bonding: fix PACKET_ORIGDEV regression (3c963a33) · Commits · 戴 / test

This patch fixes a subtle PACKET_ORIGDEV regression which was a side effect of fixes introduced by: bonding: pass link-local packets to bonding master also. ... to: bonding: deliver link-local packets with skb->dev set to link that packets arrived on While restored pre- presence of link-local packets on bonding masters (which is required e.g. by linux bridges participating in spanning tree or needed for lab-like setups created with group_fwd_mask) it also caused the originating device information to be lost due to cloning. Maciej Żenczykowski proposed another solution that doesn't require packet cloning and retains original device information - instead of returning RX_HANDLER_PASS for all link-local packets it's now limited only to packets from inactive slaves. At the same time, packets passed to bonding masters retain correct information about the originating device and PACKET_ORIGDEV can be used to determine it. This elegantly solves all issues so far: - link-local packets that were removed from bonding masters - LLDP daemons being forced to explicitly bind to slave interfaces - PACKET_ORIGDEV having no effect on bond interfaces Fixes: (bonding: pass link-local packets to bonding master also.) Reported-by:

Vincent Bernat <vincent@bernat.ch> Signed-off-by:

Michal Soltys <soltys@ziu.info> Signed-off-by:

Maciej Żenczykowski <maze@google.com> Signed-off-by:

David S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_main.c

+14 −21

Original line number	Diff line number	Diff line
		@@ -1183,29 +1183,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
		}
		}

		/* Link-local multicast packets should be passed to the
		* stack on the link they arrive as well as pass them to the
		* bond-master device. These packets are mostly usable when
		* stack receives it with the link on which they arrive
		* (e.g. LLDP) they also must be available on master. Some of
		* the use cases include (but are not limited to): LLDP agents
		* that must be able to operate both on enslaved interfaces as
		* well as on bonds themselves; linux bridges that must be able
		* to process/pass BPDUs from attached bonds when any kind of
		* STP version is enabled on the network.
		/*
		* For packets determined by bond_should_deliver_exact_match() call to
		* be suppressed we want to make an exception for link-local packets.
		* This is necessary for e.g. LLDP daemons to be able to monitor
		* inactive slave links without being forced to bind to them
		* explicitly.
		*
		* At the same time, packets that are passed to the bonding master
		* (including link-local ones) can have their originating interface
		* determined via PACKET_ORIGDEV socket option.
		*/
		if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) {
		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);

		if (nskb) {
		nskb->dev = bond->dev;
		nskb->queue_mapping = 0;
		netif_rx(nskb);
		}
		if (bond_should_deliver_exact_match(skb, slave, bond)) {
		if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
		return RX_HANDLER_PASS;
		}
		if (bond_should_deliver_exact_match(skb, slave, bond))
		return RX_HANDLER_EXACT;
		}

		skb->dev = bond->dev;

Admin message