Bug 30892

Summary:	atl1c driver timeouts!
Product:	Networking	Reporter:	Darksurf (piroisl33t)
Component:	IPV4	Assignee:	Stephen Hemminger (stephen)
Status:	RESOLVED CODE_FIX
Severity:	high	CC:	alan, andreas.tunek, mcgrof, nic-devel
Priority:	P1
Hardware:	All
OS:	Linux
Kernel Version:	3.0	Subsystem:
Regression:	No	Bisected commit-id:

Description Darksurf 2011-03-10 18:27:47 UTC

I've got a fresh sabayon linux install, no policy routing or firewall (on my machine) and half of the networks I try to use, I cannot! I'm using kernel 2.6.37.2 on a toshiba L645D-4033, kernel is tainted due to use of FGLRX nothing else.

[  350.220773] atl1c 0000:08:00.0: atl1c: eth0 NIC Link is Up<100 Mbps Full Duplex>
[  355.712251] ------------[ cut here ]------------
[  355.712271] WARNING: at net/sched/sch_generic.c:258 dev_watchdog+0x142/0x1dc()
[  355.712278] Hardware name: Satellite L645D
[  355.712284] NETDEV WATCHDOG: eth0 (atl1c): transmit queue 0 timed out
[  355.712289] Modules linked in: rtl8192ce rtl8192c_common rtlwifi mac80211 compat cfg80211 snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss ipv6 snd_hda_codec_conexant snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer fglrx(P) uvcvideo videodev v4l1_compat v4l2_compat_ioctl32 snd i2c_piix4 snd_page_alloc i2c_core tpm_tis edac_core tpm atl1c k10temp tpm_bios shpchp pci_hotplug joydev pcspkr sparse_keymap serio_raw video output xts gf128mul iscsi_tcp tg3 e1000 scsi_wait_scan sl811_hcd ohci_hcd uhci_hcd ehci_hcd sx8 imm parport pata_pcmcia pcmcia
[  355.712377] Pid: 0, comm: kworker/0:0 Tainted: P            2.6.37-sabayon #1
[  355.712384] Call Trace:
[  355.712389]  <IRQ>  [<ffffffff8103da7e>] warn_slowpath_common+0x80/0x98
[  355.712410]  [<ffffffff8103db2a>] warn_slowpath_fmt+0x41/0x43
[  355.712420]  [<ffffffff817aa8c6>] dev_watchdog+0x142/0x1dc
[  355.712431]  [<ffffffff81047d00>] run_timer_softirq+0x16b/0x1f8
[  355.712440]  [<ffffffff817aa784>] ? dev_watchdog+0x0/0x1dc
[  355.712449]  [<ffffffff81042d3c>] __do_softirq+0x8f/0x120
[  355.712458]  [<ffffffff81002e6c>] call_softirq+0x1c/0x28
[  355.712466]  [<ffffffff810049ff>] do_softirq+0x33/0x68
[  355.712473]  [<ffffffff81042bd3>] irq_exit+0x36/0x78
[  355.712481]  [<ffffffff810040e5>] do_IRQ+0xa3/0xba
[  355.712489]  [<ffffffff81873253>] ret_from_intr+0x0/0xa
[  355.712494]  <EOI>  [<ffffffff810095a8>] ? default_idle+0x24/0x39
[  355.712507]  [<ffffffff81009708>] c1e_idle+0xcd/0xea
[  355.712515]  [<ffffffff810012d8>] cpu_idle+0x5a/0x91
[  355.712524]  [<ffffffff8186b0e4>] start_secondary+0x1a6/0x1aa
[  355.712531] ---[ end trace 9c9405f36c466cda ]---
[  355.733614] atl1c 0000:08:00.0: irq 43 for MSI/MSI-X
[  355.733835] atl1c 0000:08:00.0: atl1c: eth0 NIC Link is Up<100 Mbps Full Duplex>

I can jack into a network, sometimes nothing happens. I need to ifconfig eth0 down then ifconfig eth0 up and it picks up. After I get a connection I get a solid connection for approximately 60 seconds then It shows I'm connected with IP address but I cannot access anything!  This ethernet jack is next to useless at work or at college. It works fine on my small home network.

I believe that this may be related to another bug (BUG 14958), but I have no proof, just similar results and issues.

Comment 1 Andrew Morton 2011-03-12 00:16:08 UTC

(switched to email.  Please respond via emailed reply-to-all, not via the
bugzilla web interface).

atl1c issue in 2.6.37.2.  It might be a regression - that's unclear?

On Thu, 10 Mar 2011 18:27:48 GMT
bugzilla-daemon@bugzilla.kernel.org wrote:

> https://bugzilla.kernel.org/show_bug.cgi?id=30892
> 
>            Summary: atl1c driver timeouts!
>            Product: Networking
>            Version: 2.5
>           Platform: All
>         OS/Version: Linux
>               Tree: Mainline
>             Status: NEW
>           Severity: high
>           Priority: P1
>          Component: IPV4
>         AssignedTo: shemminger@linux-foundation.org
>         ReportedBy: piroisl33t@gmail.com
>         Regression: No
> 
> 
> I've got a fresh sabayon linux install, no policy routing or firewall (on my
> machine) and half of the networks I try to use, I cannot! I'm using kernel
> 2.6.37.2 on a toshiba L645D-4033, kernel is tainted due to use of FGLRX
> nothing
> else.
> 
> [  350.220773] atl1c 0000:08:00.0: atl1c: eth0 NIC Link is Up<100 Mbps Full
> Duplex>
> [  355.712251] ------------[ cut here ]------------
> [  355.712271] WARNING: at net/sched/sch_generic.c:258
> dev_watchdog+0x142/0x1dc()
> [  355.712278] Hardware name: Satellite L645D
> [  355.712284] NETDEV WATCHDOG: eth0 (atl1c): transmit queue 0 timed out
> [  355.712289] Modules linked in: rtl8192ce rtl8192c_common rtlwifi mac80211
> compat cfg80211 snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq
> snd_seq_device snd_pcm_oss snd_mixer_oss ipv6 snd_hda_codec_conexant
> snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer fglrx(P) uvcvideo
> videodev v4l1_compat v4l2_compat_ioctl32 snd i2c_piix4 snd_page_alloc
> i2c_core
> tpm_tis edac_core tpm atl1c k10temp tpm_bios shpchp pci_hotplug joydev pcspkr
> sparse_keymap serio_raw video output xts gf128mul iscsi_tcp tg3 e1000
> scsi_wait_scan sl811_hcd ohci_hcd uhci_hcd ehci_hcd sx8 imm parport
> pata_pcmcia
> pcmcia
> [  355.712377] Pid: 0, comm: kworker/0:0 Tainted: P            2.6.37-sabayon
> #1
> [  355.712384] Call Trace:
> [  355.712389]  <IRQ>  [<ffffffff8103da7e>] warn_slowpath_common+0x80/0x98
> [  355.712410]  [<ffffffff8103db2a>] warn_slowpath_fmt+0x41/0x43
> [  355.712420]  [<ffffffff817aa8c6>] dev_watchdog+0x142/0x1dc
> [  355.712431]  [<ffffffff81047d00>] run_timer_softirq+0x16b/0x1f8
> [  355.712440]  [<ffffffff817aa784>] ? dev_watchdog+0x0/0x1dc
> [  355.712449]  [<ffffffff81042d3c>] __do_softirq+0x8f/0x120
> [  355.712458]  [<ffffffff81002e6c>] call_softirq+0x1c/0x28
> [  355.712466]  [<ffffffff810049ff>] do_softirq+0x33/0x68
> [  355.712473]  [<ffffffff81042bd3>] irq_exit+0x36/0x78
> [  355.712481]  [<ffffffff810040e5>] do_IRQ+0xa3/0xba
> [  355.712489]  [<ffffffff81873253>] ret_from_intr+0x0/0xa
> [  355.712494]  <EOI>  [<ffffffff810095a8>] ? default_idle+0x24/0x39
> [  355.712507]  [<ffffffff81009708>] c1e_idle+0xcd/0xea
> [  355.712515]  [<ffffffff810012d8>] cpu_idle+0x5a/0x91
> [  355.712524]  [<ffffffff8186b0e4>] start_secondary+0x1a6/0x1aa
> [  355.712531] ---[ end trace 9c9405f36c466cda ]---
> [  355.733614] atl1c 0000:08:00.0: irq 43 for MSI/MSI-X
> [  355.733835] atl1c 0000:08:00.0: atl1c: eth0 NIC Link is Up<100 Mbps Full
> Duplex>
> 
> I can jack into a network, sometimes nothing happens. I need to ifconfig eth0
> down then ifconfig eth0 up and it picks up. After I get a connection I get a
> solid connection for approximately 60 seconds then It shows I'm connected
> with
> IP address but I cannot access anything!  This ethernet jack is next to
> useless
> at work or at college. It works fine on my small home network.
> 
> I believe that this may be related to another bug (BUG 14958), but I have no
> proof, just similar results and issues.
>

Comment 2 Andreas Tunek 2011-07-12 21:12:35 UTC

There are some more info in the Fedora bugzilla (https://bugzilla.redhat.com/show_bug.cgi?id=711489). Should I post that here?

Comment 3 Andreas Tunek 2011-08-05 17:38:41 UTC

Crash still happens in latest Fedora (3.0 based) Linux.

Comment 4 qnic 2012-08-21 00:47:55 UTC

hi Andreas Tunek, would you describe your system (kernel version) in detailed ?
so can we duplicate it. thanks!

Comment 5 qnic 2012-08-21 00:54:57 UTC

we have a patch for tx timeout which is accepted by David Miller at July 9th,2012. 
does your kernel include that patch ?

Comment 6 Andreas Tunek 2012-08-21 19:03:00 UTC

I am currently running Fedora's 3.5.2 and it seems to work without the workaround. I do not get any crashes anymore and can pull out and plug in the ethernet cable as many times as I want without any error.