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, 71 insertions, 18 deletions

diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 5b2ab95afa07..ce3775abc6e7 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -113,24 +113,26 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 	}
 
 	if (conn->c_version < RDS_PROTOCOL(3, 1)) {
-		printk(KERN_NOTICE "RDS/IB: Connection to %pI4 version %u.%u failed,"
-		       " no longer supported\n",
-		       &conn->c_faddr,
-		       RDS_PROTOCOL_MAJOR(conn->c_version),
-		       RDS_PROTOCOL_MINOR(conn->c_version));
+		pr_notice("RDS/IB: Connection <%pI4,%pI4> version %u.%u no longer supported\n",
+			  &conn->c_laddr, &conn->c_faddr,
+			  RDS_PROTOCOL_MAJOR(conn->c_version),
+			  RDS_PROTOCOL_MINOR(conn->c_version));
 		rds_conn_destroy(conn);
 		return;
 	} else {
-		printk(KERN_NOTICE "RDS/IB: connected to %pI4 version %u.%u%s\n",
-		       &conn->c_faddr,
-		       RDS_PROTOCOL_MAJOR(conn->c_version),
-		       RDS_PROTOCOL_MINOR(conn->c_version),
-		       ic->i_flowctl ? ", flow control" : "");
+		pr_notice("RDS/IB: %s conn connected <%pI4,%pI4> version %u.%u%s\n",
+			  ic->i_active_side ? "Active" : "Passive",
+			  &conn->c_laddr, &conn->c_faddr,
+			  RDS_PROTOCOL_MAJOR(conn->c_version),
+			  RDS_PROTOCOL_MINOR(conn->c_version),
+			  ic->i_flowctl ? ", flow control" : "");
 	}
 
-	/*
-	 * Init rings and fill recv. this needs to wait until protocol negotiation
-	 * is complete, since ring layout is different from 3.0 to 3.1.
+	atomic_set(&ic->i_cq_quiesce, 0);
+
+	/* Init rings and fill recv. this needs to wait until protocol
+	 * negotiation is complete, since ring layout is different
+	 * from 3.1 to 4.1.
 	 */
 	rds_ib_send_init_ring(ic);
 	rds_ib_recv_init_ring(ic);
@@ -267,6 +269,10 @@ static void rds_ib_tasklet_fn_send(unsigned long data)
 
 	rds_ib_stats_inc(s_ib_tasklet_call);
 
+	/* if cq has been already reaped, ignore incoming cq event */
+	if (atomic_read(&ic->i_cq_quiesce))
+		return;
+
 	poll_scq(ic, ic->i_send_cq, ic->i_send_wc);
 	ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
 	poll_scq(ic, ic->i_send_cq, ic->i_send_wc);
@@ -308,6 +314,10 @@ static void rds_ib_tasklet_fn_recv(unsigned long data)
 
 	rds_ib_stats_inc(s_ib_tasklet_call);
 
+	/* if cq has been already reaped, ignore incoming cq event */
+	if (atomic_read(&ic->i_cq_quiesce))
+		return;
+
 	memset(&state, 0, sizeof(state));
 	poll_rcq(ic, ic->i_recv_cq, ic->i_recv_wc, &state);
 	ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
@@ -358,6 +368,28 @@ static void rds_ib_cq_comp_handler_send(struct ib_cq *cq, void *context)
 	tasklet_schedule(&ic->i_send_tasklet);
 }
 
+static inline int ibdev_get_unused_vector(struct rds_ib_device *rds_ibdev)
+{
+	int min = rds_ibdev->vector_load[rds_ibdev->dev->num_comp_vectors - 1];
+	int index = rds_ibdev->dev->num_comp_vectors - 1;
+	int i;
+
+	for (i = rds_ibdev->dev->num_comp_vectors - 1; i >= 0; i--) {
+		if (rds_ibdev->vector_load[i] < min) {
+			index = i;
+			min = rds_ibdev->vector_load[i];
+		}
+	}
+
+	rds_ibdev->vector_load[index]++;
+	return index;
+}
+
+static inline void ibdev_put_vector(struct rds_ib_device *rds_ibdev, int index)
+{
+	rds_ibdev->vector_load[index]--;
+}
+
 /*
  * This needs to be very careful to not leave IS_ERR pointers around for
  * cleanup to trip over.
@@ -383,7 +415,10 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	 * completion queue and send queue. This extra space is used for FRMR
 	 * registration and invalidation work requests
 	 */
-	fr_queue_space = (rds_ibdev->use_fastreg ? RDS_IB_DEFAULT_FR_WR : 0);
+	fr_queue_space = rds_ibdev->use_fastreg ?
+			 (RDS_IB_DEFAULT_FR_WR + 1) +
+			 (RDS_IB_DEFAULT_FR_INV_WR + 1)
+			 : 0;
 
 	/* add the conn now so that connection establishment has the dev */
 	rds_ib_add_conn(rds_ibdev, conn);
@@ -396,25 +431,30 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	/* Protection domain and memory range */
 	ic->i_pd = rds_ibdev->pd;
 
+	ic->i_scq_vector = ibdev_get_unused_vector(rds_ibdev);
 	cq_attr.cqe = ic->i_send_ring.w_nr + fr_queue_space + 1;
-
+	cq_attr.comp_vector = ic->i_scq_vector;
 	ic->i_send_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_send,
 				     rds_ib_cq_event_handler, conn,
 				     &cq_attr);
 	if (IS_ERR(ic->i_send_cq)) {
 		ret = PTR_ERR(ic->i_send_cq);
 		ic->i_send_cq = NULL;
+		ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
 		rdsdebug("ib_create_cq send failed: %d\n", ret);
 		goto out;
 	}
 
+	ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
 	cq_attr.cqe = ic->i_recv_ring.w_nr;
+	cq_attr.comp_vector = ic->i_rcq_vector;
 	ic->i_recv_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_recv,
 				     rds_ib_cq_event_handler, conn,
 				     &cq_attr);
 	if (IS_ERR(ic->i_recv_cq)) {
 		ret = PTR_ERR(ic->i_recv_cq);
 		ic->i_recv_cq = NULL;
+		ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
 		rdsdebug("ib_create_cq recv failed: %d\n", ret);
 		goto out;
 	}
@@ -445,6 +485,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	attr.send_cq = ic->i_send_cq;
 	attr.recv_cq = ic->i_recv_cq;
 	atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
+	atomic_set(&ic->i_fastunreg_wrs, RDS_IB_DEFAULT_FR_INV_WR);
 
 	/*
 	 * XXX this can fail if max_*_wr is too large?  Are we supposed
@@ -682,6 +723,7 @@ out:
 		if (ic->i_cm_id == cm_id)
 			ret = 0;
 	}
+	ic->i_active_side = true;
 	return ret;
 }
 
@@ -767,17 +809,27 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 		wait_event(rds_ib_ring_empty_wait,
 			   rds_ib_ring_empty(&ic->i_recv_ring) &&
 			   (atomic_read(&ic->i_signaled_sends) == 0) &&
-			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR));
+			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR) &&
+			   (atomic_read(&ic->i_fastunreg_wrs) == RDS_IB_DEFAULT_FR_INV_WR));
 		tasklet_kill(&ic->i_send_tasklet);
 		tasklet_kill(&ic->i_recv_tasklet);
 
+		atomic_set(&ic->i_cq_quiesce, 1);
+
 		/* first destroy the ib state that generates callbacks */
 		if (ic->i_cm_id->qp)
 			rdma_destroy_qp(ic->i_cm_id);
-		if (ic->i_send_cq)
+		if (ic->i_send_cq) {
+			if (ic->rds_ibdev)
+				ibdev_put_vector(ic->rds_ibdev, ic->i_scq_vector);
 			ib_destroy_cq(ic->i_send_cq);
-		if (ic->i_recv_cq)
+		}
+
+		if (ic->i_recv_cq) {
+			if (ic->rds_ibdev)
+				ibdev_put_vector(ic->rds_ibdev, ic->i_rcq_vector);
 			ib_destroy_cq(ic->i_recv_cq);
+		}
 
 		/* then free the resources that ib callbacks use */
 		if (ic->i_send_hdrs)
@@ -855,6 +907,7 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 	ic->i_sends = NULL;
 	vfree(ic->i_recvs);
 	ic->i_recvs = NULL;
+	ic->i_active_side = false;
 }
 
 int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)