Hallo, When I boot a kernel with iommu=force (this forces all pci_map_sgs through the K8 aperture) and slab debugging on a Nforce4 x86-64 system the network corrupts data very quickly. Even when just sshing somewhere ssh quickly aborts with MAC errors etc.
Reverting only forcedeth.c to the one from 2.6.14 fixes the problem. I also tried to apply Ayaz's TSO fix, but that didn't fix the problem. Any ideas? The system is unusable with this so it's a release critical bug for 2.6.15 imho. The system is a Tyan S2895 SLI board with two on board Nvidia NICs: forcedeth.c: Reverse Engineered nForce ethernet driver. Version 0.48. eth0: forcedeth.c: subsystem: 010f1:2895 bound to 0000:00:0a.0 eth1: forcedeth.c: subsystem: 010f1:2895 bound to 0000:80:0a.0 80:0a.0 Bridge: nVidia Corporation CK804 Ethernet Controller (rev a3) Subsystem: Tyan Computer: Unknown device 2895 Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Step ping- SERR- FastB2B- Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- Latency: 0 (250ns min, 5000ns max) Interrupt: pin A routed to IRQ 185 Region 0: Memory at 00000000d8401000 (32-bit, non-prefetchable) [size=4K ] Region 1: I/O ports at 3000 [size=8] Capabilities: [44] Power Management version 2 Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0+,D1+,D2+,D3hot +,D3cold+) Status: D0 PME-Enable- DSel=0 DScale=0 PME- 00: de 10 57 00 07 00 b0 00 a3 00 80 06 00 00 00 00 10: 00 10 40 d8 01 30 00 00 00 00 00 00 00 00 00 00 20: 00 00 00 00 00 00 00 00 00 00 00 00 f1 10 95 28 30: 00 00 00 00 44 00 00 00 00 00 00 00 05 01 01 14 00:0a.0 Bridge: nVidia Corporation CK804 Ethernet Controller (rev a3) Subsystem: Tyan Computer: Unknown device 2895 Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SE RR- FastB2B- Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- Latency: 0 (250ns min, 5000ns max) Interrupt: pin A routed to IRQ 177 Region 0: Memory at 00000000c8005000 (32-bit, non-prefetchable) [size=4K] Region 1: I/O ports at 1c60 [size=8] Capabilities: [44] Power Management version 2 Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0+,D1+,D2+,D3hot+,D3cold +) Status: D0 PME-Enable+ DSel=0 DScale=0 PME- 00: de 10 57 00 07 00 b0 00 a3 00 80 06 00 00 00 00 10: 00 50 00 c8 61 1c 00 00 00 00 00 00 00 00 00 00 20: 00 00 00 00 00 00 00 00 00 00 00 00 f1 10 95 28 30: 00 00 00 00 44 00 00 00 00 00 00 00 0b 01 01 14 -Andi - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html