All of lore.kernel.org
 help / color / mirror / Atom feed
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
To: topperxin <topperxin@126.com>
Cc: xen-devel <xen-devel@lists.xensource.com>
Subject: Re: 3GB memory restriction for pv domU with NIC PCI Passthrough
Date: Fri, 18 Apr 2014 09:28:02 -0400	[thread overview]
Message-ID: <20140418132802.GA4429@phenom.dumpdata.com> (raw)
In-Reply-To: <25bb480.3f1c.1456d73af21.Coremail.topperxin@126.com>

On Thu, Apr 17, 2014 at 10:11:09AM +0800, topperxin wrote:
> Hi 
>      We have to use 4.1.5 now.
>      Is it possible to fix in xen 4.1.5? 

No.
>      If possible, could you please tell me how to modify in xen 4.1.5?

You would need to backport the 'e820_hole' patches. I did post on the xen-devel
at some point an version of them: see

http://lists.xen.org/archives/html/xen-devel/2012-03/msg02134.html
and
http://lists.xen.org/archives/html/xen-devel/2012-03/msg02131.html

>      Thanks a lot.  
> At 2014-04-16 21:08:14,"Konrad Rzeszutek Wilk" <konrad.wilk@oracle.com> wrote:
> >On Wed, Apr 16, 2014 at 10:55:18AM +0800, topperxin wrote:
> >> 
> >> 
> >> Hi
> >>   I met the same problem that you have already talked about.
> >>   I assigned 28 vCPUs , 4G memory, Intel 82599 VF to a PV domU VM.
> >>   I can not see the intel 82599 VF from lspci.
> >>  The xen version is 4.1.5
> >
> >Right. This is fixed in Xen 4.3. Please try that.
> >
> >>  please refer to the dmesg:
> >> =========================================================
> >> [    3.540273] pcifront pci-0: PCI host bridge to bus 0000:00
> >> [    3.540280] pci_bus 0000:00: root bus resource [io  0x0000-0xffff]
> >> [    3.540285] pci_bus 0000:00: root bus resource [mem 0x00000000-0x3fffffffffff]
> >> [    3.540291] pci_bus 0000:00: root bus resource [bus 00-ff]
> >> [    3.541343] pci 0000:00:00.3: [8086:10ed] type 00 class 0x020000
> >> [    3.542147] pci 0000:00:00.3: reg 0x10: [mem 0xdf904000-0xdf907fff 64bit]
> >> [    3.542816] pci 0000:00:00.3: reg 0x1c: [mem 0xdfa04000-0xdfa07fff 64bit]
> >> [    3.545523] pcifront pci-0: New device on 0000:00:00.3 found.
> >> [    3.551644] pcifront pci-0: claiming resource 0000:00:00.3/0
> >> [    3.551657] pci 0000:00:00.3: address space collision: [mem 0xdf904000-0xdf907fff 64bit] conflicts with System RAM [mem 0x00100000-0xffffffff]
> >> [    3.551662] pcifront pci-0: Could not claim resource 0000:00:00.3/0! Device offline. Try using e820_host=1 in the guest config.
> >> [    3.551682] pcifront pci-0: claiming resource 0000:00:00.3/3
> >> [    3.551688] pci 0000:00:00.3: address space collision: [mem 0xdfa04000-0xdfa07fff 64bit] conflicts with System RAM [mem 0x00100000-0xffffffff]
> >> [    3.551692] pcifront pci-0: Could not claim resource 0000:00:00.3/3! Device offline. Try using e820_host=1 in the guest config.
> >> [    3.743814] microcode: CPU19 sig=0x206d7, pf=0x1, revision=0x70a
> >> [    3.750305] microcode: CPU20 sig=0x206d7, pf=0x1, revision=0x70a
> >> [    3.756410] microcode: CPU21 sig=0x206d7, pf=0x1, revision=0x70a
> >> [    3.761506] ixgbevf: Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver - version 2.7.12-k
> >> [    3.761513] ixgbevf: Copyright (c) 2009 - 2012 Intel Corporation.
> >> [    3.761650] ixgbevf 0000:00:00.3: device not available (can't reserve [mem 0xdf904000-0xdf907fff 64bit])
> >> [    3.761684] ixgbevf: probe of 0000:00:00.3 failed with error -22
> >> =========================================================
> >> 
> >> 
> >> At 2014-04-15 18:43:30,"Konrad Rzeszutek Wilk" <konrad.wilk@oracle.com> wrote:
> >> >On Tue, Apr 15, 2014 at 04:15:53PM +0800, topperxin wrote:
> >> >> Hi list
> >> >>      These I'm checking PCI Passthrough to PV domU, and I found when the memory larger than 3G, the PCI passthrough will not successfully. I got some information from the google. Some guys said it's a bug, and has already fixed, Why do I still meet this problem? What should I do?
> >> >
> >> >It should be fixed. Did you find any issues when doing PCI passthrough?
> >> >
> >> >> 
> >> >> 
> >> >> please refer to :
> >> >> 
> >> >> 
> >> >> http://bugzilla.xensource.com/bugzilla/show_bug.cgi?id=1673
> >> >> Bug 1673 - 3GB memory restriction for pv domU with PCI
> >> >> 
> >> >> 
> >> >> Thanks a lot.
> >> >
> >> >> _______________________________________________
> >> >> Xen-devel mailing list
> >> >> Xen-devel@lists.xen.org
> >> >> http://lists.xen.org/xen-devel
> >> >

      reply	other threads:[~2014-04-18 13:28 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-04-15  8:15 3GB memory restriction for pv domU with NIC PCI Passthrough topperxin
2014-04-15  9:04 ` George Dunlap
2014-04-15 10:43 ` Konrad Rzeszutek Wilk
2014-04-16  2:55   ` topperxin
2014-04-16 13:08     ` Konrad Rzeszutek Wilk
2014-04-17  2:11       ` topperxin
2014-04-18 13:28         ` Konrad Rzeszutek Wilk [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140418132802.GA4429@phenom.dumpdata.com \
    --to=konrad.wilk@oracle.com \
    --cc=topperxin@126.com \
    --cc=xen-devel@lists.xensource.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.