From: David Wei Add a ynl netdev family operation called bind-queue that _binds_ an rxq from a real netdev to a virtual netdev i.e. netkit or veth. This bound or _mapped_ rxq in the virtual netdev acts as a proxy for the parent real rxq, and can be used by processes running in a container to use memory providers (io_uring zero-copy rx or devmem) or 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 rxq respectively. dst-ifindex is the virtual netdev. Note that this op doesn't take dst-queue-id, because the expectation is that the op will _create_ a new rxq in the virtual netdev. The virtual netdev must have real_num_rx_queues less than num_rx_queues at the time of calling bind-queue. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0] --- Documentation/netlink/specs/netdev.yaml | 37 +++++++++++++++++++++++++ include/uapi/linux/netdev.h | 11 ++++++++ net/core/netdev-genl-gen.c | 14 ++++++++++ net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 4 +++ tools/include/uapi/linux/netdev.h | 11 ++++++++ 6 files changed, 78 insertions(+) diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index e00d3fa1c152..99a430ea8a9a 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -561,6 +561,29 @@ attribute-sets: type: u32 checks: min: 1 + - + name: queue-pair + attributes: + - + name: src-ifindex + doc: netdev ifindex of the physical device + type: u32 + checks: + min: 1 + - + name: src-queue-id + doc: netdev queue id of the physical device + type: u32 + - + name: dst-ifindex + doc: netdev ifindex of the virtual device + type: u32 + checks: + min: 1 + - + name: dst-queue-id + doc: netdev queue id of the virtual device + type: u32 operations: list: @@ -772,6 +795,20 @@ operations: attributes: - id + - + name: bind-queue + doc: Bind a physical netdev queue to a virtual one + attribute-set: queue-pair + do: + request: + attributes: + - 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..05e17765a39d 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -210,6 +210,16 @@ enum { NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) }; +enum { + NETDEV_A_QUEUE_PAIR_SRC_IFINDEX = 1, + 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 +236,7 @@ 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..10b2ab4dd500 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -106,6 +106,13 @@ 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_SRC_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_QUEUE_PAIR_SRC_QUEUE_ID] = { .type = NLA_U32, }, + [NETDEV_A_QUEUE_PAIR_DST_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -204,6 +211,13 @@ 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_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..b0aea27bf84e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -1120,6 +1120,10 @@ 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) +{ +} + 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..05e17765a39d 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -210,6 +210,16 @@ enum { NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) }; +enum { + NETDEV_A_QUEUE_PAIR_SRC_IFINDEX = 1, + 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 +236,7 @@ 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 Add a peer pointer to netdev_rx_queue that points from the real rxq to the mapped rxq in a virtual netdev, and vice versa. Add related helpers that set, unset, get and check the peer pointer. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/net/netdev_rx_queue.h | 51 +++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index 8cdcd138b33f..47126ccaf854 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -28,6 +28,7 @@ struct netdev_rx_queue { #endif struct napi_struct *napi; struct pp_memory_provider_params mp_params; + struct netdev_rx_queue *peer; } ____cacheline_aligned_in_smp; /* @@ -58,4 +59,54 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) 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) +{ + src_rxq->peer = dst_rxq; + dst_rxq->peer = src_rxq; +} + +static inline void netdev_rx_queue_peer(struct net_device *src_dev, + struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + dev_hold(src_dev); + __netdev_rx_queue_peer(src_rxq, dst_rxq); +} + +static inline void __netdev_rx_queue_unpeer(struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + src_rxq->peer = NULL; + dst_rxq->peer = NULL; +} + +static inline void netdev_rx_queue_unpeer(struct net_device *src_dev, + struct netdev_rx_queue *src_rxq, + struct netdev_rx_queue *dst_rxq) +{ + __netdev_rx_queue_unpeer(src_rxq, dst_rxq); + dev_put(src_dev); +} + +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; +} + +static inline struct netdev_rx_queue * +__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx) +{ + struct netdev_rx_queue *rxq = __netif_get_rx_queue(*dev, *rxq_idx); + + if (rxq->peer) { + rxq = rxq->peer; + *rxq_idx = get_netdev_rx_queue_index(rxq); + *dev = rxq->dev; + } + return rxq; +} #endif -- 2.43.0 From: David Wei Add ndo_queue_create() to netdev_queue_mgmt_ops that will create a new rxq specifically for mapping to a real rxq. The intent is for only virtual netdevs i.e. netkit and veth to implement this ndo. This will be called from ynl netdev fam bind-queue op to atomically create a mapped rxq and bind it to a real rxq. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/net/netdev_queues.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index cd00e0406cf4..6b0d2416728d 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -149,6 +149,7 @@ 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); -- 2.43.0 Add ndo_{peer,unpeer}_queues() callback which can be used by virtual drivers that implement rxq mapping to a real rxq to update their internal state or exposed capability flags from the set of rxq mappings. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei --- include/linux/netdevice.h | 15 ++++++++++++++- include/net/netdev_rx_queue.h | 4 ++++ 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1c54d44805fa..43b3c4e3593e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -65,6 +65,7 @@ struct macsec_context; struct macsec_ops; struct netdev_config; struct netdev_name_node; +struct netdev_rx_queue; struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ @@ -1404,6 +1405,15 @@ struct netdev_net_notifier { * struct kernel_hwtstamp_config *kernel_config, * struct netlink_ext_ack *extack); * Change the hardware timestamping parameters for NIC device. + * + * void (*ndo_peer_queues)(struct net_device *dev, struct netdev_rx_queue *rxq); + * Custom callback for drivers when a physical queue gets peered with + * a virtual one, so that device drivers can update exposed device flags. + * + * void (*ndo_unpeer_queues)(struct net_device *dev, struct netdev_rx_queue *rxq); + * Custom callback for drivers when a physical queue gets unpeered with + * a virtual one, so that device drivers can update exposed device flags. + * Reverse operation of ndo_peer_queues. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1651,7 +1661,10 @@ struct net_device_ops { int (*ndo_hwtstamp_set)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config, struct netlink_ext_ack *extack); - + void (*ndo_peer_queues)(struct net_device *dev, + struct netdev_rx_queue *rxq); + void (*ndo_unpeer_queues)(struct net_device *dev, + struct netdev_rx_queue *rxq); #if IS_ENABLED(CONFIG_NET_SHAPER) /** * @net_shaper_ops: Device shaping offload operations diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index 47126ccaf854..fdfacd28c2ae 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -72,6 +72,8 @@ static inline void netdev_rx_queue_peer(struct net_device *src_dev, { dev_hold(src_dev); __netdev_rx_queue_peer(src_rxq, dst_rxq); + if (dst_rxq->dev->netdev_ops->ndo_peer_queues) + dst_rxq->dev->netdev_ops->ndo_peer_queues(dst_rxq->dev, dst_rxq); } static inline void __netdev_rx_queue_unpeer(struct netdev_rx_queue *src_rxq, @@ -85,6 +87,8 @@ static inline void netdev_rx_queue_unpeer(struct net_device *src_dev, struct netdev_rx_queue *src_rxq, struct netdev_rx_queue *dst_rxq) { + if (dst_rxq->dev->netdev_ops->ndo_unpeer_queues) + dst_rxq->dev->netdev_ops->ndo_unpeer_queues(dst_rxq->dev, dst_rxq); __netdev_rx_queue_unpeer(src_rxq, dst_rxq); dev_put(src_dev); } -- 2.43.0 From: David Wei Implement netdev_nl_bind_queue_doit() that creates a mapped rxq in a virtual netdev and then binds it to a real rxq in a physical netdev by setting the peer pointer in netdev_rx_queue. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- net/core/netdev-genl.c | 117 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 117 insertions(+) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index b0aea27bf84e..ed0ce3dbfc6f 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -1122,6 +1122,123 @@ 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) { + u32 src_ifidx, src_qid, dst_ifidx, dst_qid; + struct netdev_rx_queue *src_rxq, *dst_rxq; + struct net_device *src_dev, *dst_dev; + struct netdev_nl_sock *priv; + struct sk_buff *rsp; + int err = 0; + void *hdr; + + if (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]); + if (dst_ifidx == src_ifidx) { + NL_SET_ERR_MSG(info->extack, + "Destination driver cannot be same as source driver"); + return -EOPNOTSUPP; + } + + priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); + if (IS_ERR(priv)) + return PTR_ERR(priv); + + 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; + } + + mutex_lock(&priv->lock); + + src_dev = netdev_get_by_index_lock(genl_info_net(info), src_ifidx); + if (!src_dev) { + err = -ENODEV; + goto err_unlock_sock; + } + if (!netif_device_present(src_dev)) { + err = -ENODEV; + goto err_unlock_src_dev; + } + if (!src_dev->dev.parent) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Source driver is a virtual device"); + goto err_unlock_src_dev; + } + 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_src_dev; + } + if (src_qid >= src_dev->num_rx_queues) { + err = -ERANGE; + NL_SET_ERR_MSG(info->extack, + "Source driver queue 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 driver queue already bound"); + goto err_unlock_src_dev; + } + + dst_dev = netdev_get_by_index_lock(genl_info_net(info), dst_ifidx); + if (!dst_dev) { + err = -ENODEV; + goto err_unlock_src_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; + } + + err = dst_dev->queue_mgmt_ops->ndo_queue_create(dst_dev); + if (err <= 0) { + NL_SET_ERR_MSG(info->extack, + "Destination driver unable to create a new queue"); + goto err_unlock_dst_dev; + } + + dst_qid = err - 1; + 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(dst_dev); + netdev_unlock(src_dev); + mutex_unlock(&priv->lock); + + return genlmsg_reply(rsp, info); + +err_unlock_dst_dev: + netdev_unlock(dst_dev); +err_unlock_src_dev: + netdev_unlock(src_dev); +err_unlock_sock: + mutex_unlock(&priv->lock); +err_genlmsg_free: + nlmsg_free(rsp); + return err; } void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv) -- 2.43.0 From: David Wei Add a nested peer field to the queue-get response that returns the peered ifindex and queue id. If the queried queue is a mapped queue in a virtual netdev, the nested fields for dmabuf/io-uring/xsk will be filled in, too. Example: # ip netns exec foo ./pyynl/cli.py \ --spec ~/netlink/specs/netdev.yaml \ --do queue-get \ --json '{"ifindex": 3, "id": 1, "type": "rx"}' {'id': 1, 'ifindex': 3, 'peer': {'id': 15, 'ifindex': 4}, 'io-uring': {}, 'type': 'rx'} Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- Documentation/netlink/specs/netdev.yaml | 17 +++++++++++++++++ include/uapi/linux/netdev.h | 9 +++++++++ net/core/netdev-genl.c | 23 ++++++++++++++++++++++- tools/include/uapi/linux/netdev.h | 9 +++++++++ 4 files changed, 57 insertions(+), 1 deletion(-) diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 99a430ea8a9a..1467c36f6b5f 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -297,6 +297,17 @@ 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: queue attributes: @@ -338,6 +349,11 @@ 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: | @@ -706,6 +722,7 @@ operations: - dmabuf - io-uring - xsk + - peer dump: request: attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 05e17765a39d..73d1590e4696 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -150,6 +150,14 @@ 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_MAX, + NETDEV_A_PEER_INFO_MAX = (__NETDEV_A_PEER_INFO_MAX - 1) +}; + enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, @@ -158,6 +166,7 @@ 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 ed0ce3dbfc6f..c20922539216 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -393,6 +393,7 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, struct pp_memory_provider_params *params; struct netdev_rx_queue *rxq; struct netdev_queue *txq; + struct nlattr *nest; void *hdr; hdr = genlmsg_iput(rsp, info); @@ -410,6 +411,27 @@ 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 (netdev_rx_queue_peered(netdev, q_idx)) { + struct netdev_rx_queue *p_rxq; + struct net_device *p_netdev = netdev; + u32 p_q_idx = q_idx; + + nest = nla_nest_start(rsp, NETDEV_A_QUEUE_PEER); + if (!nest) + goto nla_put_failure; + p_rxq = __netif_get_rx_queue_peer(&p_netdev, &p_q_idx); + if (nla_put_u32(rsp, NETDEV_A_PEER_INFO_ID, p_q_idx) || + nla_put_u32(rsp, NETDEV_A_PEER_INFO_IFINDEX, p_netdev->ifindex)) + goto nla_put_failure; + nla_nest_end(rsp, nest); + + if (!netdev->dev.parent) { + netdev = p_netdev; + q_idx = p_q_idx; + rxq = p_rxq; + } + } + params = &rxq->mp_params; if (params->mp_ops && params->mp_ops->nl_fill(params->mp_priv, rsp, rxq)) @@ -419,7 +441,6 @@ 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); diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 05e17765a39d..73d1590e4696 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -150,6 +150,14 @@ 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_MAX, + NETDEV_A_PEER_INFO_MAX = (__NETDEV_A_PEER_INFO_MAX - 1) +}; + enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, @@ -158,6 +166,7 @@ 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 --- net/ethtool/channels.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index ca4f80282448..0ede1075e016 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include #include "netlink.h" @@ -169,14 +170,19 @@ 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++) + for (i = from_channel; i < old_total; i++) { + if (netdev_rx_queue_peered(dev, i)) { + GENL_SET_ERR_MSG(info, "requested channel counts are too low due to existing queue peering"); + return -EINVAL; + } 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"); return -EINVAL; } + } ret = dev->ethtool_ops->set_channels(dev, &channels); return ret < 0 ? ret : 1; -- 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 --- net/core/netdev_rx_queue.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index c7d9341b7630..238d3cd9677e 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -105,13 +105,21 @@ int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, 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 = __netif_get_rx_queue_peer(&dev, &rxq_idx); + /* Check again since dev might have changed */ + if (!netdev_need_ops_lock(dev)) + return -EOPNOTSUPP; + if (!dev->dev.parent) { + NL_SET_ERR_MSG(extack, "rx queue is mapped to a virtual netdev"); + return -EBUSY; + } if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); return -EINVAL; @@ -124,8 +132,6 @@ int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached"); return -EEXIST; } - - 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; @@ -136,7 +142,6 @@ int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, return -EBUSY; } #endif - rxq->mp_params = *p; ret = netdev_rx_queue_restart(dev, rxq_idx); if (ret) { @@ -166,7 +171,7 @@ void __net_mp_close_rxq(struct net_device *dev, unsigned int ifq_idx, if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues)) return; - rxq = __netif_get_rx_queue(dev, ifq_idx); + rxq = __netif_get_rx_queue_peer(&dev, &ifq_idx); /* Callers holding a netdev ref may get here after we already * went thru shutdown via dev_memory_provider_uninstall(). -- 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 --- 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 513c8e9704f6..47120666d8d6 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 Small refactor to move the pool registration into xsk_reg_pool_at_qid, such that the netdev and queue_id can be registered there. No change in functionality. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei --- net/xdp/xsk.c | 5 +++++ net/xdp/xsk_buff_pool.c | 16 +++------------- 2 files changed, 8 insertions(+), 13 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 72e34bd2d925..82ad89f6ba35 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -141,6 +141,11 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, dev->real_num_rx_queues, dev->real_num_tx_queues)) return -EINVAL; + if (xsk_get_pool_from_qid(dev, queue_id)) + return -EBUSY; + + pool->netdev = dev; + pool->queue_id = queue_id; if (queue_id < dev->real_num_rx_queues) dev->_rx[queue_id].pool = pool; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 26165baf99f4..375696f895d4 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -169,32 +169,24 @@ int xp_assign_dev(struct xsk_buff_pool *pool, force_zc = flags & XDP_ZEROCOPY; force_copy = flags & XDP_COPY; - if (force_zc && force_copy) return -EINVAL; - if (xsk_get_pool_from_qid(netdev, queue_id)) - return -EBUSY; - - pool->netdev = netdev; - pool->queue_id = queue_id; err = xsk_reg_pool_at_qid(netdev, pool, queue_id); if (err) return err; if (flags & XDP_USE_SG) pool->umem->flags |= XDP_UMEM_SG_FLAG; - if (flags & XDP_USE_NEED_WAKEUP) pool->uses_need_wakeup = true; - /* Tx needs to be explicitly woken up the first time. Also - * for supporting drivers that do not implement this - * feature. They will always have to call sendto() or poll(). + /* Tx needs to be explicitly woken up the first time. Also + * for supporting drivers that do not implement this feature. + * They will always have to call sendto() or poll(). */ pool->cached_need_wakeup = XDP_WAKEUP_TX; dev_hold(netdev); - if (force_copy) /* For copy-mode, we are done. */ return 0; @@ -203,12 +195,10 @@ int xp_assign_dev(struct xsk_buff_pool *pool, err = -EOPNOTSUPP; goto err_unreg_pool; } - if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) { err = -EOPNOTSUPP; goto err_unreg_pool; } - if (dev_get_min_mp_channel_count(netdev)) { err = -EBUSY; goto err_unreg_pool; -- 2.43.0 Add another small helper called xp_pool_bindable and move the current dev_get_min_mp_channel_count test into this helper. Pass in the pool object, such that we derive the netdev from the prior registered pool. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei --- net/xdp/xsk_buff_pool.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 375696f895d4..d2109d683fe5 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -54,6 +54,11 @@ int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) return 0; } +static bool xp_pool_bindable(struct xsk_buff_pool *pool) +{ + return dev_get_min_mp_channel_count(pool->netdev) == 0; +} + struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { @@ -199,7 +204,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, err = -EOPNOTSUPP; goto err_unreg_pool; } - if (dev_get_min_mp_channel_count(netdev)) { + if (!xp_pool_bindable(pool)) { err = -EBUSY; goto err_unreg_pool; } -- 2.43.0 Change the xsk_rcv_check test for inbound packets to use the xs->pool->netdev and xs->pool->queue_id of the bound socket rather than xs->dev and xs->queue_id since the latter could point to a virtual device with mapped rxq rather than the physical backing device of the pool. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei --- net/xdp/xsk.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 82ad89f6ba35..cf40c70ee59f 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -340,15 +340,13 @@ 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 (xs->pool->netdev != xdp->rxq->dev || + xs->pool->queue_id != xdp->rxq->queue_index) return -EINVAL; - if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) { xs->rx_dropped++; return -ENOSPC; } - return 0; } -- 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 such that when a virtual netdev picked a mapped rxq, the request gets through to the real rxq in the physical netdev. Change the function signatures for queue_id to unsigned int in order to pass the queue_id parameter into __netif_get_rx_queue_peer. 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 --- include/net/xdp_sock_drv.h | 4 ++-- net/xdp/xsk.c | 16 +++++++++++----- net/xdp/xsk.h | 5 ++--- 3 files changed, 15 insertions(+), 10 deletions(-) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 47120666d8d6..709af292cba7 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -29,7 +29,7 @@ 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, - u16 queue_id); + unsigned int queue_id); void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool); void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool); void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool); @@ -286,7 +286,7 @@ static inline void xsk_tx_release(struct xsk_buff_pool *pool) } static inline struct xsk_buff_pool * -xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) +xsk_get_pool_from_qid(struct net_device *dev, unsigned int queue_id) { return NULL; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cf40c70ee59f..b9efa6d8a112 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -23,6 +23,8 @@ #include #include #include + +#include #include #include #include @@ -111,19 +113,20 @@ bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) EXPORT_SYMBOL(xsk_uses_need_wakeup); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, - u16 queue_id) + unsigned int queue_id) { if (queue_id < dev->real_num_rx_queues) return dev->_rx[queue_id].pool; if (queue_id < dev->real_num_tx_queues) return dev->_tx[queue_id].pool; - return NULL; } EXPORT_SYMBOL(xsk_get_pool_from_qid); -void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) +void xsk_clear_pool_at_qid(struct net_device *dev, unsigned int queue_id) { + if (queue_id < dev->real_num_rx_queues) + __netif_get_rx_queue_peer(&dev, &queue_id); if (queue_id < dev->num_rx_queues) dev->_rx[queue_id].pool = NULL; if (queue_id < dev->num_tx_queues) @@ -135,7 +138,7 @@ void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) * This might also change during run time. */ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, - u16 queue_id) + unsigned int queue_id) { if (queue_id >= max_t(unsigned int, dev->real_num_rx_queues, @@ -143,6 +146,10 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, return -EINVAL; if (xsk_get_pool_from_qid(dev, queue_id)) return -EBUSY; + if (queue_id < dev->real_num_rx_queues) + __netif_get_rx_queue_peer(&dev, &queue_id); + if (xsk_get_pool_from_qid(dev, queue_id)) + return -EBUSY; pool->netdev = dev; pool->queue_id = queue_id; @@ -151,7 +158,6 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, dev->_rx[queue_id].pool = pool; if (queue_id < dev->real_num_tx_queues) dev->_tx[queue_id].pool = pool; - return 0; } diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index a4bc4749faac..54d9a7736fd2 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -41,8 +41,7 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock __rcu **map_entry); -void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); +void xsk_clear_pool_at_qid(struct net_device *dev, unsigned int queue_id); int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, - u16 queue_id); - + unsigned int queue_id); #endif /* XSK_H_ */ -- 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 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..ceb1393ee599 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_PAIR && + (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 45f56c9f95d9..4a2f781f3cca 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1294,6 +1294,11 @@ 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. @@ -1318,6 +1323,7 @@ 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 --- 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 ceb1393ee599..8f1285513d82 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 numrxqueues 2 type netkit As a starting point, the limit of numrxqueues for netkit is currently set to 2, but future work is going to allow mapping multiple real rxqs from physical netdevs, potentially at some point even from different physical netdevs. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- drivers/net/netkit.c | 78 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 72 insertions(+), 6 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 8f1285513d82..e5dfbf7ea351 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -9,11 +9,19 @@ #include #include +#include +#include #include #include #include -#define DRV_NAME "netkit" +#define NETKIT_DRV_NAME "netkit" + +#define NETKIT_NUM_TX_QUEUES_MAX 1 +#define NETKIT_NUM_RX_QUEUES_MAX 2 + +#define NETKIT_NUM_TX_QUEUES_REAL 1 +#define NETKIT_NUM_RX_QUEUES_REAL 1 struct netkit { __cacheline_group_begin(netkit_fastpath); @@ -37,6 +45,8 @@ 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) @@ -243,13 +253,69 @@ 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 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; + 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); + } +} + static void netkit_setup(struct net_device *dev) { static const netdev_features_t netkit_features_hw_vlan = @@ -330,8 +396,6 @@ 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 +929,7 @@ 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 +1070,9 @@ 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, @@ -1042,4 +1108,4 @@ 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 From: David Wei Implement ndo_queue_create() that adds a new rxq during the bind-queue ynl netdev 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. Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- drivers/net/netkit.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index e5dfbf7ea351..27ff84833f28 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -274,6 +274,34 @@ static const struct ethtool_ops netkit_ethtool_ops = { .get_channels = netkit_get_channels, }; +static int netkit_queue_create(struct net_device *dev) +{ + 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); + + return err ? err : rxq_count_new; +} + +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, @@ -346,8 +374,9 @@ 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; -- 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 numrxqueues 2 type netkit # ynl-bind eth0 15 nk0 # 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 dual-port Nvidia ConnectX-6 (mlx5) 100G NIC as well as Broadcom BCM957504 (bnxt_en) 100G NIC, both supporting TCP header/data split. For Cilium, the plan is to open up support for io_uring in zero-copy mode 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 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 27ff84833f28..5129b27a7c3c 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -274,6 +274,21 @@ 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) { struct netkit *nk = netkit_priv(dev); @@ -299,7 +314,8 @@ static int netkit_queue_create(struct net_device *dev) } 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 # ip netns add foo # ip link add numrxqueues 2 nk type netkit single # ynl-bind eth0 15 nk # 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]. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0] --- drivers/net/netkit.c | 121 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 5129b27a7c3c..a1d8a78bab0b 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -234,6 +235,122 @@ static void netkit_get_stats(struct net_device *dev, stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); } +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; + + 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 (!phys->netdev_ops->ndo_bpf || + !phys->netdev_ops->ndo_xdp_xmit || + !phys->netdev_ops->ndo_xsk_wakeup) + 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; + } + + return phys->netdev_ops->ndo_bpf(phys, &xdp_lower); +} + +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 (!phys->netdev_ops->ndo_xsk_wakeup) + return -EOPNOTSUPP; + + return phys->netdev_ops->ndo_xsk_wakeup(phys, + get_netdev_rx_queue_index(rxq->peer), flags); +} + +static bool netkit_xdp_supported(const struct net_device *dev) +{ + bool xdp_ok = IS_ENABLED(CONFIG_XDP_SOCKETS); + + if (!dev->netdev_ops->ndo_bpf || + !dev->netdev_ops->ndo_xdp_xmit || + !dev->netdev_ops->ndo_xsk_wakeup) + xdp_ok = false; + if ((dev->xdp_features & NETDEV_XDP_ACT_XSK) != NETDEV_XDP_ACT_XSK) + xdp_ok = false; + return xdp_ok; +} + +static void netkit_expose_xdp(struct net_device *dev, bool xdp_ok, + u32 xdp_zc_max_segs) +{ + if (xdp_ok) { + dev->xdp_zc_max_segs = xdp_zc_max_segs; + xdp_set_features_flag_locked(dev, NETDEV_XDP_ACT_XSK); + } else { + dev->xdp_zc_max_segs = 1; + xdp_set_features_flag_locked(dev, 0); + } +} + +static void netkit_calculate_xdp(struct net_device *dev, + struct netdev_rx_queue *rxq, bool skip_rxq) +{ + struct netdev_rx_queue *src_rxq, *dst_rxq; + struct net_device *src_dev; + u32 xdp_zc_max_segs = ~0; + bool xdp_ok = false; + int i; + + for (i = 1; i < dev->real_num_rx_queues; i++) { + dst_rxq = __netif_get_rx_queue(dev, i); + if (dst_rxq == rxq && skip_rxq) + continue; + src_rxq = dst_rxq->peer; + src_dev = src_rxq->dev; + xdp_zc_max_segs = min(xdp_zc_max_segs, src_dev->xdp_zc_max_segs); + xdp_ok = netkit_xdp_supported(src_dev) && + (i == 1 ? true : xdp_ok); + } + + netkit_expose_xdp(dev, xdp_ok, xdp_zc_max_segs); +} + +static void netkit_peer_queues(struct net_device *dev, + struct netdev_rx_queue *rxq) +{ + netkit_calculate_xdp(dev, rxq, false); +} + +static void netkit_unpeer_queues(struct net_device *dev, + struct netdev_rx_queue *rxq) +{ + netkit_calculate_xdp(dev, rxq, true); +} + static void netkit_uninit(struct net_device *dev); static const struct net_device_ops netkit_netdev_ops = { @@ -247,6 +364,10 @@ 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_peer_queues = netkit_peer_queues, + .ndo_unpeer_queues = netkit_unpeer_queues, + .ndo_bpf = netkit_xsk, + .ndo_xsk_wakeup = netkit_xsk_wakeup, .ndo_features_check = passthru_features_check, }; -- 2.43.0 From: David Wei Add a ynl sample application that calls bind-queue to bind a real rxq to a mapped rxq in a virtual netdev. # ethtool -X eth0 start 0 equal 15 # ethtool -X eth0 start 15 equal 1 context new # ethtool --config-ntuple eth0 flow-type [...] action 15 # ip link add numrxqueues 2 nk type netkit single # ethtool -l nk Channel parameters for nk: Pre-set maximums: RX: 2 TX: 1 Other: n/a Combined: 1 Current hardware settings: RX: 1 TX: 1 Other: n/a Combined: 0 # ip a 4: eth0: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff [...] 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 # ynl-bind eth0 15 nk bound eth0, queue 15 to nk, queue 1 # ethtool -l nk [...] Current hardware settings: RX: 2 TX: 1 Other: n/a Combined: 0 Signed-off-by: David Wei Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- tools/net/ynl/samples/bind.c | 56 ++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 tools/net/ynl/samples/bind.c diff --git a/tools/net/ynl/samples/bind.c b/tools/net/ynl/samples/bind.c new file mode 100644 index 000000000000..a6426121cbd4 --- /dev/null +++ b/tools/net/ynl/samples/bind.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +#include "netdev-user.h" + +int main(int argc, char **argv) +{ + struct netdev_bind_queue_req *req; + struct netdev_bind_queue_rsp *rsp; + char if_src[IF_NAMESIZE] = {}; + char if_dst[IF_NAMESIZE] = {}; + struct ynl_sock *ys; + struct ynl_error yerr; + int src_ifindex = 0, dst_ifindex = 0; + int src_queue_id = 0; + + if (argc > 1) + src_ifindex = if_nametoindex(argv[1]); + if (argc > 2) + src_queue_id = strtol(argv[2], NULL, 0); + if (argc > 3) + dst_ifindex = if_nametoindex(argv[3]); + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + req = netdev_bind_queue_req_alloc(); + netdev_bind_queue_req_set_src_ifindex(req, src_ifindex); + netdev_bind_queue_req_set_src_queue_id(req, src_queue_id); + netdev_bind_queue_req_set_dst_ifindex(req, dst_ifindex); + + rsp = netdev_bind_queue(ys, req); + netdev_bind_queue_req_free(req); + if (!rsp) + goto err; + + assert(rsp->_present.dst_queue_id); + printf("bound %s, queue %d to %s, queue %d\n", + if_indextoname(src_ifindex, if_src), src_queue_id, + if_indextoname(dst_ifindex, if_dst), rsp->dst_queue_id); + + netdev_bind_queue_rsp_free(rsp); + ynl_sock_destroy(ys); + return 0; +err: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} -- 2.43.0