[PATCH rdma-next v2 3/4] RDMA/bnxt_re: Refurbish CQ to NQ hash calculation

[Selvin Xavier <selvin.xavier@broadcom.com>]

From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>

There are few use cases where CQ create and destroy
is seen before re-creating the CQ, this kind of use
case is disturbing the RR distribution and all the
active CQ getting mapped to only 2 NQ alternatively.

Fixing the CQ to NQ hash calculation by implementing
a quick load sorting mechanism under a mutex.

Using this, if the CQ was allocated and destroyed
before using it, the nq selecting algorithm still
obtains the least loaded CQ. Thus balancing the load
on NQs.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
---
 drivers/infiniband/hw/bnxt_re/bnxt_re.h  |  2 ++
 drivers/infiniband/hw/bnxt_re/ib_verbs.c | 37 ++++++++++++++++++++++----------
 drivers/infiniband/hw/bnxt_re/main.c     |  2 ++
 drivers/infiniband/hw/bnxt_re/qplib_fp.c |  1 +
 drivers/infiniband/hw/bnxt_re/qplib_fp.h |  1 +
 5 files changed, 32 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index d1c839e..5f64fc4 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -159,6 +159,8 @@ struct bnxt_re_pacing {
 struct bnxt_re_nq_record {
 	struct bnxt_qplib_nq	nq[BNXT_RE_MAX_MSIX];
 	int			num_msix;
+	/* serialize NQ access */
+	struct mutex		load_lock;
 };
 
 #define MAX_CQ_HASH_BITS		(16)
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index a9c32c0..f6e9eef 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -3029,6 +3029,28 @@ 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)
 {
@@ -3047,6 +3069,8 @@ 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);
@@ -3065,8 +3089,6 @@ 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;
@@ -3117,16 +3139,10 @@ 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->nqr->nq[nq_alloc_cnt % (rdev->nqr->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) {
@@ -3136,7 +3152,6 @@ 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)
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 9669def..fcaf2b3 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1566,6 +1566,8 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
 
 	bnxt_qplib_init_res(&rdev->qplib_res);
 
+	mutex_init(&rdev->nqr->load_lock);
+
 	for (i = 1; i < rdev->nqr->num_msix ; i++) {
 		db_offt = rdev->en_dev->msix_entries[i].db_offset;
 		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nqr->nq[i - 1],
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index e2eea71..e56f42f 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -551,6 +551,7 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 	nq->pdev = pdev;
 	nq->cqn_handler = cqn_handler;
 	nq->srqn_handler = srqn_handler;
+	nq->load = 0;
 
 	/* Have a task to schedule CQ notifiers in post send case */
 	nq->cqn_wq  = create_singlethread_workqueue("bnxt_qplib_nq");
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
index b5a90581..8ff56d7 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -519,6 +519,7 @@ struct bnxt_qplib_nq {
 	struct tasklet_struct		nq_tasklet;
 	bool				requested;
 	int				budget;
+	u32				load;
 
 	cqn_handler_t			cqn_handler;
 	srqn_handler_t			srqn_handler;
-- 
2.5.5