[Bug 291105] Intel i350 not receiving arp replies

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=291105

            Bug ID: 291105
           Summary: Intel i350 not receiving arp replies
           Product: Base System
           Version: 14.3-STABLE
          Hardware: amd64
                OS: Any
            Status: New
          Severity: Affects Only Me
          Priority: ---
         Component: kern
          Assignee: bugs@FreeBSD.org
          Reporter: dave@jetcafe.org

igb0@pci0:6:0:0:        class=0x020000 rev=0x01 hdr=0x00 vendor=0x8086
device=0x1521 subvendor=0x8086 subdevice=0x5001
    vendor     = 'Intel Corporation'
    device     = 'I350 Gigabit Network Connection'
    class      = network
    subclass   = ethernet

igb0:
flags=1008947<UP,BROADCAST,DEBUG,RUNNING,PROMISC,SIMPLEX,MULTICAST,LOWER_UP>
metric 0 mtu 1500
        options=800020<JUMBO_MTU,HWSTATS>
        ether b4:96:91:56:32:0c
        inet 172.18.1.5 netmask 0xffffff00 broadcast 172.18.1.255
        media: Ethernet autoselect (1000baseT <full-duplex>)
        status: active
        nd6 options=29<PERFORMNUD,IFDISABLED,AUTO_LINKLOCAL>

# ping 172.18.1.7
PING 172.18.1.7 (172.18.1.7): 56 data bytes
ping: sendto: Host is down

# arp -an | grep 172.18.1.7
? (172.8.1.7) at (incomplete) on igb0 expired [ethernet]

Ok. So tcpdump on the .7 machine reveals:

18:36:24.446015 ARP, Request who-has 172.18.1.7 tell 172.18.1.5, length 46
18:36:24.446026 ARP, Reply 172.18.1.7 is-at 70:85:c2:c1:19:11, length 28

but tcpdump on the .5 machine simply says
18:37:44.286895 ARP, Request who-has 172.18.1.7 tell 172.18.1.5, length 28

Thus I believe I have observed the reply not getting to the destination (.5)
machine. Now I have already looked at the switch involved and moved these two
to a different switch. Same result. 

Is there something I'm missing?  

The relevant dmesg bits are:

igb0: <Intel(R) I350 (Copper)> mem 0xdec00000-0xdecfffff,0xdef0c000-0xdef0ffff
at device 0.0 on pci6
igb0: EEPROM V1.67-0 Option ROM V18-b8-p9 eTrack 0x80000fb7
igb0: Using 1024 TX descriptors and 1024 RX descriptors
igb0: Using 8 RX queues 8 TX queues
igb0: Using MSI-X interrupts with 9 vectors
igb0: Ethernet address: b4:96:91:56:32:0c
igb0: netmap queues/slots: TX 8/1024, RX 8/1024

Can anyone explain what is going on?

-- 
You are receiving this mail because:
You are the assignee for the bug.