Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 25 Aug 2005 19:24:53 -0400 (EDT)
From:      Andrew Gallatin <gallatin@cs.duke.edu>
To:        freebsd-amd64@freebsd.org
Subject:   nve status on nforce4?
Message-ID:  <17166.21317.705489.47055@grasshopper.cs.duke.edu>

next in thread | raw e-mail | index | archive | help

I've got a fairly cheap DFI nforce4 based board with an nvidia
ethernet adaptor in it.  512MB ram:

nve0: <NVIDIA nForce MCP9 Networking Adapter> port 0xb400-0xb407 mem 0xfebf9000-0xfebf9fff irq 22 at device 10.0 on pci0
nve0: Ethernet address 00:01:29:f5:6b:91
miibus1: <MII bus> on nve0
miibus1: <MII bus> on nve0
ciphy0: <Cicada CS8201 10/100/1000TX PHY> on miibus1
ciphy0:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseT, 1000baseT-FDX, auto
nve0: Ethernet address: 00:01:29:f5:6b:91
nve0: [GIANT-LOCKED]


Running 7-current from last weekend (and pretty much anything since I
installed it in June), the board passes no traffic at all according to
the netstat counters, and according to tcpdump.  Yet it does seem to
correctly detect the link accoring to ifconfig, and it seems to
generate interrupts.


This adaptor works flawlessly using another NVE based driver on
Solaris/amd64,  and it works fine using the forcedeth driver on
RHEL4, so it is not a hardware problem.

The amd64 nvnetlib.o shipped with the Solaris driver has the same
checksum as the FreeBSD one, so its not that our nvnetlib is out of
date.

My system has far less than 4GB of ram, so I don't see how it
could be a memory hole issue.

The 32-bit FreeBSD/i386 6.0-BETA2 mininst CD behaves the same, so
I don't think its a 64-bit issue.

The only report I've seen from somebody using an nve is with
a different phy than mine (ukphy0 vs ciphy0)

Has anybody with a desktop class NF4 based box had success with the
nve adaptor?   What phy does your box have?



Drew



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?17166.21317.705489.47055>