Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752338AbZL3HYI (ORCPT ); Wed, 30 Dec 2009 02:24:08 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751586AbZL3HYH (ORCPT ); Wed, 30 Dec 2009 02:24:07 -0500 Received: from mta1.srv.hcvlny.cv.net ([167.206.4.196]:33932 "EHLO mta1.srv.hcvlny.cv.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751414AbZL3HYG (ORCPT ); Wed, 30 Dec 2009 02:24:06 -0500 Date: Wed, 30 Dec 2009 02:23:20 -0500 From: Michael Breuer Subject: Re: sky2 panic in 2.6.32.1 under load (new oops) In-reply-to: <20091229114938.1f4d1c5c@nehalam> To: Stephen Hemminger Cc: Andrew Morton , "Berck E. Nash" , "linux-kernel@vger.kernel.org" , netdev@vger.kernel.org Message-id: <4B3AFFE8.3060409@majjas.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT References: <4B300A2A.8040305@gmail.com> <4B300E30.9090707@majjas.com> <4B3114E3.1070602@majjas.com> <4B329FA3.9090904@majjas.com> <20091223230102.4bb0100e.akpm@linux-foundation.org> <4B34E847.8010809@majjas.com> <20091225152200.1cf11dfe@nehalam> <4B3581C7.8000702@majjas.com> <20091226095723.7ac82b18@nehalam> <4B367409.5060202@majjas.com> <4B379378.4000102@majjas.com> <20091227102238.0df149f9@nehalam> <4B37B7E2.5070307@majjas.com> <20091229093023.3ad24786@nehalam> <4B3A5048.9090700@majjas.com> <20091229114938.1f4d1c5c@nehalam> User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.5) Gecko/20091209 Fedora/3.0-4.fc12 Thunderbird/3.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3607 Lines: 114 Ok - I called dump_txring from sky2_net_intr: --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -2725,8 +2791,10 @@ static void sky2_watchdog(unsigned long arg) /* Hardware/software error handling */ static void sky2_err_intr(struct sky2_hw *hw, u32 status) { - if (net_ratelimit()) + if (net_ratelimit()) { dev_warn(&hw->pdev->dev, "error interrupt status=%#x\n", status); + dump_txring(hw, 0); + } if (status & Y2_IS_HW_ERR) sky2_hw_intr(hw); And got this: Dec 30 02:17:23 mail kernel: sky2 0000:06:00.0: error interrupt status=0x40000008 Dec 30 02:17:23 mail kernel: sky2 0000:06:00.0: error interrupt status=0x40000008 Dec 30 02:17:23 mail kernel: sky2 Tx ring pending=28...30 report=29 done=29 Dec 30 02:17:23 mail kernel: sky2 Tx ring pending=28...30 report=29 done=29 Dec 30 02:17:23 mail kernel: sky2 0000:06:00.0: error interrupt status=0x8 Dec 30 02:17:23 mail kernel: sky2 0000:06:00.0: error interrupt status=0x8 Dec 30 02:17:23 mail kernel: sky2 Tx ring pending=30...32 report=30 done=31 Dec 30 02:17:23 mail kernel: sky2 Tx ring pending=30...32 report=30 done=31 On 12/29/2009 02:49 PM, Stephen Hemminger wrote: > This patch will dump more info in case of hardware error. > > --- a/drivers/net/sky2.c 2009-12-29 11:30:06.441137685 -0800 > +++ b/drivers/net/sky2.c 2009-12-29 11:46:37.389262922 -0800 > @@ -2629,12 +2625,71 @@ static void sky2_hw_error(struct sky2_hw > } > } > > +static void dump_txring(struct sky2_hw *hw, unsigned port) > +{ > + struct sky2_port *sky2 = netdev_priv(hw->dev[port]); > + int sop = 1; > + unsigned idx; > + > + printk(KERN_INFO PFX "Tx ring pending=%u...%u report=%d done=%d\n", > + sky2->tx_cons, sky2->tx_prod, > + sky2_read16(hw, port == 0 ? STAT_TXA1_RIDX : STAT_TXA2_RIDX), > + sky2_read16(hw, Q_ADDR(txqaddr[port], Q_DONE))); > + > + /* Dump contents of tx ring */ > + for (idx = sky2->tx_next; > + idx != sky2->tx_prod&& idx< sky2->tx_ring_size; > + idx = RING_NEXT(idx, sky2->tx_ring_size)) { > + const struct sky2_tx_le *le = sky2->tx_le + idx; > + u32 a = le32_to_cpu(le->addr); > + > + if (sop) > + printk(KERN_DEBUG "%u:", idx); > + sop = 0; > + > + switch(le->opcode& ~HW_OWNER) { > + case OP_ADDR64: > + printk(" %#x:", a); > + break; > + case OP_LRGLEN: > + printk(" mtu=%d", a); > + break; > + case OP_VLAN: > + printk(" vlan=%d", be16_to_cpu(le->length)); > + break; > + case OP_TCPLISW: > + printk(" csum=%#x", a); > + break; > + case OP_LARGESEND: > + printk(" tso=%#x(%d)", a, le16_to_cpu(le->length)); > + break; > + case OP_PACKET: > + printk(" %#x(%d)", a, le16_to_cpu(le->length)); > + break; > + case OP_BUFFER: > + printk(" frag=%#x(%d)", a, le16_to_cpu(le->length)); > + break; > + default: > + printk(" op=%#x,%#x(%d)", le->opcode, a, > + le16_to_cpu(le->length)); > + } > + > + if (le->ctrl& EOP) { > + printk("\n"); > + sop = 1; > + } > + } > +} > + > static void sky2_hw_intr(struct sky2_hw *hw) > { > struct pci_dev *pdev = hw->pdev; > u32 status = sky2_read32(hw, B0_HWE_ISRC); > u32 hwmsk = sky2_read32(hw, B0_HWE_IMSK); > > + printk(KERN_DEBUG PFX "hardware interrupt status %#x\n", status); > + dump_txring(hw, 0); > + > status&= hwmsk; > > if (status& Y2_IS_TIST_OV) > > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/