As diagnosed by Song Liu, ndo_poll_controller() can be very dangerous on loaded hosts, since the cpu calling ndo_poll_controller() might steal all NAPI contexts (for all RX/TX queues of the NIC). This capture can last for unlimited amount of time, since one cpu is generally not able to drain all the queues under load.
hinic uses NAPI for TX completions, so we better let core networking stack call the napi->poll() to avoid the capture. Note that hinic_netpoll() was incorrectly scheduling NAPI on both RX and TX queues. Signed-off-by: Eric Dumazet <eduma...@google.com> Cc: Aviad Krawczyk <aviad.krawc...@huawei.com> --- .../net/ethernet/huawei/hinic/hinic_main.c | 20 ------------------- 1 file changed, 20 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 09e9da10b786549b6232d8069c4e45857b95fd8c..4a8f82938ed5b87c8da6b09e88e08d387c652f0c 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -789,23 +789,6 @@ static void hinic_get_stats64(struct net_device *netdev, stats->tx_errors = nic_tx_stats->tx_dropped; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void hinic_netpoll(struct net_device *netdev) -{ - struct hinic_dev *nic_dev = netdev_priv(netdev); - int i, num_qps; - - num_qps = hinic_hwdev_num_qps(nic_dev->hwdev); - for (i = 0; i < num_qps; i++) { - struct hinic_txq *txq = &nic_dev->txqs[i]; - struct hinic_rxq *rxq = &nic_dev->rxqs[i]; - - napi_schedule(&txq->napi); - napi_schedule(&rxq->napi); - } -} -#endif - static const struct net_device_ops hinic_netdev_ops = { .ndo_open = hinic_open, .ndo_stop = hinic_close, @@ -818,9 +801,6 @@ static const struct net_device_ops hinic_netdev_ops = { .ndo_start_xmit = hinic_xmit_frame, .ndo_tx_timeout = hinic_tx_timeout, .ndo_get_stats64 = hinic_get_stats64, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = hinic_netpoll, -#endif }; static void netdev_features_init(struct net_device *netdev) -- 2.19.0.605.g01d371f741-goog