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>

3 files changed, 40 insertions, 42 deletions

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 33266e1b24ab..69d3758dd8dc 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1299,7 +1299,6 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 	struct sli4_sge *first_data_sgl;
 	struct ulp_bde64 *bde;
 	dma_addr_t physaddr = 0;
-	uint32_t num_bde = 0;
 	uint32_t dma_len = 0;
 	uint32_t dma_offset = 0;
 	int nseg, i, j;
@@ -1353,7 +1352,7 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 			}
 
 			sgl->word2 = 0;
-			if ((num_bde + 1) == nseg) {
+			if (nseg == 1) {
 				bf_set(lpfc_sli4_sge_last, sgl, 1);
 				bf_set(lpfc_sli4_sge_type, sgl,
 				       LPFC_SGE_TYPE_DATA);
@@ -1422,8 +1421,9 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 
 			j++;
 		}
-		if (phba->cfg_enable_pbde) {
-			/* Use PBDE support for first SGL only, offset == 0 */
+
+		/* PBDE support for first data SGE only */
+		if (nseg == 1 && phba->cfg_enable_pbde) {
 			/* Words 13-15 */
 			bde = (struct ulp_bde64 *)
 				&wqe->words[13];
@@ -1434,11 +1434,11 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 			bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
 			bde->tus.w = cpu_to_le32(bde->tus.w);
 
-			/* Word 11 */
+			/* Word 11 - set PBDE bit */
 			bf_set(wqe_pbde, &wqe->generic.wqe_com, 1);
 		} else {
 			memset(&wqe->words[13], 0, (sizeof(uint32_t) * 3));
-			bf_set(wqe_pbde, &wqe->generic.wqe_com, 0);
+			/* Word 11 - PBDE bit disabled by default template */
 		}
 
 	} else {
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;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index a2cd22728b0f..078fbea3f436 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3235,7 +3235,6 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 	struct lpfc_vport *vport = phba->pport;
 	union lpfc_wqe128 *wqe = &pwqeq->wqe;
 	dma_addr_t physaddr;
-	uint32_t num_bde = 0;
 	uint32_t dma_len;
 	uint32_t dma_offset = 0;
 	int nseg, i, j;
@@ -3297,7 +3296,7 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 		j = 2;
 		for (i = 0; i < nseg; i++) {
 			sgl->word2 = 0;
-			if ((num_bde + 1) == nseg) {
+			if (nseg == 1) {
 				bf_set(lpfc_sli4_sge_last, sgl, 1);
 				bf_set(lpfc_sli4_sge_type, sgl,
 				       LPFC_SGE_TYPE_DATA);
@@ -3366,13 +3365,15 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 
 			j++;
 		}
-		/*
-		 * Setup the first Payload BDE. For FCoE we just key off
-		 * Performance Hints, for FC we use lpfc_enable_pbde.
-		 * We populate words 13-15 of IOCB/WQE.
+
+		/* PBDE support for first data SGE only.
+		 * For FCoE, we key off Performance Hints.
+		 * For FC, we key off lpfc_enable_pbde.
 		 */
-		if ((phba->sli3_options & LPFC_SLI4_PERFH_ENABLED) ||
-		    phba->cfg_enable_pbde) {
+		if (nseg == 1 &&
+		    ((phba->sli3_options & LPFC_SLI4_PERFH_ENABLED) ||
+		     phba->cfg_enable_pbde)) {
+			/* Words 13-15 */
 			bde = (struct ulp_bde64 *)
 				&wqe->words[13];
 			bde->addrLow = first_data_sgl->addr_lo;
@@ -3382,12 +3383,15 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 			bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
 			bde->tus.w = cpu_to_le32(bde->tus.w);
 
+			/* Word 11 - set PBDE bit */
+			bf_set(wqe_pbde, &wqe->generic.wqe_com, 1);
 		} else {
 			memset(&wqe->words[13], 0, (sizeof(uint32_t) * 3));
+			/* Word 11 - PBDE bit disabled by default template */
 		}
 	} else {
 		sgl += 1;
-		/* clear the last flag in the fcp_rsp map entry */
+		/* set the last flag in the fcp_rsp map entry */
 		sgl->word2 = le32_to_cpu(sgl->word2);
 		bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
@@ -3400,10 +3404,6 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 		}
 	}
 
-	/* Word 11 */
-	if (phba->cfg_enable_pbde)
-		bf_set(wqe_pbde, &wqe->generic.wqe_com, 1);
-
 	/*
 	 * Finish initializing those IOCB fields that are dependent on the
 	 * scsi_cmnd request_buffer.  Note that for SLI-2 the bdeSize is