Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/roland/infiniband

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  RDMA/nes: Add support for new SFP+ PHY
  RDMA/nes: Add wide_ppm_offset parm for switch compatibility
  RDMA/nes: Fix SFP+ PHY initialization
  RDMA/nes: Fix nes_nic_cm_xmit() error handling
  RDMA/nes: Fix error handling issues
  RDMA/nes: Fix incorrect casts on 32-bit architectures
  IPoIB: Document newish features
  RDMA/cma: Create cm id even when IB port is down
  RDMA/cma: Use rate from IPoIB broadcast when joining IPoIB multicast groups
  IPoIB: Avoid free_netdev() BUG when destroying a child interface
  mlx4_core: Don't leak mailbox for SET_PORT on Ethernet ports
  RDMA/cxgb3: Release dependent resources only when endpoint memory is freed.
  RDMA/cxgb3: Handle EEH events
  IB/mlx4: Use pgprot_writecombine() for BlueFlame pages

Documentation/infiniband/ipoib.txt

@@ -24,6 +24,49 @@ Partitions and P_Keys
   The P_Key for any interface is given by the "pkey" file, and the
   main interface for a subinterface is in "parent."
 
+Datagram vs Connected modes
+
+  The IPoIB driver supports two modes of operation: datagram and
+  connected.  The mode is set and read through an interface's
+  /sys/class/net/<intf name>/mode file.
+
+  In datagram mode, the IB UD (Unreliable Datagram) transport is used
+  and so the interface MTU has is equal to the IB L2 MTU minus the
+  IPoIB encapsulation header (4 bytes).  For example, in a typical IB
+  fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes.
+
+  In connected mode, the IB RC (Reliable Connected) transport is used.
+  Connected mode is to takes advantage of the connected nature of the
+  IB transport and allows an MTU up to the maximal IP packet size of
+  64K, which reduces the number of IP packets needed for handling
+  large UDP datagrams, TCP segments, etc and increases the performance
+  for large messages.
+
+  In connected mode, the interface's UD QP is still used for multicast
+  and communication with peers that don't support connected mode. In
+  this case, RX emulation of ICMP PMTU packets is used to cause the
+  networking stack to use the smaller UD MTU for these neighbours.
+
+Stateless offloads
+
+  If the IB HW supports IPoIB stateless offloads, IPoIB advertises
+  TCP/IP checksum and/or Large Send (LSO) offloading capability to the
+  network stack.
+
+  Large Receive (LRO) offloading is also implemented and may be turned
+  on/off using ethtool calls.  Currently LRO is supported only for
+  checksum offload capable devices.
+
+  Stateless offloads are supported only in datagram mode.  
+
+Interrupt moderation
+
+  If the underlying IB device supports CQ event moderation, one can
+  use ethtool to set interrupt mitigation parameters and thus reduce
+  the overhead incurred by handling interrupts.  The main code path of
+  IPoIB doesn't use events for TX completion signaling so only RX
+  moderation is supported.
+
 Debugging Information
 
   By compiling the IPoIB driver with CONFIG_INFINIBAND_IPOIB_DEBUG set
@@ -55,3 +98,5 @@ References
     http://ietf.org/rfc/rfc4391.txt 
   IP over InfiniBand (IPoIB) Architecture (RFC 4392)
     http://ietf.org/rfc/rfc4392.txt 
+  IP over InfiniBand: Connected Mode (RFC 4755)
+    http://ietf.org/rfc/rfc4755.txt

drivers/infiniband/core/cma.c

@@ -297,21 +297,25 @@ static void cma_detach_from_dev(struct rdma_id_private *id_priv)
 	id_priv->cma_dev = NULL;
 }
 
-static int cma_set_qkey(struct ib_device *device, u8 port_num,
-			enum rdma_port_space ps,
-			struct rdma_dev_addr *dev_addr, u32 *qkey)
+static int cma_set_qkey(struct rdma_id_private *id_priv)
 {
 	struct ib_sa_mcmember_rec rec;
 	int ret = 0;
 
-	switch (ps) {
+	if (id_priv->qkey)
+		return 0;
+
+	switch (id_priv->id.ps) {
 	case RDMA_PS_UDP:
-		*qkey = RDMA_UDP_QKEY;
+		id_priv->qkey = RDMA_UDP_QKEY;
 		break;
 	case RDMA_PS_IPOIB:
-		ib_addr_get_mgid(dev_addr, &rec.mgid);
-		ret = ib_sa_get_mcmember_rec(device, port_num, &rec.mgid, &rec);
-		*qkey = be32_to_cpu(rec.qkey);
+		ib_addr_get_mgid(&id_priv->id.route.addr.dev_addr, &rec.mgid);
+		ret = ib_sa_get_mcmember_rec(id_priv->id.device,
+					     id_priv->id.port_num, &rec.mgid,
+					     &rec);
+		if (!ret)
+			id_priv->qkey = be32_to_cpu(rec.qkey);
 		break;
 	default:
 		break;
@@ -341,12 +345,7 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv)
 		ret = ib_find_cached_gid(cma_dev->device, &gid,
 					 &id_priv->id.port_num, NULL);
 		if (!ret) {
-			ret = cma_set_qkey(cma_dev->device,
-					   id_priv->id.port_num,
-					   id_priv->id.ps, dev_addr,
-					   &id_priv->qkey);
-			if (!ret)
-				cma_attach_to_dev(id_priv, cma_dev);
+			cma_attach_to_dev(id_priv, cma_dev);
 			break;
 		}
 	}
@@ -578,6 +577,10 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
 	*qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT;
 
 	if (cma_is_ud_ps(id_priv->id.ps)) {
+		ret = cma_set_qkey(id_priv);
+		if (ret)
+			return ret;
+
 		qp_attr->qkey = id_priv->qkey;
 		*qp_attr_mask |= IB_QP_QKEY;
 	} else {
@@ -2201,6 +2204,12 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
 			event.status = ib_event->param.sidr_rep_rcvd.status;
 			break;
 		}
+		ret = cma_set_qkey(id_priv);
+		if (ret) {
+			event.event = RDMA_CM_EVENT_ADDR_ERROR;
+			event.status = -EINVAL;
+			break;
+		}
 		if (id_priv->qkey != rep->qkey) {
 			event.event = RDMA_CM_EVENT_UNREACHABLE;
 			event.status = -EINVAL;
@@ -2480,10 +2489,14 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv,
 			     const void *private_data, int private_data_len)
 {
 	struct ib_cm_sidr_rep_param rep;
+	int ret;
 
 	memset(&rep, 0, sizeof rep);
 	rep.status = status;
 	if (status == IB_SIDR_SUCCESS) {
+		ret = cma_set_qkey(id_priv);
+		if (ret)
+			return ret;
 		rep.qp_num = id_priv->qp_num;
 		rep.qkey = id_priv->qkey;
 	}
@@ -2713,6 +2726,10 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv,
 		    IB_SA_MCMEMBER_REC_FLOW_LABEL |
 		    IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
 
+	if (id_priv->id.ps == RDMA_PS_IPOIB)
+		comp_mask |= IB_SA_MCMEMBER_REC_RATE |
+			     IB_SA_MCMEMBER_REC_RATE_SELECTOR;
+
 	mc->multicast.ib = ib_sa_join_multicast(&sa_client, id_priv->id.device,
 						id_priv->id.port_num, &rec,
 						comp_mask, GFP_KERNEL,

drivers/infiniband/hw/cxgb3/cxio_hal.c

@@ -152,7 +152,7 @@ static int cxio_hal_clear_qp_ctx(struct cxio_rdev *rdev_p, u32 qpid)
 	sge_cmd = qpid << 8 | 3;
 	wqe->sge_cmd = cpu_to_be64(sge_cmd);
 	skb->priority = CPL_PRIORITY_CONTROL;
-	return (cxgb3_ofld_send(rdev_p->t3cdev_p, skb));
+	return iwch_cxgb3_ofld_send(rdev_p->t3cdev_p, skb);
 }
 
 int cxio_create_cq(struct cxio_rdev *rdev_p, struct t3_cq *cq)
@@ -571,7 +571,7 @@ static int cxio_hal_init_ctrl_qp(struct cxio_rdev *rdev_p)
 	     (unsigned long long) rdev_p->ctrl_qp.dma_addr,
 	     rdev_p->ctrl_qp.workq, 1 << T3_CTRL_QP_SIZE_LOG2);
 	skb->priority = CPL_PRIORITY_CONTROL;
-	return (cxgb3_ofld_send(rdev_p->t3cdev_p, skb));
+	return iwch_cxgb3_ofld_send(rdev_p->t3cdev_p, skb);
 err:
 	kfree_skb(skb);
 	return err;
@@ -701,7 +701,7 @@ static int __cxio_tpt_op(struct cxio_rdev *rdev_p, u32 reset_tpt_entry,
 	u32 stag_idx;
 	u32 wptr;
 
-	if (rdev_p->flags)
+	if (cxio_fatal_error(rdev_p))
 		return -EIO;
 
 	stag_state = stag_state > 0;
@@ -858,7 +858,7 @@ int cxio_rdma_init(struct cxio_rdev *rdev_p, struct t3_rdma_init_attr *attr)
 	wqe->qp_dma_size = cpu_to_be32(attr->qp_dma_size);
 	wqe->irs = cpu_to_be32(attr->irs);
 	skb->priority = 0;	/* 0=>ToeQ; 1=>CtrlQ */
-	return (cxgb3_ofld_send(rdev_p->t3cdev_p, skb));
+	return iwch_cxgb3_ofld_send(rdev_p->t3cdev_p, skb);
 }
 
 void cxio_register_ev_cb(cxio_hal_ev_callback_func_t ev_cb)
@@ -1041,9 +1041,9 @@ void cxio_rdev_close(struct cxio_rdev *rdev_p)
 		cxio_hal_pblpool_destroy(rdev_p);
 		cxio_hal_rqtpool_destroy(rdev_p);
 		list_del(&rdev_p->entry);
-		rdev_p->t3cdev_p->ulp = NULL;
 		cxio_hal_destroy_ctrl_qp(rdev_p);
 		cxio_hal_destroy_resource(rdev_p->rscp);
+		rdev_p->t3cdev_p->ulp = NULL;
 	}
 }
 

drivers/infiniband/hw/cxgb3/cxio_hal.h

@@ -115,6 +115,11 @@ struct cxio_rdev {
 #define	CXIO_ERROR_FATAL	1
 };
 
+static inline int cxio_fatal_error(struct cxio_rdev *rdev_p)
+{
+	return rdev_p->flags & CXIO_ERROR_FATAL;
+}
+
 static inline int cxio_num_stags(struct cxio_rdev *rdev_p)
 {
 	return min((int)T3_MAX_NUM_STAG, (int)((rdev_p->rnic_info.tpt_top - rdev_p->rnic_info.tpt_base) >> 5));
@@ -188,6 +193,7 @@ void cxio_count_scqes(struct t3_cq *cq, struct t3_wq *wq, int *count);
 void cxio_flush_hw_cq(struct t3_cq *cq);
 int cxio_poll_cq(struct t3_wq *wq, struct t3_cq *cq, struct t3_cqe *cqe,
 		     u8 *cqe_flushed, u64 *cookie, u32 *credit);
+int iwch_cxgb3_ofld_send(struct t3cdev *tdev, struct sk_buff *skb);
 
 #define MOD "iw_cxgb3: "
 #define PDBG(fmt, args...) pr_debug(MOD fmt, ## args)

drivers/infiniband/hw/cxgb3/iwch.c

@@ -165,12 +165,19 @@ static void close_rnic_dev(struct t3cdev *tdev)
 static void iwch_err_handler(struct t3cdev *tdev, u32 status, u32 error)
 {
 	struct cxio_rdev *rdev = tdev->ulp;
+	struct iwch_dev *rnicp = rdev_to_iwch_dev(rdev);
+	struct ib_event event;
 
-	if (status == OFFLOAD_STATUS_DOWN)
+	if (status == OFFLOAD_STATUS_DOWN) {
 		rdev->flags = CXIO_ERROR_FATAL;
 
-	return;
+		event.device = &rnicp->ibdev;
+		event.event  = IB_EVENT_DEVICE_FATAL;
+		event.element.port_num = 0;
+		ib_dispatch_event(&event);
+	}
 
+	return;
 }
 
 static int __init iwch_init_module(void)

drivers/infiniband/hw/cxgb3/iwch.h

@@ -117,6 +117,11 @@ static inline struct iwch_dev *to_iwch_dev(struct ib_device *ibdev)
 	return container_of(ibdev, struct iwch_dev, ibdev);
 }
 
+static inline struct iwch_dev *rdev_to_iwch_dev(struct cxio_rdev *rdev)
+{
+	return container_of(rdev, struct iwch_dev, rdev);
+}
+
 static inline int t3b_device(const struct iwch_dev *rhp)
 {
 	return rhp->rdev.t3cdev_p->type == T3B;