RDMA/bnxt_re: Add extended psn structure for 57500 adapters

The new 57500 series of adapter has bigger psn search structure.  The size
of new structure is 16B. Changing the control path memory allocation and
fast path code to accommodate the new psn structure while maintaining the
backward compatibility.

There are few additional changes listed below:
 - For 57500 chip max-sge are limited to 6 for now.
 - For 57500 chip max-receive-sge should be set to 6 for now.
 - Add driver/hardware interface structure for new chip.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -884,7 +884,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
 	struct bnxt_re_qp_req ureq;
 	struct bnxt_qplib_qp *qplib_qp = &qp->qplib_qp;
 	struct ib_umem *umem;
-	int bytes = 0;
+	int bytes = 0, psn_sz;
 	struct ib_ucontext *context = pd->ib_pd.uobject->context;
 	struct bnxt_re_ucontext *cntx = container_of(context,
 						     struct bnxt_re_ucontext,
@@ -894,8 +894,12 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
 
 	bytes = (qplib_qp->sq.max_wqe * BNXT_QPLIB_MAX_SQE_ENTRY_SIZE);
 	/* Consider mapping PSN search memory only for RC QPs. */
-	if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC)
-		bytes += (qplib_qp->sq.max_wqe * sizeof(struct sq_psn_search));
+	if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC) {
+		psn_sz = bnxt_qplib_is_chip_gen_p5(&rdev->chip_ctx) ?
+					sizeof(struct sq_psn_search_ext) :
+					sizeof(struct sq_psn_search);
+		bytes += (qplib_qp->sq.max_wqe * psn_sz);
+	}
 	bytes = PAGE_ALIGN(bytes);
 	umem = ib_umem_get(udata, ureq.qpsva, bytes, IB_ACCESS_LOCAL_WRITE, 1);
 	if (IS_ERR(umem))
@@ -1652,6 +1656,9 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 			__from_ib_access_flags(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;
 	}
 	if (qp_attr_mask & IB_QP_PKEY_INDEX) {
 		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY;

drivers/infiniband/hw/bnxt_re/qplib_fp.c

@@ -870,10 +870,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	unsigned long int psn_search, poff = 0;
 	struct bnxt_qplib_q *sq = &qp->sq;
 	struct bnxt_qplib_q *rq = &qp->rq;
+	int i, rc, req_size, psn_sz = 0;
 	struct bnxt_qplib_hwq *xrrq;
-	int i, rc, req_size, psn_sz;
 	u16 cmd_flags = 0, max_ssge;
 	u32 sw_prod, qp_flags = 0;
+	u16 max_rsge;
 
 	RCFW_CMD_PREP(req, CREATE_QP, cmd_flags);
 
@@ -883,8 +884,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	req.qp_handle = cpu_to_le64(qp->qp_handle);
 
 	/* SQ */
-	psn_sz = (qp->type == CMDQ_CREATE_QP_TYPE_RC) ?
-		 sizeof(struct sq_psn_search) : 0;
+	if (qp->type == CMDQ_CREATE_QP_TYPE_RC) {
+		psn_sz = bnxt_qplib_is_chip_gen_p5(res->cctx) ?
+			 sizeof(struct sq_psn_search_ext) :
+			 sizeof(struct sq_psn_search);
+	}
 	sq->hwq.max_elements = sq->max_wqe;
 	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &sq->hwq, sq->sglist,
 				       sq->nmap, &sq->hwq.max_elements,
@@ -914,10 +918,16 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 			poff = (psn_search & ~PAGE_MASK) /
 				BNXT_QPLIB_MAX_PSNE_ENTRY_SIZE;
 		}
-		for (i = 0; i < sq->hwq.max_elements; i++)
+		for (i = 0; i < sq->hwq.max_elements; i++) {
 			sq->swq[i].psn_search =
 				&psn_search_ptr[get_psne_pg(i + poff)]
 					       [get_psne_idx(i + poff)];
+			/*psns_ext will be used only for P5 chips. */
+			sq->swq[i].psn_ext =
+				(struct sq_psn_search_ext *)
+				&psn_search_ptr[get_psne_pg(i + poff)]
+					       [get_psne_idx(i + poff)];
+		}
 	}
 	pbl = &sq->hwq.pbl[PBL_LVL_0];
 	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
@@ -1016,8 +1026,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	req.sq_fwo_sq_sge = cpu_to_le16(
 				((max_ssge & CMDQ_CREATE_QP_SQ_SGE_MASK)
 				 << CMDQ_CREATE_QP_SQ_SGE_SFT) | 0);
+	max_rsge = bnxt_qplib_is_chip_gen_p5(res->cctx) ? 6 : rq->max_sge;
 	req.rq_fwo_rq_sge = cpu_to_le16(
-				((rq->max_sge & CMDQ_CREATE_QP_RQ_SGE_MASK)
+				((max_rsge & CMDQ_CREATE_QP_RQ_SGE_MASK)
 				 << CMDQ_CREATE_QP_RQ_SGE_SFT) | 0);
 	/* ORRQ and IRRQ */
 	if (psn_sz) {
@@ -1062,6 +1073,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 
 	qp->id = le32_to_cpu(resp.xid);
 	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
+	qp->cctx = res->cctx;
 	INIT_LIST_HEAD(&qp->sq_flush);
 	INIT_LIST_HEAD(&qp->rq_flush);
 	rcfw->qp_tbl[qp->id].qp_id = qp->id;
@@ -1748,14 +1760,26 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 	}
 	swq->next_psn = sq->psn & BTH_PSN_MASK;
 	if (swq->psn_search) {
-		swq->psn_search->opcode_start_psn = cpu_to_le32(
-			((swq->start_psn << SQ_PSN_SEARCH_START_PSN_SFT) &
-			 SQ_PSN_SEARCH_START_PSN_MASK) |
-			((wqe->type << SQ_PSN_SEARCH_OPCODE_SFT) &
-			 SQ_PSN_SEARCH_OPCODE_MASK));
-		swq->psn_search->flags_next_psn = cpu_to_le32(
-			((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) &
-			 SQ_PSN_SEARCH_NEXT_PSN_MASK));
+		u32 opcd_spsn;
+		u32 flg_npsn;
+
+		opcd_spsn = ((swq->start_psn << SQ_PSN_SEARCH_START_PSN_SFT) &
+			      SQ_PSN_SEARCH_START_PSN_MASK);
+		opcd_spsn |= ((wqe->type << SQ_PSN_SEARCH_OPCODE_SFT) &
+			       SQ_PSN_SEARCH_OPCODE_MASK);
+		flg_npsn = ((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) &
+			     SQ_PSN_SEARCH_NEXT_PSN_MASK);
+		if (bnxt_qplib_is_chip_gen_p5(qp->cctx)) {
+			swq->psn_ext->opcode_start_psn =
+						cpu_to_le32(opcd_spsn);
+			swq->psn_ext->flags_next_psn =
+						cpu_to_le32(flg_npsn);
+		} else {
+			swq->psn_search->opcode_start_psn =
+						cpu_to_le32(opcd_spsn);
+			swq->psn_search->flags_next_psn =
+						cpu_to_le32(flg_npsn);
+		}
 	}
 queue_err:
 	if (sch_handler) {
@@ -2053,6 +2077,7 @@ static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp,
 		opcode = CQ_BASE_CQE_TYPE_RES_RC;
 		break;
 	case CMDQ_CREATE_QP_TYPE_UD:
+	case CMDQ_CREATE_QP_TYPE_GSI:
 		opcode = CQ_BASE_CQE_TYPE_RES_UD;
 		break;
 	}

drivers/infiniband/hw/bnxt_re/qplib_fp.h

@@ -106,6 +106,7 @@ struct bnxt_qplib_swq {
 	u32				start_psn;
 	u32				next_psn;
 	struct sq_psn_search		*psn_search;
+	struct sq_psn_search_ext	*psn_ext;
 };
 
 struct bnxt_qplib_swqe {
@@ -254,6 +255,7 @@ struct bnxt_qplib_q {
 struct bnxt_qplib_qp {
 	struct bnxt_qplib_pd		*pd;
 	struct bnxt_qplib_dpi		*dpi;
+	struct bnxt_qplib_chip_ctx	*cctx;
 	u64				qp_handle;
 #define        BNXT_QPLIB_QP_ID_INVALID        0xFFFFFFFF
 	u32				id;

drivers/infiniband/hw/bnxt_re/qplib_sp.c

@@ -119,7 +119,8 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	 * reporting the max number
 	 */
 	attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS;
-	attr->max_qp_sges = sb->max_sge;
+	attr->max_qp_sges = bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx) ?
+			    6 : sb->max_sge;
 	attr->max_cq = le32_to_cpu(sb->max_cq);
 	attr->max_cq_wqes = le32_to_cpu(sb->max_cqe);
 	attr->max_cq_sges = attr->max_qp_sges;

drivers/infiniband/hw/bnxt_re/roce_hsi.h

@@ -162,6 +162,23 @@ struct sq_psn_search {
 	#define SQ_PSN_SEARCH_FLAGS_SFT				    24
 };
 
+/* sq_psn_search_ext (size:128b/16B) */
+struct sq_psn_search_ext {
+	__le32  opcode_start_psn;
+	#define SQ_PSN_SEARCH_EXT_START_PSN_MASK		    0xffffffUL
+	#define SQ_PSN_SEARCH_EXT_START_PSN_SFT			    0
+	#define SQ_PSN_SEARCH_EXT_OPCODE_MASK			    0xff000000UL
+	#define SQ_PSN_SEARCH_EXT_OPCODE_SFT			    24
+	__le32  flags_next_psn;
+	#define SQ_PSN_SEARCH_EXT_NEXT_PSN_MASK			    0xffffffUL
+	#define SQ_PSN_SEARCH_EXT_NEXT_PSN_SFT			    0
+	#define SQ_PSN_SEARCH_EXT_FLAGS_MASK			    0xff000000UL
+	#define SQ_PSN_SEARCH_EXT_FLAGS_SFT			    24
+	__le16  start_slot_idx;
+	__le16  reserved16;
+	__le32  reserved32;
+};
+
 /* Send SQ WQE (40 bytes) */
 struct sq_send {
 	u8 wqe_type;