net/mlx5: fix trimming SW ring for vectorized Rx

Unlike mlx5_rx_burst(), mlx5_rx_burst_vec() doesn't replace completed
buffers one by one right after completion is processed but replenishes
multiple buffers later with rte_mempool_get_bulk(). Therefore, there could
be some buffer addresses left in the SW ring (rxq->elts[]) which have
already been delivered to application. As PMD doesn't own such buffers, it
must not be freed by PMD.  "Trimming" is needed before cleanup.

A problem can be seen when quitting testpmd when
CONFIG_RTE_LIBRTE_MBUF_DEBUG=y and CONFIG_RTE_LIBRTE_MEMPOOL_DEBUG=y

Trimming should be as simple as possible, it shouldn't touch any indexes
and buffer allocation isn't necessary.

Fixes: 6cb559d67b83 ("net/mlx5: add vectorized Rx/Tx burst for x86")

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>

diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index a82c415..74387a7 100644 (file)
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -642,11 +642,8 @@ priv_rehash_flows(struct priv *priv)
  *
  * @param rxq
  *   Pointer to RX queue structure.
- *
- * @return
- *   0 on success, errno value on failure.
  */
-static int
+static void
 rxq_trim_elts(struct rxq *rxq)
 {
        const uint16_t q_n = (1 << rxq->elts_n);
@@ -655,17 +652,11 @@ rxq_trim_elts(struct rxq *rxq)
        uint16_t i;
 
        if (!rxq->trim_elts)
-               return 0;
-       for (i = 0; i < used; ++i) {
-               struct rte_mbuf *buf;
-               buf = rte_pktmbuf_alloc(rxq->mp);
-               if (!buf)
-                       return ENOMEM;
-               (*rxq->elts)[(rxq->rq_ci + i) & q_mask] = buf;
-       }
-       rxq->rq_pi = rxq->rq_ci;
+               return;
+       for (i = 0; i < used; ++i)
+               (*rxq->elts)[(rxq->rq_ci + i) & q_mask] = NULL;
        rxq->trim_elts = 0;
-       return 0;
+       return;
 }
 
 /**
@@ -696,15 +687,13 @@ rxq_alloc_elts(struct rxq_ctrl *rxq_ctrl, unsigned int elts_n,
                volatile struct mlx5_wqe_data_seg *scat =
                        &(*rxq_ctrl->rxq.wqes)[i];
 
-               if (pool != NULL) {
-                       buf = (*pool)[i];
-                       assert(buf != NULL);
+               buf = (pool != NULL) ? (*pool)[i] : NULL;
+               if (buf != NULL) {
                        rte_pktmbuf_reset(buf);
                        rte_pktmbuf_refcnt_update(buf, 1);
                } else
                        buf = rte_pktmbuf_alloc(rxq_ctrl->rxq.mp);
                if (buf == NULL) {
-                       assert(pool == NULL);
                        ERROR("%p: empty mbuf pool", (void *)rxq_ctrl);
                        ret = ENOMEM;
                        goto error;
@@ -759,6 +748,7 @@ rxq_free_elts(struct rxq_ctrl *rxq_ctrl)
 {
        unsigned int i;
 
+       rxq_trim_elts(&rxq_ctrl->rxq);
        DEBUG("%p: freeing WRs", (void *)rxq_ctrl);
        if (rxq_ctrl->rxq.elts == NULL)
                return;
@@ -1078,9 +1068,8 @@ rxq_ctrl_setup(struct rte_eth_dev *dev, struct rxq_ctrl *rxq_ctrl,
        if (rxq_ctrl->rxq.elts_n) {
                assert(1 << rxq_ctrl->rxq.elts_n == desc);
                assert(rxq_ctrl->rxq.elts != tmpl.rxq.elts);
-               ret = rxq_trim_elts(&rxq_ctrl->rxq);
-               if (!ret)
-                       ret = rxq_alloc_elts(&tmpl, desc, rxq_ctrl->rxq.elts);
+               rxq_trim_elts(&rxq_ctrl->rxq);
+               ret = rxq_alloc_elts(&tmpl, desc, rxq_ctrl->rxq.elts);
        } else
                ret = rxq_alloc_elts(&tmpl, desc, NULL);
        if (ret) {