Am Dienstag, den 03.05.2016, 16:38 +0200 schrieb Uwe Kleine-König:
> In the receive path a queue's work bit was cleared unconditionally even
> if fec_enet_rx_queue only read out a part of the available packets from
> the hardware. This resulted in not reading any packets in the next napi
> turn and so packets were delayed or lost.
>
> The obvious fix is to only clear a queue's bit when the queue was
> emptied.
>
> Fixes: 4d494cdc92b3 ("net: fec: change data structure to support multiqueue")
> Signed-off-by: Uwe Kleine-König <[email protected]>
Reviewed-by: Lucas Stach <[email protected]>
> ---
> Hello,
>
> I created this patch against net/master. If you think it's to late to
> get it into 4.6 and it doesn't fit on net-next/master, just tell me and
> I will rebase.
>
> Best regards
> Uwe
>
>
> drivers/net/ethernet/freescale/fec_main.c | 10 ++++++++--
> 1 file changed, 8 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/freescale/fec_main.c
> b/drivers/net/ethernet/freescale/fec_main.c
> index 08243c2ff4b4..2a03857cca18 100644
> --- a/drivers/net/ethernet/freescale/fec_main.c
> +++ b/drivers/net/ethernet/freescale/fec_main.c
> @@ -1521,9 +1521,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
> struct fec_enet_private *fep = netdev_priv(ndev);
>
> for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
> - clear_bit(queue_id, &fep->work_rx);
> - pkt_received += fec_enet_rx_queue(ndev,
> + int ret;
> +
> + ret = fec_enet_rx_queue(ndev,
> budget - pkt_received, queue_id);
> +
> + if (ret < budget - pkt_received)
> + clear_bit(queue_id, &fep->work_rx);
> +
> + pkt_received += ret;
> }
> return pkt_received;
> }
