scsi: lpfc: Streamline NVME Initiator WQE setup

To reduce latency when initializing WQE content, create templates for the
most common wqes. This reduces the number of operations taken to set the
content. It's not a lot of speed up, but every bit helps.

This patch updates the NVME initiator path.

[mkp: fixed typo]
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/lpfc/lpfc_crtn.h

@@ -565,6 +565,7 @@ void lpfc_nvme_mod_param_dep(struct lpfc_hba *phba);
 void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdiocb,
 				struct lpfc_wcqe_complete *abts_cmpl);
+void lpfc_nvme_cmd_template(void);
 extern int lpfc_enable_nvmet_cnt;
 extern unsigned long long lpfc_enable_nvmet[];
 extern int lpfc_no_hba_reset_cnt;

drivers/scsi/lpfc/lpfc_hw4.h

@@ -4183,6 +4183,7 @@ struct wqe_common {
 #define wqe_iod_SHIFT         13
 #define wqe_iod_MASK          0x00000001
 #define wqe_iod_WORD          word10
+#define LPFC_WQE_IOD_NONE	0
 #define LPFC_WQE_IOD_WRITE	0
 #define LPFC_WQE_IOD_READ	1
 #define wqe_dbde_SHIFT        14

drivers/scsi/lpfc/lpfc_init.c

@@ -12583,6 +12583,7 @@ lpfc_init(void)
 		fc_release_transport(lpfc_transport_template);
 		return -ENOMEM;
 	}
+	lpfc_nvme_cmd_template();
 
 	/* Initialize in case vector mapping is needed */
 	lpfc_used_cpu = NULL;