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

Pull networking fixes from David Miller:
 "A little more than usual this time around. Been travelling, so that is
  part of it.

  Anyways, here are the highlights:

   1) Deal with memcontrol races wrt. listener dismantle, from Eric
      Dumazet.

   2) Handle page allocation failures properly in nfp driver, from Jaku
      Kicinski.

   3) Fix memory leaks in macsec, from Sabrina Dubroca.

   4) Fix crashes in pppol2tp_session_ioctl(), from Guillaume Nault.

   5) Several fixes in bnxt_en driver, including preventing potential
      NVRAM parameter corruption from Michael Chan.

   6) Fix for KRACK attacks in wireless, from Johannes Berg.

   7) rtnetlink event generation fixes from Xin Long.

   8) Deadlock in mlxsw driver, from Ido Schimmel.

   9) Disallow arithmetic operations on context pointers in bpf, from
      Jakub Kicinski.

  10) Missing sock_owned_by_user() check in sctp_icmp_redirect(), from
      Xin Long.

  11) Only TCP is supported for sockmap, make that explicit with a
      check, from John Fastabend.

  12) Fix IP options state races in DCCP and TCP, from Eric Dumazet.

  13) Fix panic in packet_getsockopt(), also from Eric Dumazet.

  14) Add missing locked in hv_sock layer, from Dexuan Cui.

  15) Various aquantia bug fixes, including several statistics handling
      cures. From Igor Russkikh et al.

  16) Fix arithmetic overflow in devmap code, from John Fastabend.

  17) Fix busted socket memory accounting when we get a fault in the tcp
      zero copy paths. From Willem de Bruijn.

  18) Don't leave opt->tot_len uninitialized in ipv6, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
  stmmac: Don't access tx_q->dirty_tx before netif_tx_lock
  ipv6: flowlabel: do not leave opt->tot_len with garbage
  of_mdio: Fix broken PHY IRQ in case of probe deferral
  textsearch: fix typos in library helpers
  rxrpc: Don't release call mutex on error pointer
  net: stmmac: Prevent infinite loop in get_rx_timestamp_status()
  net: stmmac: Fix stmmac_get_rx_hwtstamp()
  net: stmmac: Add missing call to dev_kfree_skb()
  mlxsw: spectrum_router: Configure TIGCR on init
  mlxsw: reg: Add Tunneling IPinIP General Configuration Register
  net: ethtool: remove error check for legacy setting transceiver type
  soreuseport: fix initialization race
  net: bridge: fix returning of vlan range op errors
  sock: correct sk_wmem_queued accounting on efault in tcp zerocopy
  bpf: add test cases to bpf selftests to cover all access tests
  bpf: fix pattern matches for direct packet access
  bpf: fix off by one for range markings with L{T, E} patterns
  bpf: devmap fix arithmetic overflow in bitmap_size calculation
  net: aquantia: Bad udp rate on default interrupt coalescing
  net: aquantia: Enable coalescing management via ethtool interface
  ...

8 files changed, 33 insertions, 48 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 91a2557942fa..f48fe6fc7e8c 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -70,11 +70,9 @@ config IP_MULTIPLE_TABLES
 	  address into account. Furthermore, the TOS (Type-Of-Service) field
 	  of the packet can be used for routing decisions as well.
 
-	  If you are interested in this, please see the preliminary
-	  documentation at <http://www.compendium.com.ar/policy-routing.txt>
-	  and <ftp://post.tepkom.ru/pub/vol2/Linux/docs/advanced-routing.tex>.
-	  You will need supporting software from
-	  <ftp://ftp.tux.org/pub/net/ip-routing/>.
+	  If you need more information, see the Linux Advanced
+	  Routing and Traffic Control documentation at
+	  <http://lartc.org/howto/lartc.rpdb.html>
 
 	  If unsure, say N.
 
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 2ae8f54cb321..82178cc69c96 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1951,7 +1951,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
-	opt = xchg(&req_inet->opt, opt);
+	opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt);
 	if (opt)
 		kfree_rcu(opt, rcu);
 
@@ -1973,11 +1973,13 @@ req_setattr_failure:
  * values on failure.
  *
  */
-static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
+static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr)
 {
+	struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1);
 	int hdr_delta = 0;
-	struct ip_options_rcu *opt = *opt_ptr;
 
+	if (!opt || opt->opt.cipso == 0)
+		return 0;
 	if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) {
 		u8 cipso_len;
 		u8 cipso_off;
@@ -2039,14 +2041,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
  */
 void cipso_v4_sock_delattr(struct sock *sk)
 {
-	int hdr_delta;
-	struct ip_options_rcu *opt;
 	struct inet_sock *sk_inet;
+	int hdr_delta;
 
 	sk_inet = inet_sk(sk);
-	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
-	if (!opt || opt->opt.cipso == 0)
-		return;
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
 	if (sk_inet->is_icsk && hdr_delta > 0) {
@@ -2066,15 +2064,7 @@ void cipso_v4_sock_delattr(struct sock *sk)
  */
 void cipso_v4_req_delattr(struct request_sock *req)
 {
-	struct ip_options_rcu *opt;
-	struct inet_request_sock *req_inet;
-
-	req_inet = inet_rsk(req);
-	opt = req_inet->opt;
-	if (!opt || opt->opt.cipso == 0)
-		return;
-
-	cipso_v4_delopt(&req_inet->opt);
+	cipso_v4_delopt(&inet_rsk(req)->ireq_opt);
 }
 
 /**
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c039c937ba90..5ec9136a7c36 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -475,6 +475,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
+	mem_cgroup_sk_alloc(newsk);
 out:
 	release_sock(sk);
 	if (req)
@@ -539,9 +540,10 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct net *net = read_pnet(&ireq->ireq_net);
-	struct ip_options_rcu *opt = ireq->opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -575,10 +577,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	fl4 = &newinet->cork.fl.u.ip4;
 
-	rcu_read_lock();
-	opt = rcu_dereference(newinet->inet_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -591,13 +592,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
-	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
-	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 597bb4cfe805..e7d15fb0d94d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -456,10 +456,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
 			return reuseport_add_sock(sk, sk2);
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b1bb1b3a1082..77cf32a80952 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	ireq->opt = tcp_v4_save_options(sock_net(sk), skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5d7656beeee..7eec3383702b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6196,7 +6196,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
 		struct inet_request_sock *ireq = inet_rsk(req);
 
 		kmemcheck_annotate_bitfield(ireq, flags);
-		ireq->opt = NULL;
+		ireq->ireq_opt = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
 		ireq->pktopts = NULL;
 #endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 85164d4d3e53..4c43365c374c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    rcu_dereference(ireq->ireq_opt));
 		err = net_xmit_eval(err);
 	}
 
@@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req,
 			    struct sk_buff *skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
+	struct net *net = sock_net(sk_listener);
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newsk->sk_bound_dev_if = ireq->ir_iif;
-	newinet->inet_saddr	      = ireq->ir_loc_addr;
-	inet_opt	      = ireq->opt;
-	rcu_assign_pointer(newinet->inet_opt, inet_opt);
-	ireq->opt	      = NULL;
+	newinet->inet_saddr   = ireq->ir_loc_addr;
+	inet_opt	      = rcu_dereference(ireq->ireq_opt);
+	RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-	if (*own_req)
+	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
-
+		ireq->ireq_opt = NULL;
+	} else {
+		newinet->inet_opt = NULL;
+	}
 	return newsk;
 
 exit_overflow:
@@ -1416,6 +1419,7 @@ exit:
 	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e45177ceb0ee..ebfbccae62fd 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 		}
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 /**
@@ -1061,7 +1058,7 @@ back_from_confirm:
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		net_dbg_ratelimited("cork app bug 2\n");
+		net_dbg_ratelimited("socket already corked\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1144,7 +1141,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	if (unlikely(!up->pending)) {
 		release_sock(sk);
 
-		net_dbg_ratelimited("udp cork app bug 3\n");
+		net_dbg_ratelimited("cork failed\n");
 		return -EINVAL;
 	}