RDMA/cxgb4: Detach from the LLD after unregistering with the RDMA core.

index be23b5e..c7e2484 100644
@@ -504,14 +504,12 @@ static void __exit c4iw_exit_module(void)
 {
 	struct c4iw_dev *dev, *tmp;
 
-	cxgb4_unregister_uld(CXGB4_ULD_RDMA);
-
 	mutex_lock(&dev_mutex);
 	list_for_each_entry_safe(dev, tmp, &dev_list, entry) {
 		c4iw_remove(dev);
 	}
 	mutex_unlock(&dev_mutex);
-
+	cxgb4_unregister_uld(CXGB4_ULD_RDMA);
 	c4iw_cm_term();
 	debugfs_remove_recursive(c4iw_debugfs_root);
 }

index c7e2484..d870f9c 100644
@@ -306,7 +306,8 @@ static void c4iw_remove(struct c4iw_dev *dev)
 	PDBG("%s c4iw_dev %p\n", __func__,  dev);
 	cancel_delayed_work_sync(&dev->db_drop_task);
 	list_del(&dev->entry);
-	c4iw_unregister_device(dev);
+	if (dev->registered)
+		c4iw_unregister_device(dev);
 	c4iw_rdev_close(&dev->rdev);
 	idr_destroy(&dev->cqidr);
 	idr_destroy(&dev->qpidr);

@@ -343,12 +344,6 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 	list_add_tail(&devp->entry, &dev_list);
 	mutex_unlock(&dev_mutex);
 
-	if (c4iw_register_device(devp)) {
-		printk(KERN_ERR MOD "Unable to register device\n");
-		mutex_lock(&dev_mutex);
-		c4iw_remove(devp);
-		mutex_unlock(&dev_mutex);
-	}
 	if (c4iw_debugfs_root) {
 		devp->debugfs_root = debugfs_create_dir(
 					pci_name(devp->rdev.lldi.pdev),

@@ -379,9 +374,6 @@ static void *c4iw_uld_add(const struct cxgb4_lld_info *infop)
 
 	for (i = 0; i < dev->rdev.lldi.nrxq; i++)
 		PDBG("rxqid[%u] %u\n", i, dev->rdev.lldi.rxq_ids[i]);
-
-	printk(KERN_INFO MOD "Initialized device %s\n",
-	       pci_name(dev->rdev.lldi.pdev));
 out:
 	return dev;
 }

@@ -471,7 +463,41 @@ nomem:
 
 static int c4iw_uld_state_change(void *handle, enum cxgb4_state new_state)
 {
+	struct c4iw_dev *dev = handle;
+
 	PDBG("%s new_state %u\n", __func__, new_state);
+	switch (new_state) {
+	case CXGB4_STATE_UP:
+		printk(KERN_INFO MOD "%s: Up\n", pci_name(dev->rdev.lldi.pdev));
+		if (!dev->registered) {
+			int ret;
+			ret = c4iw_register_device(dev);
+			if (ret)
+				printk(KERN_ERR MOD
+				       "%s: RDMA registration failed: %d\n",
+				       pci_name(dev->rdev.lldi.pdev), ret);
+		}
+		break;
+	case CXGB4_STATE_DOWN:
+		printk(KERN_INFO MOD "%s: Down\n",
+		       pci_name(dev->rdev.lldi.pdev));
+		if (dev->registered)
+			c4iw_unregister_device(dev);
+		break;
+	case CXGB4_STATE_START_RECOVERY:
+		printk(KERN_INFO MOD "%s: Fatal Error\n",
+		       pci_name(dev->rdev.lldi.pdev));
+		if (dev->registered)
+			c4iw_unregister_device(dev);
+		break;
+	case CXGB4_STATE_DETACH:
+		printk(KERN_INFO MOD "%s: Detach\n",
+		       pci_name(dev->rdev.lldi.pdev));
+		mutex_lock(&dev_mutex);
+		c4iw_remove(dev);
+		mutex_unlock(&dev_mutex);
+		break;
+	}
 	return 0;
 }
 

index a626998..277ab58 100644
@@ -152,6 +152,7 @@ struct c4iw_dev {
 	struct list_head entry;
 	struct delayed_work db_drop_task;
 	struct dentry *debugfs_root;
+	u8 registered;
 };
 
 static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)

index dfc4902..322134b 100644
@@ -496,6 +496,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 		if (ret)
 			goto bail2;
 	}
+	dev->registered = 1;
 	return 0;
 bail2:
 	ib_unregister_device(&dev->ibdev);

@@ -514,5 +515,6 @@ void c4iw_unregister_device(struct c4iw_dev *dev)
 				   c4iw_class_attributes[i]);
 	ib_unregister_device(&dev->ibdev);
 	kfree(dev->ibdev.iwcm);
+	dev->registered = 0;
 	return;
 }

index fb1aafc..46ac00f 100644
@@ -780,6 +780,9 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 	/* account for the status page. */
 	entries++;
 
+	/* IQ needs one extra entry to differentiate full vs empty. */
+	entries++;
+
 	/*
 	 * entries must be multiple of 16 for HW.
 	 */

@@ -801,7 +804,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 
 	chp->rhp = rhp;
 	chp->cq.size--;				/* status page */
-	chp->ibcq.cqe = chp->cq.size;
+	chp->ibcq.cqe = chp->cq.size - 1;
 	spin_lock_init(&chp->lock);
 	atomic_set(&chp->refcnt, 1);
 	init_waitqueue_head(&chp->wait);

index 46ac00f..2447f52 100644
@@ -373,6 +373,7 @@ static void create_read_req_cqe(struct t4_wq *wq, struct t4_cqe *hw_cqe,
 				 V_CQE_SWCQE(SW_CQE(hw_cqe)) |
 				 V_CQE_OPCODE(FW_RI_READ_REQ) |
 				 V_CQE_TYPE(1));
+	read_cqe->bits_type_ts = hw_cqe->bits_type_ts;
 }
 
 /*

index d0e8af3..712bc56 100644
@@ -434,7 +434,7 @@ struct t4_cq {
 	struct c4iw_rdev *rdev;
 	u64 ugts;
 	size_t memsize;
-	u64 timestamp;
+	__be64 bits_type_ts;
 	u32 cqid;
 	u16 size; /* including status page */
 	u16 cidx;

@@ -487,6 +487,7 @@ static inline void t4_swcq_consume(struct t4_cq *cq)
 
 static inline void t4_hwcq_consume(struct t4_cq *cq)
 {
+	cq->bits_type_ts = cq->queue[cq->cidx].bits_type_ts;
 	cq->cidx_inc++;
 	if (++cq->cidx == cq->size) {
 		cq->cidx = 0;

@@ -501,20 +502,23 @@ static inline int t4_valid_cqe(struct t4_cq *cq, struct t4_cqe *cqe)
 
 static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe)
 {
-	int ret = 0;
-	u64 bits_type_ts = be64_to_cpu(cq->queue[cq->cidx].bits_type_ts);
+	int ret;
+	u16 prev_cidx;
 
-	if (G_CQE_GENBIT(bits_type_ts) == cq->gen) {
-		*cqe = &cq->queue[cq->cidx];
-		cq->timestamp = G_CQE_TS(bits_type_ts);
-	} else if (G_CQE_TS(bits_type_ts) > cq->timestamp)
-		ret = -EOVERFLOW;
+	if (cq->cidx == 0)
+		prev_cidx = cq->size - 1;
 	else
-		ret = -ENODATA;
-	if (ret == -EOVERFLOW) {
-		printk(KERN_ERR MOD "cq overflow cqid %u\n", cq->cqid);
+		prev_cidx = cq->cidx - 1;
+
+	if (cq->queue[prev_cidx].bits_type_ts != cq->bits_type_ts) {
+		ret = -EOVERFLOW;
 		cq->error = 1;
-	}
+		printk(KERN_ERR MOD "cq overflow cqid %u\n", cq->cqid);
+	} else if (t4_valid_cqe(cq, &cq->queue[cq->cidx])) {
+		*cqe = &cq->queue[cq->cidx];
+		ret = 0;
+	} else
+		ret = -ENODATA;
 	return ret;
 }
 

index 712bc56..333abd3 100644
@@ -449,25 +449,17 @@ struct t4_cq {
 static inline int t4_arm_cq(struct t4_cq *cq, int se)
 {
 	u32 val;
-	u16 inc;
-
-	do {
-		/*
-		 * inc must be less the both the max update value -and-
-		 * the size of the CQ.
-		 */
-		inc = cq->cidx_inc <= CIDXINC_MASK ? cq->cidx_inc :
-						     CIDXINC_MASK;
-		inc = inc <= (cq->size - 1) ? inc : (cq->size - 1);
-		if (inc == cq->cidx_inc)
-			val = SEINTARM(se) | CIDXINC(inc) | TIMERREG(6) |
-			      INGRESSQID(cq->cqid);
-		else
-			val = SEINTARM(0) | CIDXINC(inc) | TIMERREG(7) |
-			      INGRESSQID(cq->cqid);
-		cq->cidx_inc -= inc;
+
+	while (cq->cidx_inc > CIDXINC_MASK) {
+		val = SEINTARM(0) | CIDXINC(CIDXINC_MASK) | TIMERREG(7) |
+		      INGRESSQID(cq->cqid);
 		writel(val, cq->gts);
-	} while (cq->cidx_inc);
+		cq->cidx_inc -= CIDXINC_MASK;
+	}
+	val = SEINTARM(se) | CIDXINC(cq->cidx_inc) | TIMERREG(6) |
+	      INGRESSQID(cq->cqid);
+	writel(val, cq->gts);
+	cq->cidx_inc = 0;
 	return 0;
 }
 

@@ -488,7 +480,8 @@ static inline void t4_swcq_consume(struct t4_cq *cq)
 static inline void t4_hwcq_consume(struct t4_cq *cq)
 {
 	cq->bits_type_ts = cq->queue[cq->cidx].bits_type_ts;
-	cq->cidx_inc++;
+	if (++cq->cidx_inc == cq->size)
+		cq->cidx_inc = 0;
 	if (++cq->cidx == cq->size) {
 		cq->cidx = 0;
 		cq->gen ^= 1;

index e54ff6d..993ed1f 100644
@@ -712,8 +712,10 @@ struct ib_mr *c4iw_alloc_fast_reg_mr(struct ib_pd *pd, int pbl_depth)
 	php = to_c4iw_pd(pd);
 	rhp = php->rhp;
 	mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
-	if (!mhp)
+	if (!mhp) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	mhp->rhp = rhp;
 	ret = alloc_pbl(mhp, pbl_depth);

@@ -730,8 +732,10 @@ struct ib_mr *c4iw_alloc_fast_reg_mr(struct ib_pd *pd, int pbl_depth)
 	mhp->attr.state = 1;
 	mmid = (stag) >> 8;
 	mhp->ibmr.rkey = mhp->ibmr.lkey = stag;
-	if (insert_handle(rhp, &rhp->mmidr, mhp, mmid))
+	if (insert_handle(rhp, &rhp->mmidr, mhp, mmid)) {
+		ret = -ENOMEM;
 		goto err3;
+	}
 
 	PDBG("%s mmid 0x%x mhp %p stag 0x%x\n", __func__, mmid, mhp, stag);
 	return &(mhp->ibmr);

index 993ed1f..7f94da1 100644
@@ -759,9 +759,6 @@ struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
 	dma_addr_t dma_addr;
 	int size = sizeof *c4pl + page_list_len * sizeof(u64);
 
-	if (page_list_len > T4_MAX_FR_DEPTH)
-		return ERR_PTR(-EINVAL);
-
 	c4pl = dma_alloc_coherent(&dev->rdev.lldi.pdev->dev, size,
 				  &dma_addr, GFP_KERNEL);
 	if (!c4pl)

index 333abd3..1057cb9 100644
@@ -41,11 +41,13 @@
 #define T4_MAX_NUM_QP (1<<16)
 #define T4_MAX_NUM_CQ (1<<15)
 #define T4_MAX_NUM_PD (1<<15)
-#define T4_MAX_PBL_SIZE 256
-#define T4_MAX_RQ_SIZE 1024
-#define T4_MAX_SQ_SIZE 1024
-#define T4_MAX_QP_DEPTH (T4_MAX_RQ_SIZE-1)
-#define T4_MAX_CQ_DEPTH 8192
+#define T4_EQ_STATUS_ENTRIES (L1_CACHE_BYTES > 64 ? 2 : 1)
+#define T4_MAX_EQ_SIZE (65520 - T4_EQ_STATUS_ENTRIES)
+#define T4_MAX_IQ_SIZE (65520 - 1)
+#define T4_MAX_RQ_SIZE (8192 - T4_EQ_STATUS_ENTRIES)
+#define T4_MAX_SQ_SIZE (T4_MAX_EQ_SIZE - 1)
+#define T4_MAX_QP_DEPTH (T4_MAX_RQ_SIZE - 1)
+#define T4_MAX_CQ_DEPTH (T4_MAX_IQ_SIZE - 1)
 #define T4_MAX_NUM_STAG (1<<15)
 #define T4_MAX_MR_SIZE (~0ULL - 1)
 #define T4_PAGESIZE_MASK 0xffff000  /* 4KB-128MB */

@@ -79,12 +81,11 @@ struct t4_status_page {
 			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)))
-#define T4_MAX_FR_DEPTH 255
+#define T4_MAX_FR_DEPTH (T4_MAX_FR_IMMD / sizeof(u64))
 
 #define T4_RQ_NUM_SLOTS 2
 #define T4_RQ_NUM_BYTES (T4_EQ_SIZE * T4_RQ_NUM_SLOTS)
-#define T4_MAX_RECV_SGE ((T4_RQ_NUM_BYTES - sizeof(struct fw_ri_recv_wr) - \
-			sizeof(struct fw_ri_isgl)) / sizeof(struct fw_ri_sge))
+#define T4_MAX_RECV_SGE 4
 
 union t4_wr {
 	struct fw_ri_res_wr res;

index 83a01dc..9fb52fa 100644
@@ -588,6 +588,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			err = build_fastreg(wqe, wr, &len16);
 			break;
 		case IB_WR_LOCAL_INV:
+			if (wr->send_flags & IB_SEND_FENCE)
+				fw_flags |= FW_RI_LOCAL_FENCE_FLAG;
 			fw_opcode = FW_RI_INV_LSTAG_WR;
 			swsqe->opcode = FW_RI_LOCAL_INV;
 			err = build_inv_stag(wqe, wr, &len16);

index 9fb52fa..a41881b 100644
@@ -572,9 +572,13 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			err = build_rdma_write(wqe, wr, &len16);
 			break;
 		case IB_WR_RDMA_READ:
+		case IB_WR_RDMA_READ_WITH_INV:
 			fw_opcode = FW_RI_RDMA_READ_WR;
 			swsqe->opcode = FW_RI_READ_REQ;
-			fw_flags = 0;
+			if (wr->opcode == IB_WR_RDMA_READ_WITH_INV)
+				fw_flags |= FW_RI_RDMA_READ_INVALIDATE;
+			else
+				fw_flags = 0;
 			err = build_rdma_read(wqe, wr, &len16);
 			if (err)
 				break;

index a41881b..0c28ed1 100644
@@ -1345,7 +1345,6 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp)
 	wait_event(qhp->wait, !qhp->ep);
 
 	remove_handle(rhp, &rhp->qpidr, qhp->wq.sq.qid);
-	remove_handle(rhp, &rhp->qpidr, qhp->wq.rq.qid);
 	atomic_dec(&qhp->refcnt);
 	wait_event(qhp->wait, !atomic_read(&qhp->refcnt));
 

@@ -1448,30 +1447,26 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	if (ret)
 		goto err2;
 
-	ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.rq.qid);
-	if (ret)
-		goto err3;
-
 	if (udata) {
 		mm1 = kmalloc(sizeof *mm1, GFP_KERNEL);
 		if (!mm1) {
 			ret = -ENOMEM;
-			goto err4;
+			goto err3;
 		}
 		mm2 = kmalloc(sizeof *mm2, GFP_KERNEL);
 		if (!mm2) {
 			ret = -ENOMEM;
-			goto err5;
+			goto err4;
 		}
 		mm3 = kmalloc(sizeof *mm3, GFP_KERNEL);
 		if (!mm3) {
 			ret = -ENOMEM;
-			goto err6;
+			goto err5;
 		}
 		mm4 = kmalloc(sizeof *mm4, GFP_KERNEL);
 		if (!mm4) {
 			ret = -ENOMEM;
-			goto err7;
+			goto err6;
 		}
 
 		uresp.qid_mask = rhp->rdev.qpmask;

@@ -1493,7 +1488,7 @@ 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 err8;
+			goto err7;
 		mm1->key = uresp.sq_key;
 		mm1->addr = virt_to_phys(qhp->wq.sq.queue);
 		mm1->len = PAGE_ALIGN(qhp->wq.sq.memsize);

@@ -1517,16 +1512,14 @@ 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(mm4);
 err7:
-	kfree(mm3);
+	kfree(mm4);
 err6:
-	kfree(mm2);
+	kfree(mm3);
 err5:
-	kfree(mm1);
+	kfree(mm2);
 err4:
-	remove_handle(rhp, &rhp->qpidr, qhp->wq.rq.qid);
+	kfree(mm1);
 err3:
 	remove_handle(rhp, &rhp->qpidr, qhp->wq.sq.qid);
 err2: