netdev - Re: [Xen-devel] [PATCH net-next V3 2/3] xen-netfront: split event channels support for Xen frontend driver

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: <CAOsiSVUHqezpo4u+Go1pm4vm7Hots2gDUJ9YEzVK7_FPSc3zLA@mail.gmail.com>
Date:	Wed, 22 May 2013 21:38:20 +0100
From:	Wei Liu <liuw@...w.name>
To:	annie li <annie.li@...cle.com>
Cc:	Wei Liu <wei.liu2@...rix.com>,
	Ian Campbell <ian.campbell@...rix.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
	"xen-devel@...ts.xen.org" <xen-devel@...ts.xen.org>,
	David Vrabel <david.vrabel@...rix.com>,
	jbeulich <jbeulich@...e.com>
Subject: Re: [Xen-devel] [PATCH net-next V3 2/3] xen-netfront: split event
 channels support for Xen frontend driver

On Wed, May 22, 2013 at 9:35 PM, annie li <annie.li@...cle.com> wrote:
>
> On 2013-5-22 16:20, Wei Liu wrote:
>>
>> On Wed, May 22, 2013 at 8:32 PM, annie li <annie.li@...cle.com> wrote:
>>>
>>>
>>> Originally, netfront protects access to rx shared-ring with tx_lock, you
>>> remove this protection here. It is better to protect the ring access by a
>>> sperate rx_lock then.
>>>
>> TX ring and RX ring are separate rings. I don't think that comment / code
>> makes sense any more. My stress test confirms that.
>
>
> Yes, they are separate rings. Actually I am not sure why
> RING_HAS_UNCONSUMED_RESPONSES(&np->rx) is protected by any tx_lock
> originally. But for xennet_rx_interrupt, it is better to use rx_lock to
> protect RING_HAS_UNCONSUMED_RESPONSES(&np->rx).
>

This doesn't make sense to me either. Xen ring protocol is designed to
be lock-free.
And in netfront's case there is no concurrent access to the ring.


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