scsi: lpfc: Improve PBDE checks during SGL processing

The PBDE feature, setting payload buffer address explicitly in the WQE so
it doesn't have to be fetched from the SGL, only makes sense when there is
a single buffer for the I/O. When there are multiple buffers it actually
hurts performance as the SGL subsequently has to be fetched.

Rework the SGL logic to only use PBDE when a single buffer.

Link: https://lore.kernel.org/r/20210910233159.115896-14-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 21 insertions, 23 deletions

diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 6e3dd0b9bcfa..731802527b81 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -2708,7 +2708,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 	struct ulp_bde64 *bde;
 	dma_addr_t physaddr;
 	int i, cnt, nsegs;
-	int do_pbde;
+	bool use_pbde = false;
 	int xc = 1;
 
 	if (!lpfc_is_link_up(phba)) {
@@ -2816,9 +2816,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		if (!xc)
 			bf_set(wqe_xc, &wqe->fcp_tsend.wqe_com, 0);
 
-		/* Word 11 - set sup, irsp, irsplen later */
-		do_pbde = 0;
-
 		/* Word 12 */
 		wqe->fcp_tsend.fcp_data_len = rsp->transfer_length;
 
@@ -2896,12 +2893,13 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		if (!xc)
 			bf_set(wqe_xc, &wqe->fcp_treceive.wqe_com, 0);
 
-		/* Word 11 - set pbde later */
-		if (phba->cfg_enable_pbde) {
-			do_pbde = 1;
+		/* Word 11 - check for pbde */
+		if (nsegs == 1 && phba->cfg_enable_pbde) {
+			use_pbde = true;
+			/* Word 11 - PBDE bit already preset by template */
 		} else {
+			/* Overwrite default template setting */
 			bf_set(wqe_pbde, &wqe->fcp_treceive.wqe_com, 0);
-			do_pbde = 0;
 		}
 
 		/* Word 12 */
@@ -2972,7 +2970,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			       ((rsp->rsplen >> 2) - 1));
 			memcpy(&wqe->words[16], rsp->rspaddr, rsp->rsplen);
 		}
-		do_pbde = 0;
 
 		/* Word 12 */
 		wqe->fcp_trsp.rsvd_12_15[0] = 0;
@@ -3007,23 +3004,24 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
 		sgl->sge_len = cpu_to_le32(cnt);
-		if (i == 0) {
-			bde = (struct ulp_bde64 *)&wqe->words[13];
-			if (do_pbde) {
-				/* Words 13-15  (PBDE) */
-				bde->addrLow = sgl->addr_lo;
-				bde->addrHigh = sgl->addr_hi;
-				bde->tus.f.bdeSize =
-					le32_to_cpu(sgl->sge_len);
-				bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
-				bde->tus.w = cpu_to_le32(bde->tus.w);
-			} else {
-				memset(bde, 0, sizeof(struct ulp_bde64));
-			}
-		}
 		sgl++;
 		ctxp->offset += cnt;
 	}
+
+	bde = (struct ulp_bde64 *)&wqe->words[13];
+	if (use_pbde) {
+		/* decrement sgl ptr backwards once to first data sge */
+		sgl--;
+
+		/* Words 13-15 (PBDE) */
+		bde->addrLow = sgl->addr_lo;
+		bde->addrHigh = sgl->addr_hi;
+		bde->tus.f.bdeSize = le32_to_cpu(sgl->sge_len);
+		bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+		bde->tus.w = cpu_to_le32(bde->tus.w);
+	} else {
+		memset(bde, 0, sizeof(struct ulp_bde64));
+	}
 	ctxp->state = LPFC_NVME_STE_DATA;
 	ctxp->entry_cnt++;
 	return nvmewqe;