From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH] r8169: Fix rtl8169_rx_interrupt() Date: Tue, 16 Mar 2010 19:48:04 +0100 Message-ID: <1268765284.2932.17.camel@edumazet-laptop> References: <20100307192305.GA598@elte.hu> <20100308125122.GA11242@redhat.com> <1268686865.2824.4.camel@edumazet-laptop> <1268699602.2824.14.camel@edumazet-laptop> <20100316145914.GB3332@swordfish.minsk.epam.com> <1268751933.3094.45.camel@edumazet-laptop> <20100316151023.GC3332@swordfish.minsk.epam.com> <1268752826.3094.48.camel@edumazet-laptop> <20100316182619.GA3451@swordfish> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Oleg Nesterov , David Miller , Ingo Molnar , Francois Romieu , Peter Zijlstra , netdev@vger.kernel.org, linux-kernel To: Sergey Senozhatsky Return-path: In-Reply-To: <20100316182619.GA3451@swordfish> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Le mardi 16 mars 2010 =C3=A0 20:26 +0200, Sergey Senozhatsky a =C3=A9cr= it : > Hello, > Got it right now. >=20 > System completely froze. Even SysRq didn't work. > /*spin_lock deadlock?*/ >=20 > NOTE: I'm losing network constantly with pktgen tests yes, every 12 seconds there is a reset because of fifo overflow > [24208.010980] r8169 0000:02:00.0: eth0: link up > [24220.010980] r8169 0000:02:00.0: eth0: link up > [24232.011030] r8169 0000:02:00.0: eth0: link up > [24340.010980] r8169 0000:02:00.0: eth0: link up > [24352.010966] r8169 0000:02:00.0: eth0: link up > [24364.010966] r8169 0000:02:00.0: eth0: link up > [24376.010964] r8169 0000:02:00.0: eth0: link up > [24388.010961] r8169 0000:02:00.0: eth0: link up > [24400.010959] r8169 0000:02:00.0: eth0: link up > [24412.010963] r8169 0000:02:00.0: eth0: link up >=20 >=20 > Traces: > [24600.625078] INFO: task events/0:9 blocked for more than 120 second= s. > [24600.625083] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" dis= ables this message. > [24600.625087] events/0 D 00001636 0 9 2 0x00000000 > [24600.625096] f7085ebc 00000046 a87e9490 00001636 c1617cc0 c1617cc0= c1617cc0 c1617cc0 > [24600.625109] f707c250 c1617cc0 c1617cc0 00000000 00000000 00000000= 00000000 f707bfc0 > [24600.625122] c14745c8 c14745c8 f707bfc0 00000202 f7085efc c12c6449= 00000000 00085edc > [24600.625135] Call Trace: > [24600.625148] [] __mutex_lock_common+0x233/0x3af > [24600.625155] [] mutex_lock_nested+0x12/0x15 > [24600.625163] [] ? rtnl_lock+0xf/0x11 > [24600.625168] [] rtnl_lock+0xf/0x11 > [24600.625183] [] rtl8169_reset_task+0x16/0xee [r8169] > [24600.625191] [] worker_thread+0x161/0x233 > [24600.625196] [] ? worker_thread+0x11f/0x233 > [24600.625205] [] ? rtl8169_reset_task+0x0/0xee [r8169] > [24600.625214] [] ? autoremove_wake_function+0x0/0x2f > [24600.625220] [] ? worker_thread+0x0/0x233 > [24600.625225] [] kthread+0x6a/0x6f > [24600.625232] [] ? kthread+0x0/0x6f > [24600.625238] [] kernel_thread_helper+0x6/0x1a > [24600.625242] INFO: lockdep is turned off. > [24600.625259] INFO: task X:3176 blocked for more than 120 seconds. > [24600.625262] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" dis= ables this message. > [24600.625266] X D 00000000 0 3176 3175 0x00400004 > [24600.625273] f6435a10 00003046 00025709 00000000 c1617cc0 c1617cc0= c1617cc0 c1617cc0 > [24600.625286] f60897d0 c1617c ...=20 > /*THE REST IS LOST*/ >=20 >=20 OK thanks for the report, this rtl8169_reset_task() seems pretty buggy, or multiple invocation... Did you tried removing the rtl8169_schedule_work() call from rtl8169_rx_interrupt() ? Maybe the reset is not necessary at all in case of fifo overflow.. Cumulative patch : diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 9d3ebf3..d6ef4dd 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -1038,14 +1038,14 @@ static void rtl8169_vlan_rx_register(struct net= _device *dev, } =20 static int rtl8169_rx_vlan_skb(struct rtl8169_private *tp, struct RxDe= sc *desc, - struct sk_buff *skb) + struct sk_buff *skb, int polling) { u32 opts2 =3D le32_to_cpu(desc->opts2); struct vlan_group *vlgrp =3D tp->vlgrp; int ret; =20 if (vlgrp && (opts2 & RxVlanTag)) { - vlan_hwaccel_receive_skb(skb, vlgrp, swab16(opts2 & 0xffff)); + __vlan_hwaccel_rx(skb, vlgrp, swab16(opts2 & 0xffff), polling); ret =3D 0; } else ret =3D -1; @@ -1062,7 +1062,7 @@ static inline u32 rtl8169_tx_vlan_tag(struct rtl8= 169_private *tp, } =20 static int rtl8169_rx_vlan_skb(struct rtl8169_private *tp, struct RxDe= sc *desc, - struct sk_buff *skb) + struct sk_buff *skb, int polling) { return -1; } @@ -4429,12 +4429,20 @@ out: return done; } =20 +/* + * Warning : rtl8169_rx_interrupt() might be called : + * 1) from NAPI (softirq) context + * (polling =3D 1 : we should call netif_receive_skb()) + * 2) from process context (rtl8169_reset_task()) + * (polling =3D 0 : we must call netif_rx() instead) + */ =09 static int rtl8169_rx_interrupt(struct net_device *dev, struct rtl8169_private *tp, void __iomem *ioaddr, u32 budget) { unsigned int cur_rx, rx_left; unsigned int delta, count; + int polling =3D (budget !=3D ~(u32)0) ? 1 : 0; =20 cur_rx =3D tp->cur_rx; rx_left =3D NUM_RX_DESC + tp->dirty_rx - cur_rx; @@ -4459,7 +4467,6 @@ static int rtl8169_rx_interrupt(struct net_device= *dev, if (status & RxCRC) dev->stats.rx_crc_errors++; if (status & RxFOVF) { - rtl8169_schedule_work(dev, rtl8169_reset_task); dev->stats.rx_fifo_errors++; } rtl8169_mark_to_asic(desc, tp->rx_buf_sz); @@ -4496,8 +4503,12 @@ static int rtl8169_rx_interrupt(struct net_devic= e *dev, skb_put(skb, pkt_size); skb->protocol =3D eth_type_trans(skb, dev); =20 - if (rtl8169_rx_vlan_skb(tp, desc, skb) < 0) - netif_receive_skb(skb); + if (rtl8169_rx_vlan_skb(tp, desc, skb, polling) < 0) { + if (likely(polling)) + netif_receive_skb(skb); + else + netif_rx(skb); + } =20 dev->stats.rx_bytes +=3D pkt_size; dev->stats.rx_packets++;