD_BIND_QUEUE, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index e9a2a6f26cb7..8a973bc5588a 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -26,6 +26,16 @@ static const struct netlink_range_validation netdev_a_napi_defer_hard_irqs_range .max = S32_MAX, }; +static const struct netlink_range_validation netdev_a_queue_pair_src_ifindex_range = { + .min = 1ULL, + .max = S32_MAX, +}; + +static const struct netlink_range_validation netdev_a_queue_pair_dst_ifindex_range = { + .min = 1ULL, + .max = S32_MAX, +}; + /* Common nested types */ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = { [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), @@ -106,6 +116,14 @@ static const struct nla_policy netdev_bind_tx_nl_policy[NETDEV_A_DMABUF_FD + 1] [NETDEV_A_DMABUF_FD] = { .type = NLA_U32, }, }; +/* NETDEV_CMD_BIND_QUEUE - do */ +static const struct nla_policy netdev_bind_queue_nl_policy[NETDEV_A_QUEUE_PAIR_DST_IFINDEX + 1] = { + [NETDEV_A_QUEUE_PAIR_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1), + [NETDEV_A_QUEUE_PAIR_SRC_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_queue_pair_src_ifindex_range), + [NETDEV_A_QUEUE_PAIR_SRC_QUEUE_ID] = { .type = NLA_U32, }, + [NETDEV_A_QUEUE_PAIR_DST_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_queue_pair_dst_ifindex_range), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -204,6 +222,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_DMABUF_FD, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = NETDEV_CMD_BIND_QUEUE, + .doit = netdev_nl_bind_queue_doit, + .policy = netdev_bind_queue_nl_policy, + .maxattr = NETDEV_A_QUEUE_PAIR_DST_IFINDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index cf3fad74511f..309248fe2b9e 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -35,6 +35,7 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_bind_queue_doit(struct sk_buff *skb, struct genl_info *info); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 470fabbeacd9..ce1018ea390f 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -1120,6 +1120,11 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info) return err; } +int netdev_nl_bind_queue_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv) { INIT_LIST_HEAD(&priv->bindings); diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 48eb49aa03d4..4ef04d0bc412 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -210,6 +210,17 @@ enum { NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) }; +enum { + NETDEV_A_QUEUE_PAIR_QUEUE_TYPE = 1, + NETDEV_A_QUEUE_PAIR_SRC_IFINDEX, + NETDEV_A_QUEUE_PAIR_SRC_QUEUE_ID, + NETDEV_A_QUEUE_PAIR_DST_IFINDEX, + NETDEV_A_QUEUE_PAIR_DST_QUEUE_ID, + + __NETDEV_A_QUEUE_PAIR_MAX, + NETDEV_A_QUEUE_PAIR_MAX = (__NETDEV_A_QUEUE_PAIR_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -226,6 +237,7 @@ enum { NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, NETDEV_CMD_BIND_TX, + NETDEV_CMD_BIND_QUEUE, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- 2.43.0 From: David Wei Implement netdev_nl_bind_queue_doit() that creates an rx queue in a virtual netdev and then binds it to an rxq in a real netdev to create a queue pair. Example with ynl client: # ./pyynl/cli.py \ --spec ~/netlink/specs/netdev.yaml \ --do bind-queue \ --json '{"src-ifindex": 4, "src-queue-id": 15, "dst-ifindex": 8, "queue-type": "rx"}' {'dst-queue-id': 1} Note that the netdevice locking order is always from the virtual to the physical device. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov --- include/net/netdev_queues.h | 7 ++ include/net/netdev_rx_queue.h | 38 ++++++++- net/core/dev.h | 7 ++ net/core/netdev-genl.c | 150 +++++++++++++++++++++++++++++++++- net/core/netdev_rx_queue.c | 63 ++++++++++++++ 5 files changed, 262 insertions(+), 3 deletions(-) diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index cd00e0406cf4..67e89710577f 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 bound to another queue. + * Ops on this queue are redirected to the peer queue e.g. + * when opening a memory provider. On success, the new queue + * id is stored into idx. + * * 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. @@ -149,6 +154,8 @@ 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, + int *idx); }; bool netif_rxq_has_unreadable_mp(struct net_device *dev, int idx); diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index 8cdcd138b33f..3a02d47e42bc 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 *peer; + netdevice_tracker peer_tracker; } ____cacheline_aligned_in_smp; /* @@ -56,6 +58,38 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) return index; } -int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq); +static inline void __netdev_rx_queue_peer(struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + WRITE_ONCE(src_rxq->peer, dst_rxq); + WRITE_ONCE(dst_rxq->peer, src_rxq); +} -#endif +static inline void __netdev_rx_queue_unpeer(struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + WRITE_ONCE(src_rxq->peer, NULL); + WRITE_ONCE(dst_rxq->peer, NULL); +} + +static inline bool netdev_rx_queue_peered(struct net_device *dev, + u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + return dev->_rx[queue_id].peer; + return false; +} + +void netdev_rx_queue_peer(struct net_device *src_dev, + struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq); +void netdev_rx_queue_unpeer(struct net_device *src_dev, + struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq); +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq); +struct netdev_rx_queue * +netif_get_rx_queue_peer_locked(struct net_device **dev, + unsigned int *rxq_idx); +void netif_put_rx_queue_peer_locked(struct net_device *orig_dev, + struct net_device *dev); +#endif /* _LINUX_NETDEV_RX_QUEUE_H */ diff --git a/net/core/dev.h b/net/core/dev.h index 900880e8b5b4..321529477b38 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -35,6 +35,13 @@ struct net_device * netdev_xa_find_lock(struct net *net, struct net_device *dev, unsigned long *index); +static inline struct net_device *netdev_put_lock(struct net_device *dev, + netdevice_tracker *tracker) +{ + netdev_tracker_free(dev, tracker); + return __netdev_put_lock(dev, dev_net(dev)); +} + DEFINE_FREE(netdev_unlock, struct net_device *, if (_T) netdev_unlock(_T)); #define for_each_netdev_lock_scoped(net, var_name, ifindex) \ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index ce1018ea390f..4fa7e881441f 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -1122,7 +1122,155 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info) int netdev_nl_bind_queue_doit(struct sk_buff *skb, struct genl_info *info) { - return -EOPNOTSUPP; + struct netdev_rx_queue *src_rxq, *dst_rxq, *tmp_rxq; + u32 src_ifidx, src_qid, dst_ifidx, dst_qid, q_type; + struct net_device *src_dev, *dst_dev; + netdevice_tracker dev_tracker; + struct sk_buff *rsp; + int err = 0; + void *hdr; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_PAIR_QUEUE_TYPE) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_PAIR_SRC_IFINDEX) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_PAIR_SRC_QUEUE_ID) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_PAIR_DST_IFINDEX)) + return -EINVAL; + + src_ifidx = nla_get_u32(info->attrs[NETDEV_A_QUEUE_PAIR_SRC_IFINDEX]); + src_qid = nla_get_u32(info->attrs[NETDEV_A_QUEUE_PAIR_SRC_QUEUE_ID]); + dst_ifidx = nla_get_u32(info->attrs[NETDEV_A_QUEUE_PAIR_DST_IFINDEX]); + q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_PAIR_QUEUE_TYPE]); + + if (q_type != NETDEV_QUEUE_TYPE_RX) { + NL_SET_ERR_MSG(info->extack, "Only binding of RX queue supported"); + return -EOPNOTSUPP; + } + if (dst_ifidx == src_ifidx) { + NL_SET_ERR_MSG(info->extack, + "Destination driver cannot be same as source driver"); + return -EOPNOTSUPP; + } + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_genlmsg_free; + } + + /* Locking order is always from the virtual to the physical device + * since this is also the same order when applications open the + * memory provider later on. + */ + dst_dev = netdev_get_by_index_lock(genl_info_net(info), dst_ifidx); + if (!dst_dev) { + err = -ENODEV; + goto err_genlmsg_free; + } + if (dst_dev->dev.parent) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Destination device is not a virtual device"); + goto err_unlock_dst_dev; + } + if (!dst_dev->queue_mgmt_ops || + !dst_dev->queue_mgmt_ops->ndo_queue_create) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Destination driver does not support queue management operations"); + goto err_unlock_dst_dev; + } + if (dst_dev->real_num_rx_queues < 1) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Destination device must have at least one real RX queue"); + goto err_unlock_dst_dev; + } + + src_dev = netdev_get_by_index(genl_info_net(info), src_ifidx, + &dev_tracker, GFP_KERNEL); + if (!src_dev) { + err = -ENODEV; + goto err_unlock_dst_dev; + } + if (!src_dev->dev.parent) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Source device is a virtual device"); + goto err_unlock_dst_dev_src_dev_put; + } + if (!netif_device_present(src_dev)) { + err = -ENODEV; + NL_SET_ERR_MSG(info->extack, + "Source device has been removed from the system"); + goto err_unlock_dst_dev_src_dev_put; + } + if (!src_dev->queue_mgmt_ops) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Source driver does not support queue management operations"); + goto err_unlock_dst_dev_src_dev_put; + } + + src_dev = netdev_put_lock(src_dev, &dev_tracker); + if (!src_dev) { + err = -ENODEV; + goto err_unlock_dst_dev; + } + if (src_qid >= src_dev->real_num_rx_queues) { + err = -ERANGE; + NL_SET_ERR_MSG(info->extack, + "Source device queue is out of range"); + goto err_unlock_src_dev; + } + + src_rxq = __netif_get_rx_queue(src_dev, src_qid); + if (src_rxq->peer) { + err = -EBUSY; + NL_SET_ERR_MSG(info->extack, + "Source device queue is already bound"); + goto err_unlock_src_dev; + } + + tmp_rxq = __netif_get_rx_queue(dst_dev, dst_dev->real_num_rx_queues - 1); + if (tmp_rxq->peer && tmp_rxq->peer->dev != src_dev) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Binding multiple queues from different source devices not supported"); + goto err_unlock_src_dev; + } + + err = dst_dev->queue_mgmt_ops->ndo_queue_create(dst_dev, &dst_qid); + if (err) { + NL_SET_ERR_MSG(info->extack, + "Destination device is unable to create a new queue"); + goto err_unlock_src_dev; + } + + dst_rxq = __netif_get_rx_queue(dst_dev, dst_qid); + netdev_rx_queue_peer(src_dev, src_rxq, dst_rxq); + + nla_put_u32(rsp, NETDEV_A_QUEUE_PAIR_DST_QUEUE_ID, dst_qid); + genlmsg_end(rsp, hdr); + + netdev_unlock(src_dev); + netdev_unlock(dst_dev); + + return genlmsg_reply(rsp, info); + +err_unlock_dst_dev_src_dev_put: + netdev_put(src_dev, &dev_tracker); + goto err_unlock_dst_dev; +err_unlock_src_dev: + netdev_unlock(src_dev); +err_unlock_dst_dev: + netdev_unlock(dst_dev); +err_genlmsg_free: + nlmsg_free(rsp); + return err; } void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv) diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index c7d9341b7630..6eb12f3b969c 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -18,6 +18,69 @@ bool netif_rxq_has_unreadable_mp(struct net_device *dev, int idx) } EXPORT_SYMBOL(netif_rxq_has_unreadable_mp); +void netdev_rx_queue_peer(struct net_device *src_dev, + struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + netdev_assert_locked(src_dev); + netdev_assert_locked(dst_rxq->dev); + + netdev_hold(src_dev, &src_rxq->peer_tracker, GFP_KERNEL); + __netdev_rx_queue_peer(src_rxq, dst_rxq); +} + +void netdev_rx_queue_unpeer(struct net_device *src_dev, + struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + WARN_ON_ONCE(READ_ONCE(dst_rxq->dev->reg_state) != NETREG_UNREGISTERING); + + netdev_assert_locked(dst_rxq->dev); + netdev_assert_locked(src_dev); + + __netdev_rx_queue_unpeer(src_rxq, dst_rxq); + netdev_put(src_dev, &src_rxq->peer_tracker); +} + +static struct netdev_rx_queue * +__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx) +{ + struct net_device *orig_dev = *dev; + struct netdev_rx_queue *rxq = __netif_get_rx_queue(orig_dev, *rxq_idx); + + if (rxq->peer) { + if (orig_dev->dev.parent) + return NULL; + rxq = rxq->peer; + *rxq_idx = get_netdev_rx_queue_index(rxq); + *dev = rxq->dev; + } + return rxq; +} + +struct netdev_rx_queue * +netif_get_rx_queue_peer_locked(struct net_device **dev, unsigned int *rxq_idx) +{ + struct net_device *orig_dev = *dev; + struct netdev_rx_queue *rxq; + + /* Locking order is always from the virtual to the physical device + * see netdev_nl_bind_queue_doit(). + */ + netdev_ops_assert_locked(orig_dev); + rxq = __netif_get_rx_queue_peer(dev, rxq_idx); + if (rxq && orig_dev != *dev) + netdev_lock(*dev); + return rxq; +} + +void netif_put_rx_queue_peer_locked(struct net_device *orig_dev, + struct net_device *dev) +{ + if (orig_dev != dev) + netdev_unlock(dev); +} + int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx) { struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, rxq_idx); -- 2.43.0 From: David Wei Add a nested peer field to the queue-get response that returns the peered ifindex, queue id and optionally netns id if the device resides in a different netns. Example with ynl client: # ip a [...] 4: enp10s0f0np0: mtu 1500 xdp/id:24 qdisc mq state UP group default qlen 1000 link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff inet 10.0.0.2/24 scope global enp10s0f0np0 valid_lft forever preferred_lft forever inet6 fe80::eaeb:d3ff:fea3:43f6/64 scope link proto kernel_ll valid_lft forever preferred_lft forever [...] # ethtool -i enp10s0f0np0 driver: mlx5_core [...] # ip netns exec foo ./pyynl/cli.py \ --spec ~/netlink/specs/netdev.yaml \ --do queue-get \ --json '{"ifindex": 4, "id": 15, "type": "rx"}' {'id': 15, 'ifindex': 4, 'napi-id': 8227, 'peer': {'id': 1, 'ifindex': 8, 'netns-id': 0}, 'type': 'rx', 'xsk': {}} # ip netns list foo (id: 0) # ip netns exec foo ip a [...] 8: nk@NONE: mtu 1500 qdisc noqueue state UP group default qlen 1000 link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff inet6 fe80::200:ff:fe00:0/64 scope link proto kernel_ll valid_lft forever preferred_lft forever [...] # ip netns exec foo ethtool -i nk driver: netkit [...] # ip netns exec foo ./pyynl/cli.py \ --spec ~/netlink/specs/netdev.yaml \ --do queue-get \ --json '{"ifindex": 8, "id": 1, "type": "rx"}' {'id': 1, 'ifindex': 8, 'type': 'rx'} Note that the caller of netdev_nl_queue_fill_one() holds the netdevice lock. For the queue-get we do not lock both devices. When queues get {un,}peered, both devices are locked, thus if __netif_get_rx_queue_peer() returns true, the peer pointer points to a valid device. The netns-id is fetched via peernet2id_alloc() similarly as done in OVS. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov --- Documentation/netlink/specs/netdev.yaml | 24 +++++++++++++++++ include/net/netdev_rx_queue.h | 9 +++++++ include/uapi/linux/netdev.h | 10 ++++++++ net/core/netdev-genl.c | 34 +++++++++++++++++++++++-- net/core/netdev_rx_queue.c | 19 +++++++++++--- tools/include/uapi/linux/netdev.h | 10 ++++++++ 6 files changed, 100 insertions(+), 6 deletions(-) diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 1e24c7f76de0..e1735b486222 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -297,6 +297,24 @@ attribute-sets: - name: xsk-info attributes: [] + - + name: peer-info + attributes: + - + name: id + doc: Queue index of the netdevice to which the peer queue belongs. + type: u32 + - + name: ifindex + doc: ifindex of the netdevice to which the peer queue belongs. + type: u32 + - + name: netns-id + doc: | + Network namespace of the netdevice to which the peer queue belongs. + This is populated if the netdevices are not in the same network + namespace. + type: s32 - name: queue attributes: @@ -338,6 +356,11 @@ attribute-sets: doc: XSK information for this queue, if any. type: nest nested-attributes: xsk-info + - + name: peer + doc: Whether this queue was bound to another peer queue. + type: nest + nested-attributes: peer-info - name: qstats doc: | @@ -723,6 +746,7 @@ operations: - dmabuf - io-uring - xsk + - peer dump: request: attributes: diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index 3a02d47e42bc..d2505d099400 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -92,4 +92,13 @@ netif_get_rx_queue_peer_locked(struct net_device **dev, unsigned int *rxq_idx); void netif_put_rx_queue_peer_locked(struct net_device *orig_dev, struct net_device *dev); + +enum netif_peer_dir { + NETIF_VIRT_TO_PHYS, + NETIF_PHYS_TO_VIRT, +}; + +struct netdev_rx_queue * +__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx, + enum netif_peer_dir dir); #endif /* _LINUX_NETDEV_RX_QUEUE_H */ diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 4ef04d0bc412..d4d5d9f86eee 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -150,6 +150,15 @@ enum { NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) }; +enum { + NETDEV_A_PEER_INFO_ID = 1, + NETDEV_A_PEER_INFO_IFINDEX, + NETDEV_A_PEER_INFO_NETNS_ID, + + __NETDEV_A_PEER_INFO_MAX, + NETDEV_A_PEER_INFO_MAX = (__NETDEV_A_PEER_INFO_MAX - 1) +}; + enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, @@ -158,6 +167,7 @@ enum { NETDEV_A_QUEUE_DMABUF, NETDEV_A_QUEUE_IO_URING, NETDEV_A_QUEUE_XSK, + NETDEV_A_QUEUE_PEER, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 4fa7e881441f..5cf7a9ca2e4b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -391,8 +391,11 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { struct pp_memory_provider_params *params; + struct net_device *orig_netdev = netdev; struct netdev_rx_queue *rxq; struct netdev_queue *txq; + u32 peer_q_idx = q_idx; + struct nlattr *nest; void *hdr; hdr = genlmsg_iput(rsp, info); @@ -410,6 +413,33 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, if (nla_put_napi_id(rsp, rxq->napi)) goto nla_put_failure; + if (__netif_get_rx_queue_peer(&netdev, &peer_q_idx, + NETIF_PHYS_TO_VIRT)) { + struct net *net, *peer_net; + + nest = nla_nest_start(rsp, NETDEV_A_QUEUE_PEER); + if (!nest) + goto nla_put_failure; + + if (nla_put_u32(rsp, NETDEV_A_PEER_INFO_ID, peer_q_idx) || + nla_put_u32(rsp, NETDEV_A_PEER_INFO_IFINDEX, + READ_ONCE(netdev->ifindex))) + goto nla_put_failure; + + rcu_read_lock(); + peer_net = dev_net_rcu(netdev); + net = dev_net_rcu(orig_netdev); + if (!net_eq(net, peer_net)) { + s32 id = peernet2id_alloc(net, peer_net, GFP_ATOMIC); + + if (nla_put_s32(rsp, NETDEV_A_PEER_INFO_NETNS_ID, id)) + goto nla_put_failure_unlock; + } + rcu_read_unlock(); + nla_nest_end(rsp, nest); + netdev = orig_netdev; + } + params = &rxq->mp_params; if (params->mp_ops && params->mp_ops->nl_fill(params->mp_priv, rsp, rxq)) @@ -419,7 +449,6 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK)) goto nla_put_failure; #endif - break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); @@ -434,9 +463,10 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, } genlmsg_end(rsp, hdr); - return 0; +nla_put_failure_unlock: + rcu_read_unlock(); nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index 6eb12f3b969c..889b7382cdb6 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -42,14 +42,25 @@ void netdev_rx_queue_unpeer(struct net_device *src_dev, netdev_put(src_dev, &src_rxq->peer_tracker); } -static struct netdev_rx_queue * -__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx) +static bool netif_peer_dir_ok(const struct net_device *dev, + enum netif_peer_dir dir) +{ + if (dir == NETIF_VIRT_TO_PHYS && !dev->dev.parent) + return true; + if (dir == NETIF_PHYS_TO_VIRT && dev->dev.parent) + return true; + return false; +} + +struct netdev_rx_queue * +__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx, + enum netif_peer_dir dir) { struct net_device *orig_dev = *dev; struct netdev_rx_queue *rxq = __netif_get_rx_queue(orig_dev, *rxq_idx); if (rxq->peer) { - if (orig_dev->dev.parent) + if (!netif_peer_dir_ok(orig_dev, dir)) return NULL; rxq = rxq->peer; *rxq_idx = get_netdev_rx_queue_index(rxq); @@ -68,7 +79,7 @@ netif_get_rx_queue_peer_locked(struct net_device **dev, unsigned int *rxq_idx) * see netdev_nl_bind_queue_doit(). */ netdev_ops_assert_locked(orig_dev); - rxq = __netif_get_rx_queue_peer(dev, rxq_idx); + rxq = __netif_get_rx_queue_peer(dev, rxq_idx, NETIF_VIRT_TO_PHYS); if (rxq && orig_dev != *dev) netdev_lock(*dev); return rxq; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 4ef04d0bc412..d4d5d9f86eee 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -150,6 +150,15 @@ enum { NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) }; +enum { + NETDEV_A_PEER_INFO_ID = 1, + NETDEV_A_PEER_INFO_IFINDEX, + NETDEV_A_PEER_INFO_NETNS_ID, + + __NETDEV_A_PEER_INFO_MAX, + NETDEV_A_PEER_INFO_MAX = (__NETDEV_A_PEER_INFO_MAX - 1) +}; + enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, @@ -158,6 +167,7 @@ enum { NETDEV_A_QUEUE_DMABUF, NETDEV_A_QUEUE_IO_URING, NETDEV_A_QUEUE_XSK, + NETDEV_A_QUEUE_PEER, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) -- 2.43.0 Similar to AF_XDP, do not allow queues in a physical netdev to be resized by ethtool -L when they are peered. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Nikolay Aleksandrov --- include/linux/ethtool.h | 1 + net/ethtool/channels.c | 12 ++++++------ net/ethtool/common.c | 10 +++++++++- net/ethtool/ioctl.c | 4 ++-- 4 files changed, 18 insertions(+), 9 deletions(-) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c2d8b4ec62eb..151fc920234d 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1481,4 +1481,5 @@ struct ethtool_forced_speed_map { void ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); +bool ethtool_channel_busy(struct net_device *dev, u32 channel); #endif /* _LINUX_ETHTOOL_H */ diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index ca4f80282448..b3de8064275c 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#include - #include "netlink.h" #include "common.h" @@ -169,14 +167,16 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) if (ret) return ret; - /* Disabling channels, query zero-copy AF_XDP sockets */ + /* ensure channels are not busy at the moment */ from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); - for (i = from_channel; i < old_total; i++) - if (xsk_get_pool_from_qid(dev, i)) { - GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); + for (i = from_channel; i < old_total; i++) { + if (ethtool_channel_busy(dev, i)) { + GENL_SET_ERR_MSG(info, + "requested channel counts are too low due to busy queues (AF_XDP or queue peering)"); return -EINVAL; } + } ret = dev->ethtool_ops->set_channels(dev, &channels); return ret < 0 ? ret : 1; diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 55223ebc2a7e..a67382c2208b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -6,13 +6,15 @@ #include #include #include + #include +#include +#include #include "netlink.h" #include "common.h" #include "../core/dev.h" - const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_SG_BIT] = "tx-scatter-gather", [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", @@ -1101,6 +1103,12 @@ EXPORT_SYMBOL(ethtool_get_ts_info_by_layer); const struct ethtool_phy_ops *ethtool_phy_ops; +bool ethtool_channel_busy(struct net_device *dev, u32 channel) +{ + return netdev_rx_queue_peered(dev, channel) || + xsk_get_pool_from_qid(dev, channel); +} + void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) { ASSERT_RTNL(); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index fa83ddade4f8..9ed87a18e48a 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2282,12 +2282,12 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, if (ret) return ret; - /* Disabling channels, query zero-copy AF_XDP sockets */ + /* Disabling channels, query busy queues (AF_XDP, queue peering) */ from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count); for (i = from_channel; i < to_channel; i++) - if (xsk_get_pool_from_qid(dev, i)) + if (ethtool_channel_busy(dev, i)) return -EINVAL; ret = dev->ethtool_ops->set_channels(dev, &channels); -- 2.43.0 From: David Wei When a process in a container wants to setup a memory provider, it will use the virtual netdev and a mapped rxq, and call net_mp_{open,close}_rxq to try and restart the queue. At this point, proxy the queue restart on the real rxq in the physical netdev. For memory providers (io_uring zero-copy rx and devmem), it causes the real rxq in the physical netdev to be filled from a memory provider that has DMA mapped memory from a process within a container. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov --- include/net/page_pool/memory_provider.h | 4 +- net/core/netdev_rx_queue.c | 55 +++++++++++++++++-------- 2 files changed, 39 insertions(+), 20 deletions(-) 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/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index 889b7382cdb6..0e43254b64cd 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -174,49 +174,63 @@ 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) { + struct net_device *orig_dev = dev; struct netdev_rx_queue *rxq; int ret; if (!netdev_need_ops_lock(dev)) return -EOPNOTSUPP; - if (rxq_idx >= dev->real_num_rx_queues) { NL_SET_ERR_MSG(extack, "rx queue index out of range"); return -ERANGE; } - rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues); + rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues); + rxq = netif_get_rx_queue_peer_locked(&dev, &rxq_idx); + if (!rxq) { + NL_SET_ERR_MSG(extack, "rx queue peered to a virtual netdev"); + return -EBUSY; + } + if (!dev->dev.parent) { + NL_SET_ERR_MSG(extack, "rx queue is mapped to a virtual netdev"); + ret = -EBUSY; + goto out; + } if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); - return -EINVAL; + ret = -EINVAL; + goto out; } if (dev->cfg->hds_thresh) { NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); - return -EINVAL; + ret = -EINVAL; + goto out; } if (dev_xdp_prog_count(dev)) { NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached"); - return -EEXIST; + ret = -EEXIST; + goto out; } - - rxq = __netif_get_rx_queue(dev, rxq_idx); if (rxq->mp_params.mp_ops) { NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); - return -EEXIST; + ret = -EEXIST; + goto out; } #ifdef CONFIG_XDP_SOCKETS if (rxq->pool) { NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); - return -EBUSY; + ret = -EBUSY; + goto out; } #endif - rxq->mp_params = *p; ret = netdev_rx_queue_restart(dev, rxq_idx); if (ret) { rxq->mp_params.mp_ops = NULL; rxq->mp_params.mp_priv = NULL; } +out: + netif_put_rx_queue_peer_locked(orig_dev, dev); return ret; } @@ -231,38 +245,43 @@ int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, return ret; } -void __net_mp_close_rxq(struct net_device *dev, unsigned int ifq_idx, +void __net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx, const struct pp_memory_provider_params *old_p) { + struct net_device *orig_dev = dev; struct netdev_rx_queue *rxq; int err; - if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues)) + if (WARN_ON_ONCE(rxq_idx >= dev->real_num_rx_queues)) return; - rxq = __netif_get_rx_queue(dev, ifq_idx); + rxq = netif_get_rx_queue_peer_locked(&dev, &rxq_idx); + if (WARN_ON_ONCE(!rxq)) + return; /* Callers holding a netdev ref may get here after we already * went thru shutdown via dev_memory_provider_uninstall(). */ if (dev->reg_state > NETREG_REGISTERED && !rxq->mp_params.mp_ops) - return; + goto out; if (WARN_ON_ONCE(rxq->mp_params.mp_ops != old_p->mp_ops || rxq->mp_params.mp_priv != old_p->mp_priv)) - return; + goto out; rxq->mp_params.mp_ops = NULL; rxq->mp_params.mp_priv = NULL; - err = netdev_rx_queue_restart(dev, ifq_idx); + err = netdev_rx_queue_restart(dev, rxq_idx); WARN_ON(err && err != -ENETDOWN); +out: + netif_put_rx_queue_peer_locked(orig_dev, dev); } -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) { netdev_lock(dev); - __net_mp_close_rxq(dev, ifq_idx, old_p); + __net_mp_close_rxq(dev, rxq_idx, old_p); netdev_unlock(dev); } -- 2.43.0 Move NETDEV_XDP_ACT_ZC into xdp_sock_drv.h header such that external code can reuse it, and rename it into more generic NETDEV_XDP_ACT_XSK. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Maciej Fijalkowski Reviewed-by: Nikolay Aleksandrov --- include/net/xdp_sock_drv.h | 4 ++++ net/xdp/xsk_buff_pool.c | 6 +----- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 4f2d3268a676..242e34f771cc 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -12,6 +12,10 @@ #define XDP_UMEM_MIN_CHUNK_SHIFT 11 #define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT) +#define NETDEV_XDP_ACT_XSK (NETDEV_XDP_ACT_BASIC | \ + NETDEV_XDP_ACT_REDIRECT | \ + NETDEV_XDP_ACT_XSK_ZEROCOPY) + struct xsk_cb_desc { void *src; u8 off; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index aa9788f20d0d..26165baf99f4 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -158,10 +158,6 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool) } } -#define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \ - NETDEV_XDP_ACT_REDIRECT | \ - NETDEV_XDP_ACT_XSK_ZEROCOPY) - int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { @@ -203,7 +199,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, /* For copy-mode, we are done. */ return 0; - if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) { + if ((netdev->xdp_features & NETDEV_XDP_ACT_XSK) != NETDEV_XDP_ACT_XSK) { err = -EOPNOTSUPP; goto err_unreg_pool; } -- 2.43.0 xsk_rcv_check tests for inbound packets to see whether they match the bound AF_XDP socket. Refactor the test into a small helper xsk_dev_queue_valid and move the validation against xs->dev and xs->queue_id there. The fast-path case stays in place and allows for quick return in xsk_dev_queue_valid. If it fails, the validation is extended to check whether the AF_XDP socket is bound against a peered queue, and if the case then the test is redone. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei --- net/xdp/xsk.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7b0c68a70888..6ae9ad5f27ad 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -331,14 +331,31 @@ static bool xsk_is_bound(struct xdp_sock *xs) return false; } +static bool xsk_dev_queue_valid(const struct xdp_sock *xs, + const struct xdp_rxq_info *info) +{ + struct net_device *dev = xs->dev; + u32 queue_index = xs->queue_id; + struct netdev_rx_queue *rxq; + + if (info->dev == dev && + info->queue_index == queue_index) + return true; + + rxq = READ_ONCE(__netif_get_rx_queue(dev, queue_index)->peer); + if (!rxq) + return false; + + return info->dev == rxq->dev && + info->queue_index == get_netdev_rx_queue_index(rxq); +} + static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { if (!xsk_is_bound(xs)) return -ENXIO; - - if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) + if (!xsk_dev_queue_valid(xs, xdp->rxq)) return -EINVAL; - if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) { xs->rx_dropped++; return -ENOSPC; -- 2.43.0 Similarly what we do for net_mp_{open,close}_rxq for mapped queues, proxy also the xsk_{reg,clear}_pool_at_qid via netif_get_rx_queue_peer_locked such that when a virtual netdev picked a mapped rxq, the request gets through to the real rxq in the physical netdev. The proxying is only relevant for queue_id < dev->real_num_rx_queues since right now its only supported for rxqs. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei --- net/xdp/xsk.c | 48 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 35 insertions(+), 13 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 6ae9ad5f27ad..872b243b7fcc 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -23,6 +23,8 @@ #include #include #include + +#include #include #include #include @@ -124,10 +126,18 @@ EXPORT_SYMBOL(xsk_get_pool_from_qid); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) { - if (queue_id < dev->num_rx_queues) - dev->_rx[queue_id].pool = NULL; - if (queue_id < dev->num_tx_queues) - dev->_tx[queue_id].pool = NULL; + struct net_device *orig_dev = dev; + unsigned int id = queue_id; + + if (id < dev->real_num_rx_queues) + WARN_ON_ONCE(!netif_get_rx_queue_peer_locked(&dev, &id)); + + if (id < dev->real_num_rx_queues) + dev->_rx[id].pool = NULL; + if (id < dev->real_num_tx_queues) + dev->_tx[id].pool = NULL; + + netif_put_rx_queue_peer_locked(orig_dev, dev); } /* The buffer pool is stored both in the _rx struct and the _tx struct as we do @@ -137,17 +147,29 @@ void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id) { - if (queue_id >= max_t(unsigned int, - dev->real_num_rx_queues, - dev->real_num_tx_queues)) - return -EINVAL; + struct net_device *orig_dev = dev; + unsigned int id = queue_id; + int ret = 0; - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].pool = pool; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].pool = pool; + if (id >= max(dev->real_num_rx_queues, + dev->real_num_tx_queues)) + return -EINVAL; + if (id < dev->real_num_rx_queues) { + if (!netif_get_rx_queue_peer_locked(&dev, &id)) + return -EBUSY; + if (xsk_get_pool_from_qid(dev, id)) { + ret = -EBUSY; + goto out; + } + } - return 0; + if (id < dev->real_num_rx_queues) + dev->_rx[id].pool = pool; + if (id < dev->real_num_tx_queues) + dev->_tx[id].pool = pool; +out: + netif_put_rx_queue_peer_locked(orig_dev, dev); + return ret; } static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len, -- 2.43.0 Add a single device mode for netkit instead of netkit pairs. The primary target for the paired devices is to connect network namespaces, of course, and support has been implemented in projects like Cilium [0]. For the rxq binding the plan is to support two main scenarios related to single device mode: * For the use-case of io_uring zero-copy, the control plane can either set up a netkit pair where the peer device can perform rxq binding which is then tied to the lifetime of the peer device, or the control plane can use a regular netkit pair to connect the hostns to a Pod/container and dynamically add/remove rxq bindings through a single device without having to interrupt the device pair. In the case of io_uring, the memory pool is used as skb non-linear pages, and thus the skb will go its way through the regular stack into netkit. Things like the netkit policy when no BPF is attached or skb scrubbing etc apply as-is in case the paired devices are used, or if the backend memory is tied to the single device and traffic goes through a paired device. * For the use-case of AF_XDP, the control plane needs to use netkit in the single device mode. The single device mode currently enforces only a pass policy when no BPF is attached, and does not yet support BPF link attachments for AF_XDP. skbs sent to that device get dropped at the moment. Given AF_XDP operates at a lower layer of the stack tying this to the netkit pair did not make sense. In future, the plan is to allow BPF at the XDP layer which can: i) process traffic coming from the AF_XDP application (e.g. QEMU with AF_XDP backend) to filter egress traffic or to push selected egress traffic up to the single netkit device to the local stack (e.g. DHCP requests), and ii) vice-versa skbs sent to the single netkit into the AF_XDP application (e.g. DHCP replies). Also, the control-plane can dynamically add/remove rxq bindings for the single netkit device without having to interrupt (e.g. down/up cycle) the main netkit pair for the Pod which has traffic going in and out. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Jordan Rife Reviewed-by: Nikolay Aleksandrov Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0] --- drivers/net/netkit.c | 108 ++++++++++++++++++++++------------- include/uapi/linux/if_link.h | 6 ++ 2 files changed, 74 insertions(+), 40 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 492be60f2e70..e3a2445d83fc 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -25,6 +25,7 @@ struct netkit { /* Needed in slow-path */ enum netkit_mode mode; + enum netkit_pairing pair; bool primary; u32 headroom; }; @@ -133,6 +134,10 @@ static int netkit_open(struct net_device *dev) struct netkit *nk = netkit_priv(dev); struct net_device *peer = rtnl_dereference(nk->peer); + if (nk->pair == NETKIT_DEVICE_SINGLE) { + netif_carrier_on(dev); + return 0; + } if (!peer) return -ENOTCONN; if (peer->flags & IFF_UP) { @@ -333,6 +338,7 @@ static int netkit_new_link(struct net_device *dev, enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT; enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT; struct nlattr *peer_tb[IFLA_MAX + 1], **tbp, *attr; + enum netkit_pairing pair = NETKIT_DEVICE_PAIR; enum netkit_action policy_prim = NETKIT_PASS; enum netkit_action policy_peer = NETKIT_PASS; struct nlattr **data = params->data; @@ -341,7 +347,7 @@ static int netkit_new_link(struct net_device *dev, struct nlattr **tb = params->tb; u16 headroom = 0, tailroom = 0; struct ifinfomsg *ifmp = NULL; - struct net_device *peer; + struct net_device *peer = NULL; char ifname[IFNAMSIZ]; struct netkit *nk; int err; @@ -378,6 +384,8 @@ static int netkit_new_link(struct net_device *dev, headroom = nla_get_u16(data[IFLA_NETKIT_HEADROOM]); if (data[IFLA_NETKIT_TAILROOM]) tailroom = nla_get_u16(data[IFLA_NETKIT_TAILROOM]); + if (data[IFLA_NETKIT_PAIRING]) + pair = nla_get_u32(data[IFLA_NETKIT_PAIRING]); } if (ifmp && tbp[IFLA_IFNAME]) { @@ -390,45 +398,49 @@ static int netkit_new_link(struct net_device *dev, if (mode != NETKIT_L2 && (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) return -EOPNOTSUPP; + if (pair == NETKIT_DEVICE_SINGLE && + (tb != tbp || + tb[IFLA_NETKIT_PEER_POLICY] || + tb[IFLA_NETKIT_PEER_SCRUB] || + policy_prim != NETKIT_PASS)) + return -EOPNOTSUPP; - peer = rtnl_create_link(peer_net, ifname, ifname_assign_type, - &netkit_link_ops, tbp, extack); - if (IS_ERR(peer)) - return PTR_ERR(peer); - - netif_inherit_tso_max(peer, dev); - if (headroom) { - peer->needed_headroom = headroom; - dev->needed_headroom = headroom; - } - if (tailroom) { - peer->needed_tailroom = tailroom; - dev->needed_tailroom = tailroom; - } - - if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) - eth_hw_addr_random(peer); - if (ifmp && dev->ifindex) - peer->ifindex = ifmp->ifi_index; - - nk = netkit_priv(peer); - nk->primary = false; - nk->policy = policy_peer; - nk->scrub = scrub_peer; - nk->mode = mode; - nk->headroom = headroom; - bpf_mprog_bundle_init(&nk->bundle); + if (pair == NETKIT_DEVICE_PAIR) { + peer = rtnl_create_link(peer_net, ifname, ifname_assign_type, + &netkit_link_ops, tbp, extack); + if (IS_ERR(peer)) + return PTR_ERR(peer); + + netif_inherit_tso_max(peer, dev); + if (headroom) + peer->needed_headroom = headroom; + if (tailroom) + peer->needed_tailroom = tailroom; + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) + eth_hw_addr_random(peer); + if (ifmp && dev->ifindex) + peer->ifindex = ifmp->ifi_index; - err = register_netdevice(peer); - if (err < 0) - goto err_register_peer; - netif_carrier_off(peer); - if (mode == NETKIT_L2) - dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL); + nk = netkit_priv(peer); + nk->primary = false; + nk->policy = policy_peer; + nk->scrub = scrub_peer; + nk->mode = mode; + nk->pair = pair; + nk->headroom = headroom; + bpf_mprog_bundle_init(&nk->bundle); + + err = register_netdevice(peer); + if (err < 0) + goto err_register_peer; + netif_carrier_off(peer); + if (mode == NETKIT_L2) + dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL); - err = rtnl_configure_link(peer, NULL, 0, NULL); - if (err < 0) - goto err_configure_peer; + err = rtnl_configure_link(peer, NULL, 0, NULL); + if (err < 0) + goto err_configure_peer; + } if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); @@ -436,12 +448,17 @@ static int netkit_new_link(struct net_device *dev, nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); else strscpy(dev->name, "nk%d", IFNAMSIZ); + if (headroom) + dev->needed_headroom = headroom; + if (tailroom) + dev->needed_tailroom = tailroom; nk = netkit_priv(dev); nk->primary = true; nk->policy = policy_prim; nk->scrub = scrub_prim; nk->mode = mode; + nk->pair = pair; nk->headroom = headroom; bpf_mprog_bundle_init(&nk->bundle); @@ -453,10 +470,12 @@ static int netkit_new_link(struct net_device *dev, dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL); rcu_assign_pointer(netkit_priv(dev)->peer, peer); - rcu_assign_pointer(netkit_priv(peer)->peer, dev); + if (peer) + rcu_assign_pointer(netkit_priv(peer)->peer, dev); return 0; err_configure_peer: - unregister_netdevice(peer); + if (peer) + unregister_netdevice(peer); return err; err_register_peer: free_netdev(peer); @@ -516,6 +535,8 @@ static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 whi nk = netkit_priv(dev); if (!nk->primary) return ERR_PTR(-EACCES); + if (nk->pair == NETKIT_DEVICE_SINGLE) + return ERR_PTR(-EOPNOTSUPP); if (which == BPF_NETKIT_PEER) { dev = rcu_dereference_rtnl(nk->peer); if (!dev) @@ -877,6 +898,7 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], { IFLA_NETKIT_PEER_INFO, "peer info" }, { IFLA_NETKIT_HEADROOM, "headroom" }, { IFLA_NETKIT_TAILROOM, "tailroom" }, + { IFLA_NETKIT_PAIRING, "pairing" }, }; if (!nk->primary) { @@ -896,9 +918,11 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_NETKIT_POLICY]) { + err = -EOPNOTSUPP; attr = data[IFLA_NETKIT_POLICY]; policy = nla_get_u32(attr); - err = netkit_check_policy(policy, attr, extack); + if (nk->pair == NETKIT_DEVICE_PAIR) + err = netkit_check_policy(policy, attr, extack); if (err) return err; WRITE_ONCE(nk->policy, policy); @@ -929,6 +953,7 @@ static size_t netkit_get_size(const struct net_device *dev) nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */ nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_HEADROOM */ nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_TAILROOM */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PAIRING */ 0; } @@ -949,6 +974,8 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev) return -EMSGSIZE; if (nla_put_u16(skb, IFLA_NETKIT_TAILROOM, dev->needed_tailroom)) return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_PAIRING, nk->pair)) + return -EMSGSIZE; if (peer) { nk = netkit_priv(peer); @@ -970,6 +997,7 @@ static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = { [IFLA_NETKIT_TAILROOM] = { .type = NLA_U16 }, [IFLA_NETKIT_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT), [IFLA_NETKIT_PEER_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT), + [IFLA_NETKIT_PAIRING] = NLA_POLICY_MAX(NLA_U32, NETKIT_DEVICE_SINGLE), [IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT, .reject_message = "Primary attribute is read-only" }, }; 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) -- 2.43.0 Instead of a comment, just use two cachline groups to document the intent for members often accessed in fast or slow path. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Nikolay Aleksandrov --- drivers/net/netkit.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index e3a2445d83fc..96734828bfb8 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -16,18 +16,20 @@ #define DRV_NAME "netkit" struct netkit { - /* Needed in fast-path */ + __cacheline_group_begin(netkit_fastpath); struct net_device __rcu *peer; struct bpf_mprog_entry __rcu *active; enum netkit_action policy; enum netkit_scrub scrub; struct bpf_mprog_bundle bundle; + __cacheline_group_end(netkit_fastpath); - /* Needed in slow-path */ + __cacheline_group_begin(netkit_slowpath); enum netkit_mode mode; enum netkit_pairing pair; bool primary; u32 headroom; + __cacheline_group_end(netkit_slowpath); }; struct netkit_link { -- 2.43.0 From: David Wei Implement rtnl_link_ops->alloc that allows the number of rx queues to be set when netkit is created. By default, netkit has only a single rxq (and single txq). The number of queues is deliberately not allowed to be changed via ethtool -L and is fixed for the lifetime of a netkit instance. For netkit device creation, numrxqueues with larger than one rxq can be specified. These rxqs are then mappable to real rxqs in physical netdevs: ip link add type netkit peer numrxqueues 64 # for device pair ip link add numrxqueues 64 type netkit single # for single device The limit of numrxqueues for netkit is currently set to 256, which allows binding multiple real rxqs from physical netdevs. The implementation of ndo_queue_create() adds a new rxq during the bind queue operation. We allow to create queues either in single device mode or for the case of dual device mode for the netkit peer device which gets placed into the target network namespace. For dual device mode the bind against the primary device does not make sense for the targeted use cases, and therefore gets rejected. We also need to add a lockdep class for netkit, such that lockdep does not trip over us, similarly done as in commit 0bef512012b1 ("net: add netdev_lockdep_set_classes() to virtual drivers"). Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov --- drivers/net/netkit.c | 130 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 118 insertions(+), 12 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 96734828bfb8..92a65350f389 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -9,11 +9,20 @@ #include #include +#include +#include +#include #include #include #include -#define DRV_NAME "netkit" +#define NETKIT_DRV_NAME "netkit" + +#define NETKIT_NUM_RX_QUEUES_MAX 256 +#define NETKIT_NUM_TX_QUEUES_MAX 1 + +#define NETKIT_NUM_RX_QUEUES_REAL 1 +#define NETKIT_NUM_TX_QUEUES_REAL 1 struct netkit { __cacheline_group_begin(netkit_fastpath); @@ -37,6 +46,8 @@ struct netkit_link { struct net_device *dev; }; +static struct rtnl_link_ops netkit_link_ops; + static __always_inline int netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, enum netkit_action ret) @@ -224,9 +235,16 @@ static void netkit_get_stats(struct net_device *dev, stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); } +static int netkit_init(struct net_device *dev) +{ + netdev_lockdep_set_classes(dev); + return 0; +} + static void netkit_uninit(struct net_device *dev); static const struct net_device_ops netkit_netdev_ops = { + .ndo_init = netkit_init, .ndo_open = netkit_open, .ndo_stop = netkit_close, .ndo_start_xmit = netkit_xmit, @@ -243,13 +261,100 @@ static const struct net_device_ops netkit_netdev_ops = { static void netkit_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strscpy(info->driver, DRV_NAME, sizeof(info->driver)); + strscpy(info->driver, NETKIT_DRV_NAME, sizeof(info->driver)); +} + +static void netkit_get_channels(struct net_device *dev, + struct ethtool_channels *channels) +{ + channels->max_rx = dev->num_rx_queues; + channels->max_tx = dev->num_tx_queues; + channels->max_other = 0; + channels->max_combined = 1; + channels->rx_count = dev->real_num_rx_queues; + channels->tx_count = dev->real_num_tx_queues; + channels->other_count = 0; + channels->combined_count = 0; } static const struct ethtool_ops netkit_ethtool_ops = { .get_drvinfo = netkit_get_drvinfo, + .get_channels = netkit_get_channels, }; +static int netkit_queue_create(struct net_device *dev, int *idx) +{ + struct netkit *nk = netkit_priv(dev); + u32 rxq_count_old, rxq_count_new; + int err; + + rxq_count_old = dev->real_num_rx_queues; + rxq_count_new = rxq_count_old + 1; + + /* Only allow to bind in single device mode or to bind against + * the peer device which then ends up in the target netns. + */ + if (nk->pair == NETKIT_DEVICE_PAIR && nk->primary) + return -EOPNOTSUPP; + + if (netif_running(dev)) + netif_carrier_off(dev); + err = netif_set_real_num_rx_queues(dev, rxq_count_new); + if (netif_running(dev)) + netif_carrier_on(dev); + if (!err) + *idx = rxq_count_old; + return err; +} + +static const struct netdev_queue_mgmt_ops netkit_queue_mgmt_ops = { + .ndo_queue_create = netkit_queue_create, +}; + +static struct net_device *netkit_alloc(struct nlattr *tb[], + const char *ifname, + unsigned char name_assign_type, + unsigned int num_tx_queues, + unsigned int num_rx_queues) +{ + const struct rtnl_link_ops *ops = &netkit_link_ops; + struct net_device *dev; + + if (num_tx_queues > NETKIT_NUM_TX_QUEUES_MAX || + num_rx_queues > NETKIT_NUM_RX_QUEUES_MAX) + return ERR_PTR(-EOPNOTSUPP); + + dev = alloc_netdev_mqs(ops->priv_size, ifname, + name_assign_type, ops->setup, + num_tx_queues, num_rx_queues); + if (dev) { + dev->real_num_tx_queues = NETKIT_NUM_TX_QUEUES_REAL; + dev->real_num_rx_queues = NETKIT_NUM_RX_QUEUES_REAL; + } + return dev; +} + +static void netkit_queue_unpeer(struct net_device *dev) +{ + struct netdev_rx_queue *src_rxq, *dst_rxq; + struct net_device *src_dev; + int i; + + if (dev->real_num_rx_queues == 1) + return; + netdev_lock(dev); + for (i = 1; i < dev->real_num_rx_queues; i++) { + dst_rxq = __netif_get_rx_queue(dev, i); + src_rxq = dst_rxq->peer; + src_dev = src_rxq->dev; + + netdev_lock(src_dev); + netdev_rx_queue_unpeer(src_dev, src_rxq, dst_rxq); + netdev_unlock(src_dev); + } + netdev_unlock(dev); +} + static void netkit_setup(struct net_device *dev) { static const netdev_features_t netkit_features_hw_vlan = @@ -280,8 +385,9 @@ static void netkit_setup(struct net_device *dev) dev->priv_flags |= IFF_DISABLE_NETPOLL; dev->lltx = true; - dev->ethtool_ops = &netkit_ethtool_ops; - dev->netdev_ops = &netkit_netdev_ops; + dev->netdev_ops = &netkit_netdev_ops; + dev->ethtool_ops = &netkit_ethtool_ops; + dev->queue_mgmt_ops = &netkit_queue_mgmt_ops; dev->features |= netkit_features; dev->hw_features = netkit_features; @@ -330,8 +436,6 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } -static struct rtnl_link_ops netkit_link_ops; - static int netkit_new_link(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) @@ -865,6 +969,7 @@ static void netkit_release_all(struct net_device *dev) static void netkit_uninit(struct net_device *dev) { netkit_release_all(dev); + netkit_queue_unpeer(dev); } static void netkit_del_link(struct net_device *dev, struct list_head *head) @@ -1005,8 +1110,9 @@ static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = { }; static struct rtnl_link_ops netkit_link_ops = { - .kind = DRV_NAME, + .kind = NETKIT_DRV_NAME, .priv_size = sizeof(struct netkit), + .alloc = netkit_alloc, .setup = netkit_setup, .newlink = netkit_new_link, .dellink = netkit_del_link, @@ -1020,7 +1126,7 @@ static struct rtnl_link_ops netkit_link_ops = { .maxtype = IFLA_NETKIT_MAX, }; -static __init int netkit_init(void) +static __init int netkit_mod_init(void) { BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT || (int)NETKIT_PASS != (int)TCX_PASS || @@ -1030,16 +1136,16 @@ static __init int netkit_init(void) return rtnl_link_register(&netkit_link_ops); } -static __exit void netkit_exit(void) +static __exit void netkit_mod_exit(void) { rtnl_link_unregister(&netkit_link_ops); } -module_init(netkit_init); -module_exit(netkit_exit); +module_init(netkit_mod_init); +module_exit(netkit_mod_exit); MODULE_DESCRIPTION("BPF-programmable network device"); MODULE_AUTHOR("Daniel Borkmann "); MODULE_AUTHOR("Nikolay Aleksandrov "); MODULE_LICENSE("GPL"); -MODULE_ALIAS_RTNL_LINK(DRV_NAME); +MODULE_ALIAS_RTNL_LINK(NETKIT_DRV_NAME); -- 2.43.0 Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events. If the target device is indeed NETREG_UNREGISTERING and was previously peered to a netkit device, then collect the related netkit devices and batch-unregister_netdevice_many() them. If this would not be done, then the netkit device would hold a reference on the peered physical device preventing it from going away. However, in case of both io_uring zero-copy as well as AF_XDP this situation is handled gracefully and the allocated resources as torn down. In the case where mentioned infra is used through netkit, the applications have a reference on netkit, and netkit in turn holds a reference on the physical device. In order to have netkit release the reference on the physical device, we need such watcher to then unregister the netkit ones. This is generally quite similar to the dependency handling in case of tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device gets removed along with the physical device. # ip a [...] 4: enp10s0f0np0: mtu 1500 qdisc mq state DOWN group default qlen 1000 link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff inet 10.0.0.2/24 scope global enp10s0f0np0 valid_lft forever preferred_lft forever [...] 8: nk@NONE: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff [...] # rmmod mlx5_ib # rmmod mlx5_core [ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN [ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) [ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) [ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) [ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup [ 345.345709] mlx5_core 0000:0a:00.0: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) [ 345.357524] mlx5_core 0000:0a:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) [ 350.995989] mlx5_core 0000:0a:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) [ 351.574396] mlx5_core 0000:0a:00.0: E-Switch: cleanup # ip a [...] [ both enp10s0f0np0 and nk gone ] [...] Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Nikolay Aleksandrov --- drivers/net/netkit.c | 57 ++++++++++++++++++++++++++++++++++++++- include/linux/netdevice.h | 6 +++++ 2 files changed, 62 insertions(+), 1 deletion(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 92a65350f389..2871d8b08f6d 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -1050,6 +1050,48 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], return 0; } +static void netkit_check_peer_unregister(struct net_device *dev) +{ + LIST_HEAD(list_kill); + u32 q_idx; + + if (READ_ONCE(dev->reg_state) != NETREG_UNREGISTERING || + !dev->dev.parent) + return; + + for (q_idx = 0; q_idx < dev->real_num_rx_queues; q_idx++) { + struct net_device *peer = dev; + u32 peer_q_idx = q_idx; + + if (__netif_get_rx_queue_peer(&peer, &peer_q_idx, + NETIF_PHYS_TO_VIRT)) { + if (peer->netdev_ops != &netkit_netdev_ops) + continue; + /* A single phys device can have multiple queues peered + * to one netkit device. We can only queue that netkit + * device once to the list_kill. Queues of that phys + * device can be peered with different individual netkit + * devices, hence we batch via list_kill. + */ + if (unregister_netdevice_queued(peer)) + continue; + netkit_del_link(peer, &list_kill); + } + } + + unregister_netdevice_many(&list_kill); +} + +static int netkit_notifier(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (event == NETDEV_UNREGISTER) + netkit_check_peer_unregister(dev); + return NOTIFY_DONE; +} + static size_t netkit_get_size(const struct net_device *dev) { return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */ @@ -1126,18 +1168,31 @@ static struct rtnl_link_ops netkit_link_ops = { .maxtype = IFLA_NETKIT_MAX, }; +static struct notifier_block netkit_netdev_notifier = { + .notifier_call = netkit_notifier, +}; + static __init int netkit_mod_init(void) { + int ret; + BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT || (int)NETKIT_PASS != (int)TCX_PASS || (int)NETKIT_DROP != (int)TCX_DROP || (int)NETKIT_REDIRECT != (int)TCX_REDIRECT); - return rtnl_link_register(&netkit_link_ops); + ret = rtnl_link_register(&netkit_link_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&netkit_netdev_notifier); + if (ret) + rtnl_link_unregister(&netkit_link_ops); + return ret; } static __exit void netkit_mod_exit(void) { + unregister_netdevice_notifier(&netkit_netdev_notifier); rtnl_link_unregister(&netkit_link_ops); } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c1e5042c5e7..efc3c9fb4567 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3385,11 +3385,17 @@ 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); -- 2.43.0 From: David Wei This adds the last missing bit to netkit for supporting io_uring with zero-copy mode [0]. Up until this point it was not possible to consume the latter out of containers or Kubernetes Pods where applications are in their own network namespace. Thus, as a last missing bit, implement ndo_queue_get_dma_dev() in netkit to return the physical device of the real rxq for DMA. This allows memory providers like io_uring zero-copy or devmem to bind to the physically mapped rxq in netkit. io_uring example with eth0 being a physical device with 16 queues where netkit is bound to the last queue, iou-zcrx.c is binary from selftests. Flow steering to that queue is based on the service VIP:port of the server utilizing io_uring: # ethtool -X eth0 start 0 equal 15 # ethtool -X eth0 start 15 equal 1 context new # ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15 # ip netns add foo # ip link add type netkit peer numrxqueues 2 # ./pyynl/cli.py --spec ~/netlink/specs/netdev.yaml \ --do bind-queue \ --json "{"src-ifindex": $(ifindex eth0), "src-queue-id": 15, \ "dst-ifindex": $(ifindex nk0), "queue-type": "rx"}" {'dst-queue-id': 1} # ip link set nk0 netns foo # ip link set nk1 up # ip netns exec foo ip link set lo up # ip netns exec foo ip link set nk0 up # ip netns exec foo ip addr add 1.2.3.4/32 dev nk0 [ ... setup routing etc to get external traffic into the netns ... ] # ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1 Remote io_uring client: # ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536 We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC, supporting TCP header/data split. Similarly, this also works for devmem which we tested using ncdevmem: # ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1 And on the remote client: # ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0 For Cilium, the plan is to open up support for the various memory providers for regular Kubernetes Pods when Cilium is configured with netkit datapath mode. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0] --- drivers/net/netkit.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 2871d8b08f6d..f46b21f18700 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -282,6 +282,21 @@ static const struct ethtool_ops netkit_ethtool_ops = { .get_channels = netkit_get_channels, }; +static struct device *netkit_queue_get_dma_dev(struct net_device *dev, int idx) +{ + struct netdev_rx_queue *rxq, *peer_rxq; + unsigned int peer_idx; + + rxq = __netif_get_rx_queue(dev, idx); + if (!rxq->peer) + return NULL; + + peer_rxq = rxq->peer; + peer_idx = get_netdev_rx_queue_index(peer_rxq); + + return netdev_queue_get_dma_dev(peer_rxq->dev, peer_idx); +} + static int netkit_queue_create(struct net_device *dev, int *idx) { struct netkit *nk = netkit_priv(dev); @@ -308,7 +323,8 @@ static int netkit_queue_create(struct net_device *dev, int *idx) } static const struct netdev_queue_mgmt_ops netkit_queue_mgmt_ops = { - .ndo_queue_create = netkit_queue_create, + .ndo_queue_get_dma_dev = netkit_queue_get_dma_dev, + .ndo_queue_create = netkit_queue_create, }; static struct net_device *netkit_alloc(struct nlattr *tb[], -- 2.43.0 Enable support for AF_XDP applications to operate on a netkit device. The goal is that AF_XDP applications can natively consume AF_XDP from network namespaces. The use-case from Cilium side is to support Kubernetes KubeVirt VMs through QEMU's AF_XDP backend. KubeVirt is a virtual machine management add-on for Kubernetes which aims to provide a common ground for virtualization. KubeVirt spawns the VMs inside Kubernetes Pods which reside in their own network namespace just like regular Pods. Raw QEMU AF_XDP backend example with eth0 being a physical device with 16 queues where netkit is bound to the last queue (for multi-queue RSS context can be used if supported by the driver): # ethtool -X eth0 start 0 equal 15 # ethtool -X eth0 start 15 equal 1 context new # ethtool --config-ntuple eth0 flow-type ether \ src 00:00:00:00:00:00 \ src-mask ff:ff:ff:ff:ff:ff \ dst $mac dst-mask 00:00:00:00:00:00 \ proto 0 proto-mask 0xffff action 15 [ ... setup BPF/XDP prog on eth0 to steer into shared xsk map ... ] # ip netns add foo # ip link add numrxqueues 2 nk type netkit single # ./pyynl/cli.py --spec ~/netlink/specs/netdev.yaml \ --do bind-queue \ --json "{"src-ifindex": $(ifindex eth0), "src-queue-id": 15, \ "dst-ifindex": $(ifindex nk), "queue-type": "rx"}" {'dst-queue-id': 1} # ip link set nk netns foo # ip netns exec foo ip link set lo up # ip netns exec foo ip link set nk up # ip netns exec foo qemu-system-x86_64 \ -kernel $kernel \ -drive file=${image_name},index=0,media=disk,format=raw \ -append "root=/dev/sda rw console=ttyS0" \ -cpu host \ -m $memory \ -enable-kvm \ -device virtio-net-pci,netdev=net0,mac=$mac \ -netdev af-xdp,ifname=nk,id=net0,mode=native,queues=1,start-queue=1,inhibit=on,map-path=$dir/xsks_map \ -nographic We have tested the above against a dual-port Nvidia ConnectX-6 (mlx5) 100G NIC with successful network connectivity out of QEMU. An earlier iteration of this work was presented at LSF/MM/BPF [0]. For getting to a first starting point to connect all things with KubeVirt, bind mounting the xsk map from Cilium into the VM launcher Pod which acts as a regular Kubernetes Pod while not perfect, is not a big problem given its out of reach from the application sitting inside the VM (and some of the control plane aspects are baked in the launcher Pod already), so the isolation barrier is still the VM. Eventually the goal is to have a XDP/XSK redirect extension where there is no need to have the xsk map, and the BPF program can just derive the target xsk through the queue where traffic was received on. The exposure through netkit is because Cilium should not act as a proxy handing out xsk sockets. Existing applications expect a netdev from kernel side and should not need to rewrite just to implement against a CNI's protocol. Also, all the memory should not be accounted against Cilium but rather the application Pod itself which is consuming AF_XDP. Further, on up/downgrades we expect the data plane to being completely decoupled from the control plane; if Cilium would own the sockets that would be disruptive. Another use-case which opens up and is regularly asked from users would be to have DPDK applications on top of AF_XDP in regular Kubernetes Pods. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Nikolay Aleksandrov Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0] --- drivers/net/netkit.c | 76 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 75 insertions(+), 1 deletion(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index f46b21f18700..5fda2f0c71f8 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -235,6 +236,76 @@ static void netkit_get_stats(struct net_device *dev, stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); } +static bool netkit_xsk_supported_at_phys(const struct net_device *dev) +{ + if (!dev->netdev_ops->ndo_bpf || + !dev->netdev_ops->ndo_xdp_xmit || + !dev->netdev_ops->ndo_xsk_wakeup) + return false; + if ((dev->xdp_features & NETDEV_XDP_ACT_XSK) != NETDEV_XDP_ACT_XSK) + return false; + return true; +} + +static int netkit_xsk(struct net_device *dev, struct netdev_bpf *xdp) +{ + struct netkit *nk = netkit_priv(dev); + struct netdev_bpf xdp_lower; + struct netdev_rx_queue *rxq; + struct net_device *phys; + int ret = -EBUSY; + + switch (xdp->command) { + case XDP_SETUP_XSK_POOL: + if (nk->pair == NETKIT_DEVICE_PAIR) + return -EOPNOTSUPP; + if (xdp->xsk.queue_id >= dev->real_num_rx_queues) + return -EINVAL; + + rxq = __netif_get_rx_queue(dev, xdp->xsk.queue_id); + if (!rxq->peer) + return -EOPNOTSUPP; + + phys = rxq->peer->dev; + if (!netkit_xsk_supported_at_phys(phys)) + return -EOPNOTSUPP; + + memcpy(&xdp_lower, xdp, sizeof(xdp_lower)); + xdp_lower.xsk.queue_id = get_netdev_rx_queue_index(rxq->peer); + break; + case XDP_SETUP_PROG: + return -EPERM; + default: + return -EINVAL; + } + + netdev_lock(phys); + if (!dev_get_min_mp_channel_count(phys)) + ret = phys->netdev_ops->ndo_bpf(phys, &xdp_lower); + netdev_unlock(phys); + return ret; +} + +static int netkit_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) +{ + struct netdev_rx_queue *rxq; + struct net_device *phys; + + if (queue_id >= dev->real_num_rx_queues) + return -EINVAL; + + rxq = __netif_get_rx_queue(dev, queue_id); + if (!rxq->peer) + return -EOPNOTSUPP; + + phys = rxq->peer->dev; + if (!netkit_xsk_supported_at_phys(phys)) + return -EOPNOTSUPP; + + return phys->netdev_ops->ndo_xsk_wakeup(phys, + get_netdev_rx_queue_index(rxq->peer), flags); +} + static int netkit_init(struct net_device *dev) { netdev_lockdep_set_classes(dev); @@ -255,6 +326,8 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_get_peer_dev = netkit_peer_dev, .ndo_get_stats64 = netkit_get_stats, .ndo_uninit = netkit_uninit, + .ndo_bpf = netkit_xsk, + .ndo_xsk_wakeup = netkit_xsk_wakeup, .ndo_features_check = passthru_features_check, }; @@ -410,10 +483,11 @@ static void netkit_setup(struct net_device *dev) dev->hw_enc_features = netkit_features; dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; dev->vlan_features = dev->features & ~netkit_features_hw_vlan; - dev->needs_free_netdev = true; netif_set_tso_max_size(dev, GSO_MAX_SIZE); + + xdp_set_features_flag(dev, NETDEV_XDP_ACT_XSK); } static struct net *netkit_get_link_net(const struct net_device *dev) -- 2.43.0