[dpdk-dev] [PATCH v2 10/13] net/dpaa: separate Rx function for LS1046

[Hemant Agrawal <hemant.agrawal@nxp.com>]

This is to avoid the checks in datapath and help in performance.
LS1046 has different data stash settings.

Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
 drivers/net/dpaa/dpaa_ethdev.c |  9 +++++--
 drivers/net/dpaa/dpaa_rxtx.c   | 60 +++++++++++++++++++++++++++++++++---------
 drivers/net/dpaa/dpaa_rxtx.h   |  3 +++
 3 files changed, 58 insertions(+), 14 deletions(-)

diff --git a/drivers/net/dpaa/dpaa_ethdev.c b/drivers/net/dpaa/dpaa_ethdev.c
index c2d6f44..c430cac 100644
--- a/drivers/net/dpaa/dpaa_ethdev.c
+++ b/drivers/net/dpaa/dpaa_ethdev.c
@@ -657,8 +657,13 @@ int dpaa_eth_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
 				"ret:%d(%s)", rxq->fqid, ret, strerror(ret));
 			return ret;
 		}
-		rxq->cb.dqrr_dpdk_pull_cb = dpaa_rx_cb;
-		rxq->cb.dqrr_prepare = dpaa_rx_cb_prepare;
+		if (dpaa_svr_family == SVR_LS1043A_FAMILY) {
+			rxq->cb.dqrr_dpdk_pull_cb = dpaa_rx_cb_no_prefetch;
+		} else {
+			rxq->cb.dqrr_dpdk_pull_cb = dpaa_rx_cb;
+			rxq->cb.dqrr_prepare = dpaa_rx_cb_prepare;
+		}
+
 		rxq->is_static = true;
 	}
 	dev->data->rx_queues[queue_idx] = rxq;
diff --git a/drivers/net/dpaa/dpaa_rxtx.c b/drivers/net/dpaa/dpaa_rxtx.c
index 6698c97..2c57741 100644
--- a/drivers/net/dpaa/dpaa_rxtx.c
+++ b/drivers/net/dpaa/dpaa_rxtx.c
@@ -398,8 +398,9 @@ dpaa_eth_fd_to_mbuf(const struct qm_fd *fd, uint32_t ifid)
 	return mbuf;
 }
 
+/* Specific for LS1043 */
 void
-dpaa_rx_cb(struct qman_fq **fq, struct qm_dqrr_entry **dqrr,
+dpaa_rx_cb_no_prefetch(struct qman_fq **fq, struct qm_dqrr_entry **dqrr,
 	   void **bufs, int num_bufs)
 {
 	struct rte_mbuf *mbuf;
@@ -411,17 +412,13 @@ dpaa_rx_cb(struct qman_fq **fq, struct qm_dqrr_entry **dqrr,
 	uint32_t length;
 	uint8_t format;
 
-	if (dpaa_svr_family != SVR_LS1046A_FAMILY) {
-		bp_info = DPAA_BPID_TO_POOL_INFO(dqrr[0]->fd.bpid);
-		ptr = rte_dpaa_mem_ptov(qm_fd_addr(&dqrr[0]->fd));
-		rte_prefetch0((void *)((uint8_t *)ptr + DEFAULT_RX_ICEOF));
-		bufs[0] = (struct rte_mbuf *)((char *)ptr -
-				bp_info->meta_data_size);
-	}
+	bp_info = DPAA_BPID_TO_POOL_INFO(dqrr[0]->fd.bpid);
+	ptr = rte_dpaa_mem_ptov(qm_fd_addr(&dqrr[0]->fd));
+	rte_prefetch0((void *)((uint8_t *)ptr + DEFAULT_RX_ICEOF));
+	bufs[0] = (struct rte_mbuf *)((char *)ptr - bp_info->meta_data_size);
 
 	for (i = 0; i < num_bufs; i++) {
-		if (dpaa_svr_family != SVR_LS1046A_FAMILY &&
-		    i < num_bufs - 1) {
+		if (i < num_bufs - 1) {
 			bp_info = DPAA_BPID_TO_POOL_INFO(dqrr[i + 1]->fd.bpid);
 			ptr = rte_dpaa_mem_ptov(qm_fd_addr(&dqrr[i + 1]->fd));
 			rte_prefetch0((void *)((uint8_t *)ptr +
@@ -458,6 +455,46 @@ dpaa_rx_cb(struct qman_fq **fq, struct qm_dqrr_entry **dqrr,
 	}
 }
 
+void
+dpaa_rx_cb(struct qman_fq **fq, struct qm_dqrr_entry **dqrr,
+	   void **bufs, int num_bufs)
+{
+	struct rte_mbuf *mbuf;
+	const struct qm_fd *fd;
+	struct dpaa_if *dpaa_intf;
+	uint16_t offset, i;
+	uint32_t length;
+	uint8_t format;
+
+	for (i = 0; i < num_bufs; i++) {
+		fd = &dqrr[i]->fd;
+		dpaa_intf = fq[0]->dpaa_intf;
+
+		format = (fd->opaque & DPAA_FD_FORMAT_MASK) >>
+				DPAA_FD_FORMAT_SHIFT;
+		if (unlikely(format == qm_fd_sg)) {
+			bufs[i] = dpaa_eth_sg_to_mbuf(fd, dpaa_intf->ifid);
+			continue;
+		}
+
+		offset = (fd->opaque & DPAA_FD_OFFSET_MASK) >>
+				DPAA_FD_OFFSET_SHIFT;
+		length = fd->opaque & DPAA_FD_LENGTH_MASK;
+
+		mbuf = bufs[i];
+		mbuf->data_off = offset;
+		mbuf->data_len = length;
+		mbuf->pkt_len = length;
+		mbuf->port = dpaa_intf->ifid;
+
+		mbuf->nb_segs = 1;
+		mbuf->ol_flags = 0;
+		mbuf->next = NULL;
+		rte_mbuf_refcnt_set(mbuf, 1);
+		dpaa_eth_packet_info(mbuf, mbuf->buf_addr);
+	}
+}
+
 void dpaa_rx_cb_prepare(struct qm_dqrr_entry *dq, void **bufs)
 {
 	struct dpaa_bp_info *bp_info = DPAA_BPID_TO_POOL_INFO(dq->fd.bpid);
@@ -468,8 +505,7 @@ void dpaa_rx_cb_prepare(struct qm_dqrr_entry *dq, void **bufs)
 	 * So we prefetch the annoation beforehand, so that it is available
 	 * in cache when accessed.
 	 */
-	if (dpaa_svr_family == SVR_LS1046A_FAMILY)
-		rte_prefetch0((void *)((uint8_t *)ptr + DEFAULT_RX_ICEOF));
+	rte_prefetch0((void *)((uint8_t *)ptr + DEFAULT_RX_ICEOF));
 
 	*bufs = (struct rte_mbuf *)((char *)ptr - bp_info->meta_data_size);
 }
diff --git a/drivers/net/dpaa/dpaa_rxtx.h b/drivers/net/dpaa/dpaa_rxtx.h
index 6de70a7..75b093c 100644
--- a/drivers/net/dpaa/dpaa_rxtx.h
+++ b/drivers/net/dpaa/dpaa_rxtx.h
@@ -270,4 +270,7 @@ void dpaa_rx_cb(struct qman_fq **fq,
 		struct qm_dqrr_entry **dqrr, void **bufs, int num_bufs);
 
 void dpaa_rx_cb_prepare(struct qm_dqrr_entry *dq, void **bufs);
+
+void dpaa_rx_cb_no_prefetch(struct qman_fq **fq,
+		    struct qm_dqrr_entry **dqrr, void **bufs, int num_bufs);
 #endif
-- 
2.7.4