On Tuesday 25 September 2007, Rusty Russell wrote:
> On Tue, 2007-09-25 at 00:18 +0200, Arnd Bergmann wrote:
> > This is a pattern I've seen a few times before, but could never understand
> > what it's good for. What is your reason for defining a new data structure
> > that is used only once, inste
These patches enable memory mapped TPR shadow (FlexPriority).
Since TPR is accessed very frequently by 32bit Windows, especially SMP
guest, with FlexPriority enabled, we saw significant performance gain.
The issue is: FlexPriority needs to add a memory slot to the vm to make
shadow work with APIC
On Tue, Sep 25, 2007 at 12:11:15PM +1000, Rusty Russell wrote:
> On Mon, 2007-09-24 at 18:57 -0700, Greg KH wrote:
> > On Tue, Sep 25, 2007 at 10:50:04AM +1000, Rusty Russell wrote:
> > > Not sure why I need the modalias here when it's in sysfs. But, it
> > > works.
> >
> > udev does not read fro
The attachment is the .config I am using now.
And one more difference is in our testing most guests are created with qcow
images.
Thanks
Yunfeng
>-Original Message-
>From: Avi Kivity [mailto:[EMAIL PROTECTED]
>Sent: 2007年9月25日 0:13
>To: Zhao, Yunfeng
>Cc: Laurent Vivier; kvm-devel@lists.
On Mon, 2007-09-24 at 18:57 -0700, Greg KH wrote:
> On Tue, Sep 25, 2007 at 10:50:04AM +1000, Rusty Russell wrote:
> > Not sure why I need the modalias here when it's in sysfs. But, it
> > works.
>
> udev does not read from sysfs anymore, it just uses the environment
> variables. It's faster and
On Tue, Sep 25, 2007 at 10:50:04AM +1000, Rusty Russell wrote:
> On Mon, 2007-09-24 at 09:02 -0700, Greg KH wrote:
> > On Mon, Sep 24, 2007 at 07:16:34PM +1000, Rusty Russell wrote:
> > > This adds the logic to convert the virtio ids into module aliases, and
> > > includes a modalias entry in sysfs
Hi,
On 24/09/2007, Dan Kenigsberg <[EMAIL PROTECTED]> wrote:
> As with previous "Takes" of this patch, its purpose is to expose host
> CPU features to guests. It proved rather helpful to KVM in various
> benchmarks, and it should similarly speed kqemu up. Note that it does
> not extend the set of
On Mon, 2007-09-24 at 09:02 -0700, Greg KH wrote:
> On Mon, Sep 24, 2007 at 07:16:34PM +1000, Rusty Russell wrote:
> > This adds the logic to convert the virtio ids into module aliases, and
> > includes a modalias entry in sysfs.
> >
> > Unfortunately this does not seem sufficient to have the modu
On Mon, 2007-09-24 at 15:44 +0200, Dor Laor wrote:
> Seems like there is a problem with shared irq line, the interrupt
> handler always returns IRQ_HANDLED (except for the trivial case
> were the callback is null).
>
> It can be solved by having a host irq counter (in the shared ring) and
> a guest
On Tue, 2007-09-25 at 00:18 +0200, Arnd Bergmann wrote:
> On Monday 24 September 2007, Rusty Russell wrote:
> > This attempts to implement a "virtual I/O" layer which should allow
> > common drivers to be efficiently used across most virtual I/O
> > mechanisms. It will no-doubt need further enhanc
On Monday 24 September 2007, Rusty Russell wrote:
> This attempts to implement a "virtual I/O" layer which should allow
> common drivers to be efficiently used across most virtual I/O
> mechanisms. It will no-doubt need further enhancement.
Hi Rusty,
Thanks for your update, as you can imagine, I
Ryan Harper wrote:
> * Avi Kivity <[EMAIL PROTECTED]> [2007-09-24 02:57]:
>
>> Ryan Harper wrote:
>>
>>> I've run into a nasty bug while trying to install a Linux guest using
>>> VMware Server inside a kvm guest (full dmesg attached and recreate
>>> instructions below bug).
>>>
>>>
>>>
* Avi Kivity <[EMAIL PROTECTED]> [2007-09-24 02:57]:
> Ryan Harper wrote:
> >I've run into a nasty bug while trying to install a Linux guest using
> >VMware Server inside a kvm guest (full dmesg attached and recreate
> >instructions below bug).
> >
> >
>
> Can you reproduce this with AUDIT turne
I think you forgot to include the patch?
Regards,
Anthony Liguori
Izik Eidus wrote:
>
> in order to be able to allocate the memory to kvm from userspace we have
> to remove
> the private usage made by the rmap.
>
> this patch add array to each memory slot sorted by gfn that hold rmap to
> each p
in order to be able to allocate the memory to kvm from userspace we have
to remove
the private usage made by the rmap.
this patch add array to each memory slot sorted by gfn that hold rmap to
each page.
to make the finding of gfn from spte address, we are adding another page
to each kvm_mmu_pag
As with previous "Takes" of this patch, its purpose is to expose host
CPU features to guests. It proved rather helpful to KVM in various
benchmarks, and it should similarly speed kqemu up. Note that it does
not extend the set of emulated opcodes, only exposes what's supported by
the host CPU.
Anot
Heinz Ulrich Stille wrote:
> On Monday 24 September 2007, Avi Kivity wrote:
>
>> You'll need to emulate a card that supports these resolutions. I don't
>> think cirrus does. The vmware vga display in qemu-cvs probably does,
>> but it hasn't been ported to kvm yet. You might try that.
>>
>
Zhao, Yunfeng wrote:
> Still doesn't work after updated to the kvm-44.
> 0n 64bit host a xp guest with 2vcpus still gets froze during booting
> Just like this
> https://sourceforge.net/tracker/download.php?group_id=180599&atid=893831&file_id=246597&aid=1799596
> The test machine is a harwitch + p
On Mon, Sep 24, 2007 at 07:16:34PM +1000, Rusty Russell wrote:
> This adds the logic to convert the virtio ids into module aliases, and
> includes a modalias entry in sysfs.
>
> Unfortunately this does not seem sufficient to have the module
> autoprobed at startup on my Ubuntu system. Greg? Am I
Laurent Vivier wrote:
> BTW, what is your politic about qemu: do you update qemu inside kvm on qemu
> release only ?
>
>
I plan to do a merge soon (if things become too stable), but if qemu
releases before that, I'd be much happier.
Merging soon has the benefits of bringing in all the good stu
On Monday 24 September 2007, Avi Kivity wrote:
> You'll need to emulate a card that supports these resolutions. I don't
> think cirrus does. The vmware vga display in qemu-cvs probably does,
> but it hasn't been ported to kvm yet. You might try that.
I use Windows XP on std-vga. I tried hacking
Avi Kivity wrote:
> Heinz Ulrich Stille wrote:
>> Hi!
>>
>> I'd like to use screen resolutions of 1920x1200 to 2560x1600 at 32bpp.
>> So far I managed to raise the pixel limit, but not the memory size, and
>> 8MB is a bit low for what I want. [EMAIL PROTECTED] works fine, but 32bpp
>> results in a
Still doesn't work after updated to the kvm-44.
0n 64bit host a xp guest with 2vcpus still gets froze during booting
Just like this
https://sourceforge.net/tracker/download.php?group_id=180599&atid=893831&file_id=246597&aid=1799596
The test machine is a harwitch + paxville with 16 LPs
I build t
Heinz Ulrich Stille wrote:
> Hi!
>
> I'd like to use screen resolutions of 1920x1200 to 2560x1600 at 32bpp.
> So far I managed to raise the pixel limit, but not the memory size, and
> 8MB is a bit low for what I want. [EMAIL PROTECTED] works fine, but 32bpp
> results in a segfault. Increasing VGA_R
Purify x86_decode_insn() error case management,
the only valid case is on protected page access, other cases are errors
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
---
drivers/kvm/kvm_main.c | 10 +++---
1 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/kvm/kvm_ma
Hi!
I'd like to use screen resolutions of 1920x1200 to 2560x1600 at 32bpp.
So far I managed to raise the pixel limit, but not the memory size, and
8MB is a bit low for what I want. [EMAIL PROTECTED] works fine, but 32bpp
results in a segfault. Increasing VGA_RAM_SIZE in qemu/vl.h doesn't help.
Wha
Carsten Otte wrote:
> Hi list,
>
> I've observed that current kvm-44 userspace with Avi's git as of
> yesterday does not boot our debian test image on an AMD64 machine. The
> kernel seems to die various panic's in sequence (too fast to observe),
> the final one is in __delay(). Everything seems
Avi Kivity wrote:
> Laurent Vivier wrote:
>> Avi Kivity wrote:
>>
>>> Farkas Levente wrote:
>>>
hi,
it seems we've got a real tester:-) for ma all of the bellow are
serious
bugs (tomorrow i'll try to send more detail of our host crash too) and
imho the latest 'stable'
On 9/24/07, Carsten Otte <[EMAIL PROTECTED]> wrote:
> Hi list,
>
> I've observed that current kvm-44 userspace with Avi's git as of
> yesterday does not boot our debian test image on an AMD64 machine. The
> kernel seems to die various panic's in sequence (too fast to observe),
> the final one is in
Hi list,
I've observed that current kvm-44 userspace with Avi's git as of
yesterday does not boot our debian test image on an AMD64 machine. The
kernel seems to die various panic's in sequence (too fast to observe),
the final one is in __delay(). Everything seems well without -no-kvm
option wi
Laurent Vivier wrote:
> Avi Kivity wrote:
>
>> Farkas Levente wrote:
>>
>>> hi,
>>> it seems we've got a real tester:-) for ma all of the bellow are serious
>>> bugs (tomorrow i'll try to send more detail of our host crash too) and
>>> imho the latest 'stable' version was kvm-36. wouldn't b
Avi Kivity wrote:
> Farkas Levente wrote:
>> hi,
>> it seems we've got a real tester:-) for ma all of the bellow are serious
>> bugs (tomorrow i'll try to send more detail of our host crash too) and
>> imho the latest 'stable' version was kvm-36. wouldn't be better to
>> postpone all patches and in
Oh... Just checked the source code in our build machine, the kvm.git is not
updated to latest.
I have fixed the issue, let's wait and see the new testing results.
Sorry for the mistake!
Thanks
Yunfeng
>-Original Message-
>From: Laurent Vivier [mailto:[EMAIL PROTECTED]
>Sent: 2007年9月24日
Rusty Russell wrote:
These helper routines supply most of the virtqueue_ops for hypervisors
which want to use a ring for virtio. Unlike the previous lguest
implementation:
1) The rings are variable sized (2^n-1 elements).
2) They have an unfortunate limit of 65535 bytes per sg element.
3) The
He, Qing wrote:
> If no apic is enabled in the bitmap of an interrupt delivery with
> delivery
> mode of lowest priority, a warning should be reported rather than select
> a fallback vcpu
>
>
Applied, thanks.
--
error compiling committee.c: too many arguments to function
---
He, Qing wrote:
> (p.s., this patch is before Laurent's patch of no_wb removal, the change
> is minor to adapt to OP_NONE)
>
>
Applied, thanks. Does it solve some specific issue with a guest? I'll
have to send it for 2.6.23 as well if it does.
--
error compiling committee.c: too many argum
Laurent Vivier wrote:
> This patch series makes some cleanups in x86_emulate.c
>
> [PATCH 1/3] move some parts of x86_decode_insn() into functions.
> [PATCH 2/3] remove _eflags and use directly ctxt->eflags
> [PATCH 3/3] remove no_wb
>
> It has been rebased to current master.
>
>
Applied all, t
Avi Kivity wrote:
> Zhao, Yunfeng wrote:
>> Avi,
>> I still cannot boot up the smp windows against the latest commits.
>>
>
> What are the symptoms, exactly? It works reliably here.
It works for me too (winXP + smp 4), but I had to update kvm-userspace to last
commits as well. Yunfeng, did yo
Farkas Levente wrote:
> hi,
> it seems we've got a real tester:-) for ma all of the bellow are serious
> bugs (tomorrow i'll try to send more detail of our host crash too) and
> imho the latest 'stable' version was kvm-36. wouldn't be better to
> postpone all patches and infrastructure changes (vir
Zhao, Yunfeng wrote:
> Avi,
> I still cannot boot up the smp windows against the latest commits.
>
What are the symptoms, exactly? It works reliably here.
--
error compiling committee.c: too many arguments to function
hi,
it seems we've got a real tester:-) for ma all of the bellow are serious
bugs (tomorrow i'll try to send more detail of our host crash too) and
imho the latest 'stable' version was kvm-36. wouldn't be better to
postpone all patches and infrastructure changes (virtio and others)
until these have
Avi,
I still cannot boot up the smp windows against the latest commits.
Thanks
Yunfeng
>-Original Message-
>From: Avi Kivity [mailto:[EMAIL PROTECTED]
>Sent: 2007年9月22日 20:41
>To: Zhao, Yunfeng
>Cc: kvm-devel@lists.sourceforge.net
>Subject: Re: [kvm-devel] Test result for KVM, kernel 06f0
Hi, all,
This is today's KVM test result against kvm.git
62d1ea7fdcdb905072198e4cec8f724c8ad33092 and kvm-userspace.git
667f2deff8cea6327f0c832afea2f4952b8f199e.
In today's testing, smp windows still couldn't be booted up.
1 issue is closed
1. save
>> I *think* it happens because I'm changing guest page tables from outside
>> (i.e. host application), and the new intel pgtable optimization bits
>> don't expect that (yes, it is a vt box).
>
> Well, the older implementation doesn't expect that either. You can
> disable the optimization with by
(p.s., this patch is before Laurent's patch of no_wb removal, the change
is minor to adapt to OP_NONE)
Signed-off-by: Qing He <[EMAIL PROTECTED]>
---
drivers/kvm/x86_emulate.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/x86_emulate.c b/drivers/kvm/x86_em
If no apic is enabled in the bitmap of an interrupt delivery with
delivery
mode of lowest priority, a warning should be reported rather than select
a fallback vcpu
Signed-off-by: Qing He <[EMAIL PROTECTED]>
Signed-off-by: Eddie (Yaozu) Dong <[EMAIL PROTECTED]>
---
drivers/kvm/lapic.c | 13 +++
Gerd Hoffmann wrote:
> Avi Kivity wrote:
>
>> You can call kvm_disable_irqchip_creation() to kill in-kernel pic and
>> friends.
>>
>> (the logic is inverted -- the function should be
>> kvm_enable_irqchip_creation() so that this problem would not occur)
>>
>
> Ok, will try, next question fi
Avi Kivity wrote:
> You can call kvm_disable_irqchip_creation() to kill in-kernel pic and
> friends.
>
> (the logic is inverted -- the function should be
> kvm_enable_irqchip_creation() so that this problem would not occur)
Ok, will try, next question first though as I'm running in trouble much
e
This adds the logic to convert the virtio ids into module aliases, and
includes a modalias entry in sysfs.
Unfortunately this does not seem sufficient to have the module
autoprobed at startup on my Ubuntu system. Greg? Am I missing some
udev magic?
Signed-off-by: Rusty Russell <[EMAIL PROTECTED
These helper routines supply most of the virtqueue_ops for hypervisors
which want to use a ring for virtio. Unlike the previous lguest
implementation:
1) The rings are variable sized (2^n-1 elements).
2) They have an unfortunate limit of 65535 bytes per sg element.
3) The page numbers are always
This attempts to implement a "virtual I/O" layer which should allow
common drivers to be efficiently used across most virtual I/O
mechanisms. It will no-doubt need further enhancement.
The virtio drivers add buffers to virtio queues; as the buffers are consumed
the driver "interrupt" callbacks ar
I'm not reposting the drivers this time since they haven't changed
significantly. See http://lguest.ozlabs.org/patches for the whole
thing, from new-io.patch onwards).
Changes since last version:
- Switch to our own bus implementation, rather than relying on
an implementation-sp
Remove _eflags and use directly ctxt->eflags. Caching eflags is not needed as
it is restored to vcpu by kvm_main.c:emulate_instruction() from ctxt->eflags
only if emulation doesn't fail.
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
---
drivers/kvm/x86_emulate.c | 121 +
This patch series makes some cleanups in x86_emulate.c
[PATCH 1/3] move some parts of x86_decode_insn() into functions.
[PATCH 2/3] remove _eflags and use directly ctxt->eflags
[PATCH 3/3] remove no_wb
It has been rebased to current master.
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
---
To improve readability, move push, writeback, and grp 1a/2/3/4/5/9 emulation
parts into functions.
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
---
drivers/kvm/x86_emulate.c | 451 ++--
1 files changed, 266 insertions(+), 185 deletions(-)
diff --git
Remove no_wb, use dst.type = OP_NONE instead, idea stollen from xen-3.1
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
---
drivers/kvm/x86_emulate.c | 76 ++--
drivers/kvm/x86_emulate.h |2 +-
2 files changed, 25 insertions(+), 53 deletions(-)
dif
Avi Kivity wrote:
> Farkas Levente wrote:
>> Avi Kivity wrote:
>>
>>> Farkas Levente wrote:
>>>
Avi Kivity wrote:
> An important fix to guest smp (it boots now!), and a performance
> improvement on Intel hardware. I get about 5% boost on a kernel
> build.
>
Farkas Levente wrote:
> Avi Kivity wrote:
>
>> Farkas Levente wrote:
>>
>>> Avi Kivity wrote:
>>>
>>>
An important fix to guest smp (it boots now!), and a performance
improvement on Intel hardware. I get about 5% boost on a kernel build.
There's a new module pa
Avi Kivity wrote:
> Farkas Levente wrote:
>> Avi Kivity wrote:
>>
>>> An important fix to guest smp (it boots now!), and a performance
>>> improvement on Intel hardware. I get about 5% boost on a kernel build.
>>>
>>> There's a new module parameter to kvm-intel.ko that can disable this
>>> mecha
Ryan Harper wrote:
> I've run into a nasty bug while trying to install a Linux guest using
> VMware Server inside a kvm guest (full dmesg attached and recreate
> instructions below bug).
>
>
Can you reproduce this with AUDIT turned on (top of mmu.c)? AUDIT is
very slow, so it's recommended to
Farkas Levente wrote:
> Avi Kivity wrote:
>
>> An important fix to guest smp (it boots now!), and a performance
>> improvement on Intel hardware. I get about 5% boost on a kernel build.
>>
>> There's a new module parameter to kvm-intel.ko that can disable this
>> mechanism, bypass_guest_pf.
61 matches
Mail list logo
