bpf: bpf_fib_lookup return MTU value as output when looked up

The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup)
can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog
don't know the MTU value that caused this rejection.

If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it
need to know this MTU value for the ICMP packet.

Patch change lookup and result struct bpf_fib_lookup, to contain this MTU
value as output via a union with 'tot_len' as this is the value used for
the MTU lookup.

V5:
 - Fixed uninit value spotted by Dan Carpenter.
 - Name struct output member mtu_result
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287789952.790810.13134700381067698781.stgit@firesoul

include/uapi/linux/bpf.h

@@ -2239,6 +2239,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and output params->mtu_result contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -4990,9 +4993,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */

net/core/filter.c

@@ -5301,12 +5301,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
 #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)
+				  const struct net_device *dev, 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)
+		params->mtu_result = mtu; /* union with tot_len */
 
 	return 0;
 }
@@ -5322,8 +5324,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct net_device *dev;
 	struct fib_result res;
 	struct flowi4 fl4;
+	u32 mtu = 0;
 	int err;
-	u32 mtu;
 
 	dev = dev_get_by_index_rcu(net, params->ifindex);
 	if (unlikely(!dev))
@@ -5390,8 +5392,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	if (check_mtu) {
 		mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
-		if (params->tot_len > mtu)
+		if (params->tot_len > mtu) {
+			params->mtu_result = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	nhc = res.nhc;
@@ -5425,7 +5429,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return bpf_fib_set_fwd_params(params, neigh, dev);
+	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
 }
 #endif
 
@@ -5442,7 +5446,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct flowi6 fl6;
 	int strict = 0;
 	int oif, err;
-	u32 mtu;
+	u32 mtu = 0;
 
 	/* link local addresses are never forwarded */
 	if (rt6_need_strict(dst) || rt6_need_strict(src))
@@ -5517,8 +5521,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	if (check_mtu) {
 		mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
-		if (params->tot_len > mtu)
+		if (params->tot_len > mtu) {
+			params->mtu_result = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	if (res.nh->fib_nh_lws)
@@ -5538,7 +5544,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return bpf_fib_set_fwd_params(params, neigh, dev);
+	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
 }
 #endif
 
@@ -5614,6 +5620,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
 			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
+
+		params->mtu_result = dev->mtu; /* union with tot_len */
 	}
 
 	return rc;

tools/include/uapi/linux/bpf.h

@@ -2239,6 +2239,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and output params->mtu_result contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -4990,9 +4993,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */