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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 30 insertions, 26 deletions

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 7bff716e911e..816b19a78809 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -144,13 +144,11 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 	trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top);
 	ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
 
-#if 0 // TODO: May want to transmit final ACK under some circumstances anyway
 	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
-		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false,
+		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true,
 				  rxrpc_propose_ack_terminal_ack);
-		rxrpc_send_ack_packet(call, false, NULL);
+		//rxrpc_send_ack_packet(call, false, NULL);
 	}
-#endif
 
 	write_lock_bh(&call->state_lock);
 
@@ -315,6 +313,10 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 	unsigned int rx_pkt_offset, rx_pkt_len;
 	int ix, copy, ret = -EAGAIN, ret2;
 
+	if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) &&
+	    call->ackr_reason)
+		rxrpc_send_ack_packet(call, false, NULL);
+
 	rx_pkt_offset = call->rx_pkt_offset;
 	rx_pkt_len = call->rx_pkt_len;
 
@@ -414,6 +416,8 @@ out:
 done:
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq,
 			    rx_pkt_offset, rx_pkt_len, ret);
+	if (ret == -EAGAIN)
+		set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags);
 	return ret;
 }
 
@@ -607,9 +611,7 @@ wait_error:
  * rxrpc_kernel_recv_data - Allow a kernel service to receive data/info
  * @sock: The socket that the call exists on
  * @call: The call to send data through
- * @buf: The buffer to receive into
- * @size: The size of the buffer, including data already read
- * @_offset: The running offset into the buffer.
+ * @iter: The buffer to receive into
  * @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)
@@ -622,39 +624,30 @@ wait_error:
  * Note that we may return -EAGAIN to drain empty packets at the end of the
  * data, even if we've already copied over the requested data.
  *
- * This function adds the amount it transfers to *_offset, so this should be
- * precleared as appropriate.  Note that the amount remaining in the buffer is
- * taken to be size - *_offset.
- *
  * *_abort should also be initialised to 0.
  */
 int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
-			   void *buf, size_t size, size_t *_offset,
+			   struct iov_iter *iter,
 			   bool want_more, u32 *_abort, u16 *_service)
 {
-	struct iov_iter iter;
-	struct kvec iov;
+	size_t offset = 0;
 	int ret;
 
-	_enter("{%d,%s},%zu/%zu,%d",
+	_enter("{%d,%s},%zu,%d",
 	       call->debug_id, rxrpc_call_states[call->state],
-	       *_offset, size, want_more);
+	       iov_iter_count(iter), want_more);
 
-	ASSERTCMP(*_offset, <=, size);
 	ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING);
 
-	iov.iov_base = buf + *_offset;
-	iov.iov_len = size - *_offset;
-	iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset);
-
 	mutex_lock(&call->user_mutex);
 
 	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_CLIENT_RECV_REPLY:
 	case RXRPC_CALL_SERVER_RECV_REQUEST:
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
-		ret = rxrpc_recvmsg_data(sock, call, NULL, &iter, size, 0,
-					 _offset);
+		ret = rxrpc_recvmsg_data(sock, call, NULL, iter,
+					 iov_iter_count(iter), 0,
+					 &offset);
 		if (ret < 0)
 			goto out;
 
@@ -663,7 +656,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 		 * full buffer or have been given -EAGAIN.
 		 */
 		if (ret == 1) {
-			if (*_offset < size)
+			if (iov_iter_count(iter) > 0)
 				goto short_data;
 			if (!want_more)
 				goto read_phase_complete;
@@ -686,10 +679,21 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 read_phase_complete:
 	ret = 1;
 out:
+	switch (call->ackr_reason) {
+	case RXRPC_ACK_IDLE:
+		break;
+	case RXRPC_ACK_DELAY:
+		if (ret != -EAGAIN)
+			break;
+		/* Fall through */
+	default:
+		rxrpc_send_ack_packet(call, false, NULL);
+	}
+
 	if (_service)
 		*_service = call->service_id;
 	mutex_unlock(&call->user_mutex);
-	_leave(" = %d [%zu,%d]", ret, *_offset, *_abort);
+	_leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort);
 	return ret;
 
 short_data:
@@ -705,7 +709,7 @@ call_complete:
 	ret = call->error;
 	if (call->completion == RXRPC_CALL_SUCCEEDED) {
 		ret = 1;
-		if (size > 0)
+		if (iov_iter_count(iter) > 0)
 			ret = -ECONNRESET;
 	}
 	goto out;