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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 42 insertions, 20 deletions

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index b0d2cda6ec0a..9ea6f972767e 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -61,7 +61,7 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 			  call->cong_cwnd + call->cong_extra))
 			break;
 		if (call->state >= RXRPC_CALL_COMPLETE) {
-			ret = -call->error;
+			ret = call->error;
 			break;
 		}
 		if (signal_pending(current)) {
@@ -101,11 +101,23 @@ static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix)
 }
 
 /*
+ * Notify the owner of the call that the transmit phase is ended and the last
+ * packet has been queued.
+ */
+static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call,
+				rxrpc_notify_end_tx_t notify_end_tx)
+{
+	if (notify_end_tx)
+		notify_end_tx(&rx->sk, call, call->user_call_ID);
+}
+
+/*
  * Queue a DATA packet for transmission, set the resend timeout and send the
  * packet immediately
  */
-static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
-			       bool last)
+static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
+			       struct sk_buff *skb, bool last,
+			       rxrpc_notify_end_tx_t notify_end_tx)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	rxrpc_seq_t seq = sp->hdr.seq;
@@ -116,8 +128,10 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 
 	ASSERTCMP(seq, ==, call->tx_top + 1);
 
-	if (last)
+	if (last) {
 		annotation |= RXRPC_TX_ANNO_LAST;
+		set_bit(RXRPC_CALL_TX_LASTQ, &call->flags);
+	}
 
 	/* We have to set the timestamp before queueing as the retransmit
 	 * algorithm can see the packet as soon as we queue it.
@@ -141,6 +155,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		switch (call->state) {
 		case RXRPC_CALL_CLIENT_SEND_REQUEST:
 			call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+			rxrpc_notify_end_tx(rx, call, notify_end_tx);
 			break;
 		case RXRPC_CALL_SERVER_ACK_REQUEST:
 			call->state = RXRPC_CALL_SERVER_SEND_REPLY;
@@ -153,6 +168,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 				break;
 		case RXRPC_CALL_SERVER_SEND_REPLY:
 			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
+			rxrpc_notify_end_tx(rx, call, notify_end_tx);
 			break;
 		default:
 			break;
@@ -189,7 +205,8 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
  */
 static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
-			   struct msghdr *msg, size_t len)
+			   struct msghdr *msg, size_t len,
+			   rxrpc_notify_end_tx_t notify_end_tx)
 {
 	struct rxrpc_skb_priv *sp;
 	struct sk_buff *skb;
@@ -311,11 +328,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 				call->tx_total_len -= copy;
 		}
 
-		/* check for the far side aborting the call or a network error
-		 * occurring */
-		if (call->state == RXRPC_CALL_COMPLETE)
-			goto call_terminated;
-
 		/* add the packet to the send queue if it's now full */
 		if (sp->remain <= 0 ||
 		    (msg_data_left(msg) == 0 && !more)) {
@@ -350,9 +362,21 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 			if (ret < 0)
 				goto out;
 
-			rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more);
+			rxrpc_queue_packet(rx, call, skb,
+					   !msg_data_left(msg) && !more,
+					   notify_end_tx);
 			skb = NULL;
 		}
+
+		/* Check for the far side aborting the call or a network error
+		 * occurring.  If this happens, save any packet that was under
+		 * construction so that in the case of a network error, the
+		 * call can be retried or redirected.
+		 */
+		if (call->state == RXRPC_CALL_COMPLETE) {
+			ret = call->error;
+			goto out;
+		}
 	} while (msg_data_left(msg) > 0);
 
 success:
@@ -362,11 +386,6 @@ out:
 	_leave(" = %d", ret);
 	return ret;
 
-call_terminated:
-	rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
-	_leave(" = %d", -call->error);
-	return -call->error;
-
 maybe_error:
 	if (copied)
 		goto success;
@@ -611,7 +630,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		/* Reply phase not begun or not complete for service call. */
 		ret = -EPROTO;
 	} else {
-		ret = rxrpc_send_data(rx, call, msg, len);
+		ret = rxrpc_send_data(rx, call, msg, len, NULL);
 	}
 
 	mutex_unlock(&call->user_mutex);
@@ -631,6 +650,7 @@ error_release_sock:
  * @call: The call to send data through
  * @msg: The data to send
  * @len: The amount of data to send
+ * @notify_end_tx: Notification that the last packet is queued.
  *
  * Allow a kernel service to send data on a call.  The call must be in an state
  * appropriate to sending data.  No control data should be supplied in @msg,
@@ -638,7 +658,8 @@ error_release_sock:
  * more data to come, otherwise this data will end the transmission phase.
  */
 int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
-			   struct msghdr *msg, size_t len)
+			   struct msghdr *msg, size_t len,
+			   rxrpc_notify_end_tx_t notify_end_tx)
 {
 	int ret;
 
@@ -656,11 +677,12 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
 	case RXRPC_CALL_SERVER_SEND_REPLY:
-		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
+		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
+				      notify_end_tx);
 		break;
 	case RXRPC_CALL_COMPLETE:
 		read_lock_bh(&call->state_lock);
-		ret = -call->error;
+		ret = call->error;
 		read_unlock_bh(&call->state_lock);
 		break;
 	default: