diff mbox

[dpdk-dev,v2] net/enic: decrement Tx mbuf reference count before recycling

Message ID 1468266301-2762-1-git-send-email-johndale@cisco.com (mailing list archive)
State Accepted, archived
Headers

Commit Message

John Daley (johndale) July 11, 2016, 7:45 p.m. UTC 
  In the burst Tx cleanup function, the reference count in mbufs
returned to the pool should to be decremented before they are
returned. Decrementing is not done by rte_mempool_put_bulk()
so it must be done separately using __rte_pktmbuf_prefree_seg().

Also when returning unsent buffers when the device is stopped
use rte_mbuf_free_seg() instead of rte_mempool_put() so that
reference counts are properly decremented.

Fixes: 36935afbc53c ("net/enic: refactor Tx mbuf recycling")

Reviewed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
---
v2: Use rte_pktmbuf_free_seg when returning mbufs when the device is
stoped. Suggested by Olivier Matz <olivier.matz@6wind.com>.

 drivers/net/enic/enic_main.c |  2 +-
 drivers/net/enic/enic_rxtx.c | 10 ++++++++--
 2 files changed, 9 insertions(+), 3 deletions(-)

Comments

Thomas Monjalon July 15, 2016, 9:27 p.m. UTC | #1 
2016-07-11 12:45, John Daley:
> In the burst Tx cleanup function, the reference count in mbufs
> returned to the pool should to be decremented before they are
> returned. Decrementing is not done by rte_mempool_put_bulk()
> so it must be done separately using __rte_pktmbuf_prefree_seg().
> 
> Also when returning unsent buffers when the device is stopped
> use rte_mbuf_free_seg() instead of rte_mempool_put() so that
> reference counts are properly decremented.
> 
> Fixes: 36935afbc53c ("net/enic: refactor Tx mbuf recycling")
> 
> Reviewed-by: Nelson Escobar <neescoba@cisco.com>
> Signed-off-by: John Daley <johndale@cisco.com>

Applied, thanks
diff mbox

Patch

diff --git a/drivers/net/enic/enic_main.c b/drivers/net/enic/enic_main.c
index d8669cc..54aaa25 100644
--- a/drivers/net/enic/enic_main.c
+++ b/drivers/net/enic/enic_main.c
@@ -106,7 +106,7 @@  static void enic_free_wq_buf(struct vnic_wq_buf *buf)
 {
 	struct rte_mbuf *mbuf = (struct rte_mbuf *)buf->mb;
 
-	rte_mempool_put(mbuf->pool, mbuf);
+	rte_pktmbuf_free_seg(mbuf);
 	buf->mb = NULL;
 }
 
diff --git a/drivers/net/enic/enic_rxtx.c b/drivers/net/enic/enic_rxtx.c
index 2f4a08c..845a8e6 100644
--- a/drivers/net/enic/enic_rxtx.c
+++ b/drivers/net/enic/enic_rxtx.c
@@ -398,7 +398,14 @@  static inline void enic_free_wq_bufs(struct vnic_wq *wq, u16 completed_index)
 	pool = ((struct rte_mbuf *)buf->mb)->pool;
 	for (i = 0; i < nb_to_free; i++) {
 		buf = &wq->bufs[tail_idx];
-		m = (struct rte_mbuf *)(buf->mb);
+		m = __rte_pktmbuf_prefree_seg((struct rte_mbuf *)(buf->mb));
+		buf->mb = NULL;
+
+		if (unlikely(m == NULL)) {
+			tail_idx = enic_ring_incr(desc_count, tail_idx);
+			continue;
+		}
+
 		if (likely(m->pool == pool)) {
 			RTE_ASSERT(nb_free < ENIC_MAX_WQ_DESCS);
 			free[nb_free++] = m;
@@ -409,7 +416,6 @@  static inline void enic_free_wq_bufs(struct vnic_wq *wq, u16 completed_index)
 			pool = m->pool;
 		}
 		tail_idx = enic_ring_incr(desc_count, tail_idx);
-		buf->mb = NULL;
 	}
 
 	rte_mempool_put_bulk(pool, (void **)free, nb_free);