[dpdk-dev] [PATCH v2 7/7] net/bnxt: fix buffer allocation reattempt logic

Ajit Khaparde ajit.khaparde at broadcom.com
Thu Feb 6 19:44:32 CET 2020


From: Santoshkumar Karanappa Rastapur <santosh.rastapur at broadcom.com>

In case of a buffer allocation failure, we reattempt buffer allocation
before the rx handler exits. We were not attempting this when producer
index is greater than the number of buffers to allocate. Fixed it with
correct checks.

Fixes: d9dd0b29ed31 ("net/bnxt: fix Rx handling and buffer allocation logic")
Cc: stable at dpdk.org

Signed-off-by: Santoshkumar Karanappa Rastapur <santosh.rastapur at broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur at broadcom.com>
---
 drivers/net/bnxt/bnxt_rxr.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_rxr.c b/drivers/net/bnxt/bnxt_rxr.c
index 1f47db97b..bef9720f5 100644
--- a/drivers/net/bnxt/bnxt_rxr.c
+++ b/drivers/net/bnxt/bnxt_rxr.c
@@ -678,10 +678,11 @@ uint16_t bnxt_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 
 	/* Attempt to alloc Rx buf in case of a previous allocation failure. */
 	if (rc == -ENOMEM) {
-		int i;
+		int i = RING_NEXT(rxr->rx_ring_struct, prod);
+		int cnt = nb_rx_pkts;
 
-		for (i = prod; i <= nb_rx_pkts;
-			i = RING_NEXT(rxr->rx_ring_struct, i)) {
+		for (; cnt;
+			i = RING_NEXT(rxr->rx_ring_struct, i), cnt--) {
 			struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i];
 
 			/* Buffer already allocated for this index. */
-- 
2.21.1 (Apple Git-122.3)



More information about the dev mailing list