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: (63 commits)
  IB/qib: clean up properly if pci_set_consistent_dma_mask() fails
  IB/qib: Allow driver to load if PCIe AER fails
  IB/qib: Fix uninitialized pointer if CONFIG_PCI_MSI not set
  IB/qib: Fix extra log level in qib_early_err()
  RDMA/cxgb4: Remove unnecessary KERN_<level> use
  RDMA/cxgb3: Remove unnecessary KERN_<level> use
  IB/core: Add link layer type information to sysfs
  IB/mlx4: Add VLAN support for IBoE
  IB/core: Add VLAN support for IBoE
  IB/mlx4: Add support for IBoE
  mlx4_en: Change multicast promiscuous mode to support IBoE
  mlx4_core: Update data structures and constants for IBoE
  mlx4_core: Allow protocol drivers to find corresponding interfaces
  IB/uverbs: Return link layer type to userspace for query port operation
  IB/srp: Sync buffer before posting send
  IB/srp: Use list_first_entry()
  IB/srp: Reduce number of BUSY conditions
  IB/srp: Eliminate two forward declarations
  IB/mlx4: Signal node desc changes to SM by using FW to generate trap 144
  IB: Replace EXTRA_CFLAGS with ccflags-y
  ...

12 files changed, 556 insertions, 364 deletions

diff --git a/drivers/infiniband/hw/cxgb4/Makefile b/drivers/infiniband/hw/cxgb4/Makefile
index e31a499..cd20b13 100644
--- a/drivers/infiniband/hw/cxgb4/Makefile
+++ b/drivers/infiniband/hw/cxgb4/Makefile
@@ -1,4 +1,4 @@
-EXTRA_CFLAGS += -Idrivers/net/cxgb4
+ccflags-y := -Idrivers/net/cxgb4
 
 obj-$(CONFIG_INFINIBAND_CXGB4) += iw_cxgb4.o
 
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 32d352a..0dc62b1 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -117,9 +117,9 @@ static int rcv_win = 256 * 1024;
 module_param(rcv_win, int, 0644);
 MODULE_PARM_DESC(rcv_win, "TCP receive window in bytes (default=256KB)");
 
-static int snd_win = 32 * 1024;
+static int snd_win = 128 * 1024;
 module_param(snd_win, int, 0644);
-MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=32KB)");
+MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=128KB)");
 
 static struct workqueue_struct *workq;
 
@@ -172,7 +172,7 @@ static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb,
 	error = cxgb4_l2t_send(rdev->lldi.ports[0], skb, l2e);
 	if (error < 0)
 		kfree_skb(skb);
-	return error;
+	return error < 0 ? error : 0;
 }
 
 int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb)
@@ -187,7 +187,7 @@ int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb)
 	error = cxgb4_ofld_send(rdev->lldi.ports[0], skb);
 	if (error < 0)
 		kfree_skb(skb);
-	return error;
+	return error < 0 ? error : 0;
 }
 
 static void release_tid(struct c4iw_rdev *rdev, u32 hwtid, struct sk_buff *skb)
@@ -219,12 +219,11 @@ static void set_emss(struct c4iw_ep *ep, u16 opt)
 
 static enum c4iw_ep_state state_read(struct c4iw_ep_common *epc)
 {
-	unsigned long flags;
 	enum c4iw_ep_state state;
 
-	spin_lock_irqsave(&epc->lock, flags);
+	mutex_lock(&epc->mutex);
 	state = epc->state;
-	spin_unlock_irqrestore(&epc->lock, flags);
+	mutex_unlock(&epc->mutex);
 	return state;
 }
 
@@ -235,12 +234,10 @@ static void __state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new)
 
 static void state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&epc->lock, flags);
+	mutex_lock(&epc->mutex);
 	PDBG("%s - %s -> %s\n", __func__, states[epc->state], states[new]);
 	__state_set(epc, new);
-	spin_unlock_irqrestore(&epc->lock, flags);
+	mutex_unlock(&epc->mutex);
 	return;
 }
 
@@ -251,8 +248,8 @@ static void *alloc_ep(int size, gfp_t gfp)
 	epc = kzalloc(size, gfp);
 	if (epc) {
 		kref_init(&epc->kref);
-		spin_lock_init(&epc->lock);
-		init_waitqueue_head(&epc->waitq);
+		mutex_init(&epc->mutex);
+		c4iw_init_wr_wait(&epc->wr_wait);
 	}
 	PDBG("%s alloc ep %p\n", __func__, epc);
 	return epc;
@@ -1131,7 +1128,6 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 {
 	struct c4iw_ep *ep;
 	struct cpl_abort_rpl_rss *rpl = cplhdr(skb);
-	unsigned long flags;
 	int release = 0;
 	unsigned int tid = GET_TID(rpl);
 	struct tid_info *t = dev->rdev.lldi.tids;
@@ -1139,7 +1135,7 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = lookup_tid(t, tid);
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	BUG_ON(!ep);
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case ABORTING:
 		__state_set(&ep->com, DEAD);
@@ -1150,7 +1146,7 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		     __func__, ep, ep->com.state);
 		break;
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 
 	if (release)
 		release_ep_resources(ep);
@@ -1213,9 +1209,9 @@ static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	}
 	PDBG("%s ep %p status %d error %d\n", __func__, ep,
 	     rpl->status, status2errno(rpl->status));
-	ep->com.rpl_err = status2errno(rpl->status);
-	ep->com.rpl_done = 1;
-	wake_up(&ep->com.waitq);
+	ep->com.wr_wait.ret = status2errno(rpl->status);
+	ep->com.wr_wait.done = 1;
+	wake_up(&ep->com.wr_wait.wait);
 
 	return 0;
 }
@@ -1249,9 +1245,9 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_listen_ep *ep = lookup_stid(t, stid);
 
 	PDBG("%s ep %p\n", __func__, ep);
-	ep->com.rpl_err = status2errno(rpl->status);
-	ep->com.rpl_done = 1;
-	wake_up(&ep->com.waitq);
+	ep->com.wr_wait.ret = status2errno(rpl->status);
+	ep->com.wr_wait.done = 1;
+	wake_up(&ep->com.wr_wait.wait);
 	return 0;
 }
 
@@ -1478,7 +1474,6 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct cpl_peer_close *hdr = cplhdr(skb);
 	struct c4iw_ep *ep;
 	struct c4iw_qp_attributes attrs;
-	unsigned long flags;
 	int disconnect = 1;
 	int release = 0;
 	int closing = 0;
@@ -1489,7 +1484,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	dst_confirm(ep->dst);
 
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case MPA_REQ_WAIT:
 		__state_set(&ep->com, CLOSING);
@@ -1507,17 +1502,17 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 		 * in rdma connection migration (see c4iw_accept_cr()).
 		 */
 		__state_set(&ep->com, CLOSING);
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
+		ep->com.wr_wait.done = 1;
+		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.waitq);
+		wake_up(&ep->com.wr_wait.wait);
 		break;
 	case MPA_REP_SENT:
 		__state_set(&ep->com, CLOSING);
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
+		ep->com.wr_wait.done = 1;
+		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.waitq);
+		wake_up(&ep->com.wr_wait.wait);
 		break;
 	case FPDU_MODE:
 		start_ep_timer(ep);
@@ -1550,7 +1545,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	default:
 		BUG_ON(1);
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 	if (closing) {
 		attrs.next_state = C4IW_QP_STATE_CLOSING;
 		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
@@ -1581,7 +1576,6 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_qp_attributes attrs;
 	int ret;
 	int release = 0;
-	unsigned long flags;
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int tid = GET_TID(req);
 
@@ -1591,9 +1585,17 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		     ep->hwtid);
 		return 0;
 	}
-	spin_lock_irqsave(&ep->com.lock, flags);
 	PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
 	     ep->com.state);
+
+	/*
+	 * Wake up any threads in rdma_init() or rdma_fini().
+	 */
+	ep->com.wr_wait.done = 1;
+	ep->com.wr_wait.ret = -ECONNRESET;
+	wake_up(&ep->com.wr_wait.wait);
+
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case CONNECTING:
 		break;
@@ -1605,23 +1607,8 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		connect_reply_upcall(ep, -ECONNRESET);
 		break;
 	case MPA_REP_SENT:
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
-		PDBG("waking up ep %p\n", ep);
-		wake_up(&ep->com.waitq);
 		break;
 	case MPA_REQ_RCVD:
-
-		/*
-		 * We're gonna mark this puppy DEAD, but keep
-		 * the reference on it until the ULP accepts or
-		 * rejects the CR. Also wake up anyone waiting
-		 * in rdma connection migration (see c4iw_accept_cr()).
-		 */
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
-		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.waitq);
 		break;
 	case MORIBUND:
 	case CLOSING:
@@ -1644,7 +1631,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		break;
 	case DEAD:
 		PDBG("%s PEER_ABORT IN DEAD STATE!!!!\n", __func__);
-		spin_unlock_irqrestore(&ep->com.lock, flags);
+		mutex_unlock(&ep->com.mutex);
 		return 0;
 	default:
 		BUG_ON(1);
@@ -1655,7 +1642,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		__state_set(&ep->com, DEAD);
 		release = 1;
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 
 	rpl_skb = get_skb(skb, sizeof(*rpl), GFP_KERNEL);
 	if (!rpl_skb) {
@@ -1681,7 +1668,6 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_ep *ep;
 	struct c4iw_qp_attributes attrs;
 	struct cpl_close_con_rpl *rpl = cplhdr(skb);
-	unsigned long flags;
 	int release = 0;
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int tid = GET_TID(rpl);
@@ -1692,7 +1678,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	BUG_ON(!ep);
 
 	/* The cm_id may be null if we failed to connect */
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case CLOSING:
 		__state_set(&ep->com, MORIBUND);
@@ -1717,7 +1703,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		BUG_ON(1);
 		break;
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 	if (release)
 		release_ep_resources(ep);
 	return 0;
@@ -1725,23 +1711,24 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 
 static int terminate(struct c4iw_dev *dev, struct sk_buff *skb)
 {
-	struct c4iw_ep *ep;
-	struct cpl_rdma_terminate *term = cplhdr(skb);
+	struct cpl_rdma_terminate *rpl = cplhdr(skb);
 	struct tid_info *t = dev->rdev.lldi.tids;
-	unsigned int tid = GET_TID(term);
+	unsigned int tid = GET_TID(rpl);
+	struct c4iw_ep *ep;
+	struct c4iw_qp_attributes attrs;
 
 	ep = lookup_tid(t, tid);
+	BUG_ON(!ep);
 
-	if (state_read(&ep->com) != FPDU_MODE)
-		return 0;
+	if (ep->com.qp) {
+		printk(KERN_WARNING MOD "TERM received tid %u qpid %u\n", tid,
+		       ep->com.qp->wq.sq.qid);
+		attrs.next_state = C4IW_QP_STATE_TERMINATE;
+		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
+			       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
+	} else
+		printk(KERN_WARNING MOD "TERM received tid %u no qp\n", tid);
 
-	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
-	skb_pull(skb, sizeof *term);
-	PDBG("%s saving %d bytes of term msg\n", __func__, skb->len);
-	skb_copy_from_linear_data(skb, ep->com.qp->attr.terminate_buffer,
-				  skb->len);
-	ep->com.qp->attr.terminate_msg_len = skb->len;
-	ep->com.qp->attr.is_terminate_local = 0;
 	return 0;
 }
 
@@ -1762,8 +1749,8 @@ static int fw4_ack(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = lookup_tid(t, tid);
 	PDBG("%s ep %p tid %u credits %u\n", __func__, ep, ep->hwtid, credits);
 	if (credits == 0) {
-		PDBG(KERN_ERR "%s 0 credit ack ep %p tid %u state %u\n",
-			__func__, ep, ep->hwtid, state_read(&ep->com));
+		PDBG("%s 0 credit ack ep %p tid %u state %u\n",
+		     __func__, ep, ep->hwtid, state_read(&ep->com));
 		return 0;
 	}
 
@@ -2042,6 +2029,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 	}
 
 	state_set(&ep->com, LISTEN);
+	c4iw_init_wr_wait(&ep->com.wr_wait);
 	err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0], ep->stid,
 				  ep->com.local_addr.sin_addr.s_addr,
 				  ep->com.local_addr.sin_port,
@@ -2050,15 +2038,8 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 		goto fail3;
 
 	/* wait for pass_open_rpl */
-	wait_event_timeout(ep->com.waitq, ep->com.rpl_done, C4IW_WR_TO);
-	if (ep->com.rpl_done)
-		err = ep->com.rpl_err;
-	else {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(ep->com.dev->rdev.lldi.pdev));
-		ep->com.dev->rdev.flags = T4_FATAL_ERROR;
-		err = -EIO;
-	}
+	err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
+				  __func__);
 	if (!err) {
 		cm_id->provider_data = ep;
 		goto out;
@@ -2082,20 +2063,12 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
 
 	might_sleep();
 	state_set(&ep->com, DEAD);
-	ep->com.rpl_done = 0;
-	ep->com.rpl_err = 0;
+	c4iw_init_wr_wait(&ep->com.wr_wait);
 	err = listen_stop(ep);
 	if (err)
 		goto done;
-	wait_event_timeout(ep->com.waitq, ep->com.rpl_done, C4IW_WR_TO);
-	if (ep->com.rpl_done)
-		err = ep->com.rpl_err;
-	else {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(ep->com.dev->rdev.lldi.pdev));
-		ep->com.dev->rdev.flags = T4_FATAL_ERROR;
-		err = -EIO;
-	}
+	err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
+				  __func__);
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
 done:
 	cm_id->rem_ref(cm_id);
@@ -2106,12 +2079,11 @@ done:
 int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 {
 	int ret = 0;
-	unsigned long flags;
 	int close = 0;
 	int fatal = 0;
 	struct c4iw_rdev *rdev;
 
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 
 	PDBG("%s ep %p state %s, abrupt %d\n", __func__, ep,
 	     states[ep->com.state], abrupt);
@@ -2158,7 +2130,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 		break;
 	}
 
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 	if (close) {
 		if (abrupt)
 			ret = abort_connection(ep, NULL, gfp);
@@ -2172,6 +2144,13 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 	return ret;
 }
 
+static int async_event(struct c4iw_dev *dev, struct sk_buff *skb)
+{
+	struct cpl_fw6_msg *rpl = cplhdr(skb);
+	c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+	return 0;
+}
+
 /*
  * These are the real handlers that are called from a
  * work queue.
@@ -2190,7 +2169,8 @@ static c4iw_handler_func work_handlers[NUM_CPL_CMDS] = {
 	[CPL_ABORT_REQ_RSS] = peer_abort,
 	[CPL_CLOSE_CON_RPL] = close_con_rpl,
 	[CPL_RDMA_TERMINATE] = terminate,
-	[CPL_FW4_ACK] = fw4_ack
+	[CPL_FW4_ACK] = fw4_ack,
+	[CPL_FW6_MSG] = async_event
 };
 
 static void process_timeout(struct c4iw_ep *ep)
@@ -2198,7 +2178,7 @@ static void process_timeout(struct c4iw_ep *ep)
 	struct c4iw_qp_attributes attrs;
 	int abort = 1;
 
-	spin_lock_irq(&ep->com.lock);
+	mutex_lock(&ep->com.mutex);
 	PDBG("%s ep %p tid %u state %d\n", __func__, ep, ep->hwtid,
 	     ep->com.state);
 	switch (ep->com.state) {
@@ -2225,7 +2205,7 @@ static void process_timeout(struct c4iw_ep *ep)
 		WARN_ON(1);
 		abort = 0;
 	}
-	spin_unlock_irq(&ep->com.lock);
+	mutex_unlock(&ep->com.mutex);
 	if (abort)
 		abort_connection(ep, NULL, GFP_KERNEL);
 	c4iw_put_ep(&ep->com);
@@ -2309,6 +2289,7 @@ static int set_tcb_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		printk(KERN_ERR MOD "Unexpected SET_TCB_RPL status %u "
 		       "for tid %u\n", rpl->status, GET_TID(rpl));
 	}
+	kfree_skb(skb);
 	return 0;
 }
 
@@ -2323,20 +2304,25 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
 	switch (rpl->type) {
 	case 1:
 		ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff);
-		wr_waitp = (__force struct c4iw_wr_wait *)rpl->data[1];
+		wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1];
 		PDBG("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret);
 		if (wr_waitp) {
-			wr_waitp->ret = ret;
+			if (ret)
+				wr_waitp->ret = -ret;
+			else
+				wr_waitp->ret = 0;
 			wr_waitp->done = 1;
 			wake_up(&wr_waitp->wait);
 		}
+		kfree_skb(skb);
 		break;
 	case 2:
-		c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+		sched(dev, skb);
 		break;
 	default:
 		printk(KERN_ERR MOD "%s unexpected fw6 msg type %u\n", __func__,
 		       rpl->type);
+		kfree_skb(skb);
 		break;
 	}
 	return 0;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index b3daf39..8d8f8ad 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -55,7 +55,7 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			V_FW_RI_RES_WR_NRES(1) |
 			FW_WR_COMPL(1));
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (u64)&wr_wait;
+	res_wr->cookie = (unsigned long) &wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_RESET;
@@ -64,14 +64,7 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 	c4iw_init_wr_wait(&wr_wait);
 	ret = c4iw_ofld_send(rdev, skb);
 	if (!ret) {
-		wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-		if (!wr_wait.done) {
-			printk(KERN_ERR MOD "Device %s not responding!\n",
-			       pci_name(rdev->lldi.pdev));
-			rdev->flags = T4_FATAL_ERROR;
-			ret = -EIO;
-		} else
-			ret = wr_wait.ret;
+		ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
 	}
 
 	kfree(cq->sw_queue);
@@ -132,7 +125,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			V_FW_RI_RES_WR_NRES(1) |
 			FW_WR_COMPL(1));
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (u64)&wr_wait;
+	res_wr->cookie = (unsigned long) &wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_WRITE;
@@ -157,14 +150,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 	if (ret)
 		goto err4;
 	PDBG("%s wait_event wr_wait %p\n", __func__, &wr_wait);
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rdev->lldi.pdev));
-		rdev->flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
 	if (ret)
 		goto err4;
 
@@ -476,6 +462,11 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 		goto proc_cqe;
 	}
 
+	if (CQE_OPCODE(hw_cqe) == FW_RI_TERMINATE) {
+		ret = -EAGAIN;
+		goto skip_cqe;
+	}
+
 	/*
 	 * RECV completion.
 	 */
@@ -696,6 +687,7 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 		case T4_ERR_MSN_RANGE:
 		case T4_ERR_IRD_OVERFLOW:
 		case T4_ERR_OPCODE:
+		case T4_ERR_INTERNAL_ERR:
 			wc->status = IB_WC_FATAL_ERR;
 			break;
 		case T4_ERR_SWFLUSH:
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 9bbf491..54fbc11 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -49,29 +49,33 @@ static DEFINE_MUTEX(dev_mutex);
 
 static struct dentry *c4iw_debugfs_root;
 
-struct debugfs_qp_data {
+struct c4iw_debugfs_data {
 	struct c4iw_dev *devp;
 	char *buf;
 	int bufsize;
 	int pos;
 };
 
-static int count_qps(int id, void *p, void *data)
+static int count_idrs(int id, void *p, void *data)
 {
-	struct c4iw_qp *qp = p;
 	int *countp = data;
 
-	if (id != qp->wq.sq.qid)
-		return 0;
-
 	*countp = *countp + 1;
 	return 0;
 }
 
-static int dump_qps(int id, void *p, void *data)
+static ssize_t debugfs_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
+{
+	struct c4iw_debugfs_data *d = file->private_data;
+
+	return simple_read_from_buffer(buf, count, ppos, d->buf, d->pos);
+}
+
+static int dump_qp(int id, void *p, void *data)
 {
 	struct c4iw_qp *qp = p;
-	struct debugfs_qp_data *qpd = data;
+	struct c4iw_debugfs_data *qpd = data;
 	int space;
 	int cc;
 
@@ -101,7 +105,7 @@ static int dump_qps(int id, void *p, void *data)
 
 static int qp_release(struct inode *inode, struct file *file)
 {
-	struct debugfs_qp_data *qpd = file->private_data;
+	struct c4iw_debugfs_data *qpd = file->private_data;
 	if (!qpd) {
 		printk(KERN_INFO "%s null qpd?\n", __func__);
 		return 0;
@@ -113,7 +117,7 @@ static int qp_release(struct inode *inode, struct file *file)
 
 static int qp_open(struct inode *inode, struct file *file)
 {
-	struct debugfs_qp_data *qpd;
+	struct c4iw_debugfs_data *qpd;
 	int ret = 0;
 	int count = 1;
 
@@ -126,7 +130,7 @@ static int qp_open(struct inode *inode, struct file *file)
 	qpd->pos = 0;
 
 	spin_lock_irq(&qpd->devp->lock);
-	idr_for_each(&qpd->devp->qpidr, count_qps, &count);
+	idr_for_each(&qpd->devp->qpidr, count_idrs, &count);
 	spin_unlock_irq(&qpd->devp->lock);
 
 	qpd->bufsize = count * 128;
@@ -137,7 +141,7 @@ static int qp_open(struct inode *inode, struct file *file)
 	}
 
 	spin_lock_irq(&qpd->devp->lock);
-	idr_for_each(&qpd->devp->qpidr, dump_qps, qpd);
+	idr_for_each(&qpd->devp->qpidr, dump_qp, qpd);
 	spin_unlock_irq(&qpd->devp->lock);
 
 	qpd->buf[qpd->pos++] = 0;
@@ -149,43 +153,86 @@ out:
 	return ret;
 }
 
-static ssize_t qp_read(struct file *file, char __user *buf, size_t count,
-			loff_t *ppos)
+static const struct file_operations qp_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = qp_open,
+	.release = qp_release,
+	.read    = debugfs_read,
+	.llseek  = default_llseek,
+};
+
+static int dump_stag(int id, void *p, void *data)
 {
-	struct debugfs_qp_data *qpd = file->private_data;
-	loff_t pos = *ppos;
-	loff_t avail = qpd->pos;
+	struct c4iw_debugfs_data *stagd = data;
+	int space;
+	int cc;
 
-	if (pos < 0)
-		return -EINVAL;
-	if (pos >= avail)
+	space = stagd->bufsize - stagd->pos - 1;
+	if (space == 0)
+		return 1;
+
+	cc = snprintf(stagd->buf + stagd->pos, space, "0x%x\n", id<<8);
+	if (cc < space)
+		stagd->pos += cc;
+	return 0;
+}
+
+static int stag_release(struct inode *inode, struct file *file)
+{
+	struct c4iw_debugfs_data *stagd = file->private_data;
+	if (!stagd) {
+		printk(KERN_INFO "%s null stagd?\n", __func__);
 		return 0;
-	if (count > avail - pos)
-		count = avail - pos;
+	}
+	kfree(stagd->buf);
+	kfree(stagd);
+	return 0;
+}
 
-	while (count) {
-		size_t len = 0;
+static int stag_open(struct inode *inode, struct file *file)
+{
+	struct c4iw_debugfs_data *stagd;
+	int ret = 0;
+	int count = 1;
 
-		len = min((int)count, (int)qpd->pos - (int)pos);
-		if (copy_to_user(buf, qpd->buf + pos, len))
-			return -EFAULT;
-		if (len == 0)
-			return -EINVAL;
+	stagd = kmalloc(sizeof *stagd, GFP_KERNEL);
+	if (!stagd) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	stagd->devp = inode->i_private;
+	stagd->pos = 0;
+
+	spin_lock_irq(&stagd->devp->lock);
+	idr_for_each(&stagd->devp->mmidr, count_idrs, &count);
+	spin_unlock_irq(&stagd->devp->lock);
 
-		buf += len;
-		pos += len;
-		count -= len;
+	stagd->bufsize = count * sizeof("0x12345678\n");
+	stagd->buf = kmalloc(stagd->bufsize, GFP_KERNEL);
+	if (!stagd->buf) {
+		ret = -ENOMEM;
+		goto err1;
 	}
-	count = pos - *ppos;
-	*ppos = pos;
-	return count;
+
+	spin_lock_irq(&stagd->devp->lock);
+	idr_for_each(&stagd->devp->mmidr, dump_stag, stagd);
+	spin_unlock_irq(&stagd->devp->lock);
+
+	stagd->buf[stagd->pos++] = 0;
+	file->private_data = stagd;
+	goto out;
+err1:
+	kfree(stagd);
+out:
+	return ret;
 }
 
-static const struct file_operations qp_debugfs_fops = {
+static const struct file_operations stag_debugfs_fops = {
 	.owner   = THIS_MODULE,
-	.open    = qp_open,
-	.release = qp_release,
-	.read    = qp_read,
+	.open    = stag_open,
+	.release = stag_release,
+	.read    = debugfs_read,
+	.llseek  = default_llseek,
 };
 
 static int setup_debugfs(struct c4iw_dev *devp)
@@ -199,6 +246,11 @@ static int setup_debugfs(struct c4iw_dev *devp)
 				 (void *)devp, &qp_debugfs_fops);
 	if (de && de->d_inode)
 		de->d_inode->i_size = 4096;
+
+	de = debugfs_create_file("stags", S_IWUSR, devp->debugfs_root,
+				 (void *)devp, &stag_debugfs_fops);
+	if (de && de->d_inode)
+		de->d_inode->i_size = 4096;
 	return 0;
 }
 
@@ -290,7 +342,14 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 		printk(KERN_ERR MOD "error %d initializing rqt pool\n", err);
 		goto err3;
 	}
+	err = c4iw_ocqp_pool_create(rdev);
+	if (err) {
+		printk(KERN_ERR MOD "error %d initializing ocqp pool\n", err);
+		goto err4;
+	}
 	return 0;
+err4:
+	c4iw_rqtpool_destroy(rdev);
 err3:
 	c4iw_pblpool_destroy(rdev);
 err2:
@@ -317,6 +376,7 @@ static void c4iw_remove(struct c4iw_dev *dev)
 	idr_destroy(&dev->cqidr);
 	idr_destroy(&dev->qpidr);
 	idr_destroy(&dev->mmidr);
+	iounmap(dev->rdev.oc_mw_kva);
 	ib_dealloc_device(&dev->ibdev);
 }
 
@@ -332,6 +392,17 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 	}
 	devp->rdev.lldi = *infop;
 
+	devp->rdev.oc_mw_pa = pci_resource_start(devp->rdev.lldi.pdev, 2) +
+		(pci_resource_len(devp->rdev.lldi.pdev, 2) -
+		 roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size));
+	devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,
+					       devp->rdev.lldi.vr->ocq.size);
+
+	printk(KERN_INFO MOD "ocq memory: "
+	       "hw_start 0x%x size %u mw_pa 0x%lx mw_kva %p\n",
+	       devp->rdev.lldi.vr->ocq.start, devp->rdev.lldi.vr->ocq.size,
+	       devp->rdev.oc_mw_pa, devp->rdev.oc_mw_kva);
+
 	mutex_lock(&dev_mutex);
 
 	ret = c4iw_rdev_open(&devp->rdev);
@@ -383,46 +454,6 @@ out:
 	return dev;
 }
 
-static struct sk_buff *t4_pktgl_to_skb(const struct pkt_gl *gl,
-				       unsigned int skb_len,
-				       unsigned int pull_len)
-{
-	struct sk_buff *skb;
-	struct skb_shared_info *ssi;
-
-	if (gl->tot_len <= 512) {
-		skb = alloc_skb(gl->tot_len, GFP_ATOMIC);
-		if (unlikely(!skb))
-			goto out;
-		__skb_put(skb, gl->tot_len);
-		skb_copy_to_linear_data(skb, gl->va, gl->tot_len);
-	} else {
-		skb = alloc_skb(skb_len, GFP_ATOMIC);
-		if (unlikely(!skb))
-			goto out;
-		__skb_put(skb, pull_len);
-		skb_copy_to_linear_data(skb, gl->va, pull_len);
-
-		ssi = skb_shinfo(skb);
-		ssi->frags[0].page = gl->frags[0].page;
-		ssi->frags[0].page_offset = gl->frags[0].page_offset + pull_len;
-		ssi->frags[0].size = gl->frags[0].size - pull_len;
-		if (gl->nfrags > 1)
-			memcpy(&ssi->frags[1], &gl->frags[1],
-			       (gl->nfrags - 1) * sizeof(skb_frag_t));
-		ssi->nr_frags = gl->nfrags;
-
-		skb->len = gl->tot_len;
-		skb->data_len = skb->len - pull_len;
-		skb->truesize += skb->data_len;
-
-		/* Get a reference for the last page, we don't own it */
-		get_page(gl->frags[gl->nfrags - 1].page);
-	}
-out:
-	return skb;
-}
-
 static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
 			const struct pkt_gl *gl)
 {
@@ -447,7 +478,7 @@ static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
 		c4iw_ev_handler(dev, qid);
 		return 0;
 	} else {
-		skb = t4_pktgl_to_skb(gl, 128, 128);
+		skb = cxgb4_pktgl_to_skb(gl, 128, 128);
 		if (unlikely(!skb))
 			goto nomem;
 	}
diff --git a/drivers/infiniband/hw/cxgb4/ev.c b/drivers/infiniband/hw/cxgb4/ev.c
index 491e76a..c13041a 100644
--- a/drivers/infiniband/hw/cxgb4/ev.c
+++ b/drivers/infiniband/hw/cxgb4/ev.c
@@ -60,7 +60,7 @@ static void post_qp_event(struct c4iw_dev *dev, struct c4iw_cq *chp,
 	if (qhp->attr.state == C4IW_QP_STATE_RTS) {
 		attrs.next_state = C4IW_QP_STATE_TERMINATE;
 		c4iw_modify_qp(qhp->rhp, qhp, C4IW_QP_ATTR_NEXT_STATE,
-			       &attrs, 1);
+			       &attrs, 0);
 	}
 
 	event.event = ib_event;
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index ed459b8..16032cd 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -46,6 +46,7 @@
 #include <linux/timer.h>
 #include <linux/io.h>
 #include <linux/kfifo.h>
+#include <linux/mutex.h>
 
 #include <asm/byteorder.h>
 
@@ -79,21 +80,6 @@ static inline void *cplhdr(struct sk_buff *skb)
 	return skb->data;
 }
 
-#define C4IW_WR_TO (10*HZ)
-
-struct c4iw_wr_wait {
-	wait_queue_head_t wait;
-	int done;
-	int ret;
-};
-
-static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp)
-{
-	wr_waitp->ret = 0;
-	wr_waitp->done = 0;
-	init_waitqueue_head(&wr_waitp->wait);
-}
-
 struct c4iw_resource {
 	struct kfifo tpt_fifo;
 	spinlock_t tpt_fifo_lock;
@@ -127,8 +113,11 @@ struct c4iw_rdev {
 	struct c4iw_dev_ucontext uctx;
 	struct gen_pool *pbl_pool;
 	struct gen_pool *rqt_pool;
+	struct gen_pool *ocqp_pool;
 	u32 flags;
 	struct cxgb4_lld_info lldi;
+	unsigned long oc_mw_pa;
+	void __iomem *oc_mw_kva;
 };
 
 static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -141,6 +130,44 @@ static inline int c4iw_num_stags(struct c4iw_rdev *rdev)
 	return min((int)T4_MAX_NUM_STAG, (int)(rdev->lldi.vr->stag.size >> 5));
 }
 
+#define C4IW_WR_TO (10*HZ)
+
+struct c4iw_wr_wait {
+	wait_queue_head_t wait;
+	int done;
+	int ret;
+};
+
+static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp)
+{
+	wr_waitp->ret = 0;
+	wr_waitp->done = 0;
+	init_waitqueue_head(&wr_waitp->wait);
+}
+
+static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev,
+				 struct c4iw_wr_wait *wr_waitp,
+				 u32 hwtid, u32 qpid,
+				 const char *func)
+{
+	unsigned to = C4IW_WR_TO;
+	do {
+
+		wait_event_timeout(wr_waitp->wait, wr_waitp->done, to);
+		if (!wr_waitp->done) {
+			printk(KERN_ERR MOD "%s - Device %s not responding - "
+			       "tid %u qpid %u\n", func,
+			       pci_name(rdev->lldi.pdev), hwtid, qpid);
+			to = to << 2;
+		}
+	} while (!wr_waitp->done);
+	if (wr_waitp->ret)
+		printk(KERN_WARNING MOD "%s: FW reply %d tid %u qpid %u\n",
+		       pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid);
+	return wr_waitp->ret;
+}
+
+
 struct c4iw_dev {
 	struct ib_device ibdev;
 	struct c4iw_rdev rdev;
@@ -327,6 +354,7 @@ struct c4iw_qp {
 	struct c4iw_qp_attributes attr;
 	struct t4_wq wq;
 	spinlock_t lock;
+	struct mutex mutex;
 	atomic_t refcnt;
 	wait_queue_head_t wait;
 	struct timer_list timer;
@@ -579,12 +607,10 @@ struct c4iw_ep_common {
 	struct c4iw_dev *dev;
 	enum c4iw_ep_state state;
 	struct kref kref;
-	spinlock_t lock;
+	struct mutex mutex;
 	struct sockaddr_in local_addr;
 	struct sockaddr_in remote_addr;
-	wait_queue_head_t waitq;
-	int rpl_done;
-	int rpl_err;
+	struct c4iw_wr_wait wr_wait;
 	unsigned long flags;
 };
 
@@ -654,8 +680,10 @@ int c4iw_init_resource(struct c4iw_rdev *rdev, u32 nr_tpt, u32 nr_pdid);
 int c4iw_init_ctrl_qp(struct c4iw_rdev *rdev);
 int c4iw_pblpool_create(struct c4iw_rdev *rdev);
 int c4iw_rqtpool_create(struct c4iw_rdev *rdev);
+int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev);
 void c4iw_pblpool_destroy(struct c4iw_rdev *rdev);
 void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev);
+void c4iw_ocqp_pool_destroy(struct c4iw_rdev *rdev);
 void c4iw_destroy_resource(struct c4iw_resource *rscp);
 int c4iw_destroy_ctrl_qp(struct c4iw_rdev *rdev);
 int c4iw_register_device(struct c4iw_dev *dev);
@@ -721,6 +749,8 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size);
 void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
 u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size);
 void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
+u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size);
+void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size);
 int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb);
 void c4iw_flush_hw_cq(struct t4_cq *cq);
 void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 269373a..273ffe4 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -71,7 +71,7 @@ static int write_adapter_mem(struct c4iw_rdev *rdev, u32 addr, u32 len,
 		if (i == (num_wqe-1)) {
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP(FW_ULPTX_WR) |
 						    FW_WR_COMPL(1));
-			req->wr.wr_lo = (__force __be64)&wr_wait;
+			req->wr.wr_lo = (__force __be64)(unsigned long) &wr_wait;
 		} else
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP(FW_ULPTX_WR));
 		req->wr.wr_mid = cpu_to_be32(
@@ -103,14 +103,7 @@ static int write_adapter_mem(struct c4iw_rdev *rdev, u32 addr, u32 len,
 		len -= C4IW_MAX_INLINE_SIZE;
 	}
 
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rdev->lldi.pdev));
-		rdev->flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 8f645c8..f66dd8b 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -54,9 +54,9 @@
 
 #include "iw_cxgb4.h"
 
-static int fastreg_support;
+static int fastreg_support = 1;
 module_param(fastreg_support, int, 0644);
-MODULE_PARM_DESC(fastreg_support, "Advertise fastreg support (default=0)");
+MODULE_PARM_DESC(fastreg_support, "Advertise fastreg support (default=1)");
 
 static int c4iw_modify_port(struct ib_device *ibdev,
 			    u8 port, int port_modify_mask,
@@ -149,19 +149,28 @@ static int c4iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 	addr = mm->addr;
 	kfree(mm);
 
-	if ((addr >= pci_resource_start(rdev->lldi.pdev, 2)) &&
-	    (addr < (pci_resource_start(rdev->lldi.pdev, 2) +
-		       pci_resource_len(rdev->lldi.pdev, 2)))) {
+	if ((addr >= pci_resource_start(rdev->lldi.pdev, 0)) &&
+	    (addr < (pci_resource_start(rdev->lldi.pdev, 0) +
+		    pci_resource_len(rdev->lldi.pdev, 0)))) {
 
 		/*
-		 * Map T4 DB register.
+		 * MA_SYNC register...
 		 */
-		if (vma->vm_flags & VM_READ)
-			return -EPERM;
-
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-		vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND;
-		vma->vm_flags &= ~VM_MAYREAD;
+		ret = io_remap_pfn_range(vma, vma->vm_start,
+					 addr >> PAGE_SHIFT,
+					 len, vma->vm_page_prot);
+	} else if ((addr >= pci_resource_start(rdev->lldi.pdev, 2)) &&
+		   (addr < (pci_resource_start(rdev->lldi.pdev, 2) +
+		    pci_resource_len(rdev->lldi.pdev, 2)))) {
+
+		/*
+		 * Map user DB or OCQP memory...
+		 */
+		if (addr >= rdev->oc_mw_pa)
+			vma->vm_page_prot = t4_pgprot_wc(vma->vm_page_prot);
+		else
+			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		ret = io_remap_pfn_range(vma, vma->vm_start,
 					 addr >> PAGE_SHIFT,
 					 len, vma->vm_page_prot);
@@ -382,7 +391,17 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr,
 static int c4iw_get_mib(struct ib_device *ibdev,
 			union rdma_protocol_stats *stats)
 {
-	return -ENOSYS;
+	struct tp_tcp_stats v4, v6;
+	struct c4iw_dev *c4iw_dev = to_c4iw_dev(ibdev);
+
+	cxgb4_get_tcp_stats(c4iw_dev->rdev.lldi.pdev, &v4, &v6);
+	memset(stats, 0, sizeof *stats);
+	stats->iw.tcpInSegs = v4.tcpInSegs + v6.tcpInSegs;
+	stats->iw.tcpOutSegs = v4.tcpOutSegs + v6.tcpOutSegs;
+	stats->iw.tcpRetransSegs = v4.tcpRetransSegs + v6.tcpRetransSegs;
+	stats->iw.tcpOutRsts = v4.tcpOutRsts + v6.tcpOutSegs;
+
+	return 0;
 }
 
 static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
@@ -472,6 +491,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.post_send = c4iw_post_send;
 	dev->ibdev.post_recv = c4iw_post_receive;
 	dev->ibdev.get_protocol_stats = c4iw_get_mib;
+	dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 93f6e5b..057cb25 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -31,6 +31,63 @@
  */
 #include "iw_cxgb4.h"
 
+static int ocqp_support;
+module_param(ocqp_support, int, 0644);
+MODULE_PARM_DESC(ocqp_support, "Support on-chip SQs (default=0)");
+
+static void set_state(struct c4iw_qp *qhp, enum c4iw_qp_state state)
+{
+	unsigned long flag;
+	spin_lock_irqsave(&qhp->lock, flag);
+	qhp->attr.state = state;
+	spin_unlock_irqrestore(&qhp->lock, flag);
+}
+
+static void dealloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	c4iw_ocqp_pool_free(rdev, sq->dma_addr, sq->memsize);
+}
+
+static void dealloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	dma_free_coherent(&(rdev->lldi.pdev->dev), sq->memsize, sq->queue,
+			  pci_unmap_addr(sq, mapping));
+}
+
+static void dealloc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	if (t4_sq_onchip(sq))
+		dealloc_oc_sq(rdev, sq);
+	else
+		dealloc_host_sq(rdev, sq);
+}
+
+static int alloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	if (!ocqp_support || !t4_ocqp_supported())
+		return -ENOSYS;
+	sq->dma_addr = c4iw_ocqp_pool_alloc(rdev, sq->memsize);
+	if (!sq->dma_addr)
+		return -ENOMEM;
+	sq->phys_addr = rdev->oc_mw_pa + sq->dma_addr -
+			rdev->lldi.vr->ocq.start;
+	sq->queue = (__force union t4_wr *)(rdev->oc_mw_kva + sq->dma_addr -
+					    rdev->lldi.vr->ocq.start);
+	sq->flags |= T4_SQ_ONCHIP;
+	return 0;
+}
+
+static int alloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	sq->queue = dma_alloc_coherent(&(rdev->lldi.pdev->dev), sq->memsize,
+				       &(sq->dma_addr), GFP_KERNEL);
+	if (!sq->queue)
+		return -ENOMEM;
+	sq->phys_addr = virt_to_phys(sq->queue);
+	pci_unmap_addr_set(sq, mapping, sq->dma_addr);
+	return 0;
+}
+
 static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		      struct c4iw_dev_ucontext *uctx)
 {
@@ -41,9 +98,7 @@ static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	dma_free_coherent(&(rdev->lldi.pdev->dev),
 			  wq->rq.memsize, wq->rq.queue,
 			  dma_unmap_addr(&wq->rq, mapping));
-	dma_free_coherent(&(rdev->lldi.pdev->dev),
-			  wq->sq.memsize, wq->sq.queue,
-			  dma_unmap_addr(&wq->sq, mapping));
+	dealloc_sq(rdev, &wq->sq);
 	c4iw_rqtpool_free(rdev, wq->rq.rqt_hwaddr, wq->rq.rqt_size);
 	kfree(wq->rq.sw_rq);
 	kfree(wq->sq.sw_sq);
@@ -93,11 +148,12 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	if (!wq->rq.rqt_hwaddr)
 		goto err4;
 
-	wq->sq.queue = dma_alloc_coherent(&(rdev->lldi.pdev->dev),
-					  wq->sq.memsize, &(wq->sq.dma_addr),
-					  GFP_KERNEL);
-	if (!wq->sq.queue)
-		goto err5;
+	if (user) {
+		if (alloc_oc_sq(rdev, &wq->sq) && alloc_host_sq(rdev, &wq->sq))
+			goto err5;
+	} else
+		if (alloc_host_sq(rdev, &wq->sq))
+			goto err5;
 	memset(wq->sq.queue, 0, wq->sq.memsize);
 	dma_unmap_addr_set(&wq->sq, mapping, wq->sq.dma_addr);
 
@@ -144,7 +200,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 			V_FW_RI_RES_WR_NRES(2) |
 			FW_WR_COMPL(1));
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (u64)&wr_wait;
+	res_wr->cookie = (unsigned long) &wr_wait;
 	res = res_wr->res;
 	res->u.sqrq.restype = FW_RI_RES_TYPE_SQ;
 	res->u.sqrq.op = FW_RI_RES_OP_WRITE;
@@ -158,6 +214,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		V_FW_RI_RES_WR_HOSTFCMODE(0) |	/* no host cidx updates */
 		V_FW_RI_RES_WR_CPRIO(0) |	/* don't keep in chip cache */
 		V_FW_RI_RES_WR_PCIECHN(0) |	/* set by uP at ri_init time */
+		t4_sq_onchip(&wq->sq) ? F_FW_RI_RES_WR_ONCHIP : 0 |
 		V_FW_RI_RES_WR_IQID(scq->cqid));
 	res->u.sqrq.dcaen_to_eqsize = cpu_to_be32(
 		V_FW_RI_RES_WR_DCAEN(0) |
@@ -198,14 +255,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	ret = c4iw_ofld_send(rdev, skb);
 	if (ret)
 		goto err7;
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rdev->lldi.pdev));
-		rdev->flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, wq->sq.qid, __func__);
 	if (ret)
 		goto err7;
 
@@ -219,9 +269,7 @@ err7:
 			  wq->rq.memsize, wq->rq.queue,
 			  dma_unmap_addr(&wq->rq, mapping));
 err6:
-	dma_free_coherent(&(rdev->lldi.pdev->dev),
-			  wq->sq.memsize, wq->sq.queue,
-			  dma_unmap_addr(&wq->sq, mapping));
+	dealloc_sq(rdev, &wq->sq);
 err5:
 	c4iw_rqtpool_free(rdev, wq->rq.rqt_hwaddr, wq->rq.rqt_size);
 err4:
@@ -263,6 +311,9 @@ static int build_immd(struct t4_sq *sq, struct fw_ri_immd *immdp,
 			rem -= len;
 		}
 	}
+	len = roundup(plen + sizeof *immdp, 16) - (plen + sizeof *immdp);
+	if (len)
+		memset(dstp, 0, len);
 	immdp->op = FW_RI_DATA_IMMD;
 	immdp->r1 = 0;
 	immdp->r2 = 0;
@@ -292,6 +343,7 @@ static int build_isgl(__be64 *queue_start, __be64 *queue_end,
 		if (++flitp == queue_end)
 			flitp = queue_start;
 	}
+	*flitp = (__force __be64)0;
 	isglp->op = FW_RI_DATA_ISGL;
 	isglp->r1 = 0;
 	isglp->nsge = cpu_to_be16(num_sge);
@@ -453,13 +505,15 @@ static int build_rdma_recv(struct c4iw_qp *qhp, union t4_recv_wr *wqe,
 	return 0;
 }
 
-static int build_fastreg(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16)
+static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
+			 struct ib_send_wr *wr, u8 *len16)
 {
 
 	struct fw_ri_immd *imdp;
 	__be64 *p;
 	int i;
 	int pbllen = roundup(wr->wr.fast_reg.page_list_len * sizeof(u64), 32);
+	int rem;
 
 	if (wr->wr.fast_reg.page_list_len > T4_MAX_FR_DEPTH)
 		return -EINVAL;
@@ -474,32 +528,28 @@ static int build_fastreg(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16)
 	wqe->fr.va_hi = cpu_to_be32(wr->wr.fast_reg.iova_start >> 32);
 	wqe->fr.va_lo_fbo = cpu_to_be32(wr->wr.fast_reg.iova_start &
 					0xffffffff);
-	if (pbllen > T4_MAX_FR_IMMD) {
-		struct c4iw_fr_page_list *c4pl =
-				to_c4iw_fr_page_list(wr->wr.fast_reg.page_list);
-		struct fw_ri_dsgl *sglp;
-
-		sglp = (struct fw_ri_dsgl *)(&wqe->fr + 1);
-		sglp->op = FW_RI_DATA_DSGL;
-		sglp->r1 = 0;
-		sglp->nsge = cpu_to_be16(1);
-		sglp->addr0 = cpu_to_be64(c4pl->dma_addr);
-		sglp->len0 = cpu_to_be32(pbllen);
-
-		*len16 = DIV_ROUND_UP(sizeof wqe->fr + sizeof *sglp, 16);
-	} else {
-		imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
-		imdp->op = FW_RI_DATA_IMMD;
-		imdp->r1 = 0;
-		imdp->r2 = 0;
-		imdp->immdlen = cpu_to_be32(pbllen);
-		p = (__be64 *)(imdp + 1);
-		for (i = 0; i < wr->wr.fast_reg.page_list_len; i++, p++)
-			*p = cpu_to_be64(
-				(u64)wr->wr.fast_reg.page_list->page_list[i]);
-		*len16 = DIV_ROUND_UP(sizeof wqe->fr + sizeof *imdp + pbllen,
-				      16);
+	WARN_ON(pbllen > T4_MAX_FR_IMMD);
+	imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
+	imdp->op = FW_RI_DATA_IMMD;
+	imdp->r1 = 0;
+	imdp->r2 = 0;
+	imdp->immdlen = cpu_to_be32(pbllen);
+	p = (__be64 *)(imdp + 1);
+	rem = pbllen;
+	for (i = 0; i < wr->wr.fast_reg.page_list_len; i++) {
+		*p = cpu_to_be64((u64)wr->wr.fast_reg.page_list->page_list[i]);
+		rem -= sizeof *p;
+		if (++p == (__be64 *)&sq->queue[sq->size])
+			p = (__be64 *)sq->queue;
 	}
+	BUG_ON(rem < 0);
+	while (rem) {
+		*p = 0;
+		rem -= sizeof *p;
+		if (++p == (__be64 *)&sq->queue[sq->size])
+			p = (__be64 *)sq->queue;
+	}
+	*len16 = DIV_ROUND_UP(sizeof wqe->fr + sizeof *imdp + pbllen, 16);
 	return 0;
 }
 
@@ -587,7 +637,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			fw_opcode = FW_RI_RDMA_READ_WR;
 			swsqe->opcode = FW_RI_READ_REQ;
 			if (wr->opcode == IB_WR_RDMA_READ_WITH_INV)
-				fw_flags |= FW_RI_RDMA_READ_INVALIDATE;
+				fw_flags = FW_RI_RDMA_READ_INVALIDATE;
 			else
 				fw_flags = 0;
 			err = build_rdma_read(wqe, wr, &len16);
@@ -600,7 +650,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		case IB_WR_FAST_REG_MR:
 			fw_opcode = FW_RI_FR_NSMR_WR;
 			swsqe->opcode = FW_RI_FAST_REGISTER;
-			err = build_fastreg(wqe, wr, &len16);
+			err = build_fastreg(&qhp->wq.sq, wqe, wr, &len16);
 			break;
 		case IB_WR_LOCAL_INV:
 			if (wr->send_flags & IB_SEND_FENCE)
@@ -905,46 +955,38 @@ static void post_terminate(struct c4iw_qp *qhp, struct t4_cqe *err_cqe,
  * Assumes qhp lock is held.
  */
 static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
-		       struct c4iw_cq *schp, unsigned long *flag)
+		       struct c4iw_cq *schp)
 {
 	int count;
 	int flushed;
+	unsigned long flag;
 
 	PDBG("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp);
-	/* take a ref on the qhp since we must release the lock */
-	atomic_inc(&qhp->refcnt);
-	spin_unlock_irqrestore(&qhp->lock, *flag);
 
 	/* locking hierarchy: cq lock first, then qp lock. */
-	spin_lock_irqsave(&rchp->lock, *flag);
+	spin_lock_irqsave(&rchp->lock, flag);
 	spin_lock(&qhp->lock);
 	c4iw_flush_hw_cq(&rchp->cq);
 	c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
 	flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
 	spin_unlock(&qhp->lock);
-	spin_unlock_irqrestore(&rchp->lock, *flag);
+	spin_unlock_irqrestore(&rchp->lock, flag);
 	if (flushed)
 		(*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context);
 
 	/* locking hierarchy: cq lock first, then qp lock. */
-	spin_lock_irqsave(&schp->lock, *flag);
+	spin_lock_irqsave(&schp->lock, flag);
 	spin_lock(&qhp->lock);
 	c4iw_flush_hw_cq(&schp->cq);
 	c4iw_count_scqes(&schp->cq, &qhp->wq, &count);
 	flushed = c4iw_flush_sq(&qhp->wq, &schp->cq, count);
 	spin_unlock(&qhp->lock);
-	spin_unlock_irqrestore(&schp->lock, *flag);
+	spin_unlock_irqrestore(&schp->lock, flag);
 	if (flushed)
 		(*schp->ibcq.comp_handler)(&schp->ibcq, schp->ibcq.cq_context);
-
-	/* deref */
-	if (atomic_dec_and_test(&qhp->refcnt))
-		wake_up(&qhp->wait);
-
-	spin_lock_irqsave(&qhp->lock, *flag);
 }
 
-static void flush_qp(struct c4iw_qp *qhp, unsigned long *flag)
+static void flush_qp(struct c4iw_qp *qhp)
 {
 	struct c4iw_cq *rchp, *schp;
 
@@ -958,7 +1000,7 @@ static void flush_qp(struct c4iw_qp *qhp, unsigned long *flag)
 			t4_set_cq_in_error(&schp->cq);
 		return;
 	}
-	__flush_qp(qhp, rchp, schp, flag);
+	__flush_qp(qhp, rchp, schp);
 }
 
 static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
@@ -966,7 +1008,6 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 {
 	struct fw_ri_wr *wqe;
 	int ret;
-	struct c4iw_wr_wait wr_wait;
 	struct sk_buff *skb;
 
 	PDBG("%s qhp %p qid 0x%x tid %u\n", __func__, qhp, qhp->wq.sq.qid,
@@ -985,28 +1026,16 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	wqe->flowid_len16 = cpu_to_be32(
 		FW_WR_FLOWID(ep->hwtid) |
 		FW_WR_LEN16(DIV_ROUND_UP(sizeof *wqe, 16)));
-	wqe->cookie = (u64)&wr_wait;
+	wqe->cookie = (unsigned long) &ep->com.wr_wait;
 
 	wqe->u.fini.type = FW_RI_TYPE_FINI;
-	c4iw_init_wr_wait(&wr_wait);
+	c4iw_init_wr_wait(&ep->com.wr_wait);
 	ret = c4iw_ofld_send(&rhp->rdev, skb);
 	if (ret)
 		goto out;
 
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rhp->rdev.lldi.pdev));
-		rhp->rdev.flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else {
-		ret = wr_wait.ret;
-		if (ret)
-			printk(KERN_WARNING MOD
-			       "%s: Abnormal close qpid %d ret %u\n",
-			       pci_name(rhp->rdev.lldi.pdev), qhp->wq.sq.qid,
-			       ret);
-	}
+	ret = c4iw_wait_for_reply(&rhp->rdev, &ep->com.wr_wait, qhp->ep->hwtid,
+			     qhp->wq.sq.qid, __func__);
 out:
 	PDBG("%s ret %d\n", __func__, ret);
 	return ret;
@@ -1040,7 +1069,6 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 {
 	struct fw_ri_wr *wqe;
 	int ret;
-	struct c4iw_wr_wait wr_wait;
 	struct sk_buff *skb;
 
 	PDBG("%s qhp %p qid 0x%x tid %u\n", __func__, qhp, qhp->wq.sq.qid,
@@ -1060,7 +1088,7 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 		FW_WR_FLOWID(qhp->ep->hwtid) |
 		FW_WR_LEN16(DIV_ROUND_UP(sizeof *wqe, 16)));
 
-	wqe->cookie = (u64)&wr_wait;
+	wqe->cookie = (unsigned long) &qhp->ep->com.wr_wait;
 
 	wqe->u.init.type = FW_RI_TYPE_INIT;
 	wqe->u.init.mpareqbit_p2ptype =
@@ -1097,19 +1125,13 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 	if (qhp->attr.mpa_attr.initiator)
 		build_rtr_msg(qhp->attr.mpa_attr.p2p_type, &wqe->u.init);
 
-	c4iw_init_wr_wait(&wr_wait);
+	c4iw_init_wr_wait(&qhp->ep->com.wr_wait);
 	ret = c4iw_ofld_send(&rhp->rdev, skb);
 	if (ret)
 		goto out;
 
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rhp->rdev.lldi.pdev));
-		rhp->rdev.flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(&rhp->rdev, &qhp->ep->com.wr_wait,
+				  qhp->ep->hwtid, qhp->wq.sq.qid, __func__);
 out:
 	PDBG("%s ret %d\n", __func__, ret);
 	return ret;
@@ -1122,7 +1144,6 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 {
 	int ret = 0;
 	struct c4iw_qp_attributes newattr = qhp->attr;
-	unsigned long flag;
 	int disconnect = 0;
 	int terminate = 0;
 	int abort = 0;
@@ -1133,7 +1154,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	     qhp, qhp->wq.sq.qid, qhp->wq.rq.qid, qhp->ep, qhp->attr.state,
 	     (mask & C4IW_QP_ATTR_NEXT_STATE) ? attrs->next_state : -1);
 
-	spin_lock_irqsave(&qhp->lock, flag);
+	mutex_lock(&qhp->mutex);
 
 	/* Process attr changes if in IDLE */
 	if (mask & C4IW_QP_ATTR_VALID_MODIFY) {
@@ -1184,7 +1205,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			qhp->attr.mpa_attr = attrs->mpa_attr;
 			qhp->attr.llp_stream_handle = attrs->llp_stream_handle;
 			qhp->ep = qhp->attr.llp_stream_handle;
-			qhp->attr.state = C4IW_QP_STATE_RTS;
+			set_state(qhp, C4IW_QP_STATE_RTS);
 
 			/*
 			 * Ref the endpoint here and deref when we
@@ -1193,15 +1214,13 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			 * transition.
 			 */
 			c4iw_get_ep(&qhp->ep->com);
-			spin_unlock_irqrestore(&qhp->lock, flag);
 			ret = rdma_init(rhp, qhp);
-			spin_lock_irqsave(&qhp->lock, flag);
 			if (ret)
 				goto err;
 			break;
 		case C4IW_QP_STATE_ERROR:
-			qhp->attr.state = C4IW_QP_STATE_ERROR;
-			flush_qp(qhp, &flag);
+			set_state(qhp, C4IW_QP_STATE_ERROR);
+			flush_qp(qhp);
 			break;
 		default:
 			ret = -EINVAL;
@@ -1212,38 +1231,38 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 		switch (attrs->next_state) {
 		case C4IW_QP_STATE_CLOSING:
 			BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
-			qhp->attr.state = C4IW_QP_STATE_CLOSING;
+			set_state(qhp, C4IW_QP_STATE_CLOSING);
 			ep = qhp->ep;
 			if (!internal) {
 				abort = 0;
 				disconnect = 1;
-				c4iw_get_ep(&ep->com);
+				c4iw_get_ep(&qhp->ep->com);
 			}
-			spin_unlock_irqrestore(&qhp->lock, flag);
 			ret = rdma_fini(rhp, qhp, ep);
-			spin_lock_irqsave(&qhp->lock, flag);
 			if (ret) {
-				c4iw_get_ep(&ep->com);
+				if (internal)
+					c4iw_get_ep(&qhp->ep->com);
 				disconnect = abort = 1;
 				goto err;
 			}
 			break;
 		case C4IW_QP_STATE_TERMINATE:
-			qhp->attr.state = C4IW_QP_STATE_TERMINATE;
+			set_state(qhp, C4IW_QP_STATE_TERMINATE);
 			if (qhp->ibqp.uobject)
 				t4_set_wq_in_error(&qhp->wq);
 			ep = qhp->ep;
-			c4iw_get_ep(&ep->com);
-			terminate = 1;
+			if (!internal)
+				terminate = 1;
 			disconnect = 1;
+			c4iw_get_ep(&qhp->ep->com);
 			break;
 		case C4IW_QP_STATE_ERROR:
-			qhp->attr.state = C4IW_QP_STATE_ERROR;
+			set_state(qhp, C4IW_QP_STATE_ERROR);
 			if (!internal) {
 				abort = 1;
 				disconnect = 1;
 				ep = qhp->ep;
-				c4iw_get_ep(&ep->com);
+				c4iw_get_ep(&qhp->ep->com);
 			}
 			goto err;
 			break;
@@ -1259,8 +1278,8 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 		}
 		switch (attrs->next_state) {
 		case C4IW_QP_STATE_IDLE:
-			flush_qp(qhp, &flag);
-			qhp->attr.state = C4IW_QP_STATE_IDLE;
+			flush_qp(qhp);
+			set_state(qhp, C4IW_QP_STATE_IDLE);
 			qhp->attr.llp_stream_handle = NULL;
 			c4iw_put_ep(&qhp->ep->com);
 			qhp->ep = NULL;
@@ -1282,7 +1301,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			ret = -EINVAL;
 			goto out;
 		}
-		qhp->attr.state = C4IW_QP_STATE_IDLE;
+		set_state(qhp, C4IW_QP_STATE_IDLE);
 		break;
 	case C4IW_QP_STATE_TERMINATE:
 		if (!internal) {
@@ -1305,15 +1324,16 @@ err:
 
 	/* disassociate the LLP connection */
 	qhp->attr.llp_stream_handle = NULL;
-	ep = qhp->ep;
+	if (!ep)
+		ep = qhp->ep;
 	qhp->ep = NULL;
-	qhp->attr.state = C4IW_QP_STATE_ERROR;
+	set_state(qhp, C4IW_QP_STATE_ERROR);
 	free = 1;
 	wake_up(&qhp->wait);
 	BUG_ON(!ep);
-	flush_qp(qhp, &flag);
+	flush_qp(qhp);
 out:
-	spin_unlock_irqrestore(&qhp->lock, flag);
+	mutex_unlock(&qhp->mutex);
 
 	if (terminate)
 		post_terminate(qhp, NULL, internal ? GFP_ATOMIC : GFP_KERNEL);
@@ -1335,7 +1355,6 @@ out:
 	 */
 	if (free)
 		c4iw_put_ep(&ep->com);
-
 	PDBG("%s exit state %d\n", __func__, qhp->attr.state);
 	return ret;
 }
@@ -1380,7 +1399,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	int sqsize, rqsize;
 	struct c4iw_ucontext *ucontext;
 	int ret;
-	struct c4iw_mm_entry *mm1, *mm2, *mm3, *mm4;
+	struct c4iw_mm_entry *mm1, *mm2, *mm3, *mm4, *mm5 = NULL;
 
 	PDBG("%s ib_pd %p\n", __func__, pd);
 
@@ -1450,6 +1469,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	qhp->attr.max_ord = 1;
 	qhp->attr.max_ird = 1;
 	spin_lock_init(&qhp->lock);
+	mutex_init(&qhp->mutex);
 	init_waitqueue_head(&qhp->wait);
 	atomic_set(&qhp->refcnt, 1);
 
@@ -1478,7 +1498,15 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 			ret = -ENOMEM;
 			goto err6;
 		}
-
+		if (t4_sq_onchip(&qhp->wq.sq)) {
+			mm5 = kmalloc(sizeof *mm5, GFP_KERNEL);
+			if (!mm5) {
+				ret = -ENOMEM;
+				goto err7;
+			}
+			uresp.flags = C4IW_QPF_ONCHIP;
+		} else
+			uresp.flags = 0;
 		uresp.qid_mask = rhp->rdev.qpmask;
 		uresp.sqid = qhp->wq.sq.qid;
 		uresp.sq_size = qhp->wq.sq.size;
@@ -1487,6 +1515,10 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		uresp.rq_size = qhp->wq.rq.size;
 		uresp.rq_memsize = qhp->wq.rq.memsize;
 		spin_lock(&ucontext->mmap_lock);
+		if (mm5) {
+			uresp.ma_sync_key = ucontext->key;
+			ucontext->key += PAGE_SIZE;
+		}
 		uresp.sq_key = ucontext->key;
 		ucontext->key += PAGE_SIZE;
 		uresp.rq_key = ucontext->key;
@@ -1498,9 +1530,9 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		spin_unlock(&ucontext->mmap_lock);
 		ret = ib_copy_to_udata(udata, &uresp, sizeof uresp);
 		if (ret)
-			goto err7;
+			goto err8;
 		mm1->key = uresp.sq_key;
-		mm1->addr = virt_to_phys(qhp->wq.sq.queue);
+		mm1->addr = qhp->wq.sq.phys_addr;
 		mm1->len = PAGE_ALIGN(qhp->wq.sq.memsize);
 		insert_mmap(ucontext, mm1);
 		mm2->key = uresp.rq_key;
@@ -1515,6 +1547,13 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		mm4->addr = qhp->wq.rq.udb;
 		mm4->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm4);
+		if (mm5) {
+			mm5->key = uresp.ma_sync_key;
+			mm5->addr = (pci_resource_start(rhp->rdev.lldi.pdev, 0)
+				    + A_PCIE_MA_SYNC) & PAGE_MASK;
+			mm5->len = PAGE_SIZE;
+			insert_mmap(ucontext, mm5);
+		}
 	}
 	qhp->ibqp.qp_num = qhp->wq.sq.qid;
 	init_timer(&(qhp->timer));
@@ -1522,6 +1561,8 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	     __func__, qhp, qhp->attr.sq_num_entries, qhp->attr.rq_num_entries,
 	     qhp->wq.sq.qid);
 	return &qhp->ibqp;
+err8:
+	kfree(mm5);
 err7:
 	kfree(mm4);
 err6:
diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c
index 83b23df..4fb50d5 100644
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -311,6 +311,9 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->pbl_pool, size);
 	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	if (!addr && printk_ratelimit())
+		printk(KERN_WARNING MOD "%s: Out of PBL memory\n",
+		       pci_name(rdev->lldi.pdev));
 	return (u32)addr;
 }
 
@@ -370,6 +373,9 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->rqt_pool, size << 6);
 	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size << 6);
+	if (!addr && printk_ratelimit())
+		printk(KERN_WARNING MOD "%s: Out of RQT memory\n",
+		       pci_name(rdev->lldi.pdev));
 	return (u32)addr;
 }
 
@@ -416,3 +422,59 @@ void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
 {
 	gen_pool_destroy(rdev->rqt_pool);
 }
+
+/*
+ * On-Chip QP Memory.
+ */
+#define MIN_OCQP_SHIFT 12	/* 4KB == min ocqp size */
+
+u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size)
+{
+	unsigned long addr = gen_pool_alloc(rdev->ocqp_pool, size);
+	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	return (u32)addr;
+}
+
+void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size)
+{
+	PDBG("%s addr 0x%x size %d\n", __func__, addr, size);
+	gen_pool_free(rdev->ocqp_pool, (unsigned long)addr, size);
+}
+
+int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev)
+{
+	unsigned start, chunk, top;
+
+	rdev->ocqp_pool = gen_pool_create(MIN_OCQP_SHIFT, -1);
+	if (!rdev->ocqp_pool)
+		return -ENOMEM;
+
+	start = rdev->lldi.vr->ocq.start;
+	chunk = rdev->lldi.vr->ocq.size;
+	top = start + chunk;
+
+	while (start < top) {
+		chunk = min(top - start + 1, chunk);
+		if (gen_pool_add(rdev->ocqp_pool, start, chunk, -1)) {
+			PDBG("%s failed to add OCQP chunk (%x/%x)\n",
+			     __func__, start, chunk);
+			if (chunk <= 1024 << MIN_OCQP_SHIFT) {
+				printk(KERN_WARNING MOD
+				       "Failed to add all OCQP chunks (%x/%x)\n",
+				       start, top - start);
+				return 0;
+			}
+			chunk >>= 1;
+		} else {
+			PDBG("%s added OCQP chunk (%x/%x)\n",
+			     __func__, start, chunk);
+			start += chunk;
+		}
+	}
+	return 0;
+}
+
+void c4iw_ocqp_pool_destroy(struct c4iw_rdev *rdev)
+{
+	gen_pool_destroy(rdev->ocqp_pool);
+}
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 24f3690..7000442 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -52,6 +52,7 @@
 #define T4_STAG_UNSET 0xffffffff
 #define T4_FW_MAJ 0
 #define T4_EQ_STATUS_ENTRIES (L1_CACHE_BYTES > 64 ? 2 : 1)
+#define A_PCIE_MA_SYNC 0x30b4
 
 struct t4_status_page {
 	__be32 rsvd1;	/* flit 0 - hw owns */
@@ -65,7 +66,7 @@ struct t4_status_page {
 
 #define T4_EQ_ENTRY_SIZE 64
 
-#define T4_SQ_NUM_SLOTS 4
+#define T4_SQ_NUM_SLOTS 5
 #define T4_SQ_NUM_BYTES (T4_EQ_ENTRY_SIZE * T4_SQ_NUM_SLOTS)
 #define T4_MAX_SEND_SGE ((T4_SQ_NUM_BYTES - sizeof(struct fw_ri_send_wr) - \
 			sizeof(struct fw_ri_isgl)) / sizeof(struct fw_ri_sge))
@@ -78,7 +79,7 @@ struct t4_status_page {
 			sizeof(struct fw_ri_rdma_write_wr) - \
 			sizeof(struct fw_ri_isgl)) / sizeof(struct fw_ri_sge))
 #define T4_MAX_FR_IMMD ((T4_SQ_NUM_BYTES - sizeof(struct fw_ri_fr_nsmr_wr) - \
-			sizeof(struct fw_ri_immd)))
+			sizeof(struct fw_ri_immd)) & ~31UL)
 #define T4_MAX_FR_DEPTH (T4_MAX_FR_IMMD / sizeof(u64))
 
 #define T4_RQ_NUM_SLOTS 2
@@ -266,10 +267,36 @@ struct t4_swsqe {
 	u16			idx;
 };
 
+static inline pgprot_t t4_pgprot_wc(pgprot_t prot)
+{
+#if defined(__i386__) || defined(__x86_64__)
+	return pgprot_writecombine(prot);
+#elif defined(CONFIG_PPC64)
+	return __pgprot((pgprot_val(prot) | _PAGE_NO_CACHE) &
+			~(pgprot_t)_PAGE_GUARDED);
+#else
+	return pgprot_noncached(prot);
+#endif
+}
+
+static inline int t4_ocqp_supported(void)
+{
+#if defined(__i386__) || defined(__x86_64__) || defined(CONFIG_PPC64)
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+enum {
+	T4_SQ_ONCHIP = (1<<0),
+};
+
 struct t4_sq {
 	union t4_wr *queue;
 	dma_addr_t dma_addr;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
+	unsigned long phys_addr;
 	struct t4_swsqe *sw_sq;
 	struct t4_swsqe *oldest_read;
 	u64 udb;
@@ -280,6 +307,7 @@ struct t4_sq {
 	u16 cidx;
 	u16 pidx;
 	u16 wq_pidx;
+	u16 flags;
 };
 
 struct t4_swrqe {
@@ -350,6 +378,11 @@ static inline void t4_rq_consume(struct t4_wq *wq)
 		wq->rq.cidx = 0;
 }
 
+static inline int t4_sq_onchip(struct t4_sq *sq)
+{
+	return sq->flags & T4_SQ_ONCHIP;
+}
+
 static inline int t4_sq_empty(struct t4_wq *wq)
 {
 	return wq->sq.in_use == 0;
@@ -396,30 +429,27 @@ static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc)
 
 static inline int t4_wq_in_error(struct t4_wq *wq)
 {
-	return wq->sq.queue[wq->sq.size].status.qp_err;
+	return wq->rq.queue[wq->rq.size].status.qp_err;
 }
 
 static inline void t4_set_wq_in_error(struct t4_wq *wq)
 {
-	wq->sq.queue[wq->sq.size].status.qp_err = 1;
 	wq->rq.queue[wq->rq.size].status.qp_err = 1;
 }
 
 static inline void t4_disable_wq_db(struct t4_wq *wq)
 {
-	wq->sq.queue[wq->sq.size].status.db_off = 1;
 	wq->rq.queue[wq->rq.size].status.db_off = 1;
 }
 
 static inline void t4_enable_wq_db(struct t4_wq *wq)
 {
-	wq->sq.queue[wq->sq.size].status.db_off = 0;
 	wq->rq.queue[wq->rq.size].status.db_off = 0;
 }
 
 static inline int t4_wq_db_enabled(struct t4_wq *wq)
 {
-	return !wq->sq.queue[wq->sq.size].status.db_off;
+	return !wq->rq.queue[wq->rq.size].status.db_off;
 }
 
 struct t4_cq {
diff --git a/drivers/infiniband/hw/cxgb4/user.h b/drivers/infiniband/hw/cxgb4/user.h
index ed6414a..e6669d5 100644
--- a/drivers/infiniband/hw/cxgb4/user.h
+++ b/drivers/infiniband/hw/cxgb4/user.h
@@ -50,7 +50,13 @@ struct c4iw_create_cq_resp {
 	__u32 qid_mask;
 };
 
+
+enum {
+	C4IW_QPF_ONCHIP = (1<<0)
+};
+
 struct c4iw_create_qp_resp {
+	__u64 ma_sync_key;
 	__u64 sq_key;
 	__u64 rq_key;
 	__u64 sq_db_gts_key;
@@ -62,5 +68,6 @@ struct c4iw_create_qp_resp {
 	__u32 sq_size;
 	__u32 rq_size;
 	__u32 qid_mask;
+	__u32 flags;
 };
 #endif