From owner-freebsd-hackers@FreeBSD.ORG  Sun May 18 15:48:45 2014
Return-Path: <owner-freebsd-hackers@FreeBSD.ORG>
Delivered-To: freebsd-hackers@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115])
 (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits))
 (No client certificate requested)
 by hub.freebsd.org (Postfix) with ESMTPS id 278C77EA
 for <freebsd-hackers@freebsd.org>; Sun, 18 May 2014 15:48:45 +0000 (UTC)
Received: from bigwig.baldwin.cx (bigwig.baldwin.cx [IPv6:2001:470:1f11:75::1])
 (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits))
 (Client did not present a certificate)
 by mx1.freebsd.org (Postfix) with ESMTPS id 0017E2446
 for <freebsd-hackers@freebsd.org>; Sun, 18 May 2014 15:48:44 +0000 (UTC)
Received: from John-Baldwins-MacBook-Pro.local
 (CPE7cb21b17bdec-CM7cb21b17bde9.cpe.net.cable.rogers.com [99.241.40.247])
 by bigwig.baldwin.cx (Postfix) with ESMTPSA id 12AB3B941;
 Sun, 18 May 2014 11:48:43 -0400 (EDT)
Message-ID: <5378D65A.90905@FreeBSD.org>
Date: Sun, 18 May 2014 11:48:42 -0400
From: John Baldwin <jhb@FreeBSD.org>
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9;
 rv:24.0) Gecko/20100101 Thunderbird/24.5.0
MIME-Version: 1.0
To: Chris Torek <torek@torek.net>, freebsd-hackers@freebsd.org
Subject: Re: bad call to sched_bind() => hang, even with INVARIANTS
References: <201405151720.s4FHK8RC065430@elf.torek.net>
In-Reply-To: <201405151720.s4FHK8RC065430@elf.torek.net>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.7
 (bigwig.baldwin.cx); Sun, 18 May 2014 11:48:43 -0400 (EDT)
X-BeenThere: freebsd-hackers@freebsd.org
X-Mailman-Version: 2.1.18
Precedence: list
List-Id: Technical Discussions relating to FreeBSD
 <freebsd-hackers.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/options/freebsd-hackers>, 
 <mailto:freebsd-hackers-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-hackers/>
List-Post: <mailto:freebsd-hackers@freebsd.org>
List-Help: <mailto:freebsd-hackers-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-hackers>,
 <mailto:freebsd-hackers-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sun, 18 May 2014 15:48:45 -0000

On 5/15/14, 1:20 PM, Chris Torek wrote:
> I was poking around with a bhyve emulation, where the emulation
> has only one CPU but the real systems have more.
> 
> In our real-system code we had a sched_bind() that just assumed there
> were 2 or more CPUs, instead of just the 1.  This caused the entire
> system to hang.  (Note: using SCHED_ULE.)
> 
> It's not immediately obvious to me what went wrong "underneath" to
> cause the whole-system hang, but clearly it is wrong to attempt to
> pin a thread to a CPU that does not exist.  Should sched_bind()
> have a KASSERT in it to make sure that the cpu argument is
> sensible?  (Or maybe even something a little more aggressive?)

A KASSERT() is probably a good idea.

-- 
John Baldwin