If we want to keep sp live while it it's out of kvm->mmu_lock protection,
we can increase sp->active_count.
Then, the invalid page is not only for active root but also unsync sp, we
should filter those out when we make a page to unsync.
And move 'hlist_del(&sp->hash_link)' into kvm_mmu_free_page(
Rename 'root_count' to 'active_count' in kvm_mmu_page, since the unsync pages
also will use it in later patch
Signed-off-by: Xiao Guangrong
---
arch/x86/include/asm/kvm_host.h |8 +++-
arch/x86/kvm/mmu.c | 14 +++---
arch/x86/kvm/mmutrace.h |6 +++---
3
Hi Avi, Marcelo,
patch 5 and patch 6 are can't apply to current kvm tree, i'll
rebase those two patches.
Marcelo, does this patchset fix your issue? I have tested it with
Fedora12/Ubuntu/CentOS 32/64 guests, it works well.
Thanks,
Xiao
--
To unsubscribe from this list: send the line "unsubscribe
On Thu, 6 May 2010 03:49:46 pm Michael S. Tsirkin wrote:
> Now, I also added an mb() in guest between read and write so
> that last used index write can not get ahead of used index read.
> It does feel good to have it there, but I can not say why
> it's helpful. Works fine without it, but then thes
On Thu, 6 May 2010 07:30:00 pm Avi Kivity wrote:
> On 05/05/2010 11:58 PM, Michael S. Tsirkin wrote:
> > + /* We publish the last-seen used index at the end of the available ring.
> > +* It is at the end for backwards compatibility. */
> > + vr->last_used_idx =&(vr)->avail->ring[num];
> > +
On Thu, 6 May 2010 03:57:55 pm Michael S. Tsirkin wrote:
> On Thu, May 06, 2010 at 10:22:12AM +0930, Rusty Russell wrote:
> > On Wed, 5 May 2010 03:52:36 am Michael S. Tsirkin wrote:
> > > What do you think?
> >
> > I think everyone is settled on 128 byte cache lines for the forseeable
> > future,
From: Dongxiao Xu
Originally VMCLEAR/VMPTRLD is called on vcpu migration. To
support hosted VMM coexistance, VMCLEAR is executed on vcpu
schedule out, and VMPTRLD is executed on vcpu schedule in.
This could also eliminate the IPI when doing VMCLEAR.
vmm_exclusive is introduced as a module parame
From: Dongxiao Xu
SDM suggests VMXON should be called before VMPTRLD, and VMXOFF
should be called after doing VMCLEAR.
Therefore in vmm coexistence case, we should firstly call VMXON
before any VMCS operation, and then call VMXOFF after the
operation is done.
Signed-off-by: Dongxiao Xu
---
ar
Hi all,
This is hosted VMM coexistence support v3.
Main changes from v2:
1) Change vmm_coexistence to vmm_exclusive.
2) Some code structure changes. Split the original 3 patches to 4.
3) Address some comments from Avi.
Main changes from v1:
1) Add an module option "vmm_coexistence" to decide whe
From: Dongxiao Xu
Do some preparations for vmm coexistence support.
Signed-off-by: Dongxiao Xu
---
arch/x86/kvm/vmx.c | 16
1 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e77da89..49b0850 100644
--- a/arch/x86/kvm
From: Dongxiao Xu
Define vmcs_load() and kvm_cpu_vmxon() to avoid direct call of asm
code. Also move VMXE bit operation out of kvm_cpu_vmxoff().
Signed-off-by: Dongxiao Xu
---
arch/x86/kvm/vmx.c | 36 +++-
1 files changed, 23 insertions(+), 13 deletions(-)
di
Avi Kivity wrote:
> On 05/06/2010 11:45 AM, Xu, Dongxiao wrote:
>> From: Dongxiao Xu
>>
>> Originally VMCLEAR/VMPTRLD is called on vcpu migration. To
>> support hosted VMM coexistance, VMCLEAR is executed on vcpu
>> schedule out, and VMPTRLD is executed on vcpu schedule in.
>> This could also elim
Hi, Lucas
Thanks for your comment. I am sorry for no response so long time.
I will update it according to your comment.
Also thanks Michael for his comment.
- "Lucas Meneghel Rodrigues" wrote:
> From: "Lucas Meneghel Rodrigues"
> To: "Feng Yang"
> Cc: autot...@test.kernel.org, kvm
On Thu, Nov 19, 2009 at 01:19:55PM +0100, Jan Kiszka wrote:
> Hi,
>
> I just managed to push a qemu-kvm process (git rev. b496fe3431) into an
> endless loop in qcow2_alloc_cluster_offset, namely over
> QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight):
>
> (gdb) bt
> #0 0x0048
On Wed, Apr 7, 2010 at 5:49 AM, Feng Yang wrote:
> Signed-off-by: Feng Yang
> ---
> client/tests/kvm/tests/ioquit.py | 54
>
> client/tests/kvm/tests_base.cfg.sample | 4 ++
> 2 files changed, 58 insertions(+), 0 deletions(-)
> create mode 100644 cli
On Wed, Apr 7, 2010 at 5:49 AM, Feng Yang wrote:
> Signed-off-by: Feng Yang
> ---
> client/tests/kvm/tests/ioquit.py | 54
>
> client/tests/kvm/tests_base.cfg.sample | 4 ++
> 2 files changed, 58 insertions(+), 0 deletions(-)
> create mode 100644 cli
On Thu, May 6, 2010 at 11:37 PM, Matteo Signorini
wrote:
>
> Dear Yaniv, Dear Avi,
>
> I would like to add the "sidt emulation" feature in kvm, but in order to
> implement it I need to know the details on how the OPCODE works and how
> exactly opcodes are emulated within kvm.
> For example let's
On Wed, Apr 7, 2010 at 8:55 AM, Jason Wang wrote:
> The design of iofuzz is simple: it just generate random I/O port
> activity inside the virtual machine. The correctness of the device
> emulation may be verified through this test.
>
> As the instrcutions are randomly generated, guest may enter t
From: Jason Wang
The design of iofuzz is simple: it just generate random I/O port
activity inside the virtual machine. The correctness of the device
emulation may be verified through this test.
As the instrcutions are randomly generated, guest may enter the wrong
state. The test solve this issue
On Thursday, May 06, 2010 04:05:17 pm Jernej Simončič wrote:
> On Thursday, May 6, 2010, 22:36:02, Brian Jackson wrote:
> > What about the XP32 drivers from:
> > http://theiggy.com/tmp/virtio-20091208.zip
>
> This is what I currently use on XP, and it works fine (I think I
> mentioned this on IRC
On Thursday, May 6, 2010, 22:36:02, Brian Jackson wrote:
> What about the XP32 drivers from:
> http://theiggy.com/tmp/virtio-20091208.zip
This is what I currently use on XP, and it works fine (I think I
mentioned this on IRC - my nickname's ender` there).
--
< Jernej Simončič ><><><><>< http://
Dear Yaniv, Dear Avi,
I would like to add the "sidt emulation" feature in kvm, but in order to
implement it I need to know the details on how the OPCODE works and how
exactly opcodes are emulated within kvm.
For example let's take the SIDT instruction.
I know the LIDT opcode is "0F 01 /1" but w
On Thursday, May 06, 2010 03:11:00 pm Jernej Simončič wrote:
> On Thursday, May 6, 2010, 21:59:21, Brian Jackson wrote:
> > http://theiggy.com/tmp/virtio-20100228.zip
> > These are not guaranteed to work and they will probably kill kittens.
> > That said, I've had luck with them and had only a few
On Thursday, May 6, 2010, 21:59:21, Brian Jackson wrote:
> http://theiggy.com/tmp/virtio-20100228.zip
> These are not guaranteed to work and they will probably kill kittens. That
> said, I've had luck with them and had only a few reports of things not working
> (mostly with the balloon drivers).
On Tue, May 04, 2010 at 01:03:50PM +0300, Avi Kivity wrote:
> On svm, kvm_read_pdptr() may require reading guest memory, which can sleep.
>
> Push the spinlock into mmu_alloc_roots(), and only take it after we've read
> the pdptr.
>
> Signed-off-by: Avi Kivity
> ---
>
> Marcelo, dropping and re
On Sun, May 02, 2010 at 12:48:49PM +0300, Avi Kivity wrote:
> Currently we run with EFER.NX=1 on the guest even if the guest value is 0.
> This is fine with shadow, since we check bit 63 when instantiating a page
> table, and fault if bit 63 is set while EFER.NX is clear.
>
> This doesn't work wit
On Mon, May 03, 2010 at 05:19:08PM +0300, Avi Kivity wrote:
> KVM_REQ_KICK poisons vcpu->requests by having a bit set during normal
> operation. This causes the fast path check for a clear vcpu->requests
> to fail all the time, triggering tons of atomic operations.
>
> Fix by replacing KVM_REQ_KI
There was a bug recently fixed in vnc code. Apparently
there's something similar in the cirrus emulation as well.
Here it triggers _always_ (including old versions of kvm)
when running windows NT and hitting "test" button in its
display resolution dialog. Here's what gdb is to say:
Program rece
On Thursday, May 06, 2010 07:10:07 am Riccardo Veraldi wrote:
> Hello,
> if I install virtio-win drivers on windows 2008 Server R2, I have the
> problem of signed device drivers.
> I Can install the drivers but Windows 2008 server refuses to use them
> unless I start
> the machine pressing F8 every
On 05/06/2010 10:45 PM, Avi Kivity wrote:
All those control registers are annoying, we have cr1 and cr5-cr7
free, cr9-cr15 on x86_64, infinite msr space, and now we have XCRs.
Great.
Looking forward to YCR0.
I think I see the reason - xgetbv is unprivileged, so applications can
see what
On 05/06/2010 05:20 PM, Cui, Dexuan wrote:
However, switching xcr0 may be slow. That's our experience with msrs.
Can you measure its latency?
We can measure that.
However, I think the changing xcr0 to guest xcr0 in handle_xsetbv() is
necessary --
or else, inside guest xgetbv() would re
On Thu, May 06, 2010 at 03:03:48PM +0800, Lai Jiangshan wrote:
> Marcelo Tosatti wrote:
> > On Thu, Apr 29, 2010 at 09:43:40PM +0300, Avi Kivity wrote:
> >> On 04/29/2010 09:09 PM, Marcelo Tosatti wrote:
> >>> You missed quadrant on 4mb large page emulation with shadow (see updated
> >>> patch belo
We keep a qlist of assigned devices for irq updates, but we forgot to
remove entries from it if they're hot unplugged. This makes
assigned_dev_update_irqs() a timebomb that goes off when the guest is
rebooted.
Signed-off-by: Alex Williamson
---
diff --git a/hw/device-assignment.c b/hw/device-as
On Wed, 2010-05-05 at 21:52 +0100, Lukáš Doktor wrote:
> Hi,
>
> we are back with new features of KSM_overcommit test:
> * NEW: guest_reserve and host_reserve are now calculated based on used
> memory
> * NEW: tmpfs reserve is also evaluated to fit the overhead
> * NEW: VM alive check during spli
On Thu, May 6, 2010 at 11:32 AM, Anthony Liguori wrote:
> On 04/21/2010 12:53 PM, Cam Macdonell wrote:
>>
>> Support an inter-vm shared memory device that maps a shared-memory object
>> as a
>> PCI device in the guest. This patch also supports interrupts between
>> guest by
>> communicating over
On 04/21/2010 12:53 PM, Cam Macdonell wrote:
Support an inter-vm shared memory device that maps a shared-memory object as a
PCI device in the guest. This patch also supports interrupts between guest by
communicating over a unix domain socket. This patch applies to the qemu-kvm
repository.
On Mon, Apr 26, 2010 at 7:07 AM, Jason Wang wrote:
> userspace
>
> Current method may or may not work for various kinds of
> distribution. So this patch enable the ability to use customized
> commands to get the version of kvm and its userspace. "kvm_ver_cmd" is
> used for kvm verison and "kvm_use
On Mon, Apr 26, 2010 at 7:07 AM, Jason Wang wrote:
> KSM may have various control interface for different distributions,so
> this patch launch ksm through pre_command instead of the hard-coded
> bits in the test. User may specify their owner suitable commands or
> paramteres.
Applied, thanks!
>
On Mon, Apr 26, 2010 at 7:07 AM, Jason Wang wrote:
> Remove the duplicated "KERNEL vmlinuz" in unattended.py
Good catch, applied, thanks!
> Signed-off-by: Jason Wang
> ---
> client/tests/kvm/scripts/unattended.py | 1 -
> 1 files changed, 0 insertions(+), 1 deletions(-)
>
> diff --git a/cli
On Wed, May 5, 2010 at 5:20 PM, Frank Berreth wrote:
> Hi there,
> this is just an update if you are interested in the outcome. I turns out
> that my initial assumption that there would be page faults/trapping on the
> memory pages was false. The reason the throughput is so low is because the
> me
Michael S. Tsirkin wrote:
> Hi!
> I see this in virtio_ring.c:
>
> /* Put entry in available array (but don't update avail->idx *
> until they do sync). */
>
> Why is it done this way?
> It seems that updating the index straight away would be simpler, while
> this might allow the
On Thu, 2010-05-06 at 11:08 +0800, Jason Wang wrote:
> Michael Goldish wrote:
> > On 04/26/2010 01:04 PM, Jason Wang wrote:
> >
> >> As we have the ability to dump the content from serial console or use
> >> a session through it, we need to redirect the console to serial
> >> through unattended
On Wed, Apr 28, 2010 at 8:55 AM, Michael Goldish wrote:
> On 04/26/2010 01:04 PM, Jason Wang wrote:
>> If the screendump and scrialdump threads are created after the
>> process(), we may lose the progress tracking of guest shutting
>> down. So this patch creates them before calling process() in pr
Rusty Russell wrote:
> On Wed, 5 May 2010 05:47:05 am Jamie Lokier wrote:
> > Jens Axboe wrote:
> > > On Tue, May 04 2010, Rusty Russell wrote:
> > > > ISTR someone mentioning a desire for such an API years ago, so CC'ing
> > > > the
> > > > usual I/O suspects...
> > >
> > > It would be nice to h
On Thu, 2010-05-06 at 10:55 +0800, Jason Wang wrote:
> Michael Goldish wrote:
> > On 04/26/2010 01:03 PM, Jason Wang wrote:
> >
> >> Sometimes we need to send an assist string to a session in order to
> >> get the prompt especially when re-connecting to an already logged
> >> serial session. Thi
On Mon, Apr 26, 2010 at 7:04 AM, Jason Wang wrote:
> Need to raise the error when met the unknown type of shell_client in
> kvm_vm.remote_login() in order to avoid the traceback.
In order to keep consistency, please make the function return None
instead of throwing an exception. You might log the
> -Original Message-
> From: kvm-ow...@vger.kernel.org [mailto:kvm-ow...@vger.kernel.org] On
> Behalf Of Riccardo Veraldi
> Sent: Donnerstag, 06. Mai 2010 14:10
> To: kvm@vger.kernel.org
> Subject: virtio-win problem
>
> Hello,
> if I install virtio-win drivers on windows 2008 Server R2, I
Rusty Russell wrote:
> > Seems over-zealous.
> > If the recovery_header held a strong checksum of the recovery_data you would
> > not need the first fsync, and as long as you have two places to write
> > recovery
> > data, you don't need the 3rd and 4th syncs.
> > Just:
> >
> > write_internally
Avi Kivity wrote:
> On 05/06/2010 07:23 AM, Cui, Dexuan wrote:
>>
+ goto err;
+ vcpu->arch.guest_xstate_mask = new_bv;
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.guest_xstate_mask);
>>> Can't we run with the host xcr0? isn't it guaranteed to be a
>>> supe
LGTM
On Thu, May 6, 2010 at 6:24 AM, Lucas Meneghel Rodrigues
wrote:
> Fix a silly bug on graph generation: it was mapping the wrong
> columns when plotting the 2D throughput graphs. Sorry for the
> mistake.
>
> Signed-off-by: Lucas Meneghel Rodrigues
> ---
> client/tests/iozone/postprocessing
On Wednesday 05 May 2010, Takuya Yoshikawa wrote:
> Date:
> Yesterday 04:59:24
> > That's why the bitmaps are defined as little endian u64 aligned, even on
> > big endian 32-bit systems. Little endian bitmaps are wordsize agnostic,
> > and u64 alignment ensures we can use long-sized bitops on m
On 05/06/2010 11:45 AM, Xu, Dongxiao wrote:
From: Dongxiao Xu
Originally VMCLEAR/VMPTRLD is called on vcpu migration. To
support hosted VMM coexistance, VMCLEAR is executed on vcpu
schedule out, and VMPTRLD is executed on vcpu schedule in.
This could also eliminate the IPI when doing VMCLEAR.
Fix a silly bug on graph generation: it was mapping the wrong
columns when plotting the 2D throughput graphs. Sorry for the
mistake.
Signed-off-by: Lucas Meneghel Rodrigues
---
client/tests/iozone/postprocessing.py |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/client/
On 05/06/2010 11:45 AM, Xu, Dongxiao wrote:
From: Dongxiao Xu
Changelog needs to describe what's being done and why. Splitting the
changes will help.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the
On 05/06/2010 03:41 PM, Gleb Natapov wrote:
On Thu, May 06, 2010 at 03:33:12PM +0300, Avi Kivity wrote:
On 05/06/2010 03:25 PM, Gleb Natapov wrote:
We can expect that from a developer or a user subscribed to k...@.
But what about some random user running virt-manager?
On Thu, May 06, 2010 at 03:33:12PM +0300, Avi Kivity wrote:
> On 05/06/2010 03:25 PM, Gleb Natapov wrote:
> >
> >>We can expect that from a developer or a user subscribed to k...@.
> >>But what about some random user running virt-manager?
> >>
> >What virt-manager would do about such error?
>
> Ca
On 05/06/2010 03:25 PM, Gleb Natapov wrote:
We can expect that from a developer or a user subscribed to k...@.
But what about some random user running virt-manager?
What virt-manager would do about such error?
Call up abrt.
True. But the same problem exists with cpl>0 #UD. It
Hello,
if I install virtio-win drivers on windows 2008 Server R2, I have the
problem of signed device drivers.
I Can install the drivers but Windows 2008 server refuses to use them
unless I start
the machine pressing F8 every time at each reboot bypassing the checking
of signed certified driver
On Thu, May 06, 2010 at 01:13:30PM +0300, Avi Kivity wrote:
> On 05/06/2010 01:06 PM, Gleb Natapov wrote:
> >On Thu, May 06, 2010 at 12:15:58PM +0300, Avi Kivity wrote:
> >>On 04/29/2010 02:58 PM, Gleb Natapov wrote:
> >>>Do not kill VM If instruction emulation fails while vcpu is in
> >>>userspace
On 05/06/2010 12:38 PM, Roedel, Joerg wrote:
Subject: [PATCH] KVM: X86: Inject #GP with the right rip on efer writes
This patch fixes a bug in the KVM efer-msr write path. If a
guest writes to a reserved efer bit the set_efer function
injects the #GP directly. The architecture dependent wrmsr
fun
On 05/04/2010 03:45 PM, Marcelo Tosatti wrote:
Applied all, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.o
On 05/05/2010 09:24 PM, Anthony Liguori wrote:
On 05/04/2010 07:45 AM, Marcelo Tosatti wrote:
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
How does this
On 05/04/2010 03:45 PM, Marcelo Tosatti wrote:
From: Jan Kiszka
It is not safe to retrieve the KVM internal state of a given cpu
while its potentially modifying it.
Queue the request to run on cpu context, similarly to qemu-kvm.
Even better is to query the state in the cpu thread; but tha
On 05/06/2010 01:06 PM, Gleb Natapov wrote:
On Thu, May 06, 2010 at 12:15:58PM +0300, Avi Kivity wrote:
On 04/29/2010 02:58 PM, Gleb Natapov wrote:
Do not kill VM If instruction emulation fails while vcpu is in
userspace. Inject #UD instead in a hope that guest OS will kill offending
On Thu, May 06, 2010 at 12:15:58PM +0300, Avi Kivity wrote:
> On 04/29/2010 02:58 PM, Gleb Natapov wrote:
> >Do not kill VM If instruction emulation fails while vcpu is in
> >userspace. Inject #UD instead in a hope that guest OS will kill offending
> >process. Emulation failure is still traced by f
On 05/05/2010 11:58 PM, Michael S. Tsirkin wrote:
+ /* We publish the last-seen used index at the end of the available ring.
+* It is at the end for backwards compatibility. */
+ vr->last_used_idx =&(vr)->avail->ring[num];
+ /* Verify that last used index does not spill
On Wed, May 05, 2010 at 04:57:00PM -0400, Przywara, Andre wrote:
> If I understood this correctly, there is a bug somewhere, maybe even in
> KVM's nested SVM implementation. Xen is fine with this bit-set provoking
> a #GP. I haven't had time yet to further investigate this, though.
Ok, I looked
invlpg only need update unsync page, sp->unsync and sp->unsync_children
can help us to find it
Now, a gfn may have many shadow pages, when one sp need be synced, we
write protect sp->gfn and sync this sp but we keep other shadow pages
asynchronous
So, while gfn happen page fault, let it not touch
'invlpg_counter' is protected by 'kvm->mmu_lock', no need atomic
operation anymore
Signed-off-by: Xiao Guangrong
---
arch/x86/include/asm/kvm_host.h |2 +-
arch/x86/kvm/paging_tmpl.h |7 ---
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/kvm_
Let invlpg not depends on kvm_mmu_pte_write path, later patch will need
this feature
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/mmu.c | 22 +-
arch/x86/kvm/paging_tmpl.h | 44 +++-
2 files changed, 44 insertions(+), 22 d
If we want to keep sp live while it it's out of kvm->mmu_lock protection,
we can increase sp->active_count.
Then, the invalid page is not only for active root but also unsync sp, we
should filter those out when we make a page to unsync.
And move 'hlist_del(&sp->hash_link)' into kvm_mmu_free_page(
Rename 'root_count' to 'active_count' in kvm_mmu_page, since the unsync pages
also will use it in later patch
Signed-off-by: Xiao Guangrong
---
arch/x86/include/asm/kvm_host.h |7 ++-
arch/x86/kvm/mmu.c | 14 +++---
arch/x86/kvm/mmutrace.h |6 +++---
3
Allow more page become asynchronous at getting sp time, if need create new
shadow page for gfn but it not allow unsync(level > 1), we should unsync all
gfn's unsync page
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/mmu.c | 47 +--
1 files changed,
Two cases maybe happen in kvm_mmu_get_page() function:
- one case is, the goal sp is already in cache, if the sp is unsync,
we only need update it to assure this mapping is valid, but not
mark it sync and not write-protect sp->gfn since it not broke unsync
rule(one shadow page for a gfn)
-
In current code, shadow page can become asynchronous only if one
shadow page for a gfn, this rule is too strict, in fact, we can
let all last mapping page(i.e, it's the pte page) become unsync,
and sync them at invlpg or flush tlb time.
This patch allow more page become asynchronous at gfn mapping
Split kvm_sync_page() into kvm_sync_page() and kvm_sync_page_transient()
to clarify the code address Avi's suggestion
kvm_sync_page_transient() function only update shadow page but not mark
it sync and not write protect sp->gfn. it will be used by later patch
Signed-off-by: Xiao Guangrong
---
a
Changlog v4:
- fix the bug that reported by Marcelo
- fix the race in invlpg code
Changlog v3:
Those changes all form Avi's suggestion, thanks.
- use smart way to fix the bug in patch 1
- remove duplicates code in patch 5
- check error code and fix forgot release page in patch 9
- sync shadow
On 05/06/2010 12:25 PM, Gui Jianfeng wrote:
Avi Kivity wrote:
On 05/05/2010 04:03 AM, Gui Jianfeng wrote:
Currently, kvm_mmu_zap_page() returning the number of freed children sp.
This might confuse the caller, because caller don't know the actual freed
number. Let's make kvm_mmu_zap_p
Avi Kivity wrote:
> On 05/05/2010 04:03 AM, Gui Jianfeng wrote:
>> Currently, kvm_mmu_zap_page() returning the number of freed children sp.
>> This might confuse the caller, because caller don't know the actual freed
>> number. Let's make kvm_mmu_zap_page() return the number of pages it
>> actually
On 04/22/2010 12:33 PM, Gui Jianfeng wrote:
sp->unsync is bool now, so update trace event declaration.
Signed-off-by: Gui Jianfeng
---
arch/x86/kvm/mmutrace.h |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 3851
On 04/29/2010 12:14 AM, Thomas Beinicke wrote:
Hi,
I have been toying around with kvm / libvirt / virt-manager and it's migration
feature.
Both host machines are running a 2.6.33 Kernel.
One host is a Dual Quad Core Intel Xeon E5520 @ 2.27GHz and the other is a
Dual Quad Core Intel E5420 @ 2.
On 04/29/2010 02:58 PM, Gleb Natapov wrote:
Do not kill VM If instruction emulation fails while vcpu is in
userspace. Inject #UD instead in a hope that guest OS will kill offending
process. Emulation failure is still traced by ftrace point to help
analyze the problem.
Still there's the risk
On 05/05/2010 04:58 AM, Gui Jianfeng wrote:
Fix a debug output error in walk_addr
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More m
On 05/05/2010 04:09 AM, Gui Jianfeng wrote:
Sometime cmpxchg_gpte doesn't modify gpte, in such case, don't mark
page table page as dirty.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
t
On 05/05/2010 04:03 AM, Gui Jianfeng wrote:
Currently, kvm_mmu_zap_page() returning the number of freed children sp.
This might confuse the caller, because caller don't know the actual freed
number. Let's make kvm_mmu_zap_page() return the number of pages it actually
freed.
if
On 05/06/2010 07:51 AM, Suen Chun Hui wrote:
Hi,
Thanks for the reply.
On 05/05/2010 11:05 AM, Avi Kivity wrote:
On 04/30/2010 05:53 PM, Suen Chun Hui wrote:
Dear KVM developers,
I'm currently working on an open source security patch to use KVM to
implement code verification on a g
On 05/05/2010 05:04 PM, Joerg Roedel wrote:
Hi Avi, Marcelo,
here is a set of patches which fix problems in kvm-amd. Patch 1 fixes a
stupid problem with the event-reinjection introduced by me in my
previous patchset. Patch 2 was a helper to find the bug patch 3 fixes.
I kept it in the patchset
From: Dongxiao Xu
Originally VMCLEAR/VMPTRLD is called on vcpu migration. To
support hosted VMM coexistance, VMCLEAR is executed on vcpu
schedule out, and VMPTRLD is executed on vcpu schedule in.
This could also eliminate the IPI when doing VMCLEAR.
Signed-off-by: Dongxiao Xu
---
arch/x86/kvm/
Currently all fpu state access is through tsk->thread.xstate. Since we wish
to generalize fpu access to non-task contexts, wrap the state in a new
'struct fpu' and convert existing access to use an fpu API.
Signal frame handlers are not converted to the API since they will remain
task context onl
Currently all fpu accessors are wedded to task_struct. However kvm also uses
the fpu in a different context. Introduce an FPU API, and replace the
current uses with the new API.
While this patchset is oriented towards deeper changes, as a first step it
simlifies xsave for kvm.
v3:
use u
The fpu code currently uses current->thread_info->status & TS_XSAVE as
a way to distinguish between XSAVE capable processors and older processors.
The decision is not really task specific; instead we use the task status to
avoid a global memory reference - the value should be the same across all
th
From: Dongxiao Xu
Intel SDM also suggests that VMXOFF should be called after doing
VMCLEAR. Therefore VMXON should be called before VMPTRLD.
Signed-off-by: Dongxiao Xu
---
arch/x86/kvm/vmx.c | 30 --
1 files changed, 24 insertions(+), 6 deletions(-)
diff --git a/
Main changes from v1:
1) Add an module option "vmm_coexistence" to decide whether to
enable this feature. Currently it is off defaultly.
2) Each time when a KVM vcpu is scheduled in, it will invalidate EPT
and VPID TLBs to avoid conflict between different VMMs.
VMX: Support for coexistence of KVM
From: Dongxiao Xu
Signed-off-by: Dongxiao Xu
---
arch/x86/kvm/vmx.c | 36 +++-
1 files changed, 23 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 875b785..e77da89 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx
Reduces irq_window in guest by only injecting
an interrupt if guest has handled all buffers we
used so far.
Signed-off-by: Michael S. Tsirkin
---
This is the qemu part of the story.
hw/vhost_net.c |6 ++
hw/virtio.c| 15 +++
hw/virtio.h|4
3 files changed
On 05/06/2010 07:23 AM, Cui, Dexuan wrote:
+ goto err;
+ vcpu->arch.guest_xstate_mask = new_bv;
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.guest_xstate_mask);
Can't we run with the host xcr0? isn't it guaranteed to be a superset
of the guest xcr0?
On Wednesday, May 5, 2010 at 01:53:55 -0400, Srivatsa Vaddagiri wrote:
> On Wed, May 05, 2010 at 12:31:11PM -0700, Alec Istomin wrote:
>>
>> On Wednesday, May 5, 2010 at 13:27:39 -0400, Srivatsa Vaddagiri wrote:
>> >> My preliminary results show that single vCPU Linux VMs perform up to 10
>> >>
From: "Michael S. Tsirkin"
Date: Tue, 4 May 2010 14:21:01 +0300
> This is an amended pull request: I have rebased the tree to the
> correct patches. This has been through basic tests and seems
> to work fine here.
>
> The following tree includes a couple of enhancements that help vhost-net.
> Pl
Marcelo Tosatti wrote:
> On Thu, Apr 29, 2010 at 09:43:40PM +0300, Avi Kivity wrote:
>> On 04/29/2010 09:09 PM, Marcelo Tosatti wrote:
>>> You missed quadrant on 4mb large page emulation with shadow (see updated
>>> patch below).
>> Good catch.
>>
>>> Also for some reason i can't understand the ass
99 matches
Mail list logo