linux-kernel - Re: [PATCH,RFC] RCU-based detection of stalled CPUs for Classic RCU

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 2 Oct 2008 10:07:26 +0200
From:	Ingo Molnar <mingo@...e.hu>
To:	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Cc:	linux-kernel@...r.kernel.org, akpm@...ux-foundation.org,
	mathieu.desnoyers@...ymtl.ca, laijs@...fujitsu.com,
	manfred@...orfullife.com, dipankar@...ibm.com, niv@...ibm.com,
	dvhltc@...ibm.com, josht@...ux.vnet.ibm.com
Subject: Re: [PATCH,RFC] RCU-based detection of stalled CPUs for Classic RCU


* Paul E. McKenney <paulmck@...ux.vnet.ibm.com> wrote:

> Hello!
> 
> This patch adds stalled-CPU detection to Classic RCU.  This capability 
> is enabled by a new config variable CONFIG_RCU_CPU_STALL_DETECTOR, 
> which defaults disabled.  This is a debugging feature, not something 
> that non-kernel-hackers would be expected to care about.  This feature 
> can detect looping CPUs in !PREEMPT builds and looping CPUs with 
> preemption disabled in PREEMPT builds.  This is essentially a port of 
> this functionality from the treercu patch.
> 
> One current shortcoming: on some systems, stalls are detected during 
> early boot, when we normally would not care about them.  My thought is 
> to add a call from late initialization to suppress stall detection 
> until the system is well along its way to being booted, but thought I 
> should check to see if there might already be something for this 
> purpose.

could you be a bit more specific, why do those warnings show up and why 
dont we care about them? There are things like networking that 
occasionally do an rcu_sync() and a stall could mean a bootup hang.

> (Currently against 2.6.27-rc8, FYI.)
> 
> Thoughts?
> 
> Signed-off-by: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>

i think this is a very good idea in general - often the question comes 
up whether a hang seen in the RCU code is indeed caused by RCU or other 
factors. Could you perhaps rebase it against tip/core/rcu ? [or 
tip/master for convenience]

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/