bpf, netkit: Add indirect call wrapper for fetching peer dev

ndo_get_peer_dev is used in tcx BPF fast path, therefore make use of
indirect call wrapper and therefore optimize the bpf_redirect_peer()
internal handling a bit. Add a small skb_get_peer_dev() wrapper which
utilizes the INDIRECT_CALL_1() macro instead of open coding.

Future work could potentially add a peer pointer directly into struct
net_device in future and convert veth and netkit over to use it so
that eventually ndo_get_peer_dev can be removed.

Co-developed-by: Nikolay Aleksandrov <[e-mail]>
Signed-off-by: Nikolay Aleksandrov <[e-mail]>
Signed-off-by: Daniel Borkmann <[e-mail]>
Acked-by: Stanislav Fomichev <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Martin KaFai Lau <[e-mail]>

drivers/net/netkit.c

···
 #include <linux/filter.h>
 #include <linux/netfilter_netdev.h>
 #include <linux/bpf_mprog.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/netkit.h>
 #include <net/dst.h>
···
 	rcu_read_unlock();
 }
 
-static struct net_device *netkit_peer_dev(struct net_device *dev)
+INDIRECT_CALLABLE_SCOPE struct net_device *netkit_peer_dev(struct net_device *dev)
 {
 	return rcu_dereference(netkit_priv(dev)->peer);
 }

include/net/netkit.h

···
 int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
+INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev));
 #else
 static inline int netkit_prog_attach(const union bpf_attr *attr,
 				     struct bpf_prog *prog)
···
 				    union bpf_attr __user *uattr)
 {
 	return -EINVAL;
+}
+
+static inline struct net_device *netkit_peer_dev(struct net_device *dev)
+{
+	return NULL;
 }
 #endif /* CONFIG_NETKIT */
 #endif /* __NET_NETKIT_H */

net/core/filter.c

···
 #include <net/xdp.h>
 #include <net/mptcp.h>
 #include <net/netfilter/nf_conntrack_bpf.h>
+#include <net/netkit.h>
 #include <linux/un.h>
 
 #include "dev.h"
···
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
+static struct net_device *skb_get_peer_dev(struct net_device *dev)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (likely(ops->ndo_get_peer_dev))
+		return INDIRECT_CALL_1(ops->ndo_get_peer_dev,
+				       netkit_peer_dev, dev);
+	return NULL;
+}
+
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
···
 	if (unlikely(!dev))
 		goto out_drop;
 	if (flags & BPF_F_PEER) {
-		const struct net_device_ops *ops = dev->netdev_ops;
-
-		if (unlikely(!ops->ndo_get_peer_dev ||
-			     !skb_at_tc_ingress(skb)))
+		if (unlikely(!skb_at_tc_ingress(skb)))
 			goto out_drop;
-		dev = ops->ndo_get_peer_dev(dev);
+		dev = skb_get_peer_dev(dev);
 		if (unlikely(!dev ||
 			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))