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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 114 insertions, 48 deletions

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 7fb59c3f1542..a2ad4482376f 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -38,9 +38,6 @@ MODULE_PARM_DESC(debug, "RxRPC debugging mask");
 static struct proto rxrpc_proto;
 static const struct proto_ops rxrpc_rpc_ops;
 
-/* local epoch for detecting local-end reset */
-u32 rxrpc_epoch;
-
 /* current debugging ID */
 atomic_t rxrpc_debug_id;
 
@@ -56,7 +53,7 @@ static void rxrpc_sock_destructor(struct sock *);
  */
 static inline int rxrpc_writable(struct sock *sk)
 {
-	return atomic_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf;
+	return refcount_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf;
 }
 
 /*
@@ -134,9 +131,8 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx,
 static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 {
 	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr;
-	struct sock *sk = sock->sk;
 	struct rxrpc_local *local;
-	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	u16 service_id = srx->srx_service;
 	int ret;
 
@@ -148,31 +144,48 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 
 	lock_sock(&rx->sk);
 
-	if (rx->sk.sk_state != RXRPC_UNBOUND) {
-		ret = -EINVAL;
-		goto error_unlock;
-	}
-
-	memcpy(&rx->srx, srx, sizeof(rx->srx));
+	switch (rx->sk.sk_state) {
+	case RXRPC_UNBOUND:
+		rx->srx = *srx;
+		local = rxrpc_lookup_local(sock_net(&rx->sk), &rx->srx);
+		if (IS_ERR(local)) {
+			ret = PTR_ERR(local);
+			goto error_unlock;
+		}
 
-	local = rxrpc_lookup_local(&rx->srx);
-	if (IS_ERR(local)) {
-		ret = PTR_ERR(local);
-		goto error_unlock;
-	}
+		if (service_id) {
+			write_lock(&local->services_lock);
+			if (rcu_access_pointer(local->service))
+				goto service_in_use;
+			rx->local = local;
+			rcu_assign_pointer(local->service, rx);
+			write_unlock(&local->services_lock);
+
+			rx->sk.sk_state = RXRPC_SERVER_BOUND;
+		} else {
+			rx->local = local;
+			rx->sk.sk_state = RXRPC_CLIENT_BOUND;
+		}
+		break;
 
-	if (service_id) {
-		write_lock(&local->services_lock);
-		if (rcu_access_pointer(local->service))
-			goto service_in_use;
-		rx->local = local;
-		rcu_assign_pointer(local->service, rx);
-		write_unlock(&local->services_lock);
+	case RXRPC_SERVER_BOUND:
+		ret = -EINVAL;
+		if (service_id == 0)
+			goto error_unlock;
+		ret = -EADDRINUSE;
+		if (service_id == rx->srx.srx_service)
+			goto error_unlock;
+		ret = -EINVAL;
+		srx->srx_service = rx->srx.srx_service;
+		if (memcmp(srx, &rx->srx, sizeof(*srx)) != 0)
+			goto error_unlock;
+		rx->second_service = service_id;
+		rx->sk.sk_state = RXRPC_SERVER_BOUND2;
+		break;
 
-		rx->sk.sk_state = RXRPC_SERVER_BOUND;
-	} else {
-		rx->local = local;
-		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
+	default:
+		ret = -EINVAL;
+		goto error_unlock;
 	}
 
 	release_sock(&rx->sk);
@@ -209,6 +222,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 		ret = -EADDRNOTAVAIL;
 		break;
 	case RXRPC_SERVER_BOUND:
+	case RXRPC_SERVER_BOUND2:
 		ASSERT(rx->local != NULL);
 		max = READ_ONCE(rxrpc_max_backlog);
 		ret = -EINVAL;
@@ -248,6 +262,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * @srx: The address of the peer to contact
  * @key: The security context to use (defaults to socket setting)
  * @user_call_ID: The ID to use
+ * @tx_total_len: Total length of data to transmit during the call (or -1)
  * @gfp: The allocation constraints
  * @notify_rx: Where to send notifications instead of socket queue
  *
@@ -262,6 +277,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   struct sockaddr_rxrpc *srx,
 					   struct key *key,
 					   unsigned long user_call_ID,
+					   s64 tx_total_len,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx)
 {
@@ -289,7 +305,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	cp.security_level	= 0;
 	cp.exclusive		= false;
 	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp);
+	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len,
+				     gfp);
 	/* The socket has been unlocked. */
 	if (!IS_ERR(call))
 		call->notify_rx = notify_rx;
@@ -434,7 +451,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 			ret = -EAFNOSUPPORT;
 			goto error_unlock;
 		}
-		local = rxrpc_lookup_local(&rx->srx);
+		local = rxrpc_lookup_local(sock_net(sock->sk), &rx->srx);
 		if (IS_ERR(local)) {
 			ret = PTR_ERR(local);
 			goto error_unlock;
@@ -476,6 +493,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 {
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	unsigned int min_sec_level;
+	u16 service_upgrade[2];
 	int ret;
 
 	_enter(",%d,%d,,%d", level, optname, optlen);
@@ -532,6 +550,28 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			rx->min_sec_level = min_sec_level;
 			goto success;
 
+		case RXRPC_UPGRADEABLE_SERVICE:
+			ret = -EINVAL;
+			if (optlen != sizeof(service_upgrade) ||
+			    rx->service_upgrade.from != 0)
+				goto error;
+			ret = -EISCONN;
+			if (rx->sk.sk_state != RXRPC_SERVER_BOUND2)
+				goto error;
+			ret = -EFAULT;
+			if (copy_from_user(service_upgrade, optval,
+					   sizeof(service_upgrade)) != 0)
+				goto error;
+			ret = -EINVAL;
+			if ((service_upgrade[0] != rx->srx.srx_service ||
+			     service_upgrade[1] != rx->second_service) &&
+			    (service_upgrade[0] != rx->second_service ||
+			     service_upgrade[1] != rx->srx.srx_service))
+				goto error;
+			rx->service_upgrade.from = service_upgrade[0];
+			rx->service_upgrade.to = service_upgrade[1];
+			goto success;
+
 		default:
 			break;
 		}
@@ -545,6 +585,34 @@ error:
 }
 
 /*
+ * Get socket options.
+ */
+static int rxrpc_getsockopt(struct socket *sock, int level, int optname,
+			    char __user *optval, int __user *_optlen)
+{
+	int optlen;
+	
+	if (level != SOL_RXRPC)
+		return -EOPNOTSUPP;
+
+	if (get_user(optlen, _optlen))
+		return -EFAULT;
+	
+	switch (optname) {
+	case RXRPC_SUPPORTED_CMSG:
+		if (optlen < sizeof(int))
+			return -ETOOSMALL;
+		if (put_user(RXRPC__SUPPORTED - 1, (int __user *)optval) ||
+		    put_user(sizeof(int), _optlen))
+			return -EFAULT;
+		return 0;
+		
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/*
  * permit an RxRPC socket to be polled
  */
 static unsigned int rxrpc_poll(struct file *file, struct socket *sock,
@@ -582,9 +650,6 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
 
 	_enter("%p,%d", sock, protocol);
 
-	if (!net_eq(net, &init_net))
-		return -EAFNOSUPPORT;
-
 	/* we support transport protocol UDP/UDP6 only */
 	if (protocol != PF_INET &&
 	    IS_ENABLED(CONFIG_AF_RXRPC_IPV6) && protocol != PF_INET6)
@@ -665,7 +730,7 @@ static void rxrpc_sock_destructor(struct sock *sk)
 
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
-	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
+	WARN_ON(refcount_read(&sk->sk_wmem_alloc));
 	WARN_ON(!sk_unhashed(sk));
 	WARN_ON(sk->sk_socket);
 
@@ -682,7 +747,7 @@ static int rxrpc_release_sock(struct sock *sk)
 {
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
 
-	_enter("%p{%d,%d}", sk, sk->sk_state, atomic_read(&sk->sk_refcnt));
+	_enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt));
 
 	/* declare the socket closed for business */
 	sock_orphan(sk);
@@ -750,7 +815,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
 	.listen		= rxrpc_listen,
 	.shutdown	= rxrpc_shutdown,
 	.setsockopt	= rxrpc_setsockopt,
-	.getsockopt	= sock_no_getsockopt,
+	.getsockopt	= rxrpc_getsockopt,
 	.sendmsg	= rxrpc_sendmsg,
 	.recvmsg	= rxrpc_recvmsg,
 	.mmap		= sock_no_mmap,
@@ -780,8 +845,6 @@ static int __init af_rxrpc_init(void)
 
 	BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb));
 
-	get_random_bytes(&rxrpc_epoch, sizeof(rxrpc_epoch));
-	rxrpc_epoch |= RXRPC_RANDOM_EPOCH;
 	get_random_bytes(&tmp, sizeof(tmp));
 	tmp &= 0x3fffffff;
 	if (tmp == 0)
@@ -809,6 +872,10 @@ static int __init af_rxrpc_init(void)
 		goto error_security;
 	}
 
+	ret = register_pernet_subsys(&rxrpc_net_ops);
+	if (ret)
+		goto error_pernet;
+
 	ret = proto_register(&rxrpc_proto, 1);
 	if (ret < 0) {
 		pr_crit("Cannot register protocol\n");
@@ -839,11 +906,6 @@ static int __init af_rxrpc_init(void)
 		goto error_sysctls;
 	}
 
-#ifdef CONFIG_PROC_FS
-	proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops);
-	proc_create("rxrpc_conns", 0, init_net.proc_net,
-		    &rxrpc_connection_seq_fops);
-#endif
 	return 0;
 
 error_sysctls:
@@ -855,6 +917,8 @@ error_key_type:
 error_sock:
 	proto_unregister(&rxrpc_proto);
 error_proto:
+	unregister_pernet_subsys(&rxrpc_net_ops);
+error_pernet:
 	rxrpc_exit_security();
 error_security:
 	destroy_workqueue(rxrpc_workqueue);
@@ -875,14 +939,16 @@ static void __exit af_rxrpc_exit(void)
 	unregister_key_type(&key_type_rxrpc);
 	sock_unregister(PF_RXRPC);
 	proto_unregister(&rxrpc_proto);
-	rxrpc_destroy_all_calls();
-	rxrpc_destroy_all_connections();
+	unregister_pernet_subsys(&rxrpc_net_ops);
 	ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0);
 	ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0);
-	rxrpc_destroy_all_locals();
 
-	remove_proc_entry("rxrpc_conns", init_net.proc_net);
-	remove_proc_entry("rxrpc_calls", init_net.proc_net);
+	/* Make sure the local and peer records pinned by any dying connections
+	 * are released.
+	 */
+	rcu_barrier();
+	rxrpc_destroy_client_conn_ids();
+
 	destroy_workqueue(rxrpc_workqueue);
 	rxrpc_exit_security();
 	kmem_cache_destroy(rxrpc_call_jar);