Volatile point has been cast to non-volatile
point when call _mm_loadu_si128, so add compile
barrier to prevent compiler reorder.
Fixes: 9ed94e5bb04e ("i40e: add vector Rx")
Signed-off-by: Qi Zhang <qi.z.zhang at intel.com>
---
drivers/net/i40e/i40e_rxtx_vec.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/i40e/i40e_rxtx_vec.c b/drivers/net/i40e/i40e_rxtx_vec.c
index 0ee0241..ab63501 100644
--- a/drivers/net/i40e/i40e_rxtx_vec.c
+++ b/drivers/net/i40e/i40e_rxtx_vec.c
@@ -305,6 +305,7 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
/* Read desc statuses backwards to avoid race condition */
/* A.1 load 4 pkts desc */
descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+ rte_compiler_barrier();
/* B.2 copy 2 mbuf point into rx_pkts */
_mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);
@@ -313,8 +314,10 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]);
descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+ rte_compiler_barrier();
/* B.1 load 2 mbuf point */
descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+ rte_compiler_barrier();
descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
/* B.2 copy 2 mbuf point into rx_pkts */
--
2.7.4
