Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 01 May 2014 17:48:22 -0600
From:      Ian Lepore <ian@FreeBSD.org>
To:        Boris Samorodov <bsam@passap.ru>
Cc:        freebsd-arm@FreeBSD.org
Subject:   Re: wandboard-quad (IO related?): Spurious interrupt detected [0x000003ff]
Message-ID:  <1398988102.22079.146.camel@revolution.hippie.lan>
In-Reply-To: <5362BCBE.7050703@passap.ru>
References:  <5362BCBE.7050703@passap.ru>

next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 2014-05-02 at 01:29 +0400, Boris Samorodov wrote:
> Hi All,
> 
> I get "Spurious interrupt detected [0x000003ff]" at current system:
> -----
> % uname -a
> FreeBSD wandboard 11.0-CURRENT FreeBSD 11.0-CURRENT #5 r265089M: Thu May
>  1 16:48:06 SAMT 2014
> bsam@wandboard:/usr/obj/usr/src/sys/WANDBOARD-QUAD  arm
> -----
> 
> Those messages appear at hard IO (CD read/write, network - iperf).
> Seems no harm so far. Should I ignore or diagnose them deeper?
> 
> Thanks.

They are not harmful, and it's baffling to me why sometimes you get tons
of them, other times hardly any at all.  It's actually normal and
expected to get some on a multi-core system, because two cores may try
to respond to a pending interrupt at the same time, and the interrupt
controller will dispatch the actual interrupt to one of the cores and
the spurious-interrupt 3ff number to the other core.

So what we really need to be doing in the code is complaining if a whole
lot of them are happening (it might indicate some device driver is
misbehaving) but ignore the occasional one.

-- Ian





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1398988102.22079.146.camel>