kern/139093: msk FIFO rx overrun

[Sergei Cherveni]

>Number:         139093
>Category:       kern
>Synopsis:       msk  FIFO rx overrun
>Confidential:   no
>Severity:       non-critical
>Priority:       medium
>Responsible:    freebsd-bugs
>State:          open
>Quarter:        
>Keywords:       
>Date-Required:
>Class:          sw-bug
>Submitter-Id:   current-users
>Arrival-Date:   Wed Sep 23 20:50:01 UTC 2009
>Closed-Date:
>Last-Modified:
>Originator:     Sergei Cherveni
>Release:        8.0-RC1
>Organization:
>Environment:
FreeBSD hp6830s 8.0-RC1 FreeBSD 8.0-RC1 #0: Mon Sep 21 22:17:00 EEST 2009     root at hp6830s:/usr/obj/usr/src/sys/GENERIC  i386

>Description:
Periodically (sometimes every 3-5 minutes) all network connections are stuck and in the same time in /var/log/messages appears a following (the same on the console):
kernel: msk0: Rx FIFO overrun

During these periods of time there is no ping replies, and iftop stops showing info about traffic. It shows blank screen instead of rows of connections.

Simple commands "ifconfig msk0 down; ifconfig msk0 up" does restore normal operation of msk.

#pciconf -lv
mskc0 at pci0:134:0:0:     class=0x020000 card=0x30e9103c chip=0x436c11ab rev=0x00 hdr=0x00
    vendor     = 'Marvell Semiconductor (Was: Galileo Technology Ltd)'
    device     = 'Marvell 8072 Ethernet Nic (88E8072)'
    class      = network
    subclass   = ethernet

#ifconfig msk0
msk0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
        options=19b<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,TSO4>
        ether 00:24:81:66:55:01
        inet 10.9.12.2 netmask 0xffffff00 broadcast 10.9.12.255
        media: Ethernet autoselect (100baseTX <full-duplex>)
        status: active

>How-To-Repeat:
Just start downloading something and make ping to control address, then wait for 5 minutes

>Fix:


>Release-Note:
>Audit-Trail:
>Unformatted: