1 files changed, 105 insertions, 25 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index e66ae9f22c71..82023394e330 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -62,6 +62,7 @@
 
 #include "bnxt_re.h"
 #include "ib_verbs.h"
+#include "debugfs.h"
 
 #include <rdma/uverbs_types.h>
 #include <rdma/uverbs_std_types.h>
@@ -94,9 +95,9 @@ static int __from_ib_access_flags(int iflags)
 	return qflags;
 };
 
-static enum ib_access_flags __to_ib_access_flags(int qflags)
+static int __to_ib_access_flags(int qflags)
 {
-	enum ib_access_flags iflags = 0;
+	int iflags = 0;
 
 	if (qflags & BNXT_QPLIB_ACCESS_LOCAL_WRITE)
 		iflags |= IB_ACCESS_LOCAL_WRITE;
@@ -113,7 +114,49 @@ static enum ib_access_flags __to_ib_access_flags(int qflags)
 	if (qflags & BNXT_QPLIB_ACCESS_ON_DEMAND)
 		iflags |= IB_ACCESS_ON_DEMAND;
 	return iflags;
-};
+}
+
+static u8 __qp_access_flags_from_ib(struct bnxt_qplib_chip_ctx *cctx, int iflags)
+{
+	u8 qflags = 0;
+
+	if (!bnxt_qplib_is_chip_gen_p5_p7(cctx))
+		/* For Wh+ */
+		return (u8)__from_ib_access_flags(iflags);
+
+	/* For P5, P7 and later chips */
+	if (iflags & IB_ACCESS_LOCAL_WRITE)
+		qflags |= CMDQ_MODIFY_QP_ACCESS_LOCAL_WRITE;
+	if (iflags & IB_ACCESS_REMOTE_WRITE)
+		qflags |= CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE;
+	if (iflags & IB_ACCESS_REMOTE_READ)
+		qflags |= CMDQ_MODIFY_QP_ACCESS_REMOTE_READ;
+	if (iflags & IB_ACCESS_REMOTE_ATOMIC)
+		qflags |= CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC;
+
+	return qflags;
+}
+
+static int __qp_access_flags_to_ib(struct bnxt_qplib_chip_ctx *cctx, u8 qflags)
+{
+	int iflags = 0;
+
+	if (!bnxt_qplib_is_chip_gen_p5_p7(cctx))
+		/* For Wh+ */
+		return __to_ib_access_flags(qflags);
+
+	/* For P5, P7 and later chips */
+	if (qflags & CMDQ_MODIFY_QP_ACCESS_LOCAL_WRITE)
+		iflags |= IB_ACCESS_LOCAL_WRITE;
+	if (qflags & CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE)
+		iflags |= IB_ACCESS_REMOTE_WRITE;
+	if (qflags & CMDQ_MODIFY_QP_ACCESS_REMOTE_READ)
+		iflags |= IB_ACCESS_REMOTE_READ;
+	if (qflags & CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC)
+		iflags |= IB_ACCESS_REMOTE_ATOMIC;
+
+	return iflags;
+}
 
 static void bnxt_re_check_and_set_relaxed_ordering(struct bnxt_re_dev *rdev,
 						   struct bnxt_qplib_mrw *qplib_mr)
@@ -211,6 +254,22 @@ int bnxt_re_query_device(struct ib_device *ibdev,
 	return 0;
 }
 
+int bnxt_re_modify_device(struct ib_device *ibdev,
+			  int device_modify_mask,
+			  struct ib_device_modify *device_modify)
+{
+	ibdev_dbg(ibdev, "Modify device with mask 0x%x", device_modify_mask);
+
+	if (device_modify_mask & ~IB_DEVICE_MODIFY_NODE_DESC)
+		return -EOPNOTSUPP;
+
+	if (!(device_modify_mask & IB_DEVICE_MODIFY_NODE_DESC))
+		return 0;
+
+	memcpy(ibdev->node_desc, device_modify->node_desc, IB_DEVICE_NODE_DESC_MAX);
+	return 0;
+}
+
 /* Port */
 int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num,
 		       struct ib_port_attr *port_attr)
@@ -939,6 +998,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 	else if (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_UD)
 		atomic_dec(&rdev->stats.res.ud_qp_count);
 
+	bnxt_re_debug_rem_qpinfo(rdev, qp);
+
 	ib_umem_release(qp->rumem);
 	ib_umem_release(qp->sumem);
 
@@ -1622,6 +1683,7 @@ int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr,
 		if (active_qps > rdev->stats.res.ud_qp_watermark)
 			rdev->stats.res.ud_qp_watermark = active_qps;
 	}
+	bnxt_re_debug_add_qpinfo(rdev, qp);
 
 	return 0;
 qp_destroy:
@@ -1814,8 +1876,8 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 	srq->qplib_srq.wqe_size = bnxt_re_get_rwqe_size(dev_attr->max_srq_sges);
 	srq->qplib_srq.threshold = srq_init_attr->attr.srq_limit;
 	srq->srq_limit = srq_init_attr->attr.srq_limit;
-	srq->qplib_srq.eventq_hw_ring_id = rdev->nq[0].ring_id;
-	nq = &rdev->nq[0];
+	srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
+	nq = &rdev->nqr->nq[0];
 
 	if (udata) {
 		rc = bnxt_re_init_user_srq(rdev, pd, srq, udata);
@@ -2041,12 +2103,10 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 	if (qp_attr_mask & IB_QP_ACCESS_FLAGS) {
 		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS;
 		qp->qplib_qp.access =
-			__from_ib_access_flags(qp_attr->qp_access_flags);
+			__qp_access_flags_from_ib(qp->qplib_qp.cctx,
+						  qp_attr->qp_access_flags);
 		/* LOCAL_WRITE access must be set to allow RC receive */
-		qp->qplib_qp.access |= BNXT_QPLIB_ACCESS_LOCAL_WRITE;
-		/* Temp: Set all params on QP as of now */
-		qp->qplib_qp.access |= CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE;
-		qp->qplib_qp.access |= CMDQ_MODIFY_QP_ACCESS_REMOTE_READ;
+		qp->qplib_qp.access |= CMDQ_MODIFY_QP_ACCESS_LOCAL_WRITE;
 	}
 	if (qp_attr_mask & IB_QP_PKEY_INDEX) {
 		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY;
@@ -2080,7 +2140,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		qp->qplib_qp.ah.sgid_index = ctx->idx;
 		qp->qplib_qp.ah.host_sgid_index = grh->sgid_index;
 		qp->qplib_qp.ah.hop_limit = grh->hop_limit;
-		qp->qplib_qp.ah.traffic_class = grh->traffic_class;
+		qp->qplib_qp.ah.traffic_class = grh->traffic_class >> 2;
 		qp->qplib_qp.ah.sl = rdma_ah_get_sl(&qp_attr->ah_attr);
 		ether_addr_copy(qp->qplib_qp.ah.dmac,
 				qp_attr->ah_attr.roce.dmac);
@@ -2251,7 +2311,8 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 	qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state);
 	qp_attr->cur_qp_state = __to_ib_qp_state(qplib_qp->cur_qp_state);
 	qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0;
-	qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access);
+	qp_attr->qp_access_flags = __qp_access_flags_to_ib(qp->qplib_qp.cctx,
+							   qplib_qp->access);
 	qp_attr->pkey_index = qplib_qp->pkey_index;
 	qp_attr->qkey = qplib_qp->qkey;
 	qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
@@ -2972,6 +3033,28 @@ int bnxt_re_post_recv(struct ib_qp *ib_qp, const struct ib_recv_wr *wr,
 	return rc;
 }
 
+static struct bnxt_qplib_nq *bnxt_re_get_nq(struct bnxt_re_dev *rdev)
+{
+	int min, indx;
+
+	mutex_lock(&rdev->nqr->load_lock);
+	for (indx = 0, min = 0; indx < (rdev->nqr->num_msix - 1); indx++) {
+		if (rdev->nqr->nq[min].load > rdev->nqr->nq[indx].load)
+			min = indx;
+	}
+	rdev->nqr->nq[min].load++;
+	mutex_unlock(&rdev->nqr->load_lock);
+
+	return &rdev->nqr->nq[min];
+}
+
+static void bnxt_re_put_nq(struct bnxt_re_dev *rdev, struct bnxt_qplib_nq *nq)
+{
+	mutex_lock(&rdev->nqr->load_lock);
+	nq->load--;
+	mutex_unlock(&rdev->nqr->load_lock);
+}
+
 /* Completion Queues */
 int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
@@ -2990,6 +3073,8 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 		hash_del(&cq->hash_entry);
 	}
 	bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
+
+	bnxt_re_put_nq(rdev, nq);
 	ib_umem_release(cq->umem);
 
 	atomic_dec(&rdev->stats.res.cq_count);
@@ -3008,8 +3093,6 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
 	struct bnxt_qplib_chip_ctx *cctx;
-	struct bnxt_qplib_nq *nq = NULL;
-	unsigned int nq_alloc_cnt;
 	int cqe = attr->cqe;
 	int rc, entries;
 	u32 active_cqs;
@@ -3060,15 +3143,10 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 
 		cq->qplib_cq.dpi = &rdev->dpi_privileged;
 	}
-	/*
-	 * Allocating the NQ in a round robin fashion. nq_alloc_cnt is a
-	 * used for getting the NQ index.
-	 */
-	nq_alloc_cnt = atomic_inc_return(&rdev->nq_alloc_cnt);
-	nq = &rdev->nq[nq_alloc_cnt % (rdev->num_msix - 1)];
 	cq->qplib_cq.max_wqe = entries;
-	cq->qplib_cq.cnq_hw_ring_id = nq->ring_id;
-	cq->qplib_cq.nq	= nq;
+	cq->qplib_cq.coalescing = &rdev->cq_coalescing;
+	cq->qplib_cq.nq = bnxt_re_get_nq(rdev);
+	cq->qplib_cq.cnq_hw_ring_id = cq->qplib_cq.nq->ring_id;
 
 	rc = bnxt_qplib_create_cq(&rdev->qplib_res, &cq->qplib_cq);
 	if (rc) {
@@ -3078,7 +3156,6 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 
 	cq->ib_cq.cqe = entries;
 	cq->cq_period = cq->qplib_cq.period;
-	nq->budget++;
 
 	active_cqs = atomic_inc_return(&rdev->stats.res.cq_count);
 	if (active_cqs > rdev->stats.res.cq_watermark)
@@ -3633,7 +3710,7 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp,
 	wc->byte_len = orig_cqe->length;
 	wc->qp = &gsi_qp->ib_qp;
 
-	wc->ex.imm_data = cpu_to_be32(le32_to_cpu(orig_cqe->immdata));
+	wc->ex.imm_data = cpu_to_be32(orig_cqe->immdata);
 	wc->src_qp = orig_cqe->src_qp;
 	memcpy(wc->smac, orig_cqe->smac, ETH_ALEN);
 	if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) {
@@ -3778,7 +3855,10 @@ int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc)
 				 (unsigned long)(cqe->qp_handle),
 				 struct bnxt_re_qp, qplib_qp);
 			wc->qp = &qp->ib_qp;
-			wc->ex.imm_data = cpu_to_be32(le32_to_cpu(cqe->immdata));
+			if (cqe->flags & CQ_RES_RC_FLAGS_IMM)
+				wc->ex.imm_data = cpu_to_be32(cqe->immdata);
+			else
+				wc->ex.invalidate_rkey = cqe->invrkey;
 			wc->src_qp = cqe->src_qp;
 			memcpy(wc->smac, cqe->smac, ETH_ALEN);
 			wc->port_num = 1;