Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:
 "Another week, another set of bug fixes:

   1) Fix pskb_pull length in __xfrm_transport_prep(), from Xin Long.

   2) Fix double xfrm_state put in esp{4,6}_gro_receive(), also from Xin
      Long.

   3) Re-arm discovery timer properly in mac80211 mesh code, from Linus
      Lüssing.

   4) Prevent buffer overflows in nf_conntrack_pptp debug code, from
      Pablo Neira Ayuso.

   5) Fix race in ktls code between tls_sw_recvmsg() and
      tls_decrypt_done(), from Vinay Kumar Yadav.

   6) Fix crashes on TCP fallback in MPTCP code, from Paolo Abeni.

   7) More validation is necessary of untrusted GSO packets coming from
      virtualization devices, from Willem de Bruijn.

   8) Fix endianness of bnxt_en firmware message length accesses, from
      Edwin Peer.

   9) Fix infinite loop in sch_fq_pie, from Davide Caratti.

  10) Fix lockdep splat in DSA by setting lockless TX in netdev features
      for slave ports, from Vladimir Oltean.

  11) Fix suspend/resume crashes in mlx5, from Mark Bloch.

  12) Fix use after free in bpf fmod_ret, from Alexei Starovoitov.

  13) ARP retransmit timer guard uses wrong offset, from Hongbin Liu.

  14) Fix leak in inetdev_init(), from Yang Yingliang.

  15) Don't try to use inet hash and unhash in l2tp code, results in
      crashes. From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (77 commits)
  l2tp: add sk_family checks to l2tp_validate_socket
  l2tp: do not use inet_hash()/inet_unhash()
  net: qrtr: Allocate workqueue before kernel_bind
  mptcp: remove msk from the token container at destruction time.
  mptcp: fix race between MP_JOIN and close
  mptcp: fix unblocking connect()
  net/sched: act_ct: add nat mangle action only for NAT-conntrack
  devinet: fix memleak in inetdev_init()
  virtio_vsock: Fix race condition in virtio_transport_recv_pkt
  drivers/net/ibmvnic: Update VNIC protocol version reporting
  NFC: st21nfca: add missed kfree_skb() in an error path
  neigh: fix ARP retransmit timer guard
  bpf, selftests: Add a verifier test for assigning 32bit reg states to 64bit ones
  bpf, selftests: Verifier bounds tests need to be updated
  bpf: Fix a verifier issue when assigning 32bit reg states to 64bit ones
  bpf: Fix use-after-free in fmod_ret check
  net/mlx5e: replace EINVAL in mlx5e_flower_parse_meta()
  net/mlx5e: Fix MLX5_TC_CT dependencies
  net/mlx5e: Properly set default values when disabling adaptive moderation
  net/mlx5e: Fix arch depending casting issue in FEC
  ...

1 files changed, 36 insertions, 15 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 4f334b425538..248f1c1959a6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1371,6 +1371,26 @@ static inline t_key prefix_mismatch(t_key key, struct key_vector *n)
 	return (key ^ prefix) & (prefix | -prefix);
 }
 
+bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags,
+			 const struct flowi4 *flp)
+{
+	if (nhc->nhc_flags & RTNH_F_DEAD)
+		return false;
+
+	if (ip_ignore_linkdown(nhc->nhc_dev) &&
+	    nhc->nhc_flags & RTNH_F_LINKDOWN &&
+	    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
+		return false;
+
+	if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
+		if (flp->flowi4_oif &&
+		    flp->flowi4_oif != nhc->nhc_oif)
+			return false;
+	}
+
+	return true;
+}
+
 /* should be called with rcu_read_lock */
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags)
@@ -1503,6 +1523,7 @@ found:
 	/* Step 3: Process the leaf, if that fails fall back to backtracing */
 	hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) {
 		struct fib_info *fi = fa->fa_info;
+		struct fib_nh_common *nhc;
 		int nhsel, err;
 
 		if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
@@ -1528,26 +1549,25 @@ out_reject:
 		if (fi->fib_flags & RTNH_F_DEAD)
 			continue;
 
-		if (unlikely(fi->nh && nexthop_is_blackhole(fi->nh))) {
-			err = fib_props[RTN_BLACKHOLE].error;
-			goto out_reject;
+		if (unlikely(fi->nh)) {
+			if (nexthop_is_blackhole(fi->nh)) {
+				err = fib_props[RTN_BLACKHOLE].error;
+				goto out_reject;
+			}
+
+			nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp,
+						     &nhsel);
+			if (nhc)
+				goto set_result;
+			goto miss;
 		}
 
 		for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) {
-			struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel);
+			nhc = fib_info_nhc(fi, nhsel);
 
-			if (nhc->nhc_flags & RTNH_F_DEAD)
+			if (!fib_lookup_good_nhc(nhc, fib_flags, flp))
 				continue;
-			if (ip_ignore_linkdown(nhc->nhc_dev) &&
-			    nhc->nhc_flags & RTNH_F_LINKDOWN &&
-			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
-				continue;
-			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
-				if (flp->flowi4_oif &&
-				    flp->flowi4_oif != nhc->nhc_oif)
-					continue;
-			}
-
+set_result:
 			if (!(fib_flags & FIB_LOOKUP_NOREF))
 				refcount_inc(&fi->fib_clntref);
 
@@ -1568,6 +1588,7 @@ out_reject:
 			return err;
 		}
 	}
+miss:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 	this_cpu_inc(stats->semantic_match_miss);
 #endif