kern/52818: The wm driver stops working after large traffic

[Shinichi Doyashiki <clare%csel.org@localhost>]

>Number:         52818
>Category:       kern
>Synopsis:       The wm driver stops working after large traffic
>Confidential:   no
>Severity:       serious
>Priority:       medium
>Responsible:    kern-bug-people
>State:          open
>Class:          sw-bug
>Submitter-Id:   net
>Arrival-Date:   Thu Dec 14 14:45:00 +0000 2017
>Originator:     Shinichi Doyashiki
>Release:        NetBSD 8.99.9
>Organization:
	at home
>Environment:
System: NetBSD akizuki.csel.org 8.99.9 NetBSD 8.99.9 (XCYMINIPC) #3: Tue Dec 12 07:17:00 JST 2017 clare%akizuki.csel.org@localhost:/export/stage/hack/sys/arch/amd64/compile/XCYMINIPC amd64
Architecture: x86_64
Machine: amd64
>Description:
	The wm driver stops working after large traffic.
	disabling TSO and other flags does not help for me.
	NET_MPSAFE is enabled at this point.
	The wm driver seems to be stopping transmit.
	This is can be a bug or individual difference
	of the device hardware, since another box of the
	same model is running fine with checksum offloading
	and with jumbo frames.

# dmesg | grep wm1
wm1 at pci2 dev 0 function 0: Intel i82583V (rev. 0x00)
wm1: interrupting at msi2 vec 0
wm1: PCI-Express bus
wm1: 512 words (8 address bits) SPI EEPROM, version 1.10.0, Image Unique ID ffffffff
wm1: Ethernet address 0c:e8:6c:**:**:**
wm1: 0x2a4440<SPI,IOH_VALID,PCIE,ASF_FIRM,AMT,WOL>
makphy1 at wm1 phy 1: Marvell 88E1149 Gigabit PHY, rev. 1
wm1: device timeout (txfree 4093 txsfree 61 txnext 3838)
wm1: device timeout (txfree 4086 txsfree 54 txnext 10)
wm1: device timeout (txfree 4088 txsfree 56 txnext 8)
wm1: device timeout (txfree 4089 txsfree 57 txnext 7)
wm1: device timeout (txfree 4089 txsfree 57 txnext 7)
wm1: device timeout (txfree 4089 txsfree 57 txnext 7)
wm1: device timeout (txfree 4087 txsfree 55 txnext 9)
wm1: device timeout (txfree 4088 txsfree 56 txnext 8)

# ifconfig wm1
wm1: flags=0x8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> mtu 9000
	capabilities=7ff80<TSO4,IP4CSUM_Rx,IP4CSUM_Tx,TCP4CSUM_Rx>
	capabilities=7ff80<TCP4CSUM_Tx,UDP4CSUM_Rx,UDP4CSUM_Tx,TCP6CSUM_Rx>
	capabilities=7ff80<TCP6CSUM_Tx,UDP6CSUM_Rx,UDP6CSUM_Tx,TSO6>
	enabled=0
	ec_capabilities=7<VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU>
	ec_enabled=0
	address: 0c:e8:6c:**:**:**
	media: Ethernet autoselect (1000baseT full-duplex,master)
	status: active
	inet 192.168.***.***/24 broadcast 192.168.4.255 flags 0x0
	inet6 fe80::****:****:****:****%wm1/64 flags 0x0 scopeid 0x2
	inet6 ****:****:****:****::****/64 flags 0x0
>How-To-Repeat:
	NFS mount on IPv6 TCP or UDP on the wm device,
	then rsync on it to apply large traffic.
>Fix:
	Unknown.