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(-) 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