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()
  ...

9 files changed, 161 insertions, 35 deletions

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 4b0a8288c98a..9b5c46b052fd 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -246,6 +246,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 			ret = 0;
 			break;
 		}
+		/* Fall through */
 	default:
 		ret = -EBUSY;
 		break;
@@ -265,6 +266,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * @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
+ * @upgrade: Request service upgrade for call
  *
  * Allow a kernel service to begin a call on the nominated socket.  This just
  * sets up all the internal tracking structures and allocates connection and
@@ -279,7 +281,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   unsigned long user_call_ID,
 					   s64 tx_total_len,
 					   gfp_t gfp,
-					   rxrpc_notify_rx_t notify_rx)
+					   rxrpc_notify_rx_t notify_rx,
+					   bool upgrade)
 {
 	struct rxrpc_conn_parameters cp;
 	struct rxrpc_call *call;
@@ -304,6 +307,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	cp.key			= key;
 	cp.security_level	= 0;
 	cp.exclusive		= false;
+	cp.upgrade		= upgrade;
 	cp.service_id		= srx->srx_service;
 	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len,
 				     gfp);
@@ -318,6 +322,14 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 }
 EXPORT_SYMBOL(rxrpc_kernel_begin_call);
 
+/*
+ * Dummy function used to stop the notifier talking to recvmsg().
+ */
+static void rxrpc_dummy_notify_rx(struct sock *sk, struct rxrpc_call *rxcall,
+				  unsigned long call_user_ID)
+{
+}
+
 /**
  * rxrpc_kernel_end_call - Allow a kernel service to end a call it was using
  * @sock: The socket the call is on
@@ -332,12 +344,39 @@ void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call)
 
 	mutex_lock(&call->user_mutex);
 	rxrpc_release_call(rxrpc_sk(sock->sk), call);
+
+	/* Make sure we're not going to call back into a kernel service */
+	if (call->notify_rx) {
+		spin_lock_bh(&call->notify_lock);
+		call->notify_rx = rxrpc_dummy_notify_rx;
+		spin_unlock_bh(&call->notify_lock);
+	}
+
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put_kernel);
 }
 EXPORT_SYMBOL(rxrpc_kernel_end_call);
 
 /**
+ * rxrpc_kernel_check_life - Check to see whether a call is still alive
+ * @sock: The socket the call is on
+ * @call: The call to check
+ *
+ * Allow a kernel service to find out whether a call is still alive - ie. we're
+ * getting ACKs from the server.  Returns a number representing the life state
+ * which can be compared to that returned by a previous call.
+ *
+ * If this is a client call, ping ACKs will be sent to the server to find out
+ * whether it's still responsive and whether the call is still alive on the
+ * server.
+ */
+u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call)
+{
+	return call->acks_latest;
+}
+EXPORT_SYMBOL(rxrpc_kernel_check_life);
+
+/**
  * rxrpc_kernel_check_call - Check a call's state
  * @sock: The socket the call is on
  * @call: The call to check
@@ -538,6 +577,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 			m->msg_name = &rx->connect_srx;
 			m->msg_namelen = sizeof(rx->connect_srx);
 		}
+		/* Fall through */
 	case RXRPC_SERVER_BOUND:
 	case RXRPC_SERVER_LISTENING:
 		ret = rxrpc_do_sendmsg(rx, m, len);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index ea5600b747cc..b2151993d384 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -525,6 +525,7 @@ struct rxrpc_call {
 	unsigned long		flags;
 	unsigned long		events;
 	spinlock_t		lock;
+	spinlock_t		notify_lock;	/* Kernel notification lock */
 	rwlock_t		state_lock;	/* lock for state transition */
 	u32			abort_code;	/* Local/remote abort code */
 	int			error;		/* Local error incurred */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 7a77844aab16..3574508baf9a 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -386,7 +386,7 @@ recheck_state:
 
 	now = ktime_get_real();
 	if (ktime_before(call->expire_at, now)) {
-		rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
+		rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME);
 		set_bit(RXRPC_CALL_EV_ABORT, &call->events);
 		goto recheck_state;
 	}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index fcdd6555a820..4c7fbc6dcce7 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -124,6 +124,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
 	INIT_LIST_HEAD(&call->sock_link);
 	init_waitqueue_head(&call->waitq);
 	spin_lock_init(&call->lock);
+	spin_lock_init(&call->notify_lock);
 	rwlock_init(&call->state_lock);
 	atomic_set(&call->usage, 1);
 	call->debug_id = atomic_inc_return(&rxrpc_debug_id);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index e56e23ed2229..1b592073ec96 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -298,8 +298,6 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 
 	write_unlock(&call->state_lock);
 	if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) {
-		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, 0, false, true,
-				  rxrpc_propose_ack_client_tx_end);
 		trace_rxrpc_transmit(call, rxrpc_transmit_await_reply);
 	} else {
 		trace_rxrpc_transmit(call, rxrpc_transmit_end);
@@ -1125,6 +1123,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
 	case RXRPC_PACKET_TYPE_BUSY:
 		if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
 			goto discard;
+		/* Fall through */
 
 	case RXRPC_PACKET_TYPE_DATA:
 		if (sp->hdr.callNumber == 0)
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 71e6f713fbe7..f47659c7b224 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -35,7 +35,8 @@ struct rxrpc_abort_buffer {
 /*
  * Fill out an ACK packet.
  */
-static size_t rxrpc_fill_out_ack(struct rxrpc_call *call,
+static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
+				 struct rxrpc_call *call,
 				 struct rxrpc_ack_buffer *pkt,
 				 rxrpc_seq_t *_hard_ack,
 				 rxrpc_seq_t *_top,
@@ -77,8 +78,8 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call,
 		} while (before_eq(seq, top));
 	}
 
-	mtu = call->conn->params.peer->if_mtu;
-	mtu -= call->conn->params.peer->hdrsize;
+	mtu = conn->params.peer->if_mtu;
+	mtu -= conn->params.peer->hdrsize;
 	jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max;
 	pkt->ackinfo.rxMTU	= htonl(rxrpc_rx_mtu);
 	pkt->ackinfo.maxMTU	= htonl(mtu);
@@ -148,7 +149,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping)
 		}
 		call->ackr_reason = 0;
 	}
-	n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top, reason);
+	n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason);
 
 	spin_unlock_bh(&call->lock);
 
@@ -221,6 +222,16 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	rxrpc_serial_t serial;
 	int ret;
 
+	/* Don't bother sending aborts for a client call once the server has
+	 * hard-ACK'd all of its request data.  After that point, we're not
+	 * going to stop the operation proceeding, and whilst we might limit
+	 * the reply, it's not worth it if we can send a new call on the same
+	 * channel instead, thereby closing off this call.
+	 */
+	if (rxrpc_is_client_call(call) &&
+	    test_bit(RXRPC_CALL_TX_LAST, &call->flags))
+		return 0;
+
 	spin_lock_bh(&call->lock);
 	if (call->conn)
 		conn = rxrpc_get_connection_maybe(call->conn);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 5787f97f5330..d02a99f37f5f 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -411,3 +411,16 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
 	*_srx = call->peer->srx;
 }
 EXPORT_SYMBOL(rxrpc_kernel_get_peer);
+
+/**
+ * rxrpc_kernel_get_rtt - Get a call's peer RTT
+ * @sock: The socket on which the call is in progress.
+ * @call: The call to query
+ *
+ * Get the call's peer RTT.
+ */
+u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
+{
+	return call->peer->rtt;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index bdece21f313d..8510a98b87e1 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -40,7 +40,9 @@ void rxrpc_notify_socket(struct rxrpc_call *call)
 	sk = &rx->sk;
 	if (rx && sk->sk_state < RXRPC_CLOSE) {
 		if (call->notify_rx) {
+			spin_lock_bh(&call->notify_lock);
 			call->notify_rx(sk, call, call->user_call_ID);
+			spin_unlock_bh(&call->notify_lock);
 		} else {
 			write_lock_bh(&rx->recvmsg_lock);
 			if (list_empty(&call->recvmsg_link)) {
@@ -607,6 +609,7 @@ wait_error:
  * @_offset: The running offset into the buffer.
  * @want_more: True if more data is expected to be read
  * @_abort: Where the abort code is stored if -ECONNABORTED is returned
+ * @_service: Where to store the actual service ID (may be upgraded)
  *
  * Allow a kernel service to receive data and pick up information about the
  * state of a call.  Returns 0 if got what was asked for and there's more
@@ -624,7 +627,7 @@ wait_error:
  */
 int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 			   void *buf, size_t size, size_t *_offset,
-			   bool want_more, u32 *_abort)
+			   bool want_more, u32 *_abort, u16 *_service)
 {
 	struct iov_iter iter;
 	struct kvec iov;
@@ -680,6 +683,8 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 read_phase_complete:
 	ret = 1;
 out:
+	if (_service)
+		*_service = call->service_id;
 	mutex_unlock(&call->user_mutex);
 	_leave(" = %d [%zu,%d]", ret, *_offset, *_abort);
 	return ret;
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 9ea6f972767e..7d2595582c09 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -38,12 +38,86 @@ struct rxrpc_send_params {
 };
 
 /*
+ * Wait for space to appear in the Tx queue or a signal to occur.
+ */
+static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
+					 struct rxrpc_call *call,
+					 long *timeo)
+{
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (call->tx_top - call->tx_hard_ack <
+		    min_t(unsigned int, call->tx_winsize,
+			  call->cong_cwnd + call->cong_extra))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		if (signal_pending(current))
+			return sock_intr_errno(*timeo);
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		mutex_unlock(&call->user_mutex);
+		*timeo = schedule_timeout(*timeo);
+		if (mutex_lock_interruptible(&call->user_mutex) < 0)
+			return sock_intr_errno(*timeo);
+	}
+}
+
+/*
+ * Wait for space to appear in the Tx queue uninterruptibly, but with
+ * a timeout of 2*RTT if no progress was made and a signal occurred.
+ */
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call)
+{
+	rxrpc_seq_t tx_start, tx_win;
+	signed long rtt2, timeout;
+	u64 rtt;
+
+	rtt = READ_ONCE(call->peer->rtt);
+	rtt2 = nsecs_to_jiffies64(rtt) * 2;
+	if (rtt2 < 1)
+		rtt2 = 1;
+
+	timeout = rtt2;
+	tx_start = READ_ONCE(call->tx_hard_ack);
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+
+		tx_win = READ_ONCE(call->tx_hard_ack);
+		if (call->tx_top - tx_win <
+		    min_t(unsigned int, call->tx_winsize,
+			  call->cong_cwnd + call->cong_extra))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		if (timeout == 0 &&
+		    tx_win == tx_start && signal_pending(current))
+			return -EINTR;
+
+		if (tx_win != tx_start) {
+			timeout = rtt2;
+			tx_start = tx_win;
+		}
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		timeout = schedule_timeout(timeout);
+	}
+}
+
+/*
  * wait for space to appear in the transmit/ACK window
  * - caller holds the socket locked
  */
 static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 				    struct rxrpc_call *call,
-				    long *timeo)
+				    long *timeo,
+				    bool waitall)
 {
 	DECLARE_WAITQUEUE(myself, current);
 	int ret;
@@ -53,30 +127,10 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 
 	add_wait_queue(&call->waitq, &myself);
 
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		ret = 0;
-		if (call->tx_top - call->tx_hard_ack <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
-			break;
-		if (call->state >= RXRPC_CALL_COMPLETE) {
-			ret = call->error;
-			break;
-		}
-		if (signal_pending(current)) {
-			ret = sock_intr_errno(*timeo);
-			break;
-		}
-
-		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
-		mutex_unlock(&call->user_mutex);
-		*timeo = schedule_timeout(*timeo);
-		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
-			ret = sock_intr_errno(*timeo);
-			break;
-		}
-	}
+	if (waitall)
+		ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
+	else
+		ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
 
 	remove_wait_queue(&call->waitq, &myself);
 	set_current_state(TASK_RUNNING);
@@ -166,6 +220,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 					  ktime_get_real());
 			if (!last)
 				break;
+			/* Fall through */
 		case RXRPC_CALL_SERVER_SEND_REPLY:
 			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
 			rxrpc_notify_end_tx(rx, call, notify_end_tx);
@@ -254,7 +309,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 				if (msg->msg_flags & MSG_DONTWAIT)
 					goto maybe_error;
 				ret = rxrpc_wait_for_tx_window(rx, call,
-							       &timeo);
+							       &timeo,
+							       msg->msg_flags & MSG_WAITALL);
 				if (ret < 0)
 					goto maybe_error;
 			}