[bpf-next,V16,3/7] bpf: bpf_fib_lookup return MTU value as output when looked up

Message ID 161287789952.790810.13134700381067698781.stgit@firesoul
State New
Headers show
Series
  • [bpf-next,V16,1/7] bpf: Remove MTU check in __bpf_skb_max_len
Related show

Commit Message

Jesper Dangaard Brouer Feb. 9, 2021, 1:38 p.m.
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>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
 include/uapi/linux/bpf.h       |   11 +++++++++--
 net/core/filter.c              |   22 +++++++++++++++-------
 tools/include/uapi/linux/bpf.h |   11 +++++++++--
 3 files changed, 33 insertions(+), 11 deletions(-)

Patch

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c001766adcbc..05bfc8c843dc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2231,6 +2231,9 @@  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.
@@ -4981,9 +4984,13 @@  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
 	 */
diff --git a/net/core/filter.c b/net/core/filter.c
index 46b06a693e39..80c523b9cd87 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5289,12 +5289,14 @@  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;
 }
@@ -5310,8 +5312,8 @@  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))
@@ -5378,8 +5380,10 @@  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;
@@ -5413,7 +5417,7 @@  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
 
@@ -5430,7 +5434,7 @@  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))
@@ -5505,8 +5509,10 @@  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)
@@ -5526,7 +5532,7 @@  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
 
@@ -5602,6 +5608,8 @@  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;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c001766adcbc..05bfc8c843dc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2231,6 +2231,9 @@  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.
@@ -4981,9 +4984,13 @@  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
 	 */