- 21. Re: Mystery packet killing tg3 (score: 1)
- Author: <tgraf@xxxxxxx>
- Date: Thu, 05 May 2005 09:20:25 -0700
- One of the osdl e1000's in the lab is an IBM rebranded card that although it uses a 64bit slot, is really only 32bit
- /archives/netdev/2005-05/msg00205.html (10,936 bytes)
- 22. Re: Mystery packet killing tg3 (score: 1)
- Author: lo@xxxxxxxxxxx>
- Date: Thu, 05 May 2005 10:09:55 -0700
- Andi Kleen wrote: "32bit e1000"? How did you get such a beast? AFAIK all e1000s are 64bit address capable. Please supply a full boot log without iommu=force and describe what happens exactly. that wa
- /archives/netdev/2005-05/msg00208.html (19,548 bytes)
- 23. Re: Mystery packet killing tg3 (score: 1)
- Author: r@xxxxxxxxxxxx>
- Date: Thu, 05 May 2005 10:32:16 -0700
- Peter Buckingham wrote: Andi Kleen wrote: "32bit e1000"? How did you get such a beast? AFAIK all e1000s are 64bit address capable. Please supply a full boot log without iommu=force and describe what
- /archives/netdev/2005-05/msg00209.html (10,785 bytes)
- 24. Re: Mystery packet killing tg3 (score: 1)
- Author: .jones2@xxxxxx>
- Date: Thu, 05 May 2005 10:38:27 -0700
- Rick Jones wrote: IIRC the HP Itanium2 workstations (zx2000, zx6000) have a 32-bit Intel (e1000) GbE on them. I have an idea what the name of the chip was, but will defer to any and all Intel types o
- /archives/netdev/2005-05/msg00210.html (11,630 bytes)
- 25. Re: Mystery packet killing tg3 (score: 1)
- Author: <tgraf@xxxxxxx>
- Date: Thu, 5 May 2005 13:45:35 -0400
- From a zx2000: 0000:a0:03.0 Ethernet controller: Intel Corp. 82540EM Gigabit Ethernet Controller (rev 02) Subsystem: Hewlett-Packard Company: Unknown device 1274 Flags: bus master, 66MHz, medium devs
- /archives/netdev/2005-05/msg00212.html (10,863 bytes)
- 26. Re: Mystery packet killing tg3 (score: 1)
- Author: effner@xxxxxxx>
- Date: Thu, 5 May 2005 20:01:06 +0200
- Ok, but it still supports DAC. The PCI bus width is a different thing from the size of the address registers. What we are talking about here is just if the card can directly address physical memory a
- /archives/netdev/2005-05/msg00213.html (11,605 bytes)
- 27. Re: Mystery packet killing tg3 (score: 1)
- Author: een <ak@xxxxxx>
- Date: Thu, 5 May 2005 20:06:09 +0200
- The kernel should detect incorrect IOMMU setups and work around it. So even if your BIOS screws it up completely it should work (at the cost of some lost memory). That is the theory at least, but per
- /archives/netdev/2005-05/msg00214.html (12,155 bytes)
- 28. Re: Mystery packet killing tg3 (score: 1)
- Author: een <ak@xxxxxx>
- Date: Thu, 05 May 2005 11:21:26 -0700
- Andi Kleen wrote: In what initialization exactly? YOu mean changing the pci_set_dma_mask() in the e1000 driver? exactly. Kernel panic - not syncing: Cannot allocate iommu bitmap Hmm, that must be a d
- /archives/netdev/2005-05/msg00216.html (11,422 bytes)
- 29. Re: Mystery packet killing tg3 (score: 1)
- Author: r@xxxxxxxxxxxx>
- Date: Thu, 5 May 2005 20:31:44 +0200
- That should be impossible. Or it sounds like a serious hardware problem. DAC should normally always work with all e1000 AFAIK. Most likely you have some hardware problem and it is somehow magically w
- /archives/netdev/2005-05/msg00217.html (12,053 bytes)
- 30. Re: Mystery packet killing tg3 (score: 1)
- Author: @xxxxxxxxxxxxx>
- Date: Thu, 05 May 2005 11:40:24 -0700
- Andi Kleen wrote: That should be impossible. Or it sounds like a serious hardware problem. DAC should normally always work with all e1000 AFAIK. okay. I basically just force it to take a 32bit dma ma
- /archives/netdev/2005-05/msg00220.html (28,580 bytes)
- 31. Re: Mystery packet killing tg3 (score: 1)
- Author: aber@xxxxxxxxx>
- Date: Thu, 5 May 2005 20:56:35 +0200
- If you dont use iommu=force it will only cause IOMMU remapping when the memory buffer is beyond 4GB. It is basically random if that happens or not, depending on how fully your memory is. With iommu=f
- /archives/netdev/2005-05/msg00222.html (12,246 bytes)
- 32. Re: Mystery packet killing tg3 (score: 1)
- Author: een <ak@xxxxxx>
- Date: Thu, 05 May 2005 12:02:15 -0700
- Andi Kleen wrote: With iommu=force or CONFIG_IOMMU_DEBUG all IO is foced through the IOMMU. okay, that's definitely bad... Hmm - if you want to hack the kernel you could add udelay()s to the no IOMMU
- /archives/netdev/2005-05/msg00223.html (11,876 bytes)
- 33. Re: Mystery packet killing tg3 (score: 1)
- Author: xxxxxxxxxxxxxx>
- Date: Thu, 5 May 2005 21:24:05 +0200
- No, it is still broken, the kernel fixed it up. Look at the early messages. It was too small (32MB) -Andi
- /archives/netdev/2005-05/msg00226.html (10,645 bytes)
- 34. Re: Mystery packet killing tg3 (score: 1)
- Author: aber@xxxxxxxxx>
- Date: Thu, 05 May 2005 12:56:34 -0700
- Looks good. I'm adding this patch to further ignore the tg3_stop_block errors. [TG3]: Ignore tg3_stop_block() errors. tg3_stop_block() errors can be safely ignored since tg3_chip_reset() always follo
- /archives/netdev/2005-05/msg00232.html (11,433 bytes)
- 35. Re: Mystery packet killing tg3 (score: 1)
- Author: @xxxxxxxxxxxxx>
- Date: Thu, 5 May 2005 14:42:01 -0700
- Your email client wrapped the lines in the patch Michael, please use attachments if you can't avoid this. Anyways, I applied both my patch and your's (by hand) to my tree and will push upstream. Than
- /archives/netdev/2005-05/msg00240.html (9,983 bytes)
- 36. Mystery packet killing tg3 (score: 1)
- Author: Stephen Hemminger <shemminger@xxxxxxxx>
- Date: Mon, 2 May 2005 16:24:05 -0700
- While I was on vacation, OSDL did some networking changes that seems to aggravate some existing bug in the tg3 driver. Could be some VLAN related garbage, not sure. System is 2 CPU AMD64 and the tg3
- /archives/netdev/2005-05/msg01324.html (8,295 bytes)
- 37. Re: Mystery packet killing tg3 (score: 1)
- Author: "David S. Miller" <davem@xxxxxxxxxxxxx>
- Date: Mon, 2 May 2005 20:02:51 -0700
- This usually means that there is some DMA corruption. For example, some bug in the x86_64 IOMMU code or similar causes a bogus DMA address to be fed to the tg3 or even worse a DMA mapping is unmapped
- /archives/netdev/2005-05/msg01332.html (9,841 bytes)
- 38. Re: Mystery packet killing tg3 (score: 1)
- Author: Stephen Hemminger <shemminger@xxxxxxxx>
- Date: Tue, 3 May 2005 14:05:28 -0700
- Added call to tg_dump_state() tg3: tg3_stop_block timed out, ofs=4000 enable_bit=2 DEBUG: PCI status [02b0] TG3PCI state[000010e2] DEBUG: MAC_MODE[00c04c08] MAC_STATUS[00400003] MAC_EVENT[00001000] M
- /archives/netdev/2005-05/msg01361.html (22,425 bytes)
- 39. Re: Mystery packet killing tg3 (score: 1)
- Author: "David S. Miller" <davem@xxxxxxxxxxxxx>
- Date: Tue, 3 May 2005 14:13:14 -0700
- Buggy 8131 APIC, does the drivers/pci/quirks.c:quirk_amd_8131_ioapic() message: PCI: MSI quirk detected. pci_msi_quirk set. trigger? MSI support recently got added to the tg3.c driver, but it should
- /archives/netdev/2005-05/msg01362.html (9,428 bytes)
- 40. Re: Mystery packet killing tg3 (score: 1)
- Author: Stephen Hemminger <shemminger@xxxxxxxx>
- Date: Tue, 3 May 2005 14:29:52 -0700
- yes. that is there. There is no call to pci_enable_msi in the 2.6.12-rc3 source
- /archives/netdev/2005-05/msg01363.html (10,198 bytes)
This search system is powered by
Namazu