[v3 10/10] bus/dpaa: optimize qman enqueue check

[vanshika.shukla@nxp.com]

From: Hemant Agrawal <hemant.agrawal@nxp.com>

This patch improves data access during qman enequeue ring check.

Signed-off-by: Jun Yang <jun.yang@nxp.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
 drivers/bus/dpaa/base/qbman/bman.c  | 19 ++++++-------
 drivers/bus/dpaa/base/qbman/qman.c  | 41 ++++++++++++++++-------------
 drivers/bus/dpaa/include/fsl_bman.h |  7 -----
 drivers/bus/dpaa/include/fsl_qman.h |  2 +-
 4 files changed, 33 insertions(+), 36 deletions(-)

diff --git a/drivers/bus/dpaa/base/qbman/bman.c b/drivers/bus/dpaa/base/qbman/bman.c
index 13f535a679..aa86fe7a20 100644
--- a/drivers/bus/dpaa/base/qbman/bman.c
+++ b/drivers/bus/dpaa/base/qbman/bman.c
@@ -275,7 +275,7 @@ bman_release_fast(struct bman_pool *pool, const uint64_t *bufs,
 	struct bm_rcr_entry *r;
 	uint8_t i, avail;
 	uint64_t bpid = pool->params.bpid;
-	struct bm_hw_buf_desc bm_bufs[FSL_BM_BURST_MAX];
+	struct bm_buffer bm_bufs[FSL_BM_BURST_MAX];
 
 #ifdef RTE_LIBRTE_DPAA_HWDEBUG
 	if (!num || (num > FSL_BM_BURST_MAX))
@@ -297,11 +297,11 @@ bman_release_fast(struct bman_pool *pool, const uint64_t *bufs,
 	 * with the valid-bit
 	 */
 	bm_bufs[0].bpid = bpid;
-	bm_bufs[0].hi_addr = cpu_to_be16(HI16_OF_U48(bufs[0]));
-	bm_bufs[0].lo_addr = cpu_to_be32(LO32_OF_U48(bufs[0]));
+	bm_bufs[0].hi = cpu_to_be16(HI16_OF_U48(bufs[0]));
+	bm_bufs[0].lo = cpu_to_be32(LO32_OF_U48(bufs[0]));
 	for (i = 1; i < num; i++) {
-		bm_bufs[i].hi_addr = cpu_to_be16(HI16_OF_U48(bufs[i]));
-		bm_bufs[i].lo_addr = cpu_to_be32(LO32_OF_U48(bufs[i]));
+		bm_bufs[i].hi = cpu_to_be16(HI16_OF_U48(bufs[i]));
+		bm_bufs[i].lo = cpu_to_be32(LO32_OF_U48(bufs[i]));
 	}
 
 	rte_memcpy(r->bufs, bm_bufs, sizeof(struct bm_buffer) * num);
@@ -363,12 +363,13 @@ bman_extract_addr(struct bm_buffer *buf)
 }
 
 static inline uint64_t
-bman_hw_extract_addr(struct bm_hw_buf_desc *buf)
+bman_hw_extract_addr(struct bm_buffer *buf)
 {
 	uint64_t hi, lo;
 
-	hi = be16_to_cpu(buf->hi_addr);
-	lo = be32_to_cpu(buf->lo_addr);
+	hi = be16_to_cpu(buf->hi);
+	lo = be32_to_cpu(buf->lo);
+
 	return U48_BY_HI16_LO32(hi, lo);
 }
 
@@ -380,7 +381,7 @@ bman_acquire_fast(struct bman_pool *pool, uint64_t *bufs, uint8_t num)
 	struct bm_mc_command *mcc;
 	struct bm_mc_result *mcr;
 	uint8_t i, rst;
-	struct bm_hw_buf_desc bm_bufs[FSL_BM_BURST_MAX];
+	struct bm_buffer bm_bufs[FSL_BM_BURST_MAX];
 
 #ifdef RTE_LIBRTE_DPAA_HWDEBUG
 	if (!num || (num > FSL_BM_BURST_MAX))
diff --git a/drivers/bus/dpaa/base/qbman/qman.c b/drivers/bus/dpaa/base/qbman/qman.c
index fbce0638b7..60087c55a1 100644
--- a/drivers/bus/dpaa/base/qbman/qman.c
+++ b/drivers/bus/dpaa/base/qbman/qman.c
@@ -1466,7 +1466,7 @@ int qman_create_fq(u32 fqid, u32 flags, struct qman_fq *fq)
 	}
 	spin_lock_init(&fq->fqlock);
 	fq->fqid = fqid;
-	fq->fqid_le = cpu_to_be32(fqid);
+	fq->fqid_be = cpu_to_be32(fqid);
 	fq->flags = flags;
 	fq->state = qman_fq_state_oos;
 	fq->cgr_groupid = 0;
@@ -2291,7 +2291,7 @@ int qman_enqueue_multi(struct qman_fq *fq,
 	struct qm_portal *portal = &p->p;
 
 	register struct qm_eqcr *eqcr = &portal->eqcr;
-	struct qm_eqcr_entry *eq = eqcr->cursor, *prev_eq;
+	struct qm_eqcr_entry *eq = eqcr->cursor;
 
 	u8 i = 0, diff, old_ci, sent = 0;
 
@@ -2307,7 +2307,7 @@ int qman_enqueue_multi(struct qman_fq *fq,
 
 	/* try to send as many frames as possible */
 	while (eqcr->available && frames_to_send--) {
-		eq->fqid = fq->fqid_le;
+		eq->fqid = fq->fqid_be;
 		eq->fd.opaque_addr = fd->opaque_addr;
 		eq->fd.addr = cpu_to_be40(fd->addr);
 		eq->fd.status = cpu_to_be32(fd->status);
@@ -2317,8 +2317,9 @@ int qman_enqueue_multi(struct qman_fq *fq,
 				((flags[i] >> 8) & QM_EQCR_DCA_IDXMASK);
 		}
 		i++;
-		eq = (void *)((unsigned long)(eq + 1) &
-			(~(unsigned long)(QM_EQCR_SIZE << 6)));
+		eq++;
+		if (unlikely(eq >= (eqcr->ring + QM_EQCR_SIZE)))
+			eq = eqcr->ring;
 		eqcr->available--;
 		sent++;
 		fd++;
@@ -2332,11 +2333,11 @@ int qman_enqueue_multi(struct qman_fq *fq,
 	for (i = 0; i < sent; i++) {
 		eq->__dont_write_directly__verb =
 			QM_EQCR_VERB_CMD_ENQUEUE | eqcr->vbit;
-		prev_eq = eq;
-		eq = (void *)((unsigned long)(eq + 1) &
-			(~(unsigned long)(QM_EQCR_SIZE << 6)));
-		if (unlikely((prev_eq + 1) != eq))
+		eq++;
+		if (unlikely(eq >= (eqcr->ring + QM_EQCR_SIZE))) {
 			eqcr->vbit ^= QM_EQCR_VERB_VBIT;
+			eq = eqcr->ring;
+		}
 	}
 
 	/* We need  to flush all the lines but without load/store operations
@@ -2361,7 +2362,7 @@ qman_enqueue_multi_fq(struct qman_fq *fq[], const struct qm_fd *fd,
 	struct qm_portal *portal = &p->p;
 
 	register struct qm_eqcr *eqcr = &portal->eqcr;
-	struct qm_eqcr_entry *eq = eqcr->cursor, *prev_eq;
+	struct qm_eqcr_entry *eq = eqcr->cursor;
 
 	u8 i = 0, diff, old_ci, sent = 0;
 
@@ -2377,7 +2378,7 @@ qman_enqueue_multi_fq(struct qman_fq *fq[], const struct qm_fd *fd,
 
 	/* try to send as many frames as possible */
 	while (eqcr->available && frames_to_send--) {
-		eq->fqid = fq[sent]->fqid_le;
+		eq->fqid = fq[sent]->fqid_be;
 		eq->fd.opaque_addr = fd->opaque_addr;
 		eq->fd.addr = cpu_to_be40(fd->addr);
 		eq->fd.status = cpu_to_be32(fd->status);
@@ -2388,8 +2389,9 @@ qman_enqueue_multi_fq(struct qman_fq *fq[], const struct qm_fd *fd,
 		}
 		i++;
 
-		eq = (void *)((unsigned long)(eq + 1) &
-			(~(unsigned long)(QM_EQCR_SIZE << 6)));
+		eq++;
+		if (unlikely(eq >= (eqcr->ring + QM_EQCR_SIZE)))
+			eq = eqcr->ring;
 		eqcr->available--;
 		sent++;
 		fd++;
@@ -2403,11 +2405,11 @@ qman_enqueue_multi_fq(struct qman_fq *fq[], const struct qm_fd *fd,
 	for (i = 0; i < sent; i++) {
 		eq->__dont_write_directly__verb =
 			QM_EQCR_VERB_CMD_ENQUEUE | eqcr->vbit;
-		prev_eq = eq;
-		eq = (void *)((unsigned long)(eq + 1) &
-			(~(unsigned long)(QM_EQCR_SIZE << 6)));
-		if (unlikely((prev_eq + 1) != eq))
+		eq++;
+		if (unlikely(eq >= (eqcr->ring + QM_EQCR_SIZE))) {
 			eqcr->vbit ^= QM_EQCR_VERB_VBIT;
+			eq = eqcr->ring;
+		}
 	}
 
 	/* We need  to flush all the lines but without load/store operations
@@ -2416,8 +2418,9 @@ qman_enqueue_multi_fq(struct qman_fq *fq[], const struct qm_fd *fd,
 	eq = eqcr->cursor;
 	for (i = 0; i < sent; i++) {
 		dcbf(eq);
-		eq = (void *)((unsigned long)(eq + 1) &
-			(~(unsigned long)(QM_EQCR_SIZE << 6)));
+		eq++;
+		if (unlikely(eq >= (eqcr->ring + QM_EQCR_SIZE)))
+			eq = eqcr->ring;
 	}
 	/* Update cursor for the next call */
 	eqcr->cursor = eq;
diff --git a/drivers/bus/dpaa/include/fsl_bman.h b/drivers/bus/dpaa/include/fsl_bman.h
index 0107ced8c5..c3c6f84472 100644
--- a/drivers/bus/dpaa/include/fsl_bman.h
+++ b/drivers/bus/dpaa/include/fsl_bman.h
@@ -70,13 +70,6 @@ struct __rte_aligned(8) bm_buffer {
 	};
 };
 
-struct __rte_packed_begin bm_hw_buf_desc {
-	uint8_t rsv;
-	uint8_t bpid;
-	rte_be16_t hi_addr; /* High 16-bits of 48-bit address */
-	rte_be32_t lo_addr; /* Low 32-bits of 48-bit address */
-} __rte_packed_end;
-
 static inline u64 bm_buffer_get64(const struct bm_buffer *buf)
 {
 	return buf->addr;
diff --git a/drivers/bus/dpaa/include/fsl_qman.h b/drivers/bus/dpaa/include/fsl_qman.h
index b949f2c893..71d5b16878 100644
--- a/drivers/bus/dpaa/include/fsl_qman.h
+++ b/drivers/bus/dpaa/include/fsl_qman.h
@@ -1225,7 +1225,7 @@ struct qman_fq {
 	/* Caller of qman_create_fq() provides these demux callbacks */
 	struct qman_fq_cb cb;
 
-	u32 fqid_le;
+	rte_be32_t fqid_be;
 	u32 fqid;
 
 	int q_fd;
-- 
2.25.1