netdev - TG3 kernel hard lockup with 2.6.30

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 11 Jun 2009 18:07:30 -0400
From:	Web Visum <webvisum@...glemail.com>
To:	netdev@...r.kernel.org
Subject: TG3 kernel hard lockup with 2.6.30

Guys,

Apologies for emailing the world, but the situation is an emergency for me.

The box has been running 2.6.22.1 for over a year without a glitch.
Today I tried 2.6.30 and while things looked fine at the beginning,
after a few minutes of traffic though the tg3 interface I've gotten a
hard lockup, no kernel message, nothing to netconsole, just a total
and complete lockup.   Not even sysrq was able to boot the box and it
had to be power cycled.

Worse, it's reproducible.  And catastrophic, now kernel 2.6.22.1 also
locks up in exactly the same manner.

I've tried turning off TSO via ethtool and that *appears* to delay the
onset of the lockup, but it does not prevent it entirely.

The motherboard is a Tyan S2882, lspci -v -v output follows:

02:09.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5704
Gigabit Ethernet (rev 03)
        Subsystem: Broadcom Corporation Device 1644
        Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR+ FastB2B- DisINTx-
        Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=medium
>TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 64 (16000ns min), Cache Line Size: 64 bytes
        Interrupt: pin A routed to IRQ 24
        Region 0: Memory at fc9c0000 (64-bit, non-prefetchable) [size=64K]
        Region 2: Memory at fc9b0000 (64-bit, non-prefetchable) [size=64K]
        Expansion ROM at fc9a0000 [disabled] [size=64K]
        Capabilities: [40] PCI-X non-bridge device
                Command: DPERE- ERO- RBC=2048 OST=1
                Status: Dev=02:09.0 64bit+ 133MHz+ SCD- USC- DC=simple
DMMRBC=2048 DMOST=1 DMCRS=16 RSCEM- 266MHz- 533MHz-
        Capabilities: [48] Power Management version 2
                Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA
PME(D0-,D1-,D2-,D3hot+,D3cold+)
                Status: D0 PME-Enable+ DSel=0 DScale=1 PME-
        Capabilities: [50] Vital Product Data
                Not readable
        Capabilities: [58] MSI: Mask- 64bit+ Count=1/8 Enable-
                Address: 866a048401200080  Data: 1c08
        Kernel driver in use: tg3

tg3 driver version on the  2.6.22.1 kernel is: v3.77 (May 31, 2007)
while on 2.6.30 it is v3.98 (February 25, 2009)

I would very much appreciate any ideas you may have on how we can fix this.

Best,
Richard
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html