From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37430) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Zcyy8-0003mM-MS for qemu-devel@nongnu.org; Fri, 18 Sep 2015 12:57:05 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Zcyy7-00024x-4m for qemu-devel@nongnu.org; Fri, 18 Sep 2015 12:57:04 -0400 Received: from mail-pa0-x22c.google.com ([2607:f8b0:400e:c03::22c]:33471) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Zcyy6-00024J-Q1 for qemu-devel@nongnu.org; Fri, 18 Sep 2015 12:57:03 -0400 Received: by pacex6 with SMTP id ex6so55984080pac.0 for ; Fri, 18 Sep 2015 09:57:01 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: References: From: Yingshiuan Pan Date: Sat, 19 Sep 2015 00:56:42 +0800 Message-ID: Content-Type: multipart/alternative; boundary=001a11380fd8ab78340520086b00 Subject: Re: [Qemu-devel] [PATCH v3 0/3] virtio-mmio: introduce eventfd support List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Maydell Cc: Pavel Fedin , QEMU Developers , mst@redhat.com --001a11380fd8ab78340520086b00 Content-Type: text/plain; charset=UTF-8 Hi Peter, I think this patch set was already merged by Michael in Jun. :). http://git.qemu.org/?p=qemu.git;a=commit;h=434027badb421863b85ffdb4769966533c001cfa -- Best Regards, Yingshiuan Pan 2015-09-19 0:24 GMT+08:00 Peter Maydell : > On 12 May 2015 at 09:10, Pavel Fedin wrote: > > This patch set introduces eventfd support for virio-mmio. It was > originally > > published by Ying-Shiuan Pan but never got it to upstream: > > https://lists.gnu.org/archive/html/qemu-devel/2014-02/msg00715.html > > I have updated and successfully tested it with vhost-net. I confirm > that this > > solution significantly improves the network performance even without > irqfd. > > I would like to upstream it, since virtio-mmio is still there. I know > that > > some of you consider it deprecated, however i believe this is not > entirely > > true. Because you can add it to machine models which are not supposed to > > have PCI (like vexpress). > > An old patch set relied on additional "eventfd" option in order to > disable > > the support if not implemented in kernel. My version simply checks > > kvm_eventfds_enabled() for this purpose, so backwards compatibility is > much > > better. > > I decided to leave this set in three parts because ioeventfd support > should > > be enabled only when both host and guest notifiers are in place. I > believe > > it will not work with partial implementation, at least because vhost-net > > requires both sets of eventfds. In this version i added correct reset > handling. > > Hi Pavel. I've been going through my to-review folder and found this > series from back in May lurking in it. Sorry I never got to reviewing it. > Do you think it's still a change worth having? If so, please can you > rebase and resend and I'll look at it this time around. > > thanks > -- PMM > --001a11380fd8ab78340520086b00 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable
Hi Peter,

I think this patch set was al= ready merged by Michael in Jun. :).
--
Best Regards,
Yingshiuan= Pan

2015-09-19 0:24 GMT+08:00 Peter Maydell <peter.maydell@linaro.org>:
On = 12 May 2015 at 09:10, Pavel Fedin <p.fedin@samsung.com> wrote:
>=C2=A0 This patch set introduces eventfd support for virio-mmio. It was= originally
> published by Ying-Shiuan Pan but never got it to upstream:
> https://lists.gnu.org/archiv= e/html/qemu-devel/2014-02/msg00715.html
>=C2=A0 I have updated and successfully tested it with vhost-net. I conf= irm that this
> solution significantly improves the network performance even without i= rqfd.
>=C2=A0 I would like to upstream it, since virtio-mmio is still there. I= know that
> some of you consider it deprecated, however i believe this is not enti= rely
> true. Because you can add it to machine models which are not supposed = to
> have PCI (like vexpress).
>=C2=A0 An old patch set relied on additional "eventfd" option= in order to disable
> the support if not implemented in kernel. My version simply checks
> kvm_eventfds_enabled() for this purpose, so backwards compatibility is= much
> better.
>=C2=A0 I decided to leave this set in three parts because ioeventfd sup= port should
> be enabled only when both host and guest notifiers are in place. I bel= ieve
> it will not work with partial implementation, at least because vhost-n= et
> requires both sets of eventfds. In this version i added correct reset = handling.

Hi Pavel. I've been going through my to-review folder and found = this
series from back in May lurking in it. Sorry I never got to reviewing it. Do you think it's still a change worth having? If so, please can you rebase and resend and I'll look at it this time around.

thanks
-- PMM

--001a11380fd8ab78340520086b00--