Description of problem: From time to time I'm getting error message from tg3 device driver (Broadcom gigabit ethernet) on the console (and in the log files). Also, from time to time the network card simply stops working. The error message is: tg3: eth0: No interrupt was generated using MSI, switching to INTx mode. Please report this failure to the PCI maintainer and include system chipset information. The motherboard is SuperMicro H8DSP-8. The specs seem to say it has ServerWorks HT2000 and ServerWorks HT1000 chipsets (see http://www.supermicro.com/Aplus/motherboard/Opteron/HT2000/H8DSP-8.cfm for more details). lspci reports: # lspci 00:01.0 PCI bridge: Broadcom HT1000 PCI/PCI-X bridge 00:02.0 Host bridge: Broadcom HT1000 Legacy South Bridge 00:02.1 IDE interface: Broadcom HT1000 Legacy IDE controller 00:02.2 ISA bridge: Broadcom HT1000 LPC Bridge 00:03.0 USB Controller: Broadcom HT1000 USB Controller (rev 01) 00:03.1 USB Controller: Broadcom HT1000 USB Controller (rev 01) 00:03.2 USB Controller: Broadcom HT1000 USB Controller (rev 01) 00:05.0 VGA compatible controller: ATI Technologies Inc Rage XL (rev 27) 00:08.0 PCI bridge: Broadcom HT2000 PCI-X bridge (rev a3) 00:09.0 PCI bridge: Broadcom HT2000 PCI-X bridge (rev a3) 00:0a.0 PCI bridge: Broadcom HT2000 PCI-Express bridge (rev a3) 00:0b.0 PCI bridge: Broadcom HT2000 PCI-Express bridge (rev a3) 00:0c.0 PCI bridge: Broadcom HT2000 PCI-Express bridge (rev a3) 00:0d.0 PCI bridge: Broadcom HT2000 PCI-Express bridge (rev a3) 00:18.0 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] HyperTransport Technology Configuration 00:18.1 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Address Map 00:18.2 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] DRAM Controller 00:18.3 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Miscellaneous Control 00:19.0 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] HyperTransport Technology Configuration 00:19.1 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Address Map 00:19.2 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] DRAM Controller 00:19.3 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Miscellaneous Control 01:0d.0 PCI bridge: Broadcom HT1000 PCI/PCI-X bridge (rev b2) 01:0e.0 RAID bus controller: Broadcom BCM5785 (HT1000) SATA Native SATA Mode 02:06.0 RAID bus controller: Adaptec AAC-RAID (rev 02) 04:04.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5780 Gigabit Ethernet (rev 03) 04:04.1 Ethernet controller: Broadcom Corporation NetXtreme BCM5780 Gigabit Ethernet (rev 03) Version-Release number of selected component (if applicable): kernel-smp-2.6.9-42.0.2.EL How reproducible: Allways Steps to Reproduce: 1. 2. 3. Actual results: Expected results: Additional info:
Typing too fast. It isn't "network card". The Ethernet card is integrated on the motherboard.
There is a patch (jwltest-pci-msi-quirk.patch) that might help in the test kernels here: http://people.redhat.com/linville/kernels/rhel4/ Please give those kernels a try and post the results here...thanks!
Well... There's a small problem. It's a production box, and I can't really take it down for testing or to play with it. There's probability I'll have another similar box on my desk in near future. When/if it arrives, I'll give those patches a try. However it might be couple of months before that happens.
A patch that should resolve this issue was recently committed to a RHEL4 development build. If you get a chance, please use one of the test kernels located here: http://people.redhat.com/~jbaron/rhel4/
Hi Andy, I've managed to find one of those machines on the devel side, and tested the new kernel (kernel-smp-2.6.9-42.35.EL). The problem is not solved. It still reports "No interrupt was generated using MSI, switching to INTx mode. Please report this failure to the PCI maintainerand include system chipset information" on both ethernet interfaces (eth0 and eth1) as soon as the interface is brought up on boot.
Aleksandar, Thanks for the update. I will look into this further and try to get back to you soon.
This message does seem to indicate that MSI doesn't work well on your system -- its really not a tg3 issue. I'm guessing if you boot with 'pci=nomsi' you won't see these messages. I'll continue to look at it and see if there is anything that can be done.
Hmmm, looks like that option might not be available on rhel4....
Test kernels for this issue will be available here: http://people.redhat.com/agospoda/#rhel4 Please test them and report back the results. These kernels contain a patch that should disable MSI on this part: 01:0d.0 PCI bridge: Broadcom HT1000 PCI/PCI-X bridge (rev b2) If these do not work, please attach the output from `lspci -t` and `lspci -n` Thanks!
Sorry. I work at different place now, and don't have access to anything with Broadcom HT1000 PCI/PCI-X bridge (that I'm aware of) anymore. I'll forward this needinfo request to my previous manager, in case he is still interested in fixing the issue.
This is definitely a duplicate of bug 227657. *** This bug has been marked as a duplicate of 227657 ***
Hmmm... Technically, bug 227657 is duplicate of this bug. This bug is about one year older than bug 227657. Unless you intend to make bug 227657 publicly accessible, reopen this bug and mark it to depend on bug 227657.