[dpdk-dev] [PATCH] fm10k: optimize legacy TX func

[Chen Jing D(Mark)]

From: "Chen Jing D(Mark)" <jing.d.chen at intel.com>

When legacy TX func tries to free a bunch of mbufs, it will free
them one by one. This change will scan the free list and merge the
requests in case they belongs to same pool, then free once, which
will reduce cycles on freeing mbufs.

Signed-off-by: Chen Jing D(Mark) <jing.d.chen at intel.com>
---
 doc/guides/rel_notes/release_2_3.rst |    2 +
 drivers/net/fm10k/fm10k_rxtx.c       |   59 ++++++++++++++++++++++++++++-----
 2 files changed, 52 insertions(+), 9 deletions(-)

diff --git a/doc/guides/rel_notes/release_2_3.rst b/doc/guides/rel_notes/release_2_3.rst
index 99de186..20ce78d 100644
--- a/doc/guides/rel_notes/release_2_3.rst
+++ b/doc/guides/rel_notes/release_2_3.rst
@@ -3,7 +3,9 @@ DPDK Release 2.3
 
 New Features
 ------------
+* **Optimize fm10k Tx func.**
 
+  * Free multiple mbufs at a time to reduce freeing mbuf cycles.
 
 Resolved Issues
 ---------------
diff --git a/drivers/net/fm10k/fm10k_rxtx.c b/drivers/net/fm10k/fm10k_rxtx.c
index e958865..f3de691 100644
--- a/drivers/net/fm10k/fm10k_rxtx.c
+++ b/drivers/net/fm10k/fm10k_rxtx.c
@@ -369,6 +369,51 @@ fm10k_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 	return nb_rcv;
 }
 
+/*
+ * Free multiple TX mbuf at a time if they are in the same pool
+ *
+ * @txep: software desc ring index that starts to free
+ * @num: number of descs to free
+ *
+ */
+static inline void tx_free_bulk_mbuf(struct rte_mbuf **txep, int num)
+{
+	struct rte_mbuf *m, *free[RTE_FM10K_TX_MAX_FREE_BUF_SZ];
+	int i;
+	int nb_free = 0;
+
+	if (unlikely(num == 0))
+		return;
+
+	m = __rte_pktmbuf_prefree_seg(txep[0]);
+	if (likely(m != NULL)) {
+		free[0] = m;
+		nb_free = 1;
+		for (i = 1; i < num; i++) {
+			m = __rte_pktmbuf_prefree_seg(txep[i]);
+			if (likely(m != NULL)) {
+				if (likely(m->pool == free[0]->pool))
+					free[nb_free++] = m;
+				else {
+					rte_mempool_put_bulk(free[0]->pool,
+							(void *)free, nb_free);
+					free[0] = m;
+					nb_free = 1;
+				}
+			}
+			txep[i] = NULL;
+		}
+		rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
+	} else {
+		for (i = 1; i < num; i++) {
+			m = __rte_pktmbuf_prefree_seg(txep[i]);
+			if (m != NULL)
+				rte_mempool_put(m->pool, m);
+			txep[i] = NULL;
+		}
+	}
+}
+
 static inline void tx_free_descriptors(struct fm10k_tx_queue *q)
 {
 	uint16_t next_rs, count = 0;
@@ -385,11 +430,7 @@ static inline void tx_free_descriptors(struct fm10k_tx_queue *q)
 	 * including nb_desc */
 	if (q->last_free > next_rs) {
 		count = q->nb_desc - q->last_free;
-		while (q->last_free < q->nb_desc) {
-			rte_pktmbuf_free_seg(q->sw_ring[q->last_free]);
-			q->sw_ring[q->last_free] = NULL;
-			++q->last_free;
-		}
+		tx_free_bulk_mbuf(&q->sw_ring[q->last_free], count);
 		q->last_free = 0;
 	}
 
@@ -397,10 +438,10 @@ static inline void tx_free_descriptors(struct fm10k_tx_queue *q)
 	q->nb_free += count + (next_rs + 1 - q->last_free);
 
 	/* free buffers from last_free, up to and including next_rs */
-	while (q->last_free <= next_rs) {
-		rte_pktmbuf_free_seg(q->sw_ring[q->last_free]);
-		q->sw_ring[q->last_free] = NULL;
-		++q->last_free;
+	if (q->last_free <= next_rs) {
+		count = next_rs - q->last_free + 1;
+		tx_free_bulk_mbuf(&q->sw_ring[q->last_free], count);
+		q->last_free += count;
 	}
 
 	if (q->last_free == q->nb_desc)
-- 
1.7.7.6