net/nfp: fix barrier location

The barrier needs to be after reading the DD bit. It has not been
a problem because the potential reads which can not happen before
reading the DD bit seem to be far enough, so the compiler is not
rescheduling them. However, a refactoring could make this problem
to arise.

Fixes: b812daadad0d ("nfp: add Rx and Tx")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>

diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/nfp_net.c
index 5180a31..fc501d6 100644 (file)
--- a/drivers/net/nfp/nfp_net.c
+++ b/drivers/net/nfp/nfp_net.c
@@ -2019,16 +2019,16 @@ nfp_net_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
                        break;
                }
 
+               rxds = &rxq->rxds[rxq->rd_p];
+               if ((rxds->rxd.meta_len_dd & PCIE_DESC_RX_DD) == 0)
+                       break;
+
                /*
                 * Memory barrier to ensure that we won't do other
                 * reads before the DD bit.
                 */
                rte_rmb();
 
-               rxds = &rxq->rxds[rxq->rd_p];
-               if ((rxds->rxd.meta_len_dd & PCIE_DESC_RX_DD) == 0)
-                       break;
-
                /*
                 * We got a packet. Let's alloc a new mbuff for refilling the
                 * free descriptor ring as soon as possible