similar to: Problem passing an SR-IOV function to a PV domU

Hi , I am testing pcifront on freebsd domU using following sound card [ Cirrus Logic CS 4614/22/24 [CrystalClear SoundFusion Audio Accelerator] Following sound driver is used for this sound card on Freebsd: *snd_csa*-- Crystal Semiconductor CS461x/462x/4280 PCI bridge device driver I am able to detect the card. pci3: <PCI bus> on pcib3 csa0: <CS4280/CS4614/CS4622/CS4624/CS4630> mem

Hi gurus, I used xen 4.1.0 (64bit) + dom0 kernel 2.6.32.39 (32bit) + domu kernel 2.6.32.39 (32bit) environment. I was trying to passthru Broadcom NIC to domu. The NIC can be UP but not RUNNING, on domu #ifconfig eth0 eth0 Link encap:Ethernet HWaddr 00:10:18:95:25:90 inet addr:10.0.0.3 Bcast:10.0.255.255 Mask:255.255.0.0 UP BROADCAST MULTICAST MTU:1500 Metric:1

Signed-off-by: Yinghai Lu <yinghai at kernel.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk at oracle.com> Cc: virtualization at lists.linux-foundation.org --- drivers/pci/xen-pcifront.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 966abc6..c90835f 100644 --- a/drivers/pci/xen-pcifront.c +++

Signed-off-by: Yinghai Lu <yinghai at kernel.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk at oracle.com> Cc: virtualization at lists.linux-foundation.org --- drivers/pci/xen-pcifront.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 966abc6..c90835f 100644 --- a/drivers/pci/xen-pcifront.c +++

When destroying pcifront/pciback, the following message appears in the guest linux kernel log. WARNING: g.e. still in use! WARNING: leaking g.e. and page still in use! This is caused by the wrong disconnect procedure that pcifront terminates the gnttab foreign access before pciback unmaps the ring. This patch corrects the handling of pcifront/pciback destruction sequence. Firstly pcifront

I've been looking for real-world examples of this for a long time -- mainly because I'm trying to decide whether to restrict my build-options to using only components which are all compatible with IOV. I'm thinking that the constraint would be worth it, if IOV could provide a significant performance benefit for non-network peripherals such as storage, video processing, etc. (compared

Use new PCI interfaces to simplify xen-pcifront implementation: 1) Use pci_create_root_bus() instead of pci_scan_bus_parented() because pci_scan_bus_parented() is marked as __deprecated.This also gets rid of a duplicated call of pci_bus_start_devices(). 2) Use pci_stop_root_bus() and pci_remove_root_bus() instead of open-coded private implementation. 3) Use pci_set_host_bridge_release()

Use new PCI interfaces to simplify xen-pcifront implementation: 1) Use pci_create_root_bus() instead of pci_scan_bus_parented() because pci_scan_bus_parented() is marked as __deprecated.This also gets rid of a duplicated call of pci_bus_start_devices(). 2) Use pci_stop_root_bus() and pci_remove_root_bus() instead of open-coded private implementation. 3) Use pci_set_host_bridge_release()

Use new PCI interfaces to simplify xen-pcifront implementation: 1) Use pci_create_root_bus() instead of pci_scan_bus_parented() because pci_scan_bus_parented() is marked as __deprecated.This also gets rid of a duplicated call of pci_bus_start_devices(). 2) Use pci_stop_root_bus() and pci_remove_root_bus() instead of open-coded private implementation. 3) Use pci_set_host_bridge_release()

Greetings, Following patches add SR-IOV capability support to the Linux kernel. With these patches, people can turn a PCI device with the capability into multiple ones from software perspective. [PATCH 1/4 v2] PCI: introduce new base functions [PATCH 2/4 v2] PCI: support ARI capability [PATCH 3/4 v2] PCI: support SR-IOV capability [PATCH 4/4 v2] PCI: document the change Thanks to Randy Dunlap

Greetings, Patches to support Single Root I/O Virtualization (SR-IOV) capability are available for the Linux 2.6 development tree. KVM and Xen supports will come soon! --- Single Root I/O Virtualization (SR-IOV) capability defined by PCI-SIG is intended to enable multiple system software to share PCI hardware resources. PCI device that supports this capability can be extended to one Physical

Hi, We recently purchased some HP Gen8 servers with Broadcom BCM57810 NIC controllers. I am running CentOS 6.2 on these servers configured as KVM hosts. Has anyone gotten the Broadcom chips to run with SR-IOV on CentOS 6.2? Any clues on how to get it working? I see from the Broadcom glossy marketing docs that this chip supports SR-IOV, but I cannot find a procedure for configuring it. The

Hi all, I''ve fetched the xen 4.0.1 source from the usual spot and have git''d the stable dom0 source (recently) from the jeremy repository, have successfully built and installed each of these on my VT-x and VT-d capable x86_64 system, over a fedora 14 installation. Most of the features seem to be running just fine, but I''m having a real problem getting the virtual

Hello, Is there a HowTo or tutorial about the configuration of VMDq or SR-IOV with XEN? Thanks in advance. Best Regards, -- Houssem MEDHIOUB Research Engineer TELECOM & Management SudParis _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users

I''m currently unable to make it fully work. If there are successes out there that are willing to share config, etc, I''d really like to compare. My current efforts: o physical nics mapped to linux HVM guests work, get network access o virtual nics (sr-iov functions) get mapped to linux HVM guests, report link up, but do not get network access (IRQ black hole??) Does

Hi, (Already asked this on the intel wired forum: http://communities.intel.com/message/185413#185413 but some of those questiones are XEN specific, which might be why theres no response ;-) I have doubts if SR-IOV will provide the required features compared to nPAR. SR-IOV seems more flexible, but I''m not sure if performance and features are the same as nPAR. Servers will be Dell M620

On 08/28/2013 05:25 AM, Brian Rak wrote: > If I'm using the SR-IOV Pool assignment method (from > http://wiki.libvirt.org/page/Networking#Assignment_from_a_pool_of_SRIOV_VFs_in_a_libvirt_.3Cnetwork.3E_definition > ), how would I check how many virtual functions are already in use? Hi Brian Hope the following can help you. [root@sriov2 images]# virsh net-dumpxml hostnet

Hi all. I'm try to find answer for my qustion in google, but i can't. if i use openvswitch virtualport in domain and want to use sr-iov does it possible? Or if i use sr-iov traffic not goes to openvswitch? -- Vasiliy Tolstov, e-mail: v.tolstov@selfip.ru jabber: vase@selfip.ru

On 10/23/2013 05:17 PM, Vasiliy Tolstov wrote: > Hi all. I'm try to find answer for my qustion in google, but i can't. > > if i use openvswitch virtualport in domain and want to use sr-iov does > it possible? Or if i use sr-iov traffic not goes to openvswitch? > What do you mean by "use sr-iov"? If you mean directly assigning an SRIOV virtual function to a guest

Hi, This is regarding SRIOV in Rhel7. I have added intel_iommu=on in grub.cfg file. When I attach Virtual Function to VM and I try to poweron the VM, I get the below error: [root@Dell-Rhel7 ~]# virsh start rhel64x64GA error: Failed to start domain rhel64x64GA error: internal error: early end of file from monitor: possible problem: qemu-kvm: -device