Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull base rdma updates from Doug Ledford:
 "Round one of 4.8 code: while this is mostly normal, there is a new
  driver in here (the driver was hosted outside the kernel for several
  years and is actually a fairly mature and well coded driver).  It
  amounts to 13,000 of the 16,000 lines of added code in here.

  Summary:

   - Updates/fixes for iw_cxgb4 driver
   - Updates/fixes for mlx5 driver
   - Add flow steering and RSS API
   - Add hardware stats to mlx4 and mlx5 drivers
   - Add firmware version API for RDMA driver use
   - Add the rxe driver (this is a software RoCE driver that makes any
     Ethernet device a RoCE device)
   - Fixes for i40iw driver
   - Support for send only multicast joins in the cma layer
   - Other minor fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (72 commits)
  Soft RoCE driver
  IB/core: Support for CMA multicast join flags
  IB/sa: Add cached attribute containing SM information to SA port
  IB/uverbs: Fix race between uverbs_close and remove_one
  IB/mthca: Clean up error unwind flow in mthca_reset()
  IB/mthca: NULL arg to pci_dev_put is OK
  IB/hfi1: NULL arg to sc_return_credits is OK
  IB/mlx4: Add diagnostic hardware counters
  net/mlx4: Query performance and diagnostics counters
  net/mlx4: Add diagnostic counters capability bit
  Use smaller 512 byte messages for portmapper messages
  IB/ipoib: Report SG feature regardless of HW UD CSUM capability
  IB/mlx4: Don't use GFP_ATOMIC for CQ resize struct
  IB/hfi1: Disable by default
  IB/rdmavt: Disable by default
  IB/mlx5: Fix port counter ID association to QP offset
  IB/mlx5: Fix iteration overrun in GSI qps
  i40iw: Add NULL check for puda buffer
  i40iw: Change dup_ack_thresh to u8
  i40iw: Remove unnecessary check for moving CQ head
  ...

1 files changed, 161 insertions, 2 deletions

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 6298f54b4137..2e813edcddab 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -758,6 +758,12 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 	struct ib_qp *qp;
 	int ret;
 
+	if (qp_init_attr->rwq_ind_tbl &&
+	    (qp_init_attr->recv_cq ||
+	    qp_init_attr->srq || qp_init_attr->cap.max_recv_wr ||
+	    qp_init_attr->cap.max_recv_sge))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * If the callers is using the RDMA API calculate the resources
 	 * needed for the RDMA READ/WRITE operations.
@@ -775,6 +781,7 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 	qp->real_qp    = qp;
 	qp->uobject    = NULL;
 	qp->qp_type    = qp_init_attr->qp_type;
+	qp->rwq_ind_tbl = qp_init_attr->rwq_ind_tbl;
 
 	atomic_set(&qp->usecnt, 0);
 	qp->mrs_used = 0;
@@ -792,7 +799,8 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 		qp->srq = NULL;
 	} else {
 		qp->recv_cq = qp_init_attr->recv_cq;
-		atomic_inc(&qp_init_attr->recv_cq->usecnt);
+		if (qp_init_attr->recv_cq)
+			atomic_inc(&qp_init_attr->recv_cq->usecnt);
 		qp->srq = qp_init_attr->srq;
 		if (qp->srq)
 			atomic_inc(&qp_init_attr->srq->usecnt);
@@ -803,7 +811,10 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 	qp->xrcd    = NULL;
 
 	atomic_inc(&pd->usecnt);
-	atomic_inc(&qp_init_attr->send_cq->usecnt);
+	if (qp_init_attr->send_cq)
+		atomic_inc(&qp_init_attr->send_cq->usecnt);
+	if (qp_init_attr->rwq_ind_tbl)
+		atomic_inc(&qp->rwq_ind_tbl->usecnt);
 
 	if (qp_init_attr->cap.max_rdma_ctxs) {
 		ret = rdma_rw_init_mrs(qp, qp_init_attr);
@@ -1283,6 +1294,7 @@ int ib_destroy_qp(struct ib_qp *qp)
 	struct ib_pd *pd;
 	struct ib_cq *scq, *rcq;
 	struct ib_srq *srq;
+	struct ib_rwq_ind_table *ind_tbl;
 	int ret;
 
 	WARN_ON_ONCE(qp->mrs_used > 0);
@@ -1297,6 +1309,7 @@ int ib_destroy_qp(struct ib_qp *qp)
 	scq  = qp->send_cq;
 	rcq  = qp->recv_cq;
 	srq  = qp->srq;
+	ind_tbl = qp->rwq_ind_tbl;
 
 	if (!qp->uobject)
 		rdma_rw_cleanup_mrs(qp);
@@ -1311,6 +1324,8 @@ int ib_destroy_qp(struct ib_qp *qp)
 			atomic_dec(&rcq->usecnt);
 		if (srq)
 			atomic_dec(&srq->usecnt);
+		if (ind_tbl)
+			atomic_dec(&ind_tbl->usecnt);
 	}
 
 	return ret;
@@ -1558,6 +1573,150 @@ int ib_dealloc_xrcd(struct ib_xrcd *xrcd)
 }
 EXPORT_SYMBOL(ib_dealloc_xrcd);
 
+/**
+ * ib_create_wq - Creates a WQ associated with the specified protection
+ * domain.
+ * @pd: The protection domain associated with the WQ.
+ * @wq_init_attr: A list of initial attributes required to create the
+ * WQ. If WQ creation succeeds, then the attributes are updated to
+ * the actual capabilities of the created WQ.
+ *
+ * wq_init_attr->max_wr and wq_init_attr->max_sge determine
+ * the requested size of the WQ, and set to the actual values allocated
+ * on return.
+ * If ib_create_wq() succeeds, then max_wr and max_sge will always be
+ * at least as large as the requested values.
+ */
+struct ib_wq *ib_create_wq(struct ib_pd *pd,
+			   struct ib_wq_init_attr *wq_attr)
+{
+	struct ib_wq *wq;
+
+	if (!pd->device->create_wq)
+		return ERR_PTR(-ENOSYS);
+
+	wq = pd->device->create_wq(pd, wq_attr, NULL);
+	if (!IS_ERR(wq)) {
+		wq->event_handler = wq_attr->event_handler;
+		wq->wq_context = wq_attr->wq_context;
+		wq->wq_type = wq_attr->wq_type;
+		wq->cq = wq_attr->cq;
+		wq->device = pd->device;
+		wq->pd = pd;
+		wq->uobject = NULL;
+		atomic_inc(&pd->usecnt);
+		atomic_inc(&wq_attr->cq->usecnt);
+		atomic_set(&wq->usecnt, 0);
+	}
+	return wq;
+}
+EXPORT_SYMBOL(ib_create_wq);
+
+/**
+ * ib_destroy_wq - Destroys the specified WQ.
+ * @wq: The WQ to destroy.
+ */
+int ib_destroy_wq(struct ib_wq *wq)
+{
+	int err;
+	struct ib_cq *cq = wq->cq;
+	struct ib_pd *pd = wq->pd;
+
+	if (atomic_read(&wq->usecnt))
+		return -EBUSY;
+
+	err = wq->device->destroy_wq(wq);
+	if (!err) {
+		atomic_dec(&pd->usecnt);
+		atomic_dec(&cq->usecnt);
+	}
+	return err;
+}
+EXPORT_SYMBOL(ib_destroy_wq);
+
+/**
+ * ib_modify_wq - Modifies the specified WQ.
+ * @wq: The WQ to modify.
+ * @wq_attr: On input, specifies the WQ attributes to modify.
+ * @wq_attr_mask: A bit-mask used to specify which attributes of the WQ
+ *   are being modified.
+ * On output, the current values of selected WQ attributes are returned.
+ */
+int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
+		 u32 wq_attr_mask)
+{
+	int err;
+
+	if (!wq->device->modify_wq)
+		return -ENOSYS;
+
+	err = wq->device->modify_wq(wq, wq_attr, wq_attr_mask, NULL);
+	return err;
+}
+EXPORT_SYMBOL(ib_modify_wq);
+
+/*
+ * ib_create_rwq_ind_table - Creates a RQ Indirection Table.
+ * @device: The device on which to create the rwq indirection table.
+ * @ib_rwq_ind_table_init_attr: A list of initial attributes required to
+ * create the Indirection Table.
+ *
+ * Note: The life time of ib_rwq_ind_table_init_attr->ind_tbl is not less
+ *	than the created ib_rwq_ind_table object and the caller is responsible
+ *	for its memory allocation/free.
+ */
+struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device,
+						 struct ib_rwq_ind_table_init_attr *init_attr)
+{
+	struct ib_rwq_ind_table *rwq_ind_table;
+	int i;
+	u32 table_size;
+
+	if (!device->create_rwq_ind_table)
+		return ERR_PTR(-ENOSYS);
+
+	table_size = (1 << init_attr->log_ind_tbl_size);
+	rwq_ind_table = device->create_rwq_ind_table(device,
+				init_attr, NULL);
+	if (IS_ERR(rwq_ind_table))
+		return rwq_ind_table;
+
+	rwq_ind_table->ind_tbl = init_attr->ind_tbl;
+	rwq_ind_table->log_ind_tbl_size = init_attr->log_ind_tbl_size;
+	rwq_ind_table->device = device;
+	rwq_ind_table->uobject = NULL;
+	atomic_set(&rwq_ind_table->usecnt, 0);
+
+	for (i = 0; i < table_size; i++)
+		atomic_inc(&rwq_ind_table->ind_tbl[i]->usecnt);
+
+	return rwq_ind_table;
+}
+EXPORT_SYMBOL(ib_create_rwq_ind_table);
+
+/*
+ * ib_destroy_rwq_ind_table - Destroys the specified Indirection Table.
+ * @wq_ind_table: The Indirection Table to destroy.
+*/
+int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *rwq_ind_table)
+{
+	int err, i;
+	u32 table_size = (1 << rwq_ind_table->log_ind_tbl_size);
+	struct ib_wq **ind_tbl = rwq_ind_table->ind_tbl;
+
+	if (atomic_read(&rwq_ind_table->usecnt))
+		return -EBUSY;
+
+	err = rwq_ind_table->device->destroy_rwq_ind_table(rwq_ind_table);
+	if (!err) {
+		for (i = 0; i < table_size; i++)
+			atomic_dec(&ind_tbl[i]->usecnt);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(ib_destroy_rwq_ind_table);
+
 struct ib_flow *ib_create_flow(struct ib_qp *qp,
 			       struct ib_flow_attr *flow_attr,
 			       int domain)