Bug 15922

Summary:	(tg3): transmit queue 0 timed out
Product:	Drivers	Reporter:	Sebastian Köhler (sebkoehler)
Component:	Network	Assignee:	Matt Carlson (mcarlson)
Status:	RESOLVED OBSOLETE
Severity:	normal	CC:	alan, mchan
Priority:	P1
Hardware:	All
OS:	Linux
Kernel Version:	2.6.33.3	Subsystem:
Regression:	No	Bisected commit-id:

Description Sebastian Köhler 2010-05-06 17:09:38 UTC

Whenever my network card is under high load after a few minutes the card stops sending an receiving packets. I have to manually bring the interface down and up again to reactivate the interface. "dmesg" gives this output:

WARNING: at net/sched/sch_generic.c:255 dev_watchdog+0x20b/0x220()
Hardware name: Studio 1537
NETDEV WATCHDOG: eth0 (tg3): transmit queue 0 timed out
Modules linked in: jfs ext3 jbd ext2 fuse vboxnetflt vboxdrv snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device usblp snd_hda_codec_atihdmi snd_pcm_oss snd_mixer_oss snd_hda_codec_idt dell_wmi fglrx(P) rtc_cmos lib80211_crypt_tkip wl(P) usb_storage rtc_core rtc_lib uvcvideo videodev sdhci_pci sdhci v4l1_compat lib80211 mmc_core coretemp snd_hda_intel firewire_ohci firewire_core snd_hda_codec snd_hwdep video output crc_itu_t led_class battery wmi snd_pcm ac snd_timer snd soundcore snd_page_alloc thermal button dell_laptop joydev rfkill radeon ttm drm_kms_helper cpufreq_ondemand drm i2c_algo_bit tg3 libphy acpi_cpufreq psmouse uhci_hcd freq_table intel_agp agpgart serio_raw iTCO_wdt sg iTCO_vendor_support evdev dcdbas ehci_hcd usbcore i2c_i801 i2c_core processor ext4 mbcache jbd2 crc16 aes_i586 aes_generic xts gf128mul dm_crypt dm_mod sr_mod cdrom sd_mod ahci libata scsi_mod
Pid: 0, comm: swapper Tainted: P 2.6.33-ARCH #1
Call Trace:
[<c1043b4d>] warn_slowpath_common+0x6d/0xa0
[<c125595b>] ? dev_watchdog+0x20b/0x220
[<c125595b>] ? dev_watchdog+0x20b/0x220
[<c1043bc6>] warn_slowpath_fmt+0x26/0x30
[<c125595b>] dev_watchdog+0x20b/0x220
[<c105c56f>] ? insert_work+0x5f/0xd0
[<c12d27a5>] ? _raw_spin_unlock_irqrestore+0x25/0x30
[<c105cb41>] ? __queue_work+0x31/0x40
[<c1050dee>] run_timer_softirq+0x12e/0x2f0
[<c106ece6>] ? tick_do_broadcast+0x36/0x70
[<c1255750>] ? dev_watchdog+0x0/0x220
[<c104a4bd>] __do_softirq+0x8d/0x1d0
[<c109648c>] ? handle_IRQ_event+0x4c/0x190
[<c1066e8e>] ? sched_clock_tick+0x5e/0x90
[<c1099054>] ? move_native_irq+0x14/0x50
[<c104a63d>] do_softirq+0x3d/0x50
[<c104a9fd>] irq_exit+0x6d/0x70
[<c1005b00>] do_IRQ+0x50/0xc0
[<c100a378>] ? sched_clock+0x8/0x10
[<c1066b0b>] ? sched_clock_local+0xab/0x1a0
[<c1003cb0>] common_interrupt+0x30/0x38
[<c106007b>] ? sys_clock_settime+0x6b/0xa0
[<f84e2173>] ? acpi_idle_enter_bm+0x255/0x286 [processor]
[<c12290ba>] cpuidle_idle_call+0x7a/0x120
[<c10020b4>] cpu_idle+0x84/0xd0
[<c12ccba2>] start_secondary+0x1bd/0x1c3
---[ end trace 8c331e076b17dbaf ]---
tg3: eth0: transmit timed out, resetting
tg3: DEBUG: MAC_TX_STATUS[0000000b] MAC_RX_STATUS[00000006]
tg3: DEBUG: RDMAC_STATUS[00000000] WDMAC_STATUS[00000000]
tg3: tg3_stop_block timed out, ofs=2c00 enable_bit=2
tg3: tg3_stop_block timed out, ofs=1400 enable_bit=2
tg3: tg3_stop_block timed out, ofs=c00 enable_bit=2
tg3: tg3_stop_block timed out, ofs=4800 enable_bit=2

This is the card I am using:

# lspci
08:00.0 Ethernet controller: Broadcom Corporation NetLink BCM5784M Gigabit Ethernet PCIe (rev 10)
Subsystem: Dell Device 029f
Kernel driver in use: tg3
Kernel modules: tg3

Comment 1 Matt Carlson 2010-05-11 16:57:05 UTC

Does it help if you turn off both tx and rx flow control?

Comment 2 Sebastian Köhler 2010-05-12 07:05:09 UTC

(In reply to comment #1)
> Does it help if you turn off both tx and rx flow control?

Yes after switching flow control off the error seems to be gone.