Message ID | 1367118508-12340-1-git-send-email-Frank.Li@freescale.com |
---|---|
State | Changes Requested, archived |
Delegated to: | David Miller |
Headers | show |
Hi Frank, Am Sonntag, den 28.04.2013, 11:08 +0800 schrieb Frank Li: > reproduce steps > 1. flood ping from other machine > ping -f -s 41000 IP > 2. run below script > while [ 1 ]; do ethtool -s eth0 autoneg off; > sleep 3;ethtool -s eth0 autoneg on; sleep 4; done; > > You can see oops in one hour. > > The reason is fec_restart clear BD but NAPI may use it. > The solution is disable NAPI and stop xmit when reset BD. > disable NAPI may sleep, so fec_restart can't be call in > atomic context. > > Signed-off-by: Frank Li <Frank.Li@freescale.com> > --- > > Change from V1 to V2 > Add netif_tx_lock(ndev) to avoid xmit runing when reset hardware > > drivers/net/ethernet/freescale/fec.c | 41 +++++++++++++++++++++++++++++----- > drivers/net/ethernet/freescale/fec.h | 3 +- > 2 files changed, 37 insertions(+), 7 deletions(-) > > diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c > index 73195f6..d140b50 100644 > --- a/drivers/net/ethernet/freescale/fec.c > +++ b/drivers/net/ethernet/freescale/fec.c > @@ -403,6 +403,12 @@ fec_restart(struct net_device *ndev, int duplex) > const struct platform_device_id *id_entry = > platform_get_device_id(fep->pdev); > int i; > + if (netif_running(ndev)) { > + napi_disable(&fep->napi); > + netif_stop_queue(ndev); > + netif_tx_lock(ndev); > + } > + > u32 temp_mac[2]; > u32 rcntl = OPT_FRAME_SIZE | 0x04; > u32 ecntl = 0x2; /* ETHEREN */ > @@ -559,6 +565,12 @@ fec_restart(struct net_device *ndev, int duplex) > > /* Enable interrupts we wish to service */ > writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); > + > + if (netif_running(ndev)) { > + napi_enable(&fep->napi); > + netif_wake_queue(ndev); > + netif_tx_unlock(ndev); > + } > } > > static void > @@ -598,8 +610,20 @@ fec_timeout(struct net_device *ndev) > > ndev->stats.tx_errors++; > > - fec_restart(ndev, fep->full_duplex); > - netif_wake_queue(ndev); > + fep->timeout = 1; > + schedule_delayed_work(&fep->delay_work, msecs_to_jiffies(1)); > +} Why are you using delayed work here? I don't see a reason why we would like to defer execution here. Just use schedule_work(). > + > +static void fec_enet_work(struct work_struct *work) > +{ > + struct fec_enet_private *fep = > + container_of(work, struct fec_enet_private, delay_work.work); > + > + if (fep->timeout) { > + fep->timeout = 0; > + fec_restart(fep->netdev, fep->full_duplex); > + netif_wake_queue(fep->netdev); > + } > } > > static void > @@ -996,9 +1020,6 @@ static void fec_enet_adjust_link(struct net_device *ndev) > status_change = 1; > } > > - /* if any of the above changed restart the FEC */ > - if (status_change) > - fec_restart(ndev, phy_dev->duplex); > } else { > if (fep->link) { > fec_stop(ndev); > @@ -1010,8 +1031,14 @@ static void fec_enet_adjust_link(struct net_device *ndev) > spin_unlock: > spin_unlock_irqrestore(&fep->hw_lock, flags); > > - if (status_change) > + if (status_change) { > + /* if any of the above changed restart the FEC, > + * fec_restart may sleep. can't call it in spin_lock > + */ > + if (phy_dev->link) > + fec_restart(ndev, phy_dev->duplex); > phy_print_status(phy_dev); > + } > } Don't complicate things unnecessarily. Just put a patch in front of this one to remove the spinlock. As you removed it already from the RX and TX paths it doesn't protect anything anymore. > > static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) > @@ -1882,6 +1909,7 @@ fec_probe(struct platform_device *pdev) > if (ret) > goto failed_register; > > + INIT_DELAYED_WORK(&fep->delay_work, fec_enet_work); > return 0; > > failed_register: > @@ -1918,6 +1946,7 @@ fec_drv_remove(struct platform_device *pdev) > struct resource *r; > int i; > > + cancel_delayed_work_sync(&fep->delay_work); > unregister_netdev(ndev); > fec_enet_mii_remove(fep); > del_timer_sync(&fep->time_keep); > diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h > index eb43729..a367b21 100644 > --- a/drivers/net/ethernet/freescale/fec.h > +++ b/drivers/net/ethernet/freescale/fec.h > @@ -260,7 +260,8 @@ struct fec_enet_private { > int hwts_rx_en; > int hwts_tx_en; > struct timer_list time_keep; > - > + struct delayed_work delay_work; > + int timeout; > }; > > void fec_ptp_init(struct net_device *ndev, struct platform_device *pdev);
From: Frank Li <Frank.Li@freescale.com> Date: Sun, 28 Apr 2013 11:08:28 +0800 > @@ -403,6 +403,12 @@ fec_restart(struct net_device *ndev, int duplex) > const struct platform_device_id *id_entry = > platform_get_device_id(fep->pdev); > int i; > + if (netif_running(ndev)) { > + napi_disable(&fep->napi); > + netif_stop_queue(ndev); > + netif_tx_lock(ndev); > + } > + > u32 temp_mac[2]; > u32 rcntl = OPT_FRAME_SIZE | 0x04; > u32 ecntl = 0x2; /* ETHEREN */ Please don't put real statements in the middle of function variable declarations. Thanks. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
2013/4/29 Lucas Stach <l.stach@pengutronix.de>: > Hi Frank, > > Am Sonntag, den 28.04.2013, 11:08 +0800 schrieb Frank Li: >> reproduce steps >> 1. flood ping from other machine >> ping -f -s 41000 IP >> 2. run below script >> while [ 1 ]; do ethtool -s eth0 autoneg off; >> sleep 3;ethtool -s eth0 autoneg on; sleep 4; done; >> >> You can see oops in one hour. >> >> The reason is fec_restart clear BD but NAPI may use it. >> The solution is disable NAPI and stop xmit when reset BD. >> disable NAPI may sleep, so fec_restart can't be call in >> atomic context. >> >> Signed-off-by: Frank Li <Frank.Li@freescale.com> >> --- >> >> Change from V1 to V2 >> Add netif_tx_lock(ndev) to avoid xmit runing when reset hardware >> >> drivers/net/ethernet/freescale/fec.c | 41 +++++++++++++++++++++++++++++----- >> drivers/net/ethernet/freescale/fec.h | 3 +- >> 2 files changed, 37 insertions(+), 7 deletions(-) >> >> diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c >> index 73195f6..d140b50 100644 >> --- a/drivers/net/ethernet/freescale/fec.c >> +++ b/drivers/net/ethernet/freescale/fec.c >> @@ -403,6 +403,12 @@ fec_restart(struct net_device *ndev, int duplex) >> const struct platform_device_id *id_entry = >> platform_get_device_id(fep->pdev); >> int i; >> + if (netif_running(ndev)) { >> + napi_disable(&fep->napi); >> + netif_stop_queue(ndev); >> + netif_tx_lock(ndev); >> + } >> + >> u32 temp_mac[2]; >> u32 rcntl = OPT_FRAME_SIZE | 0x04; >> u32 ecntl = 0x2; /* ETHEREN */ >> @@ -559,6 +565,12 @@ fec_restart(struct net_device *ndev, int duplex) >> >> /* Enable interrupts we wish to service */ >> writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); >> + >> + if (netif_running(ndev)) { >> + napi_enable(&fep->napi); >> + netif_wake_queue(ndev); >> + netif_tx_unlock(ndev); >> + } >> } >> >> static void >> @@ -598,8 +610,20 @@ fec_timeout(struct net_device *ndev) >> >> ndev->stats.tx_errors++; >> >> - fec_restart(ndev, fep->full_duplex); >> - netif_wake_queue(ndev); >> + fep->timeout = 1; >> + schedule_delayed_work(&fep->delay_work, msecs_to_jiffies(1)); >> +} > > Why are you using delayed work here? I don't see a reason why we would > like to defer execution here. Just use schedule_work(). > There are a silicon bug, which need delay work to workaround it. So we can share a delay work in future. >> + >> +static void fec_enet_work(struct work_struct *work) >> +{ >> + struct fec_enet_private *fep = >> + container_of(work, struct fec_enet_private, delay_work.work); >> + >> + if (fep->timeout) { >> + fep->timeout = 0; >> + fec_restart(fep->netdev, fep->full_duplex); >> + netif_wake_queue(fep->netdev); >> + } >> } >> >> static void >> @@ -996,9 +1020,6 @@ static void fec_enet_adjust_link(struct net_device *ndev) >> status_change = 1; >> } >> >> - /* if any of the above changed restart the FEC */ >> - if (status_change) >> - fec_restart(ndev, phy_dev->duplex); >> } else { >> if (fep->link) { >> fec_stop(ndev); >> @@ -1010,8 +1031,14 @@ static void fec_enet_adjust_link(struct net_device *ndev) >> spin_unlock: >> spin_unlock_irqrestore(&fep->hw_lock, flags); >> >> - if (status_change) >> + if (status_change) { >> + /* if any of the above changed restart the FEC, >> + * fec_restart may sleep. can't call it in spin_lock >> + */ >> + if (phy_dev->link) >> + fec_restart(ndev, phy_dev->duplex); >> phy_print_status(phy_dev); >> + } >> } > > Don't complicate things unnecessarily. Just put a patch in front of this > one to remove the spinlock. As you removed it already from the RX and TX > paths it doesn't protect anything anymore. > >> >> static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) >> @@ -1882,6 +1909,7 @@ fec_probe(struct platform_device *pdev) >> if (ret) >> goto failed_register; >> >> + INIT_DELAYED_WORK(&fep->delay_work, fec_enet_work); >> return 0; >> >> failed_register: >> @@ -1918,6 +1946,7 @@ fec_drv_remove(struct platform_device *pdev) >> struct resource *r; >> int i; >> >> + cancel_delayed_work_sync(&fep->delay_work); >> unregister_netdev(ndev); >> fec_enet_mii_remove(fep); >> del_timer_sync(&fep->time_keep); >> diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h >> index eb43729..a367b21 100644 >> --- a/drivers/net/ethernet/freescale/fec.h >> +++ b/drivers/net/ethernet/freescale/fec.h >> @@ -260,7 +260,8 @@ struct fec_enet_private { >> int hwts_rx_en; >> int hwts_tx_en; >> struct timer_list time_keep; >> - >> + struct delayed_work delay_work; >> + int timeout; >> }; >> >> void fec_ptp_init(struct net_device *ndev, struct platform_device *pdev); > > -- > Pengutronix e.K. | Lucas Stach | > Industrial Linux Solutions | http://www.pengutronix.de/ | > Peiner Str. 6-8, 31137 Hildesheim, Germany | Phone: +49-5121-206917-5076 | > Amtsgericht Hildesheim, HRA 2686 | Fax: +49-5121-206917-5555 | > -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c index 73195f6..d140b50 100644 --- a/drivers/net/ethernet/freescale/fec.c +++ b/drivers/net/ethernet/freescale/fec.c @@ -403,6 +403,12 @@ fec_restart(struct net_device *ndev, int duplex) const struct platform_device_id *id_entry = platform_get_device_id(fep->pdev); int i; + if (netif_running(ndev)) { + napi_disable(&fep->napi); + netif_stop_queue(ndev); + netif_tx_lock(ndev); + } + u32 temp_mac[2]; u32 rcntl = OPT_FRAME_SIZE | 0x04; u32 ecntl = 0x2; /* ETHEREN */ @@ -559,6 +565,12 @@ fec_restart(struct net_device *ndev, int duplex) /* Enable interrupts we wish to service */ writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); + + if (netif_running(ndev)) { + napi_enable(&fep->napi); + netif_wake_queue(ndev); + netif_tx_unlock(ndev); + } } static void @@ -598,8 +610,20 @@ fec_timeout(struct net_device *ndev) ndev->stats.tx_errors++; - fec_restart(ndev, fep->full_duplex); - netif_wake_queue(ndev); + fep->timeout = 1; + schedule_delayed_work(&fep->delay_work, msecs_to_jiffies(1)); +} + +static void fec_enet_work(struct work_struct *work) +{ + struct fec_enet_private *fep = + container_of(work, struct fec_enet_private, delay_work.work); + + if (fep->timeout) { + fep->timeout = 0; + fec_restart(fep->netdev, fep->full_duplex); + netif_wake_queue(fep->netdev); + } } static void @@ -996,9 +1020,6 @@ static void fec_enet_adjust_link(struct net_device *ndev) status_change = 1; } - /* if any of the above changed restart the FEC */ - if (status_change) - fec_restart(ndev, phy_dev->duplex); } else { if (fep->link) { fec_stop(ndev); @@ -1010,8 +1031,14 @@ static void fec_enet_adjust_link(struct net_device *ndev) spin_unlock: spin_unlock_irqrestore(&fep->hw_lock, flags); - if (status_change) + if (status_change) { + /* if any of the above changed restart the FEC, + * fec_restart may sleep. can't call it in spin_lock + */ + if (phy_dev->link) + fec_restart(ndev, phy_dev->duplex); phy_print_status(phy_dev); + } } static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) @@ -1882,6 +1909,7 @@ fec_probe(struct platform_device *pdev) if (ret) goto failed_register; + INIT_DELAYED_WORK(&fep->delay_work, fec_enet_work); return 0; failed_register: @@ -1918,6 +1946,7 @@ fec_drv_remove(struct platform_device *pdev) struct resource *r; int i; + cancel_delayed_work_sync(&fep->delay_work); unregister_netdev(ndev); fec_enet_mii_remove(fep); del_timer_sync(&fep->time_keep); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index eb43729..a367b21 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -260,7 +260,8 @@ struct fec_enet_private { int hwts_rx_en; int hwts_tx_en; struct timer_list time_keep; - + struct delayed_work delay_work; + int timeout; }; void fec_ptp_init(struct net_device *ndev, struct platform_device *pdev);
reproduce steps 1. flood ping from other machine ping -f -s 41000 IP 2. run below script while [ 1 ]; do ethtool -s eth0 autoneg off; sleep 3;ethtool -s eth0 autoneg on; sleep 4; done; You can see oops in one hour. The reason is fec_restart clear BD but NAPI may use it. The solution is disable NAPI and stop xmit when reset BD. disable NAPI may sleep, so fec_restart can't be call in atomic context. Signed-off-by: Frank Li <Frank.Li@freescale.com> --- Change from V1 to V2 Add netif_tx_lock(ndev) to avoid xmit runing when reset hardware drivers/net/ethernet/freescale/fec.c | 41 +++++++++++++++++++++++++++++----- drivers/net/ethernet/freescale/fec.h | 3 +- 2 files changed, 37 insertions(+), 7 deletions(-)