Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752659AbbDPPbf (ORCPT ); Thu, 16 Apr 2015 11:31:35 -0400 Received: from thoth.sbs.de ([192.35.17.2]:41839 "EHLO thoth.sbs.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751434AbbDPPb0 (ORCPT ); Thu, 16 Apr 2015 11:31:26 -0400 Message-ID: <552FD5C9.2080702@siemens.com> Date: Thu, 16 Apr 2015 17:31:21 +0200 From: Jan Kiszka User-Agent: Mozilla/5.0 (X11; U; Linux i686 (x86_64); de; rv:1.8.1.12) Gecko/20080226 SUSE/2.0.0.12-1.1 Thunderbird/2.0.0.12 Mnenhy/0.7.5.666 MIME-Version: 1.0 To: Sebastian Andrzej Siewior , RT CC: Linux Kernel Mailing List , Steven Rostedt Subject: Re: [PATCH RT 3.18] ring-buffer: Mark irq_work as HARD_IRQ to prevent deadlocks References: <552FC1FE.4020406@siemens.com> <552FC6B1.1040000@linutronix.de> <552FC72A.8060709@siemens.com> <552FCDD3.2010804@linutronix.de> In-Reply-To: <552FCDD3.2010804@linutronix.de> Content-Type: text/plain; charset=iso-8859-15 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2071 Lines: 53 On 2015-04-16 16:57, Sebastian Andrzej Siewior wrote: > On 04/16/2015 04:28 PM, Jan Kiszka wrote: >> On 2015-04-16 16:26, Sebastian Andrzej Siewior wrote: >>> On 04/16/2015 04:06 PM, Jan Kiszka wrote: >>>> ftrace may trigger rb_wakeups while holding pi_lock which will also be >>>> requested via trace_...->...->ring_buffer_unlock_commit->...-> >>>> irq_work_queue->raise_softirq->try_to_wake_up. This quickly causes >>>> deadlocks when trying to use ftrace under -rt. >>>> >>>> Resolve this by marking the ring buffer's irq_work as HARD_IRQ. >>>> >>>> Signed-off-by: Jan Kiszka >>>> --- >>>> >>>> I'm not yet sure if this doesn't push work into hard-irq context that >>>> is better not done there on -rt. >>> >>> everything should be done in the soft-irq. >>> >>>> >>>> I'm also not sure if there aren't more such cases, given that -rt turns >>>> the default irq_work wakeup policy around. But maybe we are lucky. >>> >>> The only thing that is getting done in the hardirq is the FULL_NO_HZ >>> thingy. I would be _very_ glad if we could keep it that way. >> >> Then - to my current understanding - we need an NMI-safe trigger for >> soft-irq work. Is there anything like this existing already? Or can we >> still use the IPI-based kick without actually doing the work in hard-irq >> context? > > But if you trigger it via IPI it will still run in hardirq context, > right? Can you describe how run into this and try to think about it in > a quiet moment. It it just enabling the function tracer and running it? # trace-cmd record -e sched /sys/kernel/debug/tracing/events/sched/filter /sys/kernel/debug/tracing/events/*/sched/filter Hit Ctrl^C to stop recording ^C and you are dead(locked). Jan -- Siemens AG, Corporate Technology, CT RTC ITP SES-DE Corporate Competence Center Embedded Linux -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/