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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 37 insertions, 36 deletions

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index dfc8c51e4d74..5d28abf87fbf 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -36,7 +36,7 @@
  * not support simultaneous connects (two "client" sockets connecting).
  *
  * - "Server" sockets are referred to as listener sockets throughout this
- * implementation because they are in the VSOCK_SS_LISTEN state.  When a
+ * implementation because they are in the TCP_LISTEN state.  When a
  * connection request is received (the second kind of socket mentioned above),
  * we create a new socket and refer to it as a pending socket.  These pending
  * sockets are placed on the pending connection list of the listener socket.
@@ -82,6 +82,15 @@
  * argument, we must ensure the reference count is increased to ensure the
  * socket isn't freed before the function is run; the deferred function will
  * then drop the reference.
+ *
+ * - sk->sk_state uses the TCP state constants because they are widely used by
+ * other address families and exposed to userspace tools like ss(8):
+ *
+ *   TCP_CLOSE - unconnected
+ *   TCP_SYN_SENT - connecting
+ *   TCP_ESTABLISHED - connected
+ *   TCP_CLOSING - disconnecting
+ *   TCP_LISTEN - listening
  */
 
 #include <linux/types.h>
@@ -153,7 +162,6 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid);
  * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets.  The hash function
  * mods with VSOCK_HASH_SIZE to ensure this.
  */
-#define VSOCK_HASH_SIZE         251
 #define MAX_PORT_RETRIES        24
 
 #define VSOCK_HASH(addr)        ((addr)->svm_port % VSOCK_HASH_SIZE)
@@ -168,9 +176,12 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid);
 #define vsock_connected_sockets_vsk(vsk)				\
 	vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr)
 
-static struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
-static struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
-static DEFINE_SPINLOCK(vsock_table_lock);
+struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
+EXPORT_SYMBOL_GPL(vsock_bind_table);
+struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
+EXPORT_SYMBOL_GPL(vsock_connected_table);
+DEFINE_SPINLOCK(vsock_table_lock);
+EXPORT_SYMBOL_GPL(vsock_table_lock);
 
 /* Autobind this socket to the local address if necessary. */
 static int vsock_auto_bind(struct vsock_sock *vsk)
@@ -184,7 +195,7 @@ static int vsock_auto_bind(struct vsock_sock *vsk)
 	return __vsock_bind(sk, &local_addr);
 }
 
-static void vsock_init_tables(void)
+static int __init vsock_init_tables(void)
 {
 	int i;
 
@@ -193,6 +204,7 @@ static void vsock_init_tables(void)
 
 	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
 		INIT_LIST_HEAD(&vsock_connected_table[i]);
+	return 0;
 }
 
 static void __vsock_insert_bound(struct list_head *list,
@@ -248,16 +260,6 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
 	return NULL;
 }
 
-static bool __vsock_in_bound_table(struct vsock_sock *vsk)
-{
-	return !list_empty(&vsk->bound_table);
-}
-
-static bool __vsock_in_connected_table(struct vsock_sock *vsk)
-{
-	return !list_empty(&vsk->connected_table);
-}
-
 static void vsock_insert_unbound(struct vsock_sock *vsk)
 {
 	spin_lock_bh(&vsock_table_lock);
@@ -485,7 +487,7 @@ void vsock_pending_work(struct work_struct *work)
 	if (vsock_in_connected_table(vsk))
 		vsock_remove_connected(vsk);
 
-	sk->sk_state = SS_FREE;
+	sk->sk_state = TCP_CLOSE;
 
 out:
 	release_sock(sk);
@@ -625,7 +627,6 @@ struct sock *__vsock_create(struct net *net,
 
 	sk->sk_destruct = vsock_sk_destruct;
 	sk->sk_backlog_rcv = vsock_queue_rcv_skb;
-	sk->sk_state = 0;
 	sock_reset_flag(sk, SOCK_DONE);
 
 	INIT_LIST_HEAD(&vsk->bound_table);
@@ -899,7 +900,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		/* Listening sockets that have connections in their accept
 		 * queue can be read.
 		 */
-		if (sk->sk_state == VSOCK_SS_LISTEN
+		if (sk->sk_state == TCP_LISTEN
 		    && !vsock_is_accept_queue_empty(sk))
 			mask |= POLLIN | POLLRDNORM;
 
@@ -928,7 +929,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		}
 
 		/* Connected sockets that can produce data can be written. */
-		if (sk->sk_state == SS_CONNECTED) {
+		if (sk->sk_state == TCP_ESTABLISHED) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
 				bool space_avail_now = false;
 				int ret = transport->notify_poll_out(
@@ -950,7 +951,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		 * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
 		 * but local send is not shutdown.
 		 */
-		if (sk->sk_state == SS_UNCONNECTED) {
+		if (sk->sk_state == TCP_CLOSE) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 				mask |= POLLOUT | POLLWRNORM;
 
@@ -1120,9 +1121,9 @@ static void vsock_connect_timeout(struct work_struct *work)
 	sk = sk_vsock(vsk);
 
 	lock_sock(sk);
-	if (sk->sk_state == SS_CONNECTING &&
+	if (sk->sk_state == TCP_SYN_SENT &&
 	    (sk->sk_shutdown != SHUTDOWN_MASK)) {
-		sk->sk_state = SS_UNCONNECTED;
+		sk->sk_state = TCP_CLOSE;
 		sk->sk_err = ETIMEDOUT;
 		sk->sk_error_report(sk);
 		cancel = 1;
@@ -1168,7 +1169,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 		err = -EALREADY;
 		break;
 	default:
-		if ((sk->sk_state == VSOCK_SS_LISTEN) ||
+		if ((sk->sk_state == TCP_LISTEN) ||
 		    vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
 			err = -EINVAL;
 			goto out;
@@ -1191,7 +1192,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			goto out;
 
-		sk->sk_state = SS_CONNECTING;
+		sk->sk_state = TCP_SYN_SENT;
 
 		err = transport->connect(vsk);
 		if (err < 0)
@@ -1211,7 +1212,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 	timeout = vsk->connect_timeout;
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-	while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
+	while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
 		if (flags & O_NONBLOCK) {
 			/* If we're not going to block, we schedule a timeout
 			 * function to generate a timeout on the connection
@@ -1234,13 +1235,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 
 		if (signal_pending(current)) {
 			err = sock_intr_errno(timeout);
-			sk->sk_state = SS_UNCONNECTED;
+			sk->sk_state = TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
 			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
 		} else if (timeout == 0) {
 			err = -ETIMEDOUT;
-			sk->sk_state = SS_UNCONNECTED;
+			sk->sk_state = TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
 			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
@@ -1251,7 +1252,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 
 	if (sk->sk_err) {
 		err = -sk->sk_err;
-		sk->sk_state = SS_UNCONNECTED;
+		sk->sk_state = TCP_CLOSE;
 		sock->state = SS_UNCONNECTED;
 	} else {
 		err = 0;
@@ -1284,7 +1285,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 		goto out;
 	}
 
-	if (listener->sk_state != VSOCK_SS_LISTEN) {
+	if (listener->sk_state != TCP_LISTEN) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -1374,7 +1375,7 @@ static int vsock_listen(struct socket *sock, int backlog)
 	}
 
 	sk->sk_max_ack_backlog = backlog;
-	sk->sk_state = VSOCK_SS_LISTEN;
+	sk->sk_state = TCP_LISTEN;
 
 	err = 0;
 
@@ -1554,7 +1555,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	/* Callers should not provide a destination with stream sockets. */
 	if (msg->msg_namelen) {
-		err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP;
+		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -1565,7 +1566,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		goto out;
 	}
 
-	if (sk->sk_state != SS_CONNECTED ||
+	if (sk->sk_state != TCP_ESTABLISHED ||
 	    !vsock_addr_bound(&vsk->local_addr)) {
 		err = -ENOTCONN;
 		goto out;
@@ -1689,7 +1690,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	lock_sock(sk);
 
-	if (sk->sk_state != SS_CONNECTED) {
+	if (sk->sk_state != TCP_ESTABLISHED) {
 		/* Recvmsg is supposed to return 0 if a peer performs an
 		 * orderly shutdown. Differentiate between that case and when a
 		 * peer has not connected or a local shutdown occured with the
@@ -1957,8 +1958,6 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
 	vsock_proto.owner = owner;
 	transport = t;
 
-	vsock_init_tables();
-
 	vsock_device.minor = MISC_DYNAMIC_MINOR;
 	err = misc_register(&vsock_device);
 	if (err) {
@@ -2019,6 +2018,8 @@ const struct vsock_transport *vsock_core_get_transport(void)
 }
 EXPORT_SYMBOL_GPL(vsock_core_get_transport);
 
+module_init(vsock_init_tables);
+
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Socket Family");
 MODULE_VERSION("1.0.2.0-k");