From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 50F3AA0545 for ; Wed, 10 Aug 2022 16:11:07 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id DF9A74068E; Wed, 10 Aug 2022 16:11:06 +0200 (CEST) Received: from relay162.nicmail.ru (relay162.nicmail.ru [91.189.117.6]) by mails.dpdk.org (Postfix) with ESMTP id 295214067C for ; Wed, 10 Aug 2022 16:11:05 +0200 (CEST) Received: from [10.28.138.152] (port=32242 helo=mail.nic.ru) by relay.hosting.mail.nic.ru with esmtp (Exim 5.55) (envelope-from ) id 1oLmQK-00081g-7a for users@dpdk.org; Wed, 10 Aug 2022 17:11:04 +0300 Received: from [10.28.137.175] (account sysman@scaled.cloud HELO mail.nic.ru) by incarp1104.mail.hosting.nic.ru (Exim 5.55) with id 1oLmQK-0001SN-8m for users@dpdk.org; Wed, 10 Aug 2022 17:11:04 +0300 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit Date: Wed, 10 Aug 2022 17:11:04 +0300 From: sysman@scaled.cloud To: users@dpdk.org Subject: Re: How to resolve "Not all devices in IOMMU group bound to VFIO or unbound" ? In-Reply-To: <20220810065525.204e1901@hermes.local> References: <99e01fff837b85c1126ef0a235078fc3@scaled.cloud> <20220810065525.204e1901@hermes.local> User-Agent: Roundcube Webmail/1.4.12 Message-ID: X-Sender: sysman@scaled.cloud X-KLMS-AntiSpam-Auth: dkim=none X-MS-Exchange-Organization-SCL: -1 X-BeenThere: users@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK usage discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: users-bounces@dpdk.org Hello! "The best workaround if possible is to use a different NIC for eth0." Can I ask u, please, explain with more words what I'm need to do ? Thanks! Stephen Hemminger писал 2022-08-10 16:55: > On Wed, 10 Aug 2022 16:52:39 +0300 > sysman@scaled.cloud wrote: > >> Hello! >> >> I have built and deployed latest DPDK from the git, so: >> >> dpdk-devbind.py -s >> >> Network devices using DPDK-compatible driver >> ============================================ >> 0000:02:04.0 '82545EM Gigabit Ethernet Controller (Copper) 100f' >> drv=vfio-pci unused=e1000 >> 0000:02:05.0 '82545EM Gigabit Ethernet Controller (Copper) 100f' >> drv=vfio-pci unused=e1000 >> 0000:02:06.0 '82545EM Gigabit Ethernet Controller (Copper) 100f' >> drv=vfio-pci unused=e1000 >> 0000:02:07.0 '82545EM Gigabit Ethernet Controller (Copper) 100f' >> drv=vfio-pci unused=e1000 >> >> Network devices using kernel driver >> =================================== >> 0000:02:01.0 '82545EM Gigabit Ethernet Controller (Copper) 100f' >> if=eth0 >> drv=e1000 unused=vfio-pci *Active* >> >> >> >> ./ipv4_multicast >> ... >> EAL: 0000:02:04.0 VFIO group is not viable! Not all devices in IOMMU >> group bound to VFIO or unbound >> EAL: Requested device 0000:02:04.0 cannot be used >> EAL: 0000:02:05.0 VFIO group is not viable! Not all devices in IOMMU >> group bound to VFIO or unbound >> EAL: Requested device 0000:02:05.0 cannot be used >> EAL: 0000:02:06.0 VFIO group is not viable! Not all devices in IOMMU >> group bound to VFIO or unbound >> EAL: Requested device 0000:02:06.0 cannot be used >> EAL: 0000:02:07.0 VFIO group is not viable! Not all devices in IOMMU >> group bound to VFIO or unbound >> EAL: Requested device 0000:02:07.0 cannot be used >> ... >> >> >> root@devuan4-sysman:~# readlink >> "/sys/bus/pci/devices/0000:02:04.0/iommu_group" >> ../../../../kernel/iommu_groups/5 >> root@devuan4-sysman:~# readlink >> "/sys/bus/pci/devices/0000:02:05.0/iommu_group" >> ../../../../kernel/iommu_groups/5 >> root@devuan4-sysman:~# readlink >> "/sys/bus/pci/devices/0000:02:06.0/iommu_group" >> ../../../../kernel/iommu_groups/5 >> root@devuan4-sysman:~# readlink >> "/sys/bus/pci/devices/0000:02:07.0/iommu_group" >> ../../../../kernel/iommu_groups/5 >> >> >> >> Can someone, please, help me resolve this problem? > > Can't really be fixed in software, the IOMMU groups come from the > hardware. > The best workaround if possible is to use a different NIC for eth0.