1 files changed, 62 insertions, 10 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 49e4a4a50bfa..42e98e5f94cb 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -54,6 +54,10 @@
 #include "qplib_rcfw.h"
 #include "qplib_sp.h"
 #include "qplib_fp.h"
+#include <rdma/ib_addr.h>
+#include "bnxt_ulp.h"
+#include "bnxt_re.h"
+#include "ib_verbs.h"
 
 static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp);
 
@@ -347,6 +351,7 @@ static void bnxt_qplib_service_nq(struct tasklet_struct *t)
 		case NQ_BASE_TYPE_SRQ_EVENT:
 		{
 			struct bnxt_qplib_srq *srq;
+			struct bnxt_re_srq *srq_p;
 			struct nq_srq_event *nqsrqe =
 						(struct nq_srq_event *)nqe;
 
@@ -354,6 +359,12 @@ static void bnxt_qplib_service_nq(struct tasklet_struct *t)
 			q_handle |= (u64)le32_to_cpu(nqsrqe->srq_handle_high)
 				     << 32;
 			srq = (struct bnxt_qplib_srq *)q_handle;
+			srq->toggle = (le16_to_cpu(nqe->info10_type) & NQ_CN_TOGGLE_MASK)
+				      >> NQ_CN_TOGGLE_SFT;
+			srq->dbinfo.toggle = srq->toggle;
+			srq_p = container_of(srq, struct bnxt_re_srq, qplib_srq);
+			if (srq_p->uctx_srq_page)
+				*((u32 *)srq_p->uctx_srq_page) = srq->toggle;
 			bnxt_qplib_armen_db(&srq->dbinfo,
 					    DBC_DBC_TYPE_SRQ_ARMENA);
 			if (nq->srqn_handler(nq,
@@ -809,13 +820,13 @@ static int bnxt_qplib_alloc_init_swq(struct bnxt_qplib_q *que)
 {
 	int indx;
 
-	que->swq = kcalloc(que->max_wqe, sizeof(*que->swq), GFP_KERNEL);
+	que->swq = kcalloc(que->max_sw_wqe, sizeof(*que->swq), GFP_KERNEL);
 	if (!que->swq)
 		return -ENOMEM;
 
 	que->swq_start = 0;
-	que->swq_last = que->max_wqe - 1;
-	for (indx = 0; indx < que->max_wqe; indx++)
+	que->swq_last = que->max_sw_wqe - 1;
+	for (indx = 0; indx < que->max_sw_wqe; indx++)
 		que->swq[indx].next_idx = indx + 1;
 	que->swq[que->swq_last].next_idx = 0; /* Make it circular */
 	que->swq_last = 0;
@@ -851,7 +862,7 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	hwq_attr.res = res;
 	hwq_attr.sginfo = &sq->sg_info;
 	hwq_attr.stride = sizeof(struct sq_sge);
-	hwq_attr.depth = bnxt_qplib_get_depth(sq);
+	hwq_attr.depth = bnxt_qplib_get_depth(sq, qp->wqe_mode, false);
 	hwq_attr.type = HWQ_TYPE_QUEUE;
 	rc = bnxt_qplib_alloc_init_hwq(&sq->hwq, &hwq_attr);
 	if (rc)
@@ -879,7 +890,7 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		hwq_attr.res = res;
 		hwq_attr.sginfo = &rq->sg_info;
 		hwq_attr.stride = sizeof(struct sq_sge);
-		hwq_attr.depth = bnxt_qplib_get_depth(rq);
+		hwq_attr.depth = bnxt_qplib_get_depth(rq, qp->wqe_mode, false);
 		hwq_attr.type = HWQ_TYPE_QUEUE;
 		rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr);
 		if (rc)
@@ -1011,7 +1022,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	hwq_attr.res = res;
 	hwq_attr.sginfo = &sq->sg_info;
 	hwq_attr.stride = sizeof(struct sq_sge);
-	hwq_attr.depth = bnxt_qplib_get_depth(sq);
+	hwq_attr.depth = bnxt_qplib_get_depth(sq, qp->wqe_mode, true);
 	hwq_attr.aux_stride = psn_sz;
 	hwq_attr.aux_depth = psn_sz ? bnxt_qplib_set_sq_size(sq, qp->wqe_mode)
 				    : 0;
@@ -1052,7 +1063,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		hwq_attr.res = res;
 		hwq_attr.sginfo = &rq->sg_info;
 		hwq_attr.stride = sizeof(struct sq_sge);
-		hwq_attr.depth = bnxt_qplib_get_depth(rq);
+		hwq_attr.depth = bnxt_qplib_get_depth(rq, qp->wqe_mode, false);
 		hwq_attr.aux_stride = 0;
 		hwq_attr.aux_depth = 0;
 		hwq_attr.type = HWQ_TYPE_QUEUE;
@@ -2471,6 +2482,32 @@ out:
 	return rc;
 }
 
+static int bnxt_qplib_get_cqe_sq_cons(struct bnxt_qplib_q *sq, u32 cqe_slot)
+{
+	struct bnxt_qplib_hwq *sq_hwq;
+	struct bnxt_qplib_swq *swq;
+	int cqe_sq_cons = -1;
+	u32 start, last;
+
+	sq_hwq = &sq->hwq;
+
+	start = sq->swq_start;
+	last = sq->swq_last;
+
+	while (last != start) {
+		swq = &sq->swq[last];
+		if (swq->slot_idx  == cqe_slot) {
+			cqe_sq_cons = swq->next_idx;
+			dev_err(&sq_hwq->pdev->dev, "%s: Found cons wqe = %d slot = %d\n",
+				__func__, cqe_sq_cons, cqe_slot);
+			break;
+		}
+
+		last = swq->next_idx;
+	}
+	return cqe_sq_cons;
+}
+
 static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 				     struct cq_req *hwcqe,
 				     struct bnxt_qplib_cqe **pcqe, int *budget,
@@ -2478,9 +2515,10 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 {
 	struct bnxt_qplib_swq *swq;
 	struct bnxt_qplib_cqe *cqe;
+	u32 cqe_sq_cons, slot_num;
 	struct bnxt_qplib_qp *qp;
 	struct bnxt_qplib_q *sq;
-	u32 cqe_sq_cons;
+	int cqe_cons;
 	int rc = 0;
 
 	qp = (struct bnxt_qplib_qp *)((unsigned long)
@@ -2492,12 +2530,26 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 	}
 	sq = &qp->sq;
 
-	cqe_sq_cons = le16_to_cpu(hwcqe->sq_cons_idx) % sq->max_wqe;
+	cqe_sq_cons = le16_to_cpu(hwcqe->sq_cons_idx) % sq->max_sw_wqe;
 	if (qp->sq.flushed) {
 		dev_dbg(&cq->hwq.pdev->dev,
 			"%s: QP in Flush QP = %p\n", __func__, qp);
 		goto done;
 	}
+
+	if (__is_err_cqe_for_var_wqe(qp, hwcqe->status)) {
+		slot_num = le16_to_cpu(hwcqe->sq_cons_idx);
+		cqe_cons = bnxt_qplib_get_cqe_sq_cons(sq, slot_num);
+		if (cqe_cons < 0) {
+			dev_err(&cq->hwq.pdev->dev, "%s: Wrong SQ cons cqe_slot_indx = %d\n",
+				__func__, slot_num);
+			goto done;
+		}
+		cqe_sq_cons = cqe_cons;
+		dev_err(&cq->hwq.pdev->dev, "%s: cqe_sq_cons = %d swq_last = %d swq_start = %d\n",
+			__func__, cqe_sq_cons, sq->swq_last, sq->swq_start);
+	}
+
 	/* Require to walk the sq's swq to fabricate CQEs for all previously
 	 * signaled SWQEs due to CQE aggregation from the current sq cons
 	 * to the cqe_sq_cons
@@ -2882,7 +2934,7 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
 	cqe_cons = le16_to_cpu(hwcqe->sq_cons_idx);
 	if (cqe_cons == 0xFFFF)
 		goto do_rq;
-	cqe_cons %= sq->max_wqe;
+	cqe_cons %= sq->max_sw_wqe;
 
 	if (qp->sq.flushed) {
 		dev_dbg(&cq->hwq.pdev->dev,