netdev - Re: [RFC PATCH V2] New Xen netback implementation

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: <1327948241.5553.44.camel@leeds.uk.xensource.com>
Date:	Mon, 30 Jan 2012 18:30:41 +0000
From:	Wei Liu <wei.liu2@...rix.com>
To:	Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>
CC:	<wei.liu2@...rix.com>, Ian Campbell <Ian.Campbell@...rix.com>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
	"xen-devel@...ts.xensource.com" <xen-devel@...ts.xensource.com>,
	"David Vrabel" <david.vrabel@...rix.com>,
	Paul Durrant <Paul.Durrant@...rix.com>
Subject: Re: [RFC PATCH V2] New Xen netback implementation

On Mon, 2012-01-30 at 18:27 +0000, Wei Liu (Intern) wrote:
> On Sun, 2012-01-29 at 21:37 +0000, Konrad Rzeszutek Wilk wrote:
> > 
> > Sure. I also did some testing with limiting the amount of CPUs and found
> > that 'xl vcpu-set 0 N' make netback not work anymore :-( 
> > > 
> > > 
> 
> I just played with vcpu-set a bit, and I can reproduced this problem.
> That's a race condition.
> 
> One possible fix is remove cond_resched() in the kernel thread. After
> removing that, it fixes the problem (at least for me).
> 
> 
> Wei.
> 
> --- a/drivers/net/xen-netback/netback.c
> +++ b/drivers/net/xen-netback/netback.c
> @@ -994,7 +994,7 @@ int xenvif_kthread(void *data)
>                 wait_event_interruptible(vif->wq,
>                                          rx_work_todo(vif) ||
>                                          kthread_should_stop());
> -               cond_resched();
> +               /* cond_resched(); */
>  
>                 if (kthread_should_stop())
>                         break;
> 
> 

Hmm... Here it comes again. Ignore this fix. It's more complicated than
I thought.


Wei.

--
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