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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

1 files changed, 46 insertions, 4 deletions

diff --git a/net/rds/send.c b/net/rds/send.c
index 77c8c6e613ad..5cc64039caf7 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -476,12 +476,14 @@ void rds_rdma_send_complete(struct rds_message *rm, int status)
 	struct rm_rdma_op *ro;
 	struct rds_notifier *notifier;
 	unsigned long flags;
+	unsigned int notify = 0;
 
 	spin_lock_irqsave(&rm->m_rs_lock, flags);
 
+	notify =  rm->rdma.op_notify | rm->data.op_notify;
 	ro = &rm->rdma;
 	if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) &&
-	    ro->op_active && ro->op_notify && ro->op_notifier) {
+	    ro->op_active && notify && ro->op_notifier) {
 		notifier = ro->op_notifier;
 		rs = rm->m_rs;
 		sock_hold(rds_rs_to_sk(rs));
@@ -945,6 +947,11 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
 			ret = rds_cmsg_rdma_map(rs, rm, cmsg);
 			if (!ret)
 				*allocated_mr = 1;
+			else if (ret == -ENODEV)
+				/* Accommodate the get_mr() case which can fail
+				 * if connection isn't established yet.
+				 */
+				ret = -EAGAIN;
 			break;
 		case RDS_CMSG_ATOMIC_CSWP:
 		case RDS_CMSG_ATOMIC_FADD:
@@ -987,6 +994,26 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn)
 	return hash;
 }
 
+static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
+{
+	struct rds_rdma_args *args;
+	struct cmsghdr *cmsg;
+
+	for_each_cmsghdr(cmsg, msg) {
+		if (!CMSG_OK(msg, cmsg))
+			return -EINVAL;
+
+		if (cmsg->cmsg_level != SOL_RDS)
+			continue;
+
+		if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+			args = CMSG_DATA(cmsg);
+			*rdma_bytes += args->remote_vec.bytes;
+		}
+	}
+	return 0;
+}
+
 int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 {
 	struct sock *sk = sock->sk;
@@ -1001,6 +1028,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	int nonblock = msg->msg_flags & MSG_DONTWAIT;
 	long timeo = sock_sndtimeo(sk, nonblock);
 	struct rds_conn_path *cpath;
+	size_t total_payload_len = payload_len, rdma_payload_len = 0;
 
 	/* Mirror Linux UDP mirror of BSD error message compatibility */
 	/* XXX: Perhaps MSG_MORE someday */
@@ -1033,6 +1061,16 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	}
 	release_sock(sk);
 
+	ret = rds_rdma_bytes(msg, &rdma_payload_len);
+	if (ret)
+		goto out;
+
+	total_payload_len += rdma_payload_len;
+	if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) {
+		ret = -EMSGSIZE;
+		goto out;
+	}
+
 	if (payload_len > rds_sk_sndbuf(rs)) {
 		ret = -EMSGSIZE;
 		goto out;
@@ -1082,8 +1120,12 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* Parse any control messages the user may have included. */
 	ret = rds_cmsg_send(rs, rm, msg, &allocated_mr);
-	if (ret)
+	if (ret) {
+		/* Trigger connection so that its ready for the next retry */
+		if (ret ==  -EAGAIN)
+			rds_conn_connect_if_down(conn);
 		goto out;
+	}
 
 	if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) {
 		printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n",
@@ -1169,7 +1211,7 @@ out:
  * or
  *   RDS_FLAG_HB_PONG|RDS_FLAG_ACK_REQUIRED
  */
-int
+static int
 rds_send_probe(struct rds_conn_path *cp, __be16 sport,
 	       __be16 dport, u8 h_flags)
 {
@@ -1238,7 +1280,7 @@ rds_send_pong(struct rds_conn_path *cp, __be16 dport)
 	return rds_send_probe(cp, 0, dport, 0);
 }
 
-void
+static void
 rds_send_ping(struct rds_connection *conn)
 {
 	unsigned long flags;