bge problems in RELENG_9, bge0: watchdog timeout -- resetting

[Sean Bruno]

On Wed, 2012-07-04 at 18:01 -0700, YongHyeon PYUN wrote:
> here is a WIP version at the following URL.
> http://people.freebsd.org/~yongari/bge/if_bge.c
> http://people.freebsd.org/~yongari/bge/if_bgereg.h
> http://people.freebsd.org/~yongari/bge/brgphy.c
> 
> I have a couple of positive feedbacks but it seems it still has
> some issues. Let me know whether it makes any difference on your
> box. 

I grabbed these updates and applied them cleanly to stable/9 on a Dell
R620 with a quad port BCM5720, I still see watchdog timeouts and reset
indications.  I am able to ping out of the box for a short amount of
time before the device hangs and times out.



-bash-4.2# ping XXX.XXX.XXX.1
PING XXX.XXX.XXX.1 (XXX.XXX.XXX.XXX): 56 data bytes
ping: sendto: Network is down
ping: sendto: Network is down
ping: sendto: Network is down
ping: sendto: Network is down
ping: sendto: Network is down
Jul  9 17:31:41 <kern.crit> x89 kernel: bge2: watchdog timeout --
resetting
Jul  9 17:31:41 <kern.notice> x89 kernel: bge2: link state changed to
DOWN
Jul  9 17:31:41 <kern.notice> x89 kernel: bge2: link state changed to
DOWN
ping: sendto: No route to host
ping: sendto: No route to host
ping: sendto: No route to host
ping: sendto: No route to host
64 bytes from XXX.XXX.XXX.1: icmp_seq=9 ttl=64 time=1.408 ms
Jul  9 17:31:45 <kern.notice> x89 kernel: bge2: link state changed to UP
Jul  9 17:31:45 <kern.notice> x89 kernel: bge2: link state changed to UP
64 bytes from 10.73.149.1: icmp_seq=10 ttl=64 time=1.697 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=11 ttl=64 time=1.835 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=12 ttl=64 time=1.390 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=13 ttl=64 time=1.392 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=14 ttl=64 time=1.392 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=15 ttl=64 time=1.848 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=16 ttl=64 time=1.389 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=17 ttl=64 time=1.541 ms
64 bytes from XXX.XXX.XXX.1: icmp_seq=18 ttl=64 time=1.575 ms

The stats counters don't really show much here, but here they are
regardless.
dev.bge.2.%desc: Broadcom NetXtreme Gigabit Ethernet, ASIC rev.
0x5720000
dev.bge.2.%driver: bge
dev.bge.2.%location: slot=0 function=0 handle=\_SB_.PCI0.PE1C.NDX0
dev.bge.2.%pnpinfo: vendor=0x14e4 device=0x165f subvendor=0x1028
subdevice=0x1f5b class=0x020000
dev.bge.2.%parent: pci1
dev.bge.2.forced_collapse: 0
dev.bge.2.msi: 1
dev.bge.2.forced_udpcsum: 0
dev.bge.2.stats.FramesDroppedDueToFilters: 0
dev.bge.2.stats.DmaWriteQueueFull: 0
dev.bge.2.stats.DmaWriteHighPriQueueFull: 0
dev.bge.2.stats.NoMoreRxBDs: 0
dev.bge.2.stats.InputDiscards: 0
dev.bge.2.stats.InputErrors: 0
dev.bge.2.stats.RecvThresholdHit: 0
Jul  9 17:33:35 <kern.notice> x89 kernel: bge2: link state changed to
DOWN
dev.bge.2.stats.rx.ifHCInOctets: 109580
dev.bge.2.stats.rx.Fragments: 0
dev.bge.2.stats.rx.UnicastPkts: 212
dev.bge.2.stats.rx.MulticastPkts: 282
dev.bge.2.stats.rx.BroadcastPkts: 543
dev.bge.2.stats.rx.FCSErrors: 0
dev.bge.2.stats.rx.AlignmentErrors: 0
dev.bge.2.stats.rx.xonPauseFramesReceived: 0
dev.bge.2.stats.rx.xoffPauseFramesReceived: 0
dev.bge.2.stats.rx.ControlFramesReceived: 0
dev.bge.2.stats.rx.xoffStateEntered: 0
dev.bge.2.stats.rx.FramesTooLong: 0
dev.bge.2.stats.rx.Jabbers: 0
dev.bge.2.stats.rx.UndersizePkts: 0
dev.bge.2.stats.tx.ifHCOutOctets: 30916
dev.bge.2.stats.tx.Collisions: 0
dev.bge.2.stats.tx.XonSent: 0
dev.bge.2.stats.tx.XoffSent: 0
dev.bge.2.stats.tx.InternalMacTransmitErrors: 0
dev.bge.2.stats.tx.SingleCollisionFrames: 0
dev.bge.2.stats.tx.MultipleCollisionFrames: 0
dev.bge.2.stats.tx.DeferredTransmissions: 0
dev.bge.2.stats.tx.ExcessiveCollisions: 0
dev.bge.2.stats.tx.LateCollisions: 0
dev.bge.2.stats.tx.UnicastPkts: 203
dev.bge.2.stats.tx.MulticastPkts: 0
dev.bge.2.stats.tx.BroadcastPkts: 3