Date: Sun, 14 Nov 2004 22:26:38 +0100 (CET) From: Sten Spans <sten@blinkenlights.nl> To: freebsd-alpha@freebsd.org Subject: alpha and em mtu Message-ID: <Pine.SOC.4.61.0411142153430.26307@tea.blinkenlights.nl>
next in thread | raw e-mail | index | archive | help
I upgraded my ds10 with an intel gigabit card,
and encountered the following issue (RELENG_5):
deepthought# ifconfig em0 mtu 1501
deepthought#
fatal kernel trap:
trap entry = 0x4 (unaligned access fault)
faulting va = 0xfffffc001847a02e
opcode = 0x28
register = 0x1
pc = 0xfffffc00004cd0f8
ra = 0xfffffc00004cce24
sp = 0xfffffe00187a9af0
curthread = 0xfffffc001f3a70e0
pid = 14, comm = swi1: net
[thread 100006]
Stopped at tcp_input+0x368: srl t0,#0x2,t0 <t0=0x45>
db> trace
tcp_input() at tcp_input+0x368
ip_input() at ip_input+0x9fc
netisr_processqueue() at netisr_processqueue+0xac
swi_net() at swi_net+0xf0
ithread_loop() at ithread_loop+0x1d4
fork_exit() at fork_exit+0x100
exception_return() at exception_return
--- root of call graph ---
deepthought# ifconfig em0 mtu 9014
deepthought#
fatal kernel trap:
trap entry = 0x4 (unaligned access fault)
faulting va = 0xfffffc0018c5202e
opcode = 0x28
register = 0x1
pc = 0xfffffc00004cd0f8
ra = 0xfffffc00004cce24
sp = 0xfffffe00187a9af0
curthread = 0xfffffc001f3a70e0
pid = 14, comm = swi1: net
[thread 100006]
Stopped at tcp_input+0x368: srl t0,#0x2,t0 <t0=0x45>
db> trace
tcp_input() at tcp_input+0x368
ip_input() at ip_input+0x9fc
netisr_processqueue() at netisr_processqueue+0xac
swi_net() at swi_net+0x148
ithread_loop() at ithread_loop+0x1d4
fork_exit() at fork_exit+0x100
exception_return() at exception_return
--- root of call graph ---
The box crashes on the first incoming tcp packet,
icmp is fine. mpsafenet=0 and net.inet.tcp.sack.enable=0
did not seem to help.
I have an intel box (fbsd5) with the same batch em0
which supports large mtu's just fine.
tcpdump:
22:20:29.219776 IP 192.168.1.4.35993 > 192.168.1.3.23: S
2509718255:2509718255(0) win 17948 <mss 8974,sackOK,timestamp 160282313
0,nop,wscale 2>
0x0000: 0003 477a 3ef6 000d 5616 e035 0800 4510 ..Gz>...V..5..E.
0x0010: 003c f426 4000 4006 c32d c0a8 0104 c0a8 .<.&@.@..-......
0x0020: 0103 8c99 0017 9597 42ef 0000 0000 a002 ........B.......
0x0030: 461c 3ba9 0000 0204 230e 0402 080a 098d F.;.....#.......
0x0040: b6c9 0000 0000 0103 0302 ..........
22:20:29.220148 IP 192.168.1.3.23 > 192.168.1.4.35993: R 0:0(0) ack
2509718256 win 0
0x0000: 000d 5616 e035 0003 477a 3ef6 0800 4510 ..V..5..Gz>...E.
0x0010: 0028 00d8 4000 4006 b690 c0a8 0103 c0a8 .(..@.@.........
0x0020: 0104 0017 8c99 0000 0000 9597 42f0 5014 ............B.P.
0x0030: 0000 c740 0000 0000 0000 0000 ...@........
22:20:44.098530 IP 192.168.1.4.35994 > 192.168.1.3.23: S
2521517724:2521517724(0) win 17948 <mss 8974,sackOK,timestamp 160297194
0,nop,wscale 2>
0x0000: 0003 477a 3ef6 000d 5616 e035 0800 4510 ..Gz>...V..5..E.
0x0010: 003c be76 4000 4006 f8dd c0a8 0104 c0a8 .<.v@.@.........
0x0020: 0103 8c9a 0017 964b 4e9c 0000 0000 a002 .......KN.......
0x0030: 461c f525 0000 0204 230e 0402 080a 098d F..%....#.......
0x0040: f0ea 0000 0000 0103 0302 ..........
22:20:47.097687 IP 192.168.1.4.35994 > 192.168.1.3.23: S
2521517724:2521517724(0) win 17948 <mss 8974,sackOK,timestamp 160300194
0,nop,wscale 2>
0x0000: 0003 477a 3ef6 000d 5616 e035 0800 4510 ..Gz>...V..5..E.
0x0010: 003c be78 4000 4006 f8db c0a8 0104 c0a8 .<.x@.@.........
0x0020: 0103 8c9a 0017 964b 4e9c 0000 0000 a002 .......KN.......
0x0030: 461c e96d 0000 0204 230e 0402 080a 098d F..m....#.......
0x0040: fca2 0000 0000 0103 0302 ..........
22:20:49.097336 arp who-has 192.168.1.3 tell 192.168.1.4
0x0000: 0003 477a 3ef6 000d 5616 e035 0806 0001 ..Gz>...V..5....
0x0010: 0800 0604 0001 000d 5616 e035 c0a8 0104 ........V..5....
0x0020: 0000 0000 0000 c0a8 0103 ..........
Any clues ?
--
Sten Spans
"There is a crack in everything, that's how the light gets in."
Leonard Cohen - Anthem
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SOC.4.61.0411142153430.26307>