From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:44119) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yptyg-0004pL-DH for qemu-devel@nongnu.org; Wed, 06 May 2015 03:42:47 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Yptyb-0008Td-ET for qemu-devel@nongnu.org; Wed, 06 May 2015 03:42:46 -0400 Received: from mailout3.w1.samsung.com ([210.118.77.13]:12479) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yptyb-0008T8-5a for qemu-devel@nongnu.org; Wed, 06 May 2015 03:42:41 -0400 Received: from eucpsbgm1.samsung.com (unknown [203.254.199.244]) by mailout3.w1.samsung.com (Oracle Communications Messaging Server 7.0.5.31.0 64bit (built May 5 2014)) with ESMTP id <0NNX002C7432NCA0@mailout3.w1.samsung.com> for qemu-devel@nongnu.org; Wed, 06 May 2015 08:42:38 +0100 (BST) Received: from fedinw7x64 ([106.109.131.169]) by eusync3.samsung.com (Oracle Communications Messaging Server 7.0.5.31.0 64bit (built May 5 2014)) with ESMTPA id <0NNX002F7432P430@eusync3.samsung.com> for qemu-devel@nongnu.org; Wed, 06 May 2015 08:42:38 +0100 (BST) From: Pavel Fedin Date: Wed, 06 May 2015 10:42:32 +0300 Message-id: <000501d087d0$39c1bd90$ad4538b0$@samsung.com> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7bit Content-language: ru Subject: [Qemu-devel] [PATCH 0/4] Introduce eventfd support for virtio-mmio List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Hello! I have updated and successfully tested an old patch set introducing eventfd support for virtio-mmio, enabling to use vhost-net with it: https://lists.gnu.org/archive/html/qemu-devel/2014-02/msg00715.html 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 confirm that this solution significantly improves the network performance even without using irqfd. Kind regards, Pavel Fedin Expert Engineer Samsung Electronics Research center Russia