netdev - Re: 2.6.24 BUG: soft lockup

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]

Message-Id: <20080327.183844.74572930.davem@davemloft.net>
Date:	Thu, 27 Mar 2008 18:38:44 -0700 (PDT)
From:	David Miller <davem@...emloft.net>
To:	herbert@...dor.apana.org.au
Cc:	Matheos.Worku@....COM, jesse.brandeburg@...el.com,
	jarkao2@...il.com, netdev@...r.kernel.org, hadi@...erus.ca
Subject: Re: 2.6.24 BUG: soft lockup - CPU#X

From: Herbert Xu <herbert@...dor.apana.org.au>
Date: Fri, 28 Mar 2008 09:22:34 +0800

> @@ -187,6 +187,10 @@ void __qdisc_run(struct net_device *dev)
>  	do {
>  		if (!qdisc_restart(dev))
>  			break;
> +		if (need_resched()) {
> +			netif_schedule(dev);
> +			break;
> +		}
>  	} while (!netif_queue_stopped(dev));
>  
>  	clear_bit(__LINK_STATE_QDISC_RUNNING, &dev->state);

This runs from softirqs, the local thread's scheduling
state is updated from timers which also run from softirqs,
so this need_resched() test won't work.

Probably you'll need something similar to the ->poll()
NAPI breakout logic, which uses 2 jiffies as the breakout
point.  (it uses 2, because we could be very close to
transitioning to the next jiffie and thus don't want
to breakout prematurely in that case)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html