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, 82 insertions, 26 deletions

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;
 			}