From d6fe532b7499e4575f9647879b7a34625817fe7f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:16 +0200 Subject: netkit: Fix setting mac address in l2 mode When running Cilium connectivity test suite with netkit in L2 mode, we found that it is expected to be able to specify a custom MAC address for the devices, in particular, cilium-cni obtains the specified MAC address by querying the endpoint and sets the MAC address of the interface inside the Pod. Thus, fix the missing support in netkit for L2 mode. Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device") Signed-off-by: Daniel Borkmann Acked-by: Nikolay Aleksandrov Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20240524163619.26001-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- drivers/net/netkit.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'drivers/net/netkit.c') diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index a4d2e76a8d58..272894053e2c 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -155,6 +155,16 @@ static void netkit_set_multicast(struct net_device *dev) /* Nothing to do, we receive whatever gets pushed to us! */ } +static int netkit_set_macaddr(struct net_device *dev, void *sa) +{ + struct netkit *nk = netkit_priv(dev); + + if (nk->mode != NETKIT_L2) + return -EOPNOTSUPP; + + return eth_mac_addr(dev, sa); +} + static void netkit_set_headroom(struct net_device *dev, int headroom) { struct netkit *nk = netkit_priv(dev), *nk2; @@ -198,6 +208,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_start_xmit = netkit_xmit, .ndo_set_rx_mode = netkit_set_multicast, .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_set_mac_address = netkit_set_macaddr, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, .ndo_get_stats64 = netkit_get_stats, @@ -300,9 +311,11 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], if (!attr) return 0; - NL_SET_ERR_MSG_ATTR(extack, attr, - "Setting Ethernet address is not supported"); - return -EOPNOTSUPP; + if (nla_len(attr) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(attr))) + return -EADDRNOTAVAIL; + return 0; } static struct rtnl_link_ops netkit_link_ops; @@ -365,6 +378,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, strscpy(ifname, "nk%d", IFNAMSIZ); ifname_assign_type = NET_NAME_ENUM; } + if (mode != NETKIT_L2 && + (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) + return -EOPNOTSUPP; net = rtnl_link_get_net(src_net, tbp); if (IS_ERR(net)) @@ -379,7 +395,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, netif_inherit_tso_max(peer, dev); - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) eth_hw_addr_random(peer); if (ifmp && dev->ifindex) peer->ifindex = ifmp->ifi_index; @@ -402,7 +418,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, if (err < 0) goto err_configure_peer; - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); -- cgit v1.2.3 From 3998d184267dfcff858aaa84d3de17429253629d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:17 +0200 Subject: netkit: Fix pkt_type override upon netkit pass verdict When running Cilium connectivity test suite with netkit in L2 mode, we found that compared to tcx a few tests were failing which pushed traffic into an L7 proxy sitting in host namespace. The problem in particular is around the invocation of eth_type_trans() in netkit. In case of tcx, this is run before the tcx ingress is triggered inside host namespace and thus if the BPF program uses the bpf_skb_change_type() helper the newly set type is retained. However, in case of netkit, the late eth_type_trans() invocation overrides the earlier decision from the BPF program which eventually leads to the test failure. Instead of eth_type_trans(), split out the relevant parts, meaning, reset of mac header and call to eth_skb_pkt_type() before the BPF program is run in order to have the same behavior as with tcx, and refactor a small helper called eth_skb_pull_mac() which is run in case it's passed up the stack where the mac header must be pulled. With this all connectivity tests pass. Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device") Signed-off-by: Daniel Borkmann Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240524163619.26001-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- drivers/net/netkit.c | 4 +++- include/linux/etherdevice.h | 8 ++++++++ net/ethernet/eth.c | 4 +--- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'drivers/net/netkit.c') diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 272894053e2c..16789cd446e9 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet) skb_scrub_packet(skb, xnet); skb->priority = 0; nf_skip_egress(skb, true); + skb_reset_mac_header(skb); } static struct netkit *netkit_priv(const struct net_device *dev) @@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + eth_skb_pkt_type(skb, peer); skb->dev = peer; entry = rcu_dereference(nk->active); if (entry) @@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case NETKIT_NEXT: case NETKIT_PASS: - skb->protocol = eth_type_trans(skb, skb->dev); + eth_skb_pull_mac(skb); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { dev_sw_netstats_tx_add(dev, 1, len); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad1ffa4ccb9..0ed47d00549b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 049c3adeb850..4e3651101b86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - + eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* -- cgit v1.2.3