| Message ID | 1462286333-23402-1-git-send-email-u.kleine-koenig@pengutronix.de |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
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 <u.kleine-koenig@pengutronix.de> Reviewed-by: Lucas Stach <l.stach@pengutronix.de> > --- > 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; > }
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Sent: Tuesday, May 03, 2016 10:39 PM > To: Fugang Duan <fugang.duan@nxp.com>; David S . Miller > <davem@davemloft.net> > Cc: kernel@pengutronix.de; netdev@vger.kernel.org > Subject: [PATCH] net: fec: only clear a queue's work bit if the queue was > emptied > > 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 <u.kleine-koenig@pengutronix.de> > --- > 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; > } > -- > 2.8.0.rc3 Tested-by: Fugang Duan <fugang.duan@nxp.com> Acked-by: Fugang Duan <fugang.duan@nxp.com>
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Date: Tue, 3 May 2016 16:38:53 +0200 > 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 <u.kleine-koenig@pengutronix.de> Applied and queued up for -stable, thanks.
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; }
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 <u.kleine-koenig@pengutronix.de> --- 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(-)