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

Pull networking fixes from David Miller:

 1) Out of bounds access in xfrm IPSEC policy unlink, from Yue Haibing.

 2) Missing length check for esp4 UDP encap, from Sabrina Dubroca.

 3) Fix byte order of RX STBC access in mac80211, from Johannes Berg.

 4) Inifnite loop in bpftool map create, from Alban Crequy.

 5) Register mark fix in ebpf verifier after pkt/null checks, from Paul
    Chaignon.

 6) Properly use rcu_dereference_sk_user_data in L2TP code, from Eric
    Dumazet.

 7) Buffer overrun in marvell phy driver, from Andrew Lunn.

 8) Several crash and statistics handling fixes to bnxt_en driver, from
    Michael Chan and Vasundhara Volam.

 9) Several fixes to the TLS layer from Jakub Kicinski (copying negative
    amounts of data in reencrypt, reencrypt frag copying, blind nskb->sk
    NULL deref, etc).

10) Several UDP GRO fixes, from Paolo Abeni and Eric Dumazet.

11) PID/UID checks on ipv6 flow labels are inverted, from Willem de
    Bruijn.

12) Use after free in l2tp, from Eric Dumazet.

13) IPV6 route destroy races, also from Eric Dumazet.

14) SCTP state machine can erroneously run recursively, fix from Xin
    Long.

15) Adjust AF_PACKET msg_name length checks, add padding bytes if
    necessary. From Willem de Bruijn.

16) Preserve skb_iif, so that forwarded packets have consistent values
    even if fragmentation is involved. From Shmulik Ladkani.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (69 commits)
  udp: fix GRO packet of death
  ipv6: A few fixes on dereferencing rt->from
  rds: ib: force endiannes annotation
  selftests: fib_rule_tests: print the result and return 1 if any tests failed
  ipv4: ip_do_fragment: Preserve skb_iif during fragmentation
  net/tls: avoid NULL pointer deref on nskb->sk in fallback
  selftests: fib_rule_tests: Fix icmp proto with ipv6
  packet: validate msg_namelen in send directly
  packet: in recvmsg msg_name return at least sizeof sockaddr_ll
  sctp: avoid running the sctp state machine recursively
  stmmac: pci: Fix typo in IOT2000 comment
  Documentation: fix netdev-FAQ.rst markup warning
  ipv6: fix races in ip6_dst_destroy()
  l2ip: fix possible use-after-free
  appletalk: Set error code if register_snap_client failed
  net: dsa: bcm_sf2: fix buffer overflow doing set_rxnfc
  rxrpc: Fix net namespace cleanup
  ipv6/flowlabel: wait rcu grace period before put_pid()
  vrf: Use orig netdev to count Ip6InNoRoutes and a fresh route lookup when sending dest unreach
  tcp: add sanity tests in tcp_add_backlog()
  ...

5 files changed, 62 insertions, 48 deletions

diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d46b4eb645c2..cb99f6fb79b7 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -74,13 +74,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 			goto out;
 
 		if (sp->len == XFRM_MAX_DEPTH)
-			goto out;
+			goto out_reset;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET6);
 		if (!x)
-			goto out;
+			goto out_reset;
 
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
@@ -88,7 +88,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		xo = xfrm_offload(skb);
 		if (!xo) {
 			xfrm_state_put(x);
-			goto out;
+			goto out_reset;
 		}
 	}
 
@@ -109,6 +109,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 	xfrm_input(skb, IPPROTO_ESP, spi, -2);
 
 	return ERR_PTR(-EINPROGRESS);
+out_reset:
+	secpath_reset(skb);
 out:
 	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6613d8dbb0e5..91247a6fc67f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -921,9 +921,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		if (pcpu_rt) {
 			struct fib6_info *from;
 
-			from = rcu_dereference_protected(pcpu_rt->from,
-					     lockdep_is_held(&table->tb6_lock));
-			rcu_assign_pointer(pcpu_rt->from, NULL);
+			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
 			fib6_info_release(from);
 		}
 	}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cb54a8a3c273..be5f3d7ceb96 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
 	return fl;
 }
 
+static void fl_free_rcu(struct rcu_head *head)
+{
+	struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+	if (fl->share == IPV6_FL_S_PROCESS)
+		put_pid(fl->owner.pid);
+	kfree(fl->opt);
+	kfree(fl);
+}
+
 
 static void fl_free(struct ip6_flowlabel *fl)
 {
-	if (fl) {
-		if (fl->share == IPV6_FL_S_PROCESS)
-			put_pid(fl->owner.pid);
-		kfree(fl->opt);
-		kfree_rcu(fl, rcu);
-	}
+	if (fl)
+		call_rcu(&fl->rcu, fl_free_rcu);
 }
 
 static void fl_release(struct ip6_flowlabel *fl)
@@ -633,9 +639,9 @@ recheck:
 				if (fl1->share == IPV6_FL_S_EXCL ||
 				    fl1->share != fl->share ||
 				    ((fl1->share == IPV6_FL_S_PROCESS) &&
-				     (fl1->owner.pid == fl->owner.pid)) ||
+				     (fl1->owner.pid != fl->owner.pid)) ||
 				    ((fl1->share == IPV6_FL_S_USER) &&
-				     uid_eq(fl1->owner.uid, fl->owner.uid)))
+				     !uid_eq(fl1->owner.uid, fl->owner.uid)))
 					goto release;
 
 				err = -ENOMEM;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7178e32eb15d..0520aca3354b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -379,11 +379,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	rcu_read_lock();
-	from = rcu_dereference(rt->from);
-	rcu_assign_pointer(rt->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt->from, NULL);
 	fib6_info_release(from);
-	rcu_read_unlock();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1288,9 +1285,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = rcu_dereference_protected(rt6_ex->rt6i->from,
-					 lockdep_is_held(&rt6_exception_lock));
-	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
@@ -3397,11 +3392,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-	/* This fib6_info_hold() is safe here because we hold reference to rt
-	 * and rt already holds reference to fib6_info.
-	 */
-	fib6_info_hold(from);
-	rcu_read_unlock();
+	if (!from)
+		goto out;
 
 	nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
 	if (!nrt)
@@ -3413,10 +3405,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	/* No need to remove rt from the exception table if rt is
-	 * a cached route because rt6_insert_exception() will
-	 * takes care of it
-	 */
+	/* rt6_insert_exception() will take care of duplicated exceptions */
 	if (rt6_insert_exception(nrt, from)) {
 		dst_release_immediate(&nrt->dst);
 		goto out;
@@ -3429,7 +3418,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
 out:
-	fib6_info_release(from);
+	rcu_read_unlock();
 	neigh_release(neigh);
 }
 
@@ -3668,23 +3657,34 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
 {
-	int type;
 	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(dst->dev);
+	struct inet6_dev *idev;
+	int type;
+
+	if (netif_is_l3_master(skb->dev) &&
+	    dst->dev == net->loopback_dev)
+		idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+	else
+		idev = ip6_dst_idev(dst);
+
 	switch (ipstats_mib_noroutes) {
 	case IPSTATS_MIB_INNOROUTES:
 		type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
 		if (type == IPV6_ADDR_ANY) {
-			IP6_INC_STATS(dev_net(dst->dev),
-				      __in6_dev_get_safely(skb->dev),
-				      IPSTATS_MIB_INADDRERRORS);
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
 			break;
 		}
 		/* FALLTHROUGH */
 	case IPSTATS_MIB_OUTNOROUTES:
-		IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
-			      ipstats_mib_noroutes);
+		IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
 		break;
 	}
+
+	/* Start over by dropping the dst for l3mdev case */
+	if (netif_is_l3_master(skb->dev))
+		skb_dst_drop(skb);
+
 	icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
 	kfree_skb(skb);
 	return 0;
@@ -5017,16 +5017,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-
-	if (fibmatch)
-		err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
-				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-				    nlh->nlmsg_seq, 0);
-	else
-		err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
-				    &fl6.saddr, iif, RTM_NEWROUTE,
-				    NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-				    0);
+	if (from) {
+		if (fibmatch)
+			err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+					    iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+		else
+			err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+					    &fl6.saddr, iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+	} else {
+		err = -ENETUNREACH;
+	}
 	rcu_read_unlock();
 
 	if (err < 0) {
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index bc65db782bfb..d9e5f6808811 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -345,7 +345,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
 	unsigned int i;
 
 	xfrm_flush_gc();
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+	xfrm_state_flush(net, 0, false, true);
 
 	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
 		WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
@@ -402,6 +402,10 @@ static void __exit xfrm6_tunnel_fini(void)
 	xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
 	xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
 	unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+	/* Someone maybe has gotten the xfrm6_tunnel_spi.
+	 * So need to wait it.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
 }