similar to: [RFC] kvmtool: add support for modern virtio-pci

From: Asias He <asias.hejun at gmail.com> This patch is based on Sasha's 'kvm tools: Add support for virtio-mmio' patch. ioeventfds support is added which was missing in the previous one. VQ size/align is still not supported. It adds support for the new virtio-mmio transport layer added in 3.2-rc1. The purpose of this new layer is to allow virtio to work on systems which

From: Asias He <asias.hejun at gmail.com> This patch is based on Sasha's 'kvm tools: Add support for virtio-mmio' patch. ioeventfds support is added which was missing in the previous one. VQ size/align is still not supported. It adds support for the new virtio-mmio transport layer added in 3.2-rc1. The purpose of this new layer is to allow virtio to work on systems which

On 09/21/2014 04:09 AM, Michael S. Tsirkin wrote: >> The virtio 0.9.5 spec says that ISR is "unused" when in MSI-X mode. I >> > don't think that you can depend on the device to set the configuration >> > changed bit. >> > The virtio 1.0 spec seems to have fixed that. > Yes, virtio 0.9.5 has this bug. But in practice qemu always set this > bit,

On 09/21/2014 04:09 AM, Michael S. Tsirkin wrote: >> The virtio 0.9.5 spec says that ISR is "unused" when in MSI-X mode. I >> > don't think that you can depend on the device to set the configuration >> > changed bit. >> > The virtio 1.0 spec seems to have fixed that. > Yes, virtio 0.9.5 has this bug. But in practice qemu always set this > bit,

This patch adds support for the new virtio-mmio transport layer added in 3.2-rc1. The purpose of this new layer is to allow virtio to work on systems which don't necessarily support PCI, such as embedded systems. To apply the patch on top of the KVM tools tree, you must first pull Linus' tree on top. Also, CONFIG_VIRTIO_MMIO=y should be set in the guest kernel. This is an early RFC,

This patch adds support for the new virtio-mmio transport layer added in 3.2-rc1. The purpose of this new layer is to allow virtio to work on systems which don't necessarily support PCI, such as embedded systems. To apply the patch on top of the KVM tools tree, you must first pull Linus' tree on top. Also, CONFIG_VIRTIO_MMIO=y should be set in the guest kernel. This is an early RFC,

On 09/21/2014 11:02 AM, Michael S. Tsirkin wrote: > On Sun, Sep 21, 2014 at 09:47:51AM -0400, Sasha Levin wrote: >> > On 09/21/2014 04:09 AM, Michael S. Tsirkin wrote: >>>> > >> The virtio 0.9.5 spec says that ISR is "unused" when in MSI-X mode. I >>>>> > >> > don't think that you can depend on the device to set the

On 09/21/2014 11:02 AM, Michael S. Tsirkin wrote: > On Sun, Sep 21, 2014 at 09:47:51AM -0400, Sasha Levin wrote: >> > On 09/21/2014 04:09 AM, Michael S. Tsirkin wrote: >>>> > >> The virtio 0.9.5 spec says that ISR is "unused" when in MSI-X mode. I >>>>> > >> > don't think that you can depend on the device to set the

On Sun, Sep 21, 2014 at 09:47:51AM -0400, Sasha Levin wrote: > On 09/21/2014 04:09 AM, Michael S. Tsirkin wrote: > >> The virtio 0.9.5 spec says that ISR is "unused" when in MSI-X mode. I > >> > don't think that you can depend on the device to set the configuration > >> > changed bit. > >> > The virtio 1.0 spec seems to have fixed

This is a patch based on Krishna Kumar's patch series which implements multiple VQ support for virtio-net. The patch was tested with ver3 of the patch. Cc: Krishna Kumar <krkumar2 at in.ibm.com> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: virtualization at lists.linux-foundation.org Cc: netdev at vger.kernel.org Signed-off-by:

This is a patch based on Krishna Kumar's patch series which implements multiple VQ support for virtio-net. The patch was tested with ver3 of the patch. Cc: Krishna Kumar <krkumar2 at in.ibm.com> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: virtualization at lists.linux-foundation.org Cc: netdev at vger.kernel.org Signed-off-by:

Hi, I am still trying to assign pci or usbs to a domU. I get to the point where pciback seizes the devices (5 usb and 2 pci). I modified the configuration of the domU with pci = [ ''00:1d.0'' , ''00:1d.1'' , ''00:1d.2'' , ''00:1d.3'' , ''00:1d.7'', ''02:01.0'' , ''02:02.0'' ] but

Hi, some more info which I collected during physically accessing the machine while rebooting. I was suprised that while it was not able to do anything it was not a ''static'' kernel panic, but the following text was scrolling continously thru the screen: """ ata3: port reset, p_is 1 is e pis 1 cmd c017 tf 50 ss 113 se 0 ata3: status=0x50 { DriveReady SeekComplete }

Hi Lists, sorry for reposting this, but since no response has arrived so far and my time on this project is passing by I need to make a conclusion. Do I better use my DVR cards in dom0 or moving it to a separate physical machine rather than using them in a domU? Could someone shed light on why it is trickier to pass-thru one of these cards than any other pci devices? Do they try to read-write

Hi Lists, sorry for reposting this, but since no response has arrived so far and my time on this project is passing by I need to make a conclusion. Do I better use my DVR cards in dom0 or moving it to a separate physical machine rather than using them in a domU? Could someone shed light on why it is trickier to pass-thru one of these cards than any other pci devices? Do they try to read-write

server:~# dmesg|grep pciback [ 0.000000] Kernel command line: root=/dev/hda1 ro console=tty0 pciback.permissive pciback.hide=(00:1d.00)(00:1d.01)(00:1d.07) [ 0.000000] Unknown boot option `pciback.permissive'': ignoring [ 1.210945] pciback 0000:00:1d.0: seizing device [ 1.211082] pciback 0000:00:1d.1: seizing device [ 1.211215] pciback 0000:00:1d.7: seizing device [

I''m having an issue forwarding through an Intel on-board graphics adapter. This is on a Dell Optiplex 780 with 8GB of RAM. The pass-through works perfectly fine if I have 2GB of RAM assigned to the HVM domU. If I try to assign 3GB or 4GB of RAM, I get the following on the console: [ 41.222073] br0: port 2(vif1.0) entering forwarding state [ 41.269854] (cdrom_add_media_watch()

I''m having an issue forwarding through an Intel on-board graphics adapter. This is on a Dell Optiplex 780 with 8GB of RAM. The pass-through works perfectly fine if I have 2GB of RAM assigned to the HVM domU. If I try to assign 3GB or 4GB of RAM, I get the following on the console: [ 41.222073] br0: port 2(vif1.0) entering forwarding state [ 41.269854] (cdrom_add_media_watch()

Hi there, I have a question regarding PCI passthrough on the Citrix XenServer 5.6 (Xen 3.4.2). I already managed to get some soundcard passed through to a Windows guest. So I think my knowledge about that topic isn''t _that_ low. But I cannot seem to pass through a SATA/PATA controller to a Linux guest. I have some additional CD/DVD burner (PATA) attached to a SATA/PATA controller

Hello everybody, I''m experiencing some problems while exporting a whole usb hub to my DomU. My Dom0 is a Debian Etch using Xen 3.2 and kernel 2.6.18-5-xen-686 SMP on an intel core 2 duo. My DomU is a CentOs 5.1 using same kernel. Both are 32 bits environnements. I''ve exported my Usb Hub, and a ethernet card, using the pciback.hide=(04:00.0)(00:1d.0) option to Dom0 kernel. I