1 files changed, 277 insertions, 80 deletions

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 2a4fc00dfa9b..d6b184839bc2 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -74,6 +74,8 @@ static struct lpfc_iocbq *lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *,
 							 struct lpfc_iocbq *);
 static void lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *,
 				      struct hbq_dmabuf *);
+static void lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
+					  struct hbq_dmabuf *dmabuf);
 static int lpfc_sli4_fp_handle_cqe(struct lpfc_hba *, struct lpfc_queue *,
 				    struct lpfc_cqe *);
 static int lpfc_sli4_post_sgl_list(struct lpfc_hba *, struct list_head *,
@@ -479,22 +481,23 @@ lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
 	if (unlikely(!hq) || unlikely(!dq))
 		return -ENOMEM;
 	put_index = hq->host_index;
-	temp_hrqe = hq->qe[hq->host_index].rqe;
+	temp_hrqe = hq->qe[put_index].rqe;
 	temp_drqe = dq->qe[dq->host_index].rqe;
 
 	if (hq->type != LPFC_HRQ || dq->type != LPFC_DRQ)
 		return -EINVAL;
-	if (hq->host_index != dq->host_index)
+	if (put_index != dq->host_index)
 		return -EINVAL;
 	/* If the host has not yet processed the next entry then we are done */
-	if (((hq->host_index + 1) % hq->entry_count) == hq->hba_index)
+	if (((put_index + 1) % hq->entry_count) == hq->hba_index)
 		return -EBUSY;
 	lpfc_sli_pcimem_bcopy(hrqe, temp_hrqe, hq->entry_size);
 	lpfc_sli_pcimem_bcopy(drqe, temp_drqe, dq->entry_size);
 
 	/* Update the host index to point to the next slot */
-	hq->host_index = ((hq->host_index + 1) % hq->entry_count);
+	hq->host_index = ((put_index + 1) % hq->entry_count);
 	dq->host_index = ((dq->host_index + 1) % dq->entry_count);
+	hq->RQ_buf_posted++;
 
 	/* Ring The Header Receive Queue Doorbell */
 	if (!(hq->host_index % hq->entry_repost)) {
@@ -5906,7 +5909,7 @@ lpfc_set_features(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox,
 		bf_set(lpfc_mbx_set_feature_mds,
 		       &mbox->u.mqe.un.set_feature, 1);
 		bf_set(lpfc_mbx_set_feature_mds_deep_loopbk,
-		       &mbox->u.mqe.un.set_feature, 0);
+		       &mbox->u.mqe.un.set_feature, 1);
 		mbox->u.mqe.un.set_feature.feature = LPFC_SET_MDS_DIAGS;
 		mbox->u.mqe.un.set_feature.param_len = 8;
 		break;
@@ -6512,6 +6515,50 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 		 (phba->hba_flag & HBA_FCOE_MODE) ? "FCoE" : "FC");
 }
 
+int
+lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+		    struct lpfc_queue *drq, int count, int idx)
+{
+	int rc, i;
+	struct lpfc_rqe hrqe;
+	struct lpfc_rqe drqe;
+	struct lpfc_rqb *rqbp;
+	struct rqb_dmabuf *rqb_buffer;
+	LIST_HEAD(rqb_buf_list);
+
+	rqbp = hrq->rqbp;
+	for (i = 0; i < count; i++) {
+		/* IF RQ is already full, don't bother */
+		if (rqbp->buffer_count + i >= rqbp->entry_count - 1)
+			break;
+		rqb_buffer = rqbp->rqb_alloc_buffer(phba);
+		if (!rqb_buffer)
+			break;
+		rqb_buffer->hrq = hrq;
+		rqb_buffer->drq = drq;
+		rqb_buffer->idx = idx;
+		list_add_tail(&rqb_buffer->hbuf.list, &rqb_buf_list);
+	}
+	while (!list_empty(&rqb_buf_list)) {
+		list_remove_head(&rqb_buf_list, rqb_buffer, struct rqb_dmabuf,
+				 hbuf.list);
+
+		hrqe.address_lo = putPaddrLow(rqb_buffer->hbuf.phys);
+		hrqe.address_hi = putPaddrHigh(rqb_buffer->hbuf.phys);
+		drqe.address_lo = putPaddrLow(rqb_buffer->dbuf.phys);
+		drqe.address_hi = putPaddrHigh(rqb_buffer->dbuf.phys);
+		rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
+		if (rc < 0) {
+			rqbp->rqb_free_buffer(phba, rqb_buffer);
+		} else {
+			list_add_tail(&rqb_buffer->hbuf.list,
+				      &rqbp->rqb_buffer_list);
+			rqbp->buffer_count++;
+		}
+	}
+	return 1;
+}
+
 /**
  * lpfc_sli4_hba_setup - SLI4 device initialization PCI function
  * @phba: Pointer to HBA context object.
@@ -6524,7 +6571,7 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 int
 lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 {
-	int rc, i;
+	int rc, i, cnt;
 	LPFC_MBOXQ_t *mboxq;
 	struct lpfc_mqe *mqe;
 	uint8_t *vpd;
@@ -6875,6 +6922,21 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 			goto out_destroy_queue;
 		}
 		phba->sli4_hba.nvmet_xri_cnt = rc;
+
+		cnt = phba->cfg_iocb_cnt * 1024;
+		/* We need 1 iocbq for every SGL, for IO processing */
+		cnt += phba->sli4_hba.nvmet_xri_cnt;
+		/* Initialize and populate the iocb list per host */
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"2821 initialize iocb list %d total %d\n",
+				phba->cfg_iocb_cnt, cnt);
+		rc = lpfc_init_iocb_list(phba, cnt);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"1413 Failed to init iocb list.\n");
+			goto out_destroy_queue;
+		}
+
 		lpfc_nvmet_create_targetport(phba);
 	} else {
 		/* update host scsi xri-sgl sizes and mappings */
@@ -6894,28 +6956,34 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 					"and mapping: %d\n", rc);
 			goto out_destroy_queue;
 		}
+
+		cnt = phba->cfg_iocb_cnt * 1024;
+		/* Initialize and populate the iocb list per host */
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"2820 initialize iocb list %d total %d\n",
+				phba->cfg_iocb_cnt, cnt);
+		rc = lpfc_init_iocb_list(phba, cnt);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6301 Failed to init iocb list.\n");
+			goto out_destroy_queue;
+		}
 	}
 
 	if (phba->nvmet_support && phba->cfg_nvmet_mrq) {
-
 		/* Post initial buffers to all RQs created */
 		for (i = 0; i < phba->cfg_nvmet_mrq; i++) {
 			rqbp = phba->sli4_hba.nvmet_mrq_hdr[i]->rqbp;
 			INIT_LIST_HEAD(&rqbp->rqb_buffer_list);
 			rqbp->rqb_alloc_buffer = lpfc_sli4_nvmet_alloc;
 			rqbp->rqb_free_buffer = lpfc_sli4_nvmet_free;
-			rqbp->entry_count = 256;
+			rqbp->entry_count = LPFC_NVMET_RQE_DEF_COUNT;
 			rqbp->buffer_count = 0;
 
-			/* Divide by 4 and round down to multiple of 16 */
-			rc = (phba->cfg_nvmet_mrq_post >> 2) & 0xfff8;
-			phba->sli4_hba.nvmet_mrq_hdr[i]->entry_repost = rc;
-			phba->sli4_hba.nvmet_mrq_data[i]->entry_repost = rc;
-
 			lpfc_post_rq_buffer(
 				phba, phba->sli4_hba.nvmet_mrq_hdr[i],
 				phba->sli4_hba.nvmet_mrq_data[i],
-				phba->cfg_nvmet_mrq_post);
+				LPFC_NVMET_RQE_DEF_COUNT, i);
 		}
 	}
 
@@ -7082,6 +7150,7 @@ out_unset_queue:
 	/* Unset all the queues set up in this routine when error out */
 	lpfc_sli4_queue_unset(phba);
 out_destroy_queue:
+	lpfc_free_iocb_list(phba);
 	lpfc_sli4_queue_destroy(phba);
 out_stop_timers:
 	lpfc_stop_hba_timers(phba);
@@ -8621,8 +8690,11 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		memset(wqe, 0, sizeof(union lpfc_wqe128));
 	/* Some of the fields are in the right position already */
 	memcpy(wqe, &iocbq->iocb, sizeof(union lpfc_wqe));
-	wqe->generic.wqe_com.word7 = 0; /* The ct field has moved so reset */
-	wqe->generic.wqe_com.word10 = 0;
+	if (iocbq->iocb.ulpCommand != CMD_SEND_FRAME) {
+		/* The ct field has moved so reset */
+		wqe->generic.wqe_com.word7 = 0;
+		wqe->generic.wqe_com.word10 = 0;
+	}
 
 	abort_tag = (uint32_t) iocbq->iotag;
 	xritag = iocbq->sli4_xritag;
@@ -9116,6 +9188,10 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		}
 
 		break;
+	case CMD_SEND_FRAME:
+		bf_set(wqe_xri_tag, &wqe->generic.wqe_com, xritag);
+		bf_set(wqe_reqtag, &wqe->generic.wqe_com, iocbq->iotag);
+		return 0;
 	case CMD_XRI_ABORTED_CX:
 	case CMD_CREATE_XRI_CR: /* Do we expect to use this? */
 	case CMD_IOCB_FCP_IBIDIR64_CR: /* bidirectional xfer */
@@ -12788,6 +12864,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 	struct fc_frame_header *fc_hdr;
 	struct lpfc_queue *hrq = phba->sli4_hba.hdr_rq;
 	struct lpfc_queue *drq = phba->sli4_hba.dat_rq;
+	struct lpfc_nvmet_tgtport *tgtp;
 	struct hbq_dmabuf *dma_buf;
 	uint32_t status, rq_id;
 	unsigned long iflags;
@@ -12808,7 +12885,6 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"2537 Receive Frame Truncated!!\n");
-		hrq->RQ_buf_trunc++;
 	case FC_STATUS_RQ_SUCCESS:
 		lpfc_sli4_rq_release(hrq, drq);
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -12819,6 +12895,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 			goto out;
 		}
 		hrq->RQ_rcv_buf++;
+		hrq->RQ_buf_posted--;
 		memcpy(&dma_buf->cq_event.cqe.rcqe_cmpl, rcqe, sizeof(*rcqe));
 
 		/* If a NVME LS event (type 0x28), treat it as Fast path */
@@ -12832,8 +12909,21 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		workposted = true;
 		break;
-	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 	case FC_STATUS_INSUFF_BUF_FRM_DISC:
+		if (phba->nvmet_support) {
+			tgtp = phba->targetport->private;
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_NVME,
+					"6402 RQE Error x%x, posted %d err_cnt "
+					"%d: %x %x %x\n",
+					status, hrq->RQ_buf_posted,
+					hrq->RQ_no_posted_buf,
+					atomic_read(&tgtp->rcv_fcp_cmd_in),
+					atomic_read(&tgtp->rcv_fcp_cmd_out),
+					atomic_read(&tgtp->xmt_fcp_release));
+		}
+		/* fallthrough */
+
+	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 		hrq->RQ_no_posted_buf++;
 		/* Post more buffers if possible */
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -12951,7 +13041,7 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 		while ((cqe = lpfc_sli4_cq_get(cq))) {
 			workposted |= lpfc_sli4_sp_handle_mcqe(phba, cqe);
 			if (!(++ecount % cq->entry_repost))
-				lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+				break;
 			cq->CQ_mbox++;
 		}
 		break;
@@ -12965,7 +13055,7 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 				workposted |= lpfc_sli4_sp_handle_cqe(phba, cq,
 								      cqe);
 			if (!(++ecount % cq->entry_repost))
-				lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+				break;
 		}
 
 		/* Track the max number of CQEs processed in 1 EQ */
@@ -13135,6 +13225,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	struct lpfc_queue *drq;
 	struct rqb_dmabuf *dma_buf;
 	struct fc_frame_header *fc_hdr;
+	struct lpfc_nvmet_tgtport *tgtp;
 	uint32_t status, rq_id;
 	unsigned long iflags;
 	uint32_t fctl, idx;
@@ -13165,8 +13256,6 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"6126 Receive Frame Truncated!!\n");
-		hrq->RQ_buf_trunc++;
-		break;
 	case FC_STATUS_RQ_SUCCESS:
 		lpfc_sli4_rq_release(hrq, drq);
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -13178,6 +13267,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 		}
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		hrq->RQ_rcv_buf++;
+		hrq->RQ_buf_posted--;
 		fc_hdr = (struct fc_frame_header *)dma_buf->hbuf.virt;
 
 		/* Just some basic sanity checks on FCP Command frame */
@@ -13200,14 +13290,23 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 drop:
 		lpfc_in_buf_free(phba, &dma_buf->dbuf);
 		break;
-	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 	case FC_STATUS_INSUFF_BUF_FRM_DISC:
+		if (phba->nvmet_support) {
+			tgtp = phba->targetport->private;
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_NVME,
+					"6401 RQE Error x%x, posted %d err_cnt "
+					"%d: %x %x %x\n",
+					status, hrq->RQ_buf_posted,
+					hrq->RQ_no_posted_buf,
+					atomic_read(&tgtp->rcv_fcp_cmd_in),
+					atomic_read(&tgtp->rcv_fcp_cmd_out),
+					atomic_read(&tgtp->xmt_fcp_release));
+		}
+		/* fallthrough */
+
+	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 		hrq->RQ_no_posted_buf++;
 		/* Post more buffers if possible */
-		spin_lock_irqsave(&phba->hbalock, iflags);
-		phba->hba_flag |= HBA_POST_RECEIVE_BUFFER;
-		spin_unlock_irqrestore(&phba->hbalock, iflags);
-		workposted = true;
 		break;
 	}
 out:
@@ -13361,7 +13460,7 @@ process_cq:
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
 		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
 		if (!(++ecount % cq->entry_repost))
-			lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+			break;
 	}
 
 	/* Track the max number of CQEs processed in 1 EQ */
@@ -13452,7 +13551,7 @@ lpfc_sli4_fof_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe)
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
 		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
 		if (!(++ecount % cq->entry_repost))
-			lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+			break;
 	}
 
 	/* Track the max number of CQEs processed in 1 EQ */
@@ -13534,7 +13633,7 @@ lpfc_sli4_fof_intr_handler(int irq, void *dev_id)
 	while ((eqe = lpfc_sli4_eq_get(eq))) {
 		lpfc_sli4_fof_handle_eqe(phba, eqe);
 		if (!(++ecount % eq->entry_repost))
-			lpfc_sli4_eq_release(eq, LPFC_QUEUE_NOARM);
+			break;
 		eq->EQ_processed++;
 	}
 
@@ -13651,7 +13750,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 
 		lpfc_sli4_hba_handle_eqe(phba, eqe, hba_eqidx);
 		if (!(++ecount % fpeq->entry_repost))
-			lpfc_sli4_eq_release(fpeq, LPFC_QUEUE_NOARM);
+			break;
 		fpeq->EQ_processed++;
 	}
 
@@ -13832,17 +13931,10 @@ lpfc_sli4_queue_alloc(struct lpfc_hba *phba, uint32_t entry_size,
 	}
 	queue->entry_size = entry_size;
 	queue->entry_count = entry_count;
-
-	/*
-	 * entry_repost is calculated based on the number of entries in the
-	 * queue. This works out except for RQs. If buffers are NOT initially
-	 * posted for every RQE, entry_repost should be adjusted accordingly.
-	 */
-	queue->entry_repost = (entry_count >> 3);
-	if (queue->entry_repost < LPFC_QUEUE_MIN_REPOST)
-		queue->entry_repost = LPFC_QUEUE_MIN_REPOST;
 	queue->phba = phba;
 
+	/* entry_repost will be set during q creation */
+
 	return queue;
 out_fail:
 	lpfc_sli4_queue_free(queue);
@@ -14073,6 +14165,7 @@ lpfc_eq_create(struct lpfc_hba *phba, struct lpfc_queue *eq, uint32_t imax)
 		status = -ENXIO;
 	eq->host_index = 0;
 	eq->hba_index = 0;
+	eq->entry_repost = LPFC_EQ_REPOST;
 
 	mempool_free(mbox, phba->mbox_mem_pool);
 	return status;
@@ -14146,9 +14239,9 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"0361 Unsupported CQ count: "
-				"entry cnt %d sz %d pg cnt %d repost %d\n",
+				"entry cnt %d sz %d pg cnt %d\n",
 				cq->entry_count, cq->entry_size,
-				cq->page_count, cq->entry_repost);
+				cq->page_count);
 		if (cq->entry_count < 256) {
 			status = -EINVAL;
 			goto out;
@@ -14201,6 +14294,7 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	cq->assoc_qid = eq->queue_id;
 	cq->host_index = 0;
 	cq->hba_index = 0;
+	cq->entry_repost = LPFC_CQ_REPOST;
 
 out:
 	mempool_free(mbox, phba->mbox_mem_pool);
@@ -14392,6 +14486,7 @@ lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,
 		cq->assoc_qid = eq->queue_id;
 		cq->host_index = 0;
 		cq->hba_index = 0;
+		cq->entry_repost = LPFC_CQ_REPOST;
 
 		rc = 0;
 		list_for_each_entry(dmabuf, &cq->page_list, list) {
@@ -14640,6 +14735,7 @@ lpfc_mq_create(struct lpfc_hba *phba, struct lpfc_queue *mq,
 	mq->subtype = subtype;
 	mq->host_index = 0;
 	mq->hba_index = 0;
+	mq->entry_repost = LPFC_MQ_REPOST;
 
 	/* link the mq onto the parent cq child list */
 	list_add_tail(&mq->list, &cq->child_list);
@@ -14865,34 +14961,6 @@ out:
 }
 
 /**
- * lpfc_rq_adjust_repost - Adjust entry_repost for an RQ
- * @phba: HBA structure that indicates port to create a queue on.
- * @rq:   The queue structure to use for the receive queue.
- * @qno:  The associated HBQ number
- *
- *
- * For SLI4 we need to adjust the RQ repost value based on
- * the number of buffers that are initially posted to the RQ.
- */
-void
-lpfc_rq_adjust_repost(struct lpfc_hba *phba, struct lpfc_queue *rq, int qno)
-{
-	uint32_t cnt;
-
-	/* sanity check on queue memory */
-	if (!rq)
-		return;
-	cnt = lpfc_hbq_defs[qno]->entry_count;
-
-	/* Recalc repost for RQs based on buffers initially posted */
-	cnt = (cnt >> 3);
-	if (cnt < LPFC_QUEUE_MIN_REPOST)
-		cnt = LPFC_QUEUE_MIN_REPOST;
-
-	rq->entry_repost = cnt;
-}
-
-/**
  * lpfc_rq_create - Create a Receive Queue on the HBA
  * @phba: HBA structure that indicates port to create a queue on.
  * @hrq: The queue structure to use to create the header receive queue.
@@ -15077,6 +15145,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	hrq->subtype = subtype;
 	hrq->host_index = 0;
 	hrq->hba_index = 0;
+	hrq->entry_repost = LPFC_RQ_REPOST;
 
 	/* now create the data queue */
 	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
@@ -15087,7 +15156,12 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	if (phba->sli4_hba.pc_sli4_params.rqv == LPFC_Q_CREATE_VERSION_1) {
 		bf_set(lpfc_rq_context_rqe_count_1,
 		       &rq_create->u.request.context, hrq->entry_count);
-		rq_create->u.request.context.buffer_size = LPFC_DATA_BUF_SIZE;
+		if (subtype == LPFC_NVMET)
+			rq_create->u.request.context.buffer_size =
+				LPFC_NVMET_DATA_BUF_SIZE;
+		else
+			rq_create->u.request.context.buffer_size =
+				LPFC_DATA_BUF_SIZE;
 		bf_set(lpfc_rq_context_rqe_size, &rq_create->u.request.context,
 		       LPFC_RQE_SIZE_8);
 		bf_set(lpfc_rq_context_page_size, &rq_create->u.request.context,
@@ -15124,8 +15198,14 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 			       LPFC_RQ_RING_SIZE_4096);
 			break;
 		}
-		bf_set(lpfc_rq_context_buf_size, &rq_create->u.request.context,
-		       LPFC_DATA_BUF_SIZE);
+		if (subtype == LPFC_NVMET)
+			bf_set(lpfc_rq_context_buf_size,
+			       &rq_create->u.request.context,
+			       LPFC_NVMET_DATA_BUF_SIZE);
+		else
+			bf_set(lpfc_rq_context_buf_size,
+			       &rq_create->u.request.context,
+			       LPFC_DATA_BUF_SIZE);
 	}
 	bf_set(lpfc_rq_context_cq_id, &rq_create->u.request.context,
 	       cq->queue_id);
@@ -15158,6 +15238,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	drq->subtype = subtype;
 	drq->host_index = 0;
 	drq->hba_index = 0;
+	drq->entry_repost = LPFC_RQ_REPOST;
 
 	/* link the header and data RQs onto the parent cq child list */
 	list_add_tail(&hrq->list, &cq->child_list);
@@ -15270,7 +15351,7 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 			       cq->queue_id);
 			bf_set(lpfc_rq_context_data_size,
 			       &rq_create->u.request.context,
-			       LPFC_DATA_BUF_SIZE);
+			       LPFC_NVMET_DATA_BUF_SIZE);
 			bf_set(lpfc_rq_context_hdr_size,
 			       &rq_create->u.request.context,
 			       LPFC_HDR_BUF_SIZE);
@@ -15315,6 +15396,7 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 		hrq->subtype = subtype;
 		hrq->host_index = 0;
 		hrq->hba_index = 0;
+		hrq->entry_repost = LPFC_RQ_REPOST;
 
 		drq->db_format = LPFC_DB_RING_FORMAT;
 		drq->db_regaddr = phba->sli4_hba.RQDBregaddr;
@@ -15323,6 +15405,7 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 		drq->subtype = subtype;
 		drq->host_index = 0;
 		drq->hba_index = 0;
+		drq->entry_repost = LPFC_RQ_REPOST;
 
 		list_add_tail(&hrq->list, &cq->child_list);
 		list_add_tail(&drq->list, &cq->child_list);
@@ -16063,6 +16146,8 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	struct fc_vft_header *fc_vft_hdr;
 	uint32_t *header = (uint32_t *) fc_hdr;
 
+#define FC_RCTL_MDS_DIAGS	0xF4
+
 	switch (fc_hdr->fh_r_ctl) {
 	case FC_RCTL_DD_UNCAT:		/* uncategorized information */
 	case FC_RCTL_DD_SOL_DATA:	/* solicited data */
@@ -16090,6 +16175,7 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	case FC_RCTL_F_BSY:	/* fabric busy to data frame */
 	case FC_RCTL_F_BSYL:	/* fabric busy to link control frame */
 	case FC_RCTL_LCR:	/* link credit reset */
+	case FC_RCTL_MDS_DIAGS: /* MDS Diagnostics */
 	case FC_RCTL_END:	/* end */
 		break;
 	case FC_RCTL_VFTH:	/* Virtual Fabric tagging Header */
@@ -16099,12 +16185,16 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	default:
 		goto drop;
 	}
+
+#define FC_TYPE_VENDOR_UNIQUE	0xFF
+
 	switch (fc_hdr->fh_type) {
 	case FC_TYPE_BLS:
 	case FC_TYPE_ELS:
 	case FC_TYPE_FCP:
 	case FC_TYPE_CT:
 	case FC_TYPE_NVME:
+	case FC_TYPE_VENDOR_UNIQUE:
 		break;
 	case FC_TYPE_IP:
 	case FC_TYPE_ILS:
@@ -16115,12 +16205,14 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
 			"2538 Received frame rctl:%s (x%x), type:%s (x%x), "
 			"frame Data:%08x %08x %08x %08x %08x %08x %08x\n",
+			(fc_hdr->fh_r_ctl == FC_RCTL_MDS_DIAGS) ? "MDS Diags" :
 			lpfc_rctl_names[fc_hdr->fh_r_ctl], fc_hdr->fh_r_ctl,
-			lpfc_type_names[fc_hdr->fh_type], fc_hdr->fh_type,
-			be32_to_cpu(header[0]), be32_to_cpu(header[1]),
-			be32_to_cpu(header[2]), be32_to_cpu(header[3]),
-			be32_to_cpu(header[4]), be32_to_cpu(header[5]),
-			be32_to_cpu(header[6]));
+			(fc_hdr->fh_type == FC_TYPE_VENDOR_UNIQUE) ?
+			"Vendor Unique" : lpfc_type_names[fc_hdr->fh_type],
+			fc_hdr->fh_type, be32_to_cpu(header[0]),
+			be32_to_cpu(header[1]), be32_to_cpu(header[2]),
+			be32_to_cpu(header[3]), be32_to_cpu(header[4]),
+			be32_to_cpu(header[5]), be32_to_cpu(header[6]));
 	return 0;
 drop:
 	lpfc_printf_log(phba, KERN_WARNING, LOG_ELS,
@@ -16926,6 +17018,96 @@ lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *vport,
 	lpfc_sli_release_iocbq(phba, iocbq);
 }
 
+static void
+lpfc_sli4_mds_loopback_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
+			    struct lpfc_iocbq *rspiocb)
+{
+	struct lpfc_dmabuf *pcmd = cmdiocb->context2;
+
+	if (pcmd && pcmd->virt)
+		pci_pool_free(phba->lpfc_drb_pool, pcmd->virt, pcmd->phys);
+	kfree(pcmd);
+	lpfc_sli_release_iocbq(phba, cmdiocb);
+}
+
+static void
+lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
+			      struct hbq_dmabuf *dmabuf)
+{
+	struct fc_frame_header *fc_hdr;
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_iocbq *iocbq = NULL;
+	union  lpfc_wqe *wqe;
+	struct lpfc_dmabuf *pcmd = NULL;
+	uint32_t frame_len;
+	int rc;
+
+	fc_hdr = (struct fc_frame_header *)dmabuf->hbuf.virt;
+	frame_len = bf_get(lpfc_rcqe_length, &dmabuf->cq_event.cqe.rcqe_cmpl);
+
+	/* Send the received frame back */
+	iocbq = lpfc_sli_get_iocbq(phba);
+	if (!iocbq)
+		goto exit;
+
+	/* Allocate buffer for command payload */
+	pcmd = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+	if (pcmd)
+		pcmd->virt = pci_pool_alloc(phba->lpfc_drb_pool, GFP_KERNEL,
+					    &pcmd->phys);
+	if (!pcmd || !pcmd->virt)
+		goto exit;
+
+	INIT_LIST_HEAD(&pcmd->list);
+
+	/* copyin the payload */
+	memcpy(pcmd->virt, dmabuf->dbuf.virt, frame_len);
+
+	/* fill in BDE's for command */
+	iocbq->iocb.un.xseq64.bdl.addrHigh = putPaddrHigh(pcmd->phys);
+	iocbq->iocb.un.xseq64.bdl.addrLow = putPaddrLow(pcmd->phys);
+	iocbq->iocb.un.xseq64.bdl.bdeFlags = BUFF_TYPE_BDE_64;
+	iocbq->iocb.un.xseq64.bdl.bdeSize = frame_len;
+
+	iocbq->context2 = pcmd;
+	iocbq->vport = vport;
+	iocbq->iocb_flag &= ~LPFC_FIP_ELS_ID_MASK;
+	iocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
+
+	/*
+	 * Setup rest of the iocb as though it were a WQE
+	 * Build the SEND_FRAME WQE
+	 */
+	wqe = (union lpfc_wqe *)&iocbq->iocb;
+
+	wqe->send_frame.frame_len = frame_len;
+	wqe->send_frame.fc_hdr_wd0 = be32_to_cpu(*((uint32_t *)fc_hdr));
+	wqe->send_frame.fc_hdr_wd1 = be32_to_cpu(*((uint32_t *)fc_hdr + 1));
+	wqe->send_frame.fc_hdr_wd2 = be32_to_cpu(*((uint32_t *)fc_hdr + 2));
+	wqe->send_frame.fc_hdr_wd3 = be32_to_cpu(*((uint32_t *)fc_hdr + 3));
+	wqe->send_frame.fc_hdr_wd4 = be32_to_cpu(*((uint32_t *)fc_hdr + 4));
+	wqe->send_frame.fc_hdr_wd5 = be32_to_cpu(*((uint32_t *)fc_hdr + 5));
+
+	iocbq->iocb.ulpCommand = CMD_SEND_FRAME;
+	iocbq->iocb.ulpLe = 1;
+	iocbq->iocb_cmpl = lpfc_sli4_mds_loopback_cmpl;
+	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, iocbq, 0);
+	if (rc == IOCB_ERROR)
+		goto exit;
+
+	lpfc_in_buf_free(phba, &dmabuf->dbuf);
+	return;
+
+exit:
+	lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+			"2023 Unable to process MDS loopback frame\n");
+	if (pcmd && pcmd->virt)
+		pci_pool_free(phba->lpfc_drb_pool, pcmd->virt, pcmd->phys);
+	kfree(pcmd);
+	lpfc_sli_release_iocbq(phba, iocbq);
+	lpfc_in_buf_free(phba, &dmabuf->dbuf);
+}
+
 /**
  * lpfc_sli4_handle_received_buffer - Handle received buffers from firmware
  * @phba: Pointer to HBA context object.
@@ -16964,6 +17146,13 @@ lpfc_sli4_handle_received_buffer(struct lpfc_hba *phba,
 		fcfi = bf_get(lpfc_rcqe_fcf_id,
 			      &dmabuf->cq_event.cqe.rcqe_cmpl);
 
+	if (fc_hdr->fh_r_ctl == 0xF4 && fc_hdr->fh_type == 0xFF) {
+		vport = phba->pport;
+		/* Handle MDS Loopback frames */
+		lpfc_sli4_handle_mds_loopback(vport, dmabuf);
+		return;
+	}
+
 	/* d_id this frame is directed to */
 	did = sli4_did_from_fc_hdr(fc_hdr);
 
@@ -17137,6 +17326,14 @@ lpfc_sli4_post_rpi_hdr(struct lpfc_hba *phba, struct lpfc_rpi_hdr *rpi_page)
 				"status x%x add_status x%x, mbx status x%x\n",
 				shdr_status, shdr_add_status, rc);
 		rc = -ENXIO;
+	} else {
+		/*
+		 * The next_rpi stores the next logical module-64 rpi value used
+		 * to post physical rpis in subsequent rpi postings.
+		 */
+		spin_lock_irq(&phba->hbalock);
+		phba->sli4_hba.next_rpi = rpi_page->next_rpi;
+		spin_unlock_irq(&phba->hbalock);
 	}
 	return rc;
 }
@@ -18717,7 +18914,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t ring_number,
 
 		spin_lock_irqsave(&pring->ring_lock, iflags);
 		ctxp = pwqe->context2;
-		sglq = ctxp->rqb_buffer->sglq;
+		sglq = ctxp->ctxbuf->sglq;
 		if (pwqe->sli4_xritag ==  NO_XRI) {
 			pwqe->sli4_lxritag = sglq->sli4_lxritag;
 			pwqe->sli4_xritag = sglq->sli4_xritag;