bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup

The bpf_fib_lookup() also looks up the neigh table.
This was done before bpf_redirect_neigh() was added.

In the use case that does not manage the neigh table
and requires bpf_fib_lookup() to lookup a fib to
decide if it needs to redirect or not, the bpf prog can
depend only on using bpf_redirect_neigh() to lookup the
neigh. It also keeps the neigh entries fresh and connected.

This patch adds a bpf_fib_lookup flag, SKIP_NEIGH, to avoid
the double neigh lookup when the bpf prog always call
bpf_redirect_neigh() to do the neigh lookup. The params->smac
output is skipped together when SKIP_NEIGH is set because
bpf_redirect_neigh() will figure out the smac also.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230217205515.3583372-1-martin.lau@linux.dev

Author: Martin KaFai Lau

include/uapi/linux/bpf.h

@@ -3134,6 +3134,11 @@ union bpf_attr {
  *		**BPF_FIB_LOOKUP_OUTPUT**
  *			Perform lookup from an egress perspective (default is
  *			ingress).
+ *		**BPF_FIB_LOOKUP_SKIP_NEIGH**
+ *			Skip the neighbour table lookup. *params*->dmac
+ *			and *params*->smac will not be set as output. A common
+ *			use case is to call **bpf_redirect_neigh**\ () after
+ *			doing **bpf_fib_lookup**\ ().
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -6750,6 +6755,7 @@ struct bpf_raw_tracepoint_args {
 enum {
 	BPF_FIB_LOOKUP_DIRECT  = (1U << 0),
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
+	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 };
 
 enum {

net/core/filter.c

@@ -5722,12 +5722,8 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
 #endif
 
 #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
-static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
-				  const struct neighbour *neigh,
-				  const struct net_device *dev, u32 mtu)
+static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu)
 {
-	memcpy(params->dmac, neigh->ha, ETH_ALEN);
-	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
 	if (mtu)
@@ -5838,21 +5834,29 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (likely(nhc->nhc_gw_family != AF_INET6)) {
 		if (nhc->nhc_gw_family)
 			params->ipv4_dst = nhc->nhc_gw.ipv4;
-
-		neigh = __ipv4_neigh_lookup_noref(dev,
-						 (__force u32)params->ipv4_dst);
 	} else {
 		struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst;
 
 		params->family = AF_INET6;
 		*dst = nhc->nhc_gw.ipv6;
-		neigh = __ipv6_neigh_lookup_noref_stub(dev, dst);
 	}
 
+	if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH)
+		goto set_fwd_params;
+
+	if (likely(nhc->nhc_gw_family != AF_INET6))
+		neigh = __ipv4_neigh_lookup_noref(dev,
+						  (__force u32)params->ipv4_dst);
+	else
+		neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst);
+
 	if (!neigh || !(neigh->nud_state & NUD_VALID))
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
+	memcpy(params->dmac, neigh->ha, ETH_ALEN);
+	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 
-	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
+set_fwd_params:
+	return bpf_fib_set_fwd_params(params, mtu);
 }
 #endif
 
@@ -5960,24 +5964,33 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	params->rt_metric = res.f6i->fib6_metric;
 	params->ifindex = dev->ifindex;
 
+	if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH)
+		goto set_fwd_params;
+
 	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
 	 * not needed here.
 	 */
 	neigh = __ipv6_neigh_lookup_noref_stub(dev, dst);
 	if (!neigh || !(neigh->nud_state & NUD_VALID))
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
+	memcpy(params->dmac, neigh->ha, ETH_ALEN);
+	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 
-	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
+set_fwd_params:
+	return bpf_fib_set_fwd_params(params, mtu);
 }
 #endif
 
+#define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
+			     BPF_FIB_LOOKUP_SKIP_NEIGH)
+
 BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
 {
 	if (plen < sizeof(*params))
 		return -EINVAL;
 
-	if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT))
+	if (flags & ~BPF_FIB_LOOKUP_MASK)
 		return -EINVAL;
 
 	switch (params->family) {
@@ -6015,7 +6028,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	if (plen < sizeof(*params))
 		return -EINVAL;
 
-	if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT))
+	if (flags & ~BPF_FIB_LOOKUP_MASK)
 		return -EINVAL;
 
 	if (params->tot_len)

tools/include/uapi/linux/bpf.h

@@ -3134,6 +3134,11 @@ union bpf_attr {
  *		**BPF_FIB_LOOKUP_OUTPUT**
  *			Perform lookup from an egress perspective (default is
  *			ingress).
+ *		**BPF_FIB_LOOKUP_SKIP_NEIGH**
+ *			Skip the neighbour table lookup. *params*->dmac
+ *			and *params*->smac will not be set as output. A common
+ *			use case is to call **bpf_redirect_neigh**\ () after
+ *			doing **bpf_fib_lookup**\ ().
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -6750,6 +6755,7 @@ struct bpf_raw_tracepoint_args {
 enum {
 	BPF_FIB_LOOKUP_DIRECT  = (1U << 0),
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
+	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 };
 
 enum {