New: e1000e 82567LM Tx Unit Hang
Subsystems (2)
A message that is not in the archive (sent off-list or not yet received): [email protected]/
(switched to email. Please respond via emailed reply-to-all, not via the bugzilla web interface).
Quoted 18 lines · On Fri, 26 Dec 2008 02:50:52 -0800 (PST) [email protected] wrote:
http://bugzilla.kernel.org/show_bug.cgi?id=12303
Summary: e1000e 82567LM Tx Unit Hang Product: Drivers Version: 2.5 KernelVersion: 2.6.28 Platform: All OS/Version: Linux Tree: Mainline Status: NEW Severity: normal Priority: P1 Component: Network AssignedTo: [email protected] ReportedBy: [email protected] CC: [email protected]
Quoted 5 lines
Latest working kernel version: 2.6.27-git2 Earliest failing kernel version: unknown
Distribution: gentoo amd64 (~amd64), 2008.0 Hardware Environment: Thinkpad T400 with GM45 (ICH9)
An e1000e regression.
Quoted 78 lines
...
0000:00:19.0: eth0: 10/100 speed: disabling TSO
ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
eth0: no IPv6 routers present
DMAR:[DMA Read] Request device [00:19.0] fault addrfff03000DMAR:[fault reason 06] PTE Read access is not set 0000:00:19.0: eth0: Detected Tx Unit Hang:TDH <a3> TDT <b2> next_to_use <b2> next_to_clean <a3> buffer_info[next_to_clean]: time_stamp <fffe286d> next_to_watch <a3> jiffies <fffe31e5> next_to_watch.status <0> 0000:00:19.0: eth0: Detected Tx Unit Hang: TDH <a3> TDT <b2> next_to_use <b2> next_to_clean <a3> buffer_info[next_to_clean]: time_stamp <fffe286d> next_to_watch <a3> jiffies <fffe39b5> next_to_watch.status <0> 0000:00:19.0: eth0: Detected Tx Unit Hang: TDH <a3> TDT <b2> next_to_use <b2> next_to_clean <a3> buffer_info[next_to_clean]: time_stamp <fffe286d> next_to_watch <a3> jiffies <fffe418a> next_to_watch.status <0> ------------[ cut here ]------------ WARNING: at net/sched/sch_generic.c:226 dev_watchdog+0xf7/0x154() NETDEV WATCHDOG: eth0 (e1000e): transmit timed out Modules linked in: snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss uvcvideo compat_ioctl32 firewire_ohci videodev firewire_core v4l1_compat scsi_wait_scan Pid: 3956, comm: metacity Not tainted 2.6.28-gentoo #1 Call Trace: <IRQ> [<ffffffff802361ae>] warn_slowpath+0xb4/0xda [<ffffffff80490c73>] usb_hcd_submit_urb+0x733/0x7fd [<ffffffff804b11f0>] input_pass_event+0x5a/0x7b [<ffffffff804b2f5d>] input_event+0x5c/0x7f [<ffffffff804d7938>] hidinput_report_event+0x25/0x37 [<ffffffff804d4f95>] hid_input_report+0x1da/0x1f0 [<ffffffff80454531>] scsi_run_queue+0x2f8/0x395 [<ffffffff80380bfb>] __next_cpu+0x19/0x26 [<ffffffff80513aab>] netif_tx_lock+0x3d/0x68 [<ffffffff80513c1c>] dev_watchdog+0xf7/0x154 [<ffffffff8022a227>] sched_slice+0x3b/0x47 [<ffffffff8022a51a>] task_tick_fair+0x49/0x78 [<ffffffff80513b25>] dev_watchdog+0x0/0x154 [<ffffffff8023e6d8>] run_timer_softirq+0x151/0x1bf [<ffffffff8023aeec>] __do_softirq+0x7c/0x135 [<ffffffff8020d12c>] call_softirq+0x1c/0x28 [<ffffffff8020e5f4>] do_softirq+0x2c/0x68 [<ffffffff8023ac98>] irq_exit+0x3f/0x91 [<ffffffff8021b3f1>] smp_apic_timer_interrupt+0x92/0xab [<ffffffff8020cc0b>] apic_timer_interrupt+0x6b/0x70 <EOI> <4>---[ end trace 15d0e5980221c96c ]---0000:00:19.0: eth0: Link is Up 100 Mbps Full Duplex, Flow Control: None 0000:00:19.0: eth0: 10/100 speed: disabling TSO
ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready 0000:00:19.0: eth0: Detected Tx Unit Hang:TDH <0> TDT <3> next_to_use <3> next_to_clean <0> buffer_info[next_to_clean]: time_stamp <fffe4c85> next_to_watch <0> jiffies <fffe550d>
Quoted 8 lines
next_to_watch.status <0>
0000:00:19.0: eth0: Detected Tx Unit Hang:
TDH <0>Steps to reproduce:
1) get a computer with Intel Corporation 82567LM Gigabit Ethernet controller
2) compile kernel 2.6.28 (amd64) with e1000e
3) try to do some network traffic
------------------------------------------------------------------------------
I ran into this problem too with my new thinkpad (not an T400 but a x200 with the same network chip).
Quoted 7 lines
Quoted 5 lines
Latest working kernel version: 2.6.27-git2 Earliest failing kernel version: unknown
Distribution: gentoo amd64 (~amd64), 2008.0 Hardware Environment: Thinkpad T400 with GM45 (ICH9)An e1000e regression.
Couldn't find a version which worked for me. But as Wang mentioned setting acpi=off works and after some research in the net i found, that disabling CONFIG_DMAR works too (the first line of the logs is a dma error too, iirc). Are you sure that you used the same value for CONFIG_DMAR in your tests, Wang?
I'm willing to do some debugging, but I don't really know where to start if it's no regression (so bisecting won't work)...
Regards,
Signature · 2 lines
Antoine Kaufmann <[email protected]>