Merge: RDMA/bnxt_re: add missing fixes from v6.12+.

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6204

JIRA: https://issues.redhat.com/browse/RHEL-74367

Add missing upstream fixes from kernels 6.12+.

Brew:
- https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=66407609

Signed-off-by: Mohammad Heib <mheib@redhat.com>

Approved-by: Kamal Heib <kheib@redhat.com>
Approved-by: José Ignacio Tornos Martínez <jtornosm@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Patrick Talbert <ptalbert@redhat.com>

Author: ptalbert

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -156,7 +156,7 @@ int bnxt_re_query_device(struct ib_device *ibdev,
 
 	ib_attr->vendor_id = rdev->en_dev->pdev->vendor;
 	ib_attr->vendor_part_id = rdev->en_dev->pdev->device;
-	ib_attr->hw_ver = rdev->en_dev->pdev->subsystem_device;
+	ib_attr->hw_ver = rdev->en_dev->pdev->revision;
 	ib_attr->max_qp = dev_attr->max_qp;
 	ib_attr->max_qp_wr = dev_attr->max_qp_wqes;
 	ib_attr->device_cap_flags =
@@ -2107,18 +2107,20 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		}
 	}
 
-	if (qp_attr_mask & IB_QP_PATH_MTU) {
-		qp->qplib_qp.modify_flags |=
-				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
-		qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
-		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
-	} else if (qp_attr->qp_state == IB_QPS_RTR) {
-		qp->qplib_qp.modify_flags |=
-			CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
-		qp->qplib_qp.path_mtu =
-			__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
-		qp->qplib_qp.mtu =
-			ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
+	if (qp_attr->qp_state == IB_QPS_RTR) {
+		enum ib_mtu qpmtu;
+
+		qpmtu = iboe_get_mtu(rdev->netdev->mtu);
+		if (qp_attr_mask & IB_QP_PATH_MTU) {
+			if (ib_mtu_enum_to_int(qp_attr->path_mtu) >
+			    ib_mtu_enum_to_int(qpmtu))
+				return -EINVAL;
+			qpmtu = qp_attr->path_mtu;
+		}
+
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
+		qp->qplib_qp.path_mtu = __from_ib_mtu(qpmtu);
+		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qpmtu);
 	}
 
 	if (qp_attr_mask & IB_QP_TIMEOUT) {
@@ -2763,7 +2765,8 @@ static int bnxt_re_post_send_shadow_qp(struct bnxt_re_dev *rdev,
 		wr = wr->next;
 	}
 	bnxt_qplib_post_send_db(&qp->qplib_qp);
-	bnxt_ud_qp_hw_stall_workaround(qp);
+	if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx))
+		bnxt_ud_qp_hw_stall_workaround(qp);
 	spin_unlock_irqrestore(&qp->sq_lock, flags);
 	return rc;
 }
@@ -2875,7 +2878,8 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
 		wr = wr->next;
 	}
 	bnxt_qplib_post_send_db(&qp->qplib_qp);
-	bnxt_ud_qp_hw_stall_workaround(qp);
+	if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx))
+		bnxt_ud_qp_hw_stall_workaround(qp);
 	spin_unlock_irqrestore(&qp->sq_lock, flags);
 
 	return rc;

drivers/infiniband/hw/bnxt_re/main.c

@@ -1435,24 +1435,18 @@ static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev,
 
 static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev)
 {
-	int mask = IB_QP_STATE;
-	struct ib_qp_attr qp_attr;
 	struct bnxt_re_qp *qp;
 
-	qp_attr.qp_state = IB_QPS_ERR;
 	mutex_lock(&rdev->qp_lock);
 	list_for_each_entry(qp, &rdev->qp_list, list) {
 		/* Modify the state of all QPs except QP1/Shadow QP */
 		if (!bnxt_re_is_qp1_or_shadow_qp(rdev, qp)) {
 			if (qp->qplib_qp.state !=
 			    CMDQ_MODIFY_QP_NEW_STATE_RESET &&
 			    qp->qplib_qp.state !=
-			    CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+			    CMDQ_MODIFY_QP_NEW_STATE_ERR)
 				bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp,
 						       1, IB_EVENT_QP_FATAL);
-				bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask,
-						  NULL);
-			}
 		}
 	}
 	mutex_unlock(&rdev->qp_lock);
@@ -2033,30 +2027,19 @@ static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state)
 	rdev = en_info->rdev;
 	en_dev = en_info->en_dev;
 	mutex_lock(&bnxt_re_mutex);
-	/* L2 driver may invoke this callback during device error/crash or device
-	 * reset. Current RoCE driver doesn't recover the device in case of
-	 * error. Handle the error by dispatching fatal events to all qps
-	 * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as
-	 * L2 driver want to modify the MSIx table.
-	 */
 
 	ibdev_info(&rdev->ibdev, "Handle device suspend call");
 	/* Check the current device state from bnxt_en_dev and move the
 	 * device to detached state if FW_FATAL_COND is set.
 	 * This prevents more commands to HW during clean-up,
 	 * in case the device is already in error.
 	 */
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &rdev->en_dev->en_state))
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &rdev->en_dev->en_state)) {
 		set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
-
-	bnxt_re_dev_stop(rdev);
-	bnxt_re_stop_irq(adev);
-	/* Move the device states to detached and  avoid sending any more
-	 * commands to HW
-	 */
-	set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags);
-	set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
-	wake_up_all(&rdev->rcfw.cmdq.waitq);
+		set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags);
+		wake_up_all(&rdev->rcfw.cmdq.waitq);
+		bnxt_re_dev_stop(rdev);
+	}
 
 	if (rdev->pacing.dbr_pacing)
 		bnxt_re_set_pacing_dev_state(rdev);
@@ -2075,13 +2058,6 @@ static int bnxt_re_resume(struct auxiliary_device *adev)
 	struct bnxt_re_dev *rdev;
 
 	mutex_lock(&bnxt_re_mutex);
-	/* L2 driver may invoke this callback during device recovery, resume.
-	 * reset. Current RoCE driver doesn't recover the device in case of
-	 * error. Handle the error by dispatching fatal events to all qps
-	 * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as
-	 * L2 driver want to modify the MSIx table.
-	 */
-
 	bnxt_re_add_device(adev, BNXT_RE_POST_RECOVERY_INIT);
 	rdev = en_info->rdev;
 	ibdev_info(&rdev->ibdev, "Device resume completed");

drivers/infiniband/hw/bnxt_re/qplib_fp.c

@@ -658,13 +658,6 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 	rc = bnxt_qplib_alloc_init_hwq(&srq->hwq, &hwq_attr);
 	if (rc)
 		return rc;
-
-	srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq),
-			   GFP_KERNEL);
-	if (!srq->swq) {
-		rc = -ENOMEM;
-		goto fail;
-	}
 	srq->dbinfo.flags = 0;
 	bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req,
 				 CMDQ_BASE_OPCODE_CREATE_SRQ,
@@ -693,9 +686,17 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 	spin_lock_init(&srq->lock);
 	srq->start_idx = 0;
 	srq->last_idx = srq->hwq.max_elements - 1;
-	for (idx = 0; idx < srq->hwq.max_elements; idx++)
-		srq->swq[idx].next_idx = idx + 1;
-	srq->swq[srq->last_idx].next_idx = -1;
+	if (!srq->hwq.is_user) {
+		srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq),
+				   GFP_KERNEL);
+		if (!srq->swq) {
+			rc = -ENOMEM;
+			goto fail;
+		}
+		for (idx = 0; idx < srq->hwq.max_elements; idx++)
+			srq->swq[idx].next_idx = idx + 1;
+		srq->swq[srq->last_idx].next_idx = -1;
+	}
 
 	srq->id = le32_to_cpu(resp.xid);
 	srq->dbinfo.hwq = &srq->hwq;
@@ -999,9 +1000,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u32 tbl_indx;
 	u16 nsge;
 
-	if (res->dattr)
-		qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2);
-
+	qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2);
 	sq->dbinfo.flags = 0;
 	bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req,
 				 CMDQ_BASE_OPCODE_CREATE_QP,
@@ -1043,13 +1042,14 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	if (rc)
 		return rc;
 
-	rc = bnxt_qplib_alloc_init_swq(sq);
-	if (rc)
-		goto fail_sq;
-
-	if (psn_sz)
-		bnxt_qplib_init_psn_ptr(qp, psn_sz);
+	if (!sq->hwq.is_user) {
+		rc = bnxt_qplib_alloc_init_swq(sq);
+		if (rc)
+			goto fail_sq;
 
+		if (psn_sz)
+			bnxt_qplib_init_psn_ptr(qp, psn_sz);
+	}
 	req.sq_size = cpu_to_le32(bnxt_qplib_set_sq_size(sq, qp->wqe_mode));
 	pbl = &sq->hwq.pbl[PBL_LVL_0];
 	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
@@ -1075,9 +1075,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr);
 		if (rc)
 			goto sq_swq;
-		rc = bnxt_qplib_alloc_init_swq(rq);
-		if (rc)
-			goto fail_rq;
+		if (!rq->hwq.is_user) {
+			rc = bnxt_qplib_alloc_init_swq(rq);
+			if (rc)
+				goto fail_rq;
+		}
 
 		req.rq_size = cpu_to_le32(rq->max_wqe);
 		pbl = &rq->hwq.pbl[PBL_LVL_0];
@@ -1173,9 +1175,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
+	spin_lock_bh(&rcfw->tbl_lock);
 	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
 	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
 	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
+	spin_unlock_bh(&rcfw->tbl_lock);
 
 	return 0;
 fail:
@@ -2596,10 +2600,12 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 			bnxt_qplib_add_flush_qp(qp);
 		} else {
 			/* Before we complete, do WA 9060 */
-			if (do_wa9060(qp, cq, cq_cons, sq->swq_last,
-				      cqe_sq_cons)) {
-				*lib_qp = qp;
-				goto out;
+			if (!bnxt_qplib_is_chip_gen_p5_p7(qp->cctx)) {
+				if (do_wa9060(qp, cq, cq_cons, sq->swq_last,
+					      cqe_sq_cons)) {
+					*lib_qp = qp;
+					goto out;
+				}
 			}
 			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
 				cqe->status = CQ_REQ_STATUS_OK;

drivers/infiniband/hw/bnxt_re/qplib_fp.h

@@ -114,7 +114,6 @@ struct bnxt_qplib_sge {
 	u32				size;
 };
 
-#define BNXT_QPLIB_QP_MAX_SGL	6
 struct bnxt_qplib_swq {
 	u64				wr_id;
 	int				next_idx;
@@ -154,7 +153,7 @@ struct bnxt_qplib_swqe {
 #define BNXT_QPLIB_SWQE_FLAGS_UC_FENCE			BIT(2)
 #define BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT		BIT(3)
 #define BNXT_QPLIB_SWQE_FLAGS_INLINE			BIT(4)
-	struct bnxt_qplib_sge		sg_list[BNXT_QPLIB_QP_MAX_SGL];
+	struct bnxt_qplib_sge		sg_list[BNXT_VAR_MAX_SGE];
 	int				num_sge;
 	/* Max inline data is 96 bytes */
 	u32				inline_len;

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -424,7 +424,8 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw,
 
 	/* Prevent posting if f/w is not in a state to process */
 	if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags))
-		return bnxt_qplib_map_rc(opcode);
+		return -ENXIO;
+
 	if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
 		return -ETIMEDOUT;
 
@@ -493,7 +494,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 
 	rc = __send_message_basic_sanity(rcfw, msg, opcode);
 	if (rc)
-		return rc;
+		return rc == -ENXIO ? bnxt_qplib_map_rc(opcode) : rc;
 
 	rc = __send_message(rcfw, msg, opcode);
 	if (rc)

drivers/infiniband/hw/bnxt_re/qplib_sp.c

@@ -129,12 +129,14 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	attr->max_qp_init_rd_atom =
 		sb->max_qp_init_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ?
 		BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_init_rd_atom;
-	attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr);
-	/*
-	 * 128 WQEs needs to be reserved for the HW (8916). Prevent
-	 * reporting the max number
-	 */
-	attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1;
+	attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr) - 1;
+	if (!bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx)) {
+		/*
+		 * 128 WQEs needs to be reserved for the HW (8916). Prevent
+		 * reporting the max number on legacy devices
+		 */
+		attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1;
+	}
 
 	attr->max_qp_sges = cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE ?
 			    min_t(u32, sb->max_sge_var_wqe, BNXT_VAR_MAX_SGE) : 6;