d/numam-dpdk
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

net/hns3: fix stats flip overflow

Browse Source 
Currently, statistics may overflow in some scenarios.

For example, if HW statistics are reset by stats reset operation,
but there are still a lot of residual packets exist in the HW
queues and these packets are error packets, flip may occurred
because the ipacket is obtained by subtracting the number of
software error packets from the number of HW received packets.

This patch verifies the calculation and returns 0 when overflow
may occur.

Fixes: 8839c5e202f3 ("net/hns3: support device stats")
Cc: stable@dpdk.org

Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
This commit is contained in:
Chengchang Tang 2021-02-03 20:23:52 +08:00 committed by Ferruh Yigit
parent e9550856f8
commit c27e64ee3e
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
drivers/net/hns3/hns3_stats.c
View File

@ -554,8 +554,14 @@ hns3_stats_get(struct rte_eth_dev *eth_dev, struct rte_eth_stats *rte_stats)
}
rte_stats->oerrors = 0;
rte_stats->ipackets = stats->rcb_rx_ring_pktnum_rcd -
rte_stats->ierrors;
/*
* If HW statistics are reset by stats_reset, but a lot of residual
* packets exist in the hardware queue and these packets are error
* packets, flip overflow may occurred. So return 0 in this case.
*/
rte_stats->ipackets =
stats->rcb_rx_ring_pktnum_rcd > rte_stats->ierrors ?
stats->rcb_rx_ring_pktnum_rcd - rte_stats->ierrors : 0;
rte_stats->opackets = stats->rcb_tx_ring_pktnum_rcd -
rte_stats->oerrors;
rte_stats->rx_nombuf = eth_dev->data->rx_mbuf_alloc_failed;
@ -792,8 +798,15 @@ hns3_rxq_basic_stats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats,
rxq_stats = &rxq->basic_stats;
rxq_stats->errors = rxq->err_stats.l2_errors +
rxq->err_stats.pkt_len_errors;
rxq_stats->packets = stats->rcb_rx_ring_pktnum[i] -
rxq_stats->errors;
/*
* If HW statistics are reset by stats_reset, but a lot of
* residual packets exist in the hardware queue and these
* packets are error packets, flip overflow may occurred.
* So return 0 in this case.
*/
rxq_stats->packets =
stats->rcb_rx_ring_pktnum[i] > rxq_stats->errors ?
stats->rcb_rx_ring_pktnum[i] - rxq_stats->errors : 0;
rxq_stats->bytes = 0;
for (j = 0; j < HNS3_NUM_RXQ_BASIC_STATS; j++) {
val = (char *)rxq_stats +