diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index 85527532c49dbecc05f965c9811b055621f9178b..b3ad37fec578be497cc55e3dc48552e62d71c595 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -85,7 +85,7 @@ struct bnxt_re_sqp_entries {
 };
 
 #define BNXT_RE_MIN_MSIX		2
-#define BNXT_RE_MAX_MSIX		16
+#define BNXT_RE_MAX_MSIX		9
 #define BNXT_RE_AEQ_IDX			0
 #define BNXT_RE_NQ_IDX			1
 
@@ -116,7 +116,7 @@ struct bnxt_re_dev {
 	struct bnxt_qplib_rcfw		rcfw;
 
 	/* NQ */
-	struct bnxt_qplib_nq		nq;
+	struct bnxt_qplib_nq		nq[BNXT_RE_MAX_MSIX];
 
 	/* Device Resources */
 	struct bnxt_qplib_dev_attr	dev_attr;
@@ -140,6 +140,7 @@ struct bnxt_re_dev {
 	struct bnxt_re_qp		*qp1_sqp;
 	struct bnxt_re_ah		*sqp_ah;
 	struct bnxt_re_sqp_entries sqp_tbl[1024];
+	atomic_t nq_alloc_cnt;
 };
 
 #define to_bnxt_re_dev(ptr, member)	\
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 58461ee3773d429f8af4e8cf1fb801e5a4708dd7..24e2785774b81b55103fced4afd46ad0c681c76c 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -2290,6 +2290,7 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq)
 	struct bnxt_re_cq *cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
 	struct bnxt_re_dev *rdev = cq->rdev;
 	int rc;
+	struct bnxt_qplib_nq *nq = cq->qplib_cq.nq;
 
 	rc = bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
 	if (rc) {
@@ -2304,7 +2305,7 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq)
 		kfree(cq);
 	}
 	atomic_dec(&rdev->cq_count);
-	rdev->nq.budget--;
+	nq->budget--;
 	return 0;
 }
 
@@ -2318,6 +2319,8 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
 	struct bnxt_re_cq *cq = NULL;
 	int rc, entries;
 	int cqe = attr->cqe;
+	struct bnxt_qplib_nq *nq = NULL;
+	unsigned int nq_alloc_cnt;
 
 	/* Validate CQ fields */
 	if (cqe < 1 || cqe > dev_attr->max_cq_wqes) {
@@ -2369,9 +2372,15 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
 		cq->qplib_cq.sghead = NULL;
 		cq->qplib_cq.nmap = 0;
 	}
+	/*
+	 * 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 = rdev->nq.ring_id;
-	cq->qplib_cq.nq	= &rdev->nq;
+	cq->qplib_cq.cnq_hw_ring_id = nq->ring_id;
+	cq->qplib_cq.nq	= nq;
 
 	rc = bnxt_qplib_create_cq(&rdev->qplib_res, &cq->qplib_cq);
 	if (rc) {
@@ -2381,7 +2390,7 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
 
 	cq->ib_cq.cqe = entries;
 	cq->cq_period = cq->qplib_cq.period;
-	rdev->nq.budget++;
+	nq->budget++;
 
 	atomic_inc(&rdev->cq_count);
 
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 2f71123e0a9febedf25fc07eae7950b85d1ebc44..5b78d8fc28dc0e9ca69ad35d33adae9ba38c6e3d 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -161,7 +161,7 @@ static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait)
 
 static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
 {
-	int rc = 0, num_msix_want = BNXT_RE_MIN_MSIX, num_msix_got;
+	int rc = 0, num_msix_want = BNXT_RE_MAX_MSIX, num_msix_got;
 	struct bnxt_en_dev *en_dev;
 
 	if (!rdev)
@@ -169,6 +169,8 @@ static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
 
 	en_dev = rdev->en_dev;
 
+	num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus());
+
 	rtnl_lock();
 	num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP,
 							 rdev->msix_entries,
@@ -651,8 +653,12 @@ static int bnxt_re_cqn_handler(struct bnxt_qplib_nq *nq,
 
 static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
 {
-	if (rdev->nq.hwq.max_elements)
-		bnxt_qplib_disable_nq(&rdev->nq);
+	int i;
+
+	if (rdev->nq[0].hwq.max_elements) {
+		for (i = 1; i < rdev->num_msix; i++)
+			bnxt_qplib_disable_nq(&rdev->nq[i - 1]);
+	}
 
 	if (rdev->qplib_res.rcfw)
 		bnxt_qplib_cleanup_res(&rdev->qplib_res);
@@ -660,31 +666,41 @@ static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
 
 static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
 {
-	int rc = 0;
+	int rc = 0, i;
 
 	bnxt_qplib_init_res(&rdev->qplib_res);
 
-	if (rdev->msix_entries[BNXT_RE_NQ_IDX].vector <= 0)
-		return -EINVAL;
+	for (i = 1; i < rdev->num_msix ; i++) {
+		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1],
+					  i - 1, rdev->msix_entries[i].vector,
+					  rdev->msix_entries[i].db_offset,
+					  &bnxt_re_cqn_handler, NULL);
 
-	rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq,
-				  rdev->msix_entries[BNXT_RE_NQ_IDX].vector,
-				  rdev->msix_entries[BNXT_RE_NQ_IDX].db_offset,
-				  &bnxt_re_cqn_handler,
-				  NULL);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to enable NQ with rc = 0x%x", rc);
+			goto fail;
+		}
+	}
+	return 0;
+fail:
+	return rc;
+}
 
-	if (rc)
-		dev_err(rdev_to_dev(rdev), "Failed to enable NQ: %#x", rc);
+static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev, bool lock_wait)
+{
+	int i;
 
-	return rc;
+	for (i = 0; i < rdev->num_msix - 1; i++) {
+		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, lock_wait);
+		bnxt_qplib_free_nq(&rdev->nq[i]);
+	}
 }
 
 static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait)
 {
-	if (rdev->nq.hwq.max_elements) {
-		bnxt_re_net_ring_free(rdev, rdev->nq.ring_id, lock_wait);
-		bnxt_qplib_free_nq(&rdev->nq);
-	}
+	bnxt_re_free_nq_res(rdev, lock_wait);
+
 	if (rdev->qplib_res.dpi_tbl.max) {
 		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
 				       &rdev->qplib_res.dpi_tbl,
@@ -698,7 +714,7 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait)
 
 static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 {
-	int rc = 0;
+	int rc = 0, i;
 
 	/* Configure and allocate resources for qplib */
 	rdev->qplib_res.rcfw = &rdev->rcfw;
@@ -715,30 +731,42 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 				  &rdev->dpi_privileged,
 				  rdev);
 	if (rc)
-		goto fail;
+		goto dealloc_res;
 
-	rdev->nq.hwq.max_elements = BNXT_RE_MAX_CQ_COUNT +
-				    BNXT_RE_MAX_SRQC_COUNT + 2;
-	rc = bnxt_qplib_alloc_nq(rdev->en_dev->pdev, &rdev->nq);
-	if (rc) {
-		dev_err(rdev_to_dev(rdev),
-			"Failed to allocate NQ memory: %#x", rc);
-		goto fail;
-	}
-	rc = bnxt_re_net_ring_alloc
-			(rdev, rdev->nq.hwq.pbl[PBL_LVL_0].pg_map_arr,
-			 rdev->nq.hwq.pbl[rdev->nq.hwq.level].pg_count,
-			 HWRM_RING_ALLOC_CMPL, BNXT_QPLIB_NQE_MAX_CNT - 1,
-			 rdev->msix_entries[BNXT_RE_NQ_IDX].ring_idx,
-			 &rdev->nq.ring_id);
-	if (rc) {
-		dev_err(rdev_to_dev(rdev),
-			"Failed to allocate NQ ring: %#x", rc);
-		goto free_nq;
+	for (i = 0; i < rdev->num_msix - 1; i++) {
+		rdev->nq[i].hwq.max_elements = BNXT_RE_MAX_CQ_COUNT +
+			BNXT_RE_MAX_SRQC_COUNT + 2;
+		rc = bnxt_qplib_alloc_nq(rdev->en_dev->pdev, &rdev->nq[i]);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev), "Alloc Failed NQ%d rc:%#x",
+				i, rc);
+			goto dealloc_dpi;
+		}
+		rc = bnxt_re_net_ring_alloc
+			(rdev, rdev->nq[i].hwq.pbl[PBL_LVL_0].pg_map_arr,
+			 rdev->nq[i].hwq.pbl[rdev->nq[i].hwq.level].pg_count,
+			 HWRM_RING_ALLOC_CMPL,
+			 BNXT_QPLIB_NQE_MAX_CNT - 1,
+			 rdev->msix_entries[i + 1].ring_idx,
+			 &rdev->nq[i].ring_id);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to allocate NQ fw id with rc = 0x%x",
+				rc);
+			goto free_nq;
+		}
 	}
 	return 0;
 free_nq:
-	bnxt_qplib_free_nq(&rdev->nq);
+	for (i = 0; i < rdev->num_msix - 1; i++)
+		bnxt_qplib_free_nq(&rdev->nq[i]);
+dealloc_dpi:
+	bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
+			       &rdev->qplib_res.dpi_tbl,
+			       &rdev->dpi_privileged);
+dealloc_res:
+	bnxt_qplib_free_res(&rdev->qplib_res);
+
 fail:
 	rdev->qplib_res.rcfw = NULL;
 	return rc;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 31e15f31bba57dc55896ca22353375d4d69065a7..e8afc47f8949649546e83813815f4107083c743c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -365,6 +365,7 @@ void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
 	tasklet_kill(&nq->worker);
 
 	if (nq->requested) {
+		irq_set_affinity_hint(nq->vector, NULL);
 		free_irq(nq->vector, nq);
 		nq->requested = false;
 	}
@@ -378,7 +379,7 @@ void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
 }
 
 int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
-			 int msix_vector, int bar_reg_offset,
+			 int nq_idx, int msix_vector, int bar_reg_offset,
 			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
 					    struct bnxt_qplib_cq *),
 			 int (*srqn_handler)(struct bnxt_qplib_nq *nq,
@@ -402,13 +403,25 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 		goto fail;
 
 	nq->requested = false;
-	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, "bnxt_qplib_nq", nq);
+	memset(nq->name, 0, 32);
+	sprintf(nq->name, "bnxt_qplib_nq-%d", nq_idx);
+	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
 	if (rc) {
 		dev_err(&nq->pdev->dev,
 			"Failed to request IRQ for NQ: %#x", rc);
 		bnxt_qplib_disable_nq(nq);
 		goto fail;
 	}
+
+	cpumask_clear(&nq->mask);
+	cpumask_set_cpu(nq_idx, &nq->mask);
+	rc = irq_set_affinity_hint(nq->vector, &nq->mask);
+	if (rc) {
+		dev_warn(&nq->pdev->dev,
+			 "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
+			 nq->vector, nq_idx);
+	}
+
 	nq->requested = true;
 	nq->bar_reg = NQ_CONS_PCI_BAR_REGION;
 	nq->bar_reg_off = bar_reg_offset;
@@ -432,8 +445,10 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 
 void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq)
 {
-	if (nq->hwq.max_elements)
+	if (nq->hwq.max_elements) {
 		bnxt_qplib_free_hwq(nq->pdev, &nq->hwq);
+		nq->hwq.max_elements = 0;
+	}
 }
 
 int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
index 23a26d5cbe18e1d846e5d008c0be065dea222f22..8ead70ca1c1ddbc3b286d1e611ce3a7dd18fb545 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -407,6 +407,7 @@ struct bnxt_qplib_nq {
 	struct pci_dev			*pdev;
 
 	int				vector;
+	cpumask_t			mask;
 	int				budget;
 	bool				requested;
 	struct tasklet_struct		worker;
@@ -425,6 +426,7 @@ struct bnxt_qplib_nq {
 						 void *srq,
 						 u8 event);
 	struct workqueue_struct         *cqn_wq;
+	char                            name[32];
 };
 
 struct bnxt_qplib_nq_work {
@@ -435,7 +437,7 @@ struct bnxt_qplib_nq_work {
 
 void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq);
 int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
-			 int msix_vector, int bar_reg_offset,
+			 int nq_idx, int msix_vector, int bar_reg_offset,
 			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
 					    struct bnxt_qplib_cq *cq),
 			 int (*srqn_handler)(struct bnxt_qplib_nq *nq,