Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 14 Jan 2011 16:13:14 -0500
From:      John Baldwin <jhb@freebsd.org>
To:        freebsd-current@freebsd.org
Cc:        Michael Jung <mikej@paymentallianceintl.com>
Subject:   Re: unknown mtx_assert at /usr/src/sys/x86/x86/io_apic.c:161
Message-ID:  <201101141613.14748.jhb@freebsd.org>
In-Reply-To: <71E8B8120FF7A542AA24D740A9DADCFCC0FE4D@exchange.paymentallianceintl.com>
References:  <71E8B8120FF7A542AA24D740A9DADCFCC0FE4D@exchange.paymentallianceintl.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Thursday, January 13, 2011 11:26:46 am Michael Jung wrote:
> Links to crash info below.
> http://216.26.153.6/msgbuf.txt

This might be a hardware problem.  The panic you got is a "should never 
happen" panic.  Note that in the code line sourced, the second argument to 
mtx_assert() is MA_OWNED.  The panic is saying that it is some invalid value 
(i.e. something other than MA_OWNED).  Given that is a constant, that's not 
very likely at all barring some hardware glitch.

You do have a somewhat scary looking machine check logged before your panic:

MCA: Bank 1, Status 0xd000000000000171
MCA: Global Cap 0x0000000000000105, Status 0x0000000000000000
MCA: Vendor "AuthenticAMD", ID 0x20fc2, APIC ID 0
MCA: CPU 0 COR OVER ICACHE L1 EVICT error

It is a correctable error, but given the nature of the panic I'd suspect a 
hardware problem.

mcelog doesn't provide many more details:

HARDWARE ERROR. This is *NOT* a software problem!
Please contact your hardware vendor
CPU 0 1 instruction cache 
       bit62 = error overflow (multiple errors)
  memory/cache error 'evict mem transaction, instruction transaction, level 1'
STATUS d000000000000171 MCGSTATUS 0
MCGCAP 105 APICID 0 SOCKETID 0 
CPUID Vendor AMD Family 15 Model 44

-- 
John Baldwin



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201101141613.14748.jhb>