Re: [Regression, bisected] Transmit failure in et131x.

[Nick Bowler <nbowler@draconx.ca>]

Alan Cox <alan <at> lxorguk.ukuu.org.uk> writes:
> Please test the following if you would.
> 
> If it doesn't work see if you can tell from the other end and tcpdump
> if the receiver or sender side dies, and let me know if you are using
> 10, 100 or Gbit and if you have the mtu set over 1500.

Thanks a lot for your help.  Alas, this does not resolve the issue.
Using tcpdump indicates that receive continues to work while transmit
fails.

I was using gigabit, but the problem persists when I run at 100mbit.
The MTU setting remains at the default 1500 bytes.

In case it's useful, here's the lspci -nv output for my card:

02:00.0 0200: 11c1:ed00 (rev 02)
        Subsystem: 11c1:ed00
        Flags: bus master, fast devsel, latency 0, IRQ 16
        Memory at fd400000 (64-bit, non-prefetchable) [size=2M]
        Expansion ROM at fd7e0000 [disabled] [size=128K]
        Capabilities: [40] Power Management version 2
        Capabilities: [48] Express Endpoint, MSI 00
        Capabilities: [5c] Message Signalled Interrupts: Mask- 64bit+ Count=1/1
Enable-
        Capabilities: [100] Advanced Error Reporting
                UESta:  DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF-
MalfTLP- ECRC- UnsupReq+ ACSVoil-
                UEMsk:  DLP+ SDES- TLP+ FCP+ CmpltTO+ CmpltAbrt+ UnxCmplt+ RxOF+
MalfTLP+ ECRC+ UnsupReq+ ACSVoil-
                UESvrt: DLP+ SDES- TLP- FCP+ CmpltTO- CmpltAbrt- UnxCmplt- RxOF+
MalfTLP+ ECRC- UnsupReq- ACSVoil-
                CESta:  RxErr- BadTLP- BadDLLP+ Rollover- Timeout+ NonFatalErr-
                CESta:  RxErr+ BadTLP+ BadDLLP+ Rollover+ Timeout+ NonFatalErr-
                AERCap: First Error Pointer: 00, GenCap+ CGenEn- ChkCap+ ChkEn-
        Capabilities: [130] Virtual Channel <?>
        Capabilities: [14c] Device Serial Number d9-29-03-fe-ff-3b-13-02
        Kernel driver in use: et131x
        Kernel modules: et131x