[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-users] PCIPassthrough usb controller



Hi Chris,

I want to use Vt-d, of course. I've set up VGA passthrough just the same, and it's fine as far as I can tell. ;-)

regards,
Helmut


On 04.06.2010 19:24, chris wrote:
If you are using qemu for your passthrough that would be your
performance problem right there.... Did you try pvusb? VT-d?

- chris

On Fri, Jun 4, 2010 at 10:55 AM, Helmut Wieser<helmut.wieser@xxxxxxxx>  wrote:
Hi,

I used qemu-dm USB 1.1 passthrough to use a USB mouse on a windows XP domU.
I even installed the gplpv drivers, but performance is still lacking.
Next I wanted to passthrough the whole USB controller using PCI passthrough,
as described here http://wiki.xensource.com/xenwiki/XenUSBPassthrough.
I've hidden the PCI devices using xen-pciback.hide kernel parameters.

I'm running xen-4.0.0 STABLE on a 2.6.31.13 and debian 2.6.32-5-xen-amd64
kernels, same error happens on both.

xm pci-list-assignable-devices gives
0000:0f:00.0
0000:00:1a.0
0000:00:1a.1

Where 00:1a are the two USB controllers I want to pass through.
See here:
lspci -nn|grep USB
00:1a.0 USB Controller [0c03]: Intel Corporation 82801JI (ICH10 Family) USB
UHCI Controller #4 [8086:3a37]
00:1a.1 USB Controller [0c03]: Intel Corporation 82801JI (ICH10 Family) USB
UHCI Controller #5 [8086:3a38]
(....)

The domU fails to come up, here's the qemu-dm log:
domid: 1
config qemu network with xen bridge for  tap1.0 eth0
Watching /local/domain/0/device-model/1/logdirty/cmd
Watching /local/domain/0/device-model/1/command
char device redirected to /dev/pts/1
qemu_map_cache_init nr_buckets = 10000 size 4194304
shared page at pfn feffd
buffered io page at pfn feffb
Guest uuid = a0fd678b-5d01-7a2a-cc3b-8299b25201e1
Time offset set 0
Register xen platform.
Done register platform.
platform_fixed_ioport: changed ro/rw state of ROM memory area. now is rw
state.
xs_read(/local/domain/0/device-model/1/xen_extended_power_mgmt): read error
medium change watch on `hdc' (index: 1): /dev/cdrom
I/O request not ready: 0, ptr: 0, port: 0, data: 0, count: 0, size: 0
Log-dirty: no command yet.
xs_read(/local/domain/1/log-throttling): read error
qemu: ignoring not-understood drive `/local/domain/1/log-throttling'
medium change watch on `/local/domain/1/log-throttling' - unknown device,
ignored
dm-command: hot insert pass-through pci dev
register_real_device: Assigning real physical device 00:1a.1 ...
register_real_device: Enable MSI translation via per device option
register_real_device: Disable power management
pt_iomul_init: Error: pt_iomul_init can't open file /dev/xen/pci_iomul: No
such file or directory: 0x0:0x1a.0x1
pt_register_regions: IO region registered (size=0x00000020
base_addr=0x0000d021)
pci_intx: intx=2
register_real_device: Real physical device 00:1a.1 registered successfuly!
IRQ type = INTx
pt_ioport_map: e_phys=c200 pio_base=d020 len=32 index=4 first_map=1
platform_fixed_ioport: changed ro/rw state of ROM memory area. now is rw
state.
platform_fixed_ioport: changed ro/rw state of ROM memory area. now is ro
state.

I haven't tried using pci-stub yet, but I don't think the result will be
different. What's the problem here?
My domU works (more or less ;-) )fine without those two PCI devices passed
through.

regards,
Helmut

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users


_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.