Hello Stefan,
On 05/30/2012 09:19 PM, Stefan Hajnoczi wrote:
Holding the vblk->lock across kick causes poor scalability in SMP
guests. If one CPU is doing virtqueue kick and another CPU touches the
vblk->lock it will have to spin until virtqueue kick completes.
This patch reduces system% CPU u
qemu-kvm-1.1-rc4 is now available. This release is based on the upstream
qemu 1.1-rc4, plus kvm-specific enhancements. Please see the
original QEMU 1.1-rc4 release announcement [1] for details.
This release can be used with the kvm kernel modules provided by your
distribution kernel, or by the m
On Thu, May 17, 2012 at 01:14:08PM +0300, Avi Kivity wrote:
> Practically all patches to ia64 KVM are build fixes; numerous warnings remain;
> the last patch from the maintainer was committed more than three years ago.
> It
> is clear that no one is using this thing.
>
> Mark as BROKEN to ensure
On Fri, May 18, 2012 at 06:27:27AM +, Mao, Junjie wrote:
> Add unit test for basic functionality of PCID/INVPCID feature exposing in kvm.
>
> Changes from v1:
> Hard code 'invpcid' instruction
>
> Signed-off-by: Junjie Mao
> ---
> config-x86-common.mak |2 +
> config-x86_64.mak
On 05/31/2012 11:55 AM, Jan Kiszka wrote:
>>
>> No "Status", does that imply "Active" ?
>
> It should actually state that this call is in use.
>
It might be nice to point out when a call was introduced, and for
deprecated calls, when it was deprecated.
-hpa
--
H. Peter Anvin, Intel Op
On 2012-05-31 19:44, Randy Dunlap wrote:
> On 05/31/2012 01:01 AM, Raghavendra K T wrote:
>
>> From: Raghavendra K T
>>
>> Thanks Alex for KVM_HC_FEATURES inputs and Jan for VAPIC_POLL_IRQ
>>
>> Signed-off-by: Raghavendra K T
>> ---
>> diff --git a/Documentation/virtual/kvm/hypercalls.txt
>>
On 05/31/2012 01:01 AM, Raghavendra K T wrote:
> +
> +TODO:
> +1. more information on input and output needed?
> +2. Add more detail to purpose of hypercalls.
>
1. definitely, including the hypercall ABI.
-hpa
--
H. Peter Anvin, Intel Open Source Technology Center
I work for Intel. I
On 05/31/2012 01:01 AM, Raghavendra K T wrote:
> From: Raghavendra K T
>
> Thanks Alex for KVM_HC_FEATURES inputs and Jan for VAPIC_POLL_IRQ
>
> Signed-off-by: Raghavendra K T
> ---
> diff --git a/Documentation/virtual/kvm/hypercalls.txt
> b/Documentation/virtual/kvm/hypercalls.txt
> new fi
On Thu, May 31, 2012 at 01:15:13PM +0300, Gleb Natapov wrote:
> > > > + /* Cache not set: safe but we don't bother. */
> > > > + unlikely(apic->isr_cache == -1) ||
> > > > + /* Need EOI to update ioapic. */
> > > > + unlikely(kvm_ioapic_handles_vector(vcpu->k
On Thu, May 31, 2012 at 01:06:57PM +0300, Gleb Natapov wrote:
> On Wed, May 30, 2012 at 05:54:42PM -0300, Marcelo Tosatti wrote:
> > On Tue, May 22, 2012 at 03:54:56PM +0300, Michael S. Tsirkin wrote:
> > > We perform ISR lookups twice: during interrupt
> > > injection and on EOI. Typical workloads
On 05/31/2012 02:13 PM, Orit Wasserman wrote:
> For example migration between Westmere and Nehelem hosts.
> The patch fixes the guest segments similar to enter_rmode function.
>
> Signed-off-by: Orit Wasserman
> ---
> arch/x86/kvm/vmx.c | 38 ++
> 1 files ch
For example migration between Westmere and Nehelem hosts.
The code that fixes the segments for real mode guest was moved from enter_rmode
to vmx_set_segments. enter_rmode calls vmx_set_segments for each segment.
Signed-off-by: Orit Wasserman
---
arch/x86/kvm/vmx.c | 70 +++
For example migration between Westmere and Nehelem hosts.
The patch fixes the guest segments similar to enter_rmode function.
Signed-off-by: Orit Wasserman
---
arch/x86/kvm/vmx.c | 38 ++
1 files changed, 38 insertions(+), 0 deletions(-)
diff --git a/arch/x
On Thu, May 31, 2012 at 01:11:11PM +0300, Michael S. Tsirkin wrote:
> On Thu, May 31, 2012 at 12:57:10PM +0300, Gleb Natapov wrote:
> > > @@ -1345,17 +1437,40 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu
> > > *vcpu)
> > > apic_set_tpr(vcpu->arch.apic, data & 0xff);
> > > }
> > >
> > > +
On Thu, May 31, 2012 at 01:06:57PM +0300, Gleb Natapov wrote:
> On Wed, May 30, 2012 at 05:54:42PM -0300, Marcelo Tosatti wrote:
> > On Tue, May 22, 2012 at 03:54:56PM +0300, Michael S. Tsirkin wrote:
> > > We perform ISR lookups twice: during interrupt
> > > injection and on EOI. Typical workloads
On Thu, May 31, 2012 at 12:57:10PM +0300, Gleb Natapov wrote:
> > @@ -1345,17 +1437,40 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu
> > *vcpu)
> > apic_set_tpr(vcpu->arch.apic, data & 0xff);
> > }
> >
> > +/*
> > + * apic_sync_pv_eoi_to_guest - called before vmentry
> > + *
> > + * Det
On Wed, May 30, 2012 at 05:54:42PM -0300, Marcelo Tosatti wrote:
> On Tue, May 22, 2012 at 03:54:56PM +0300, Michael S. Tsirkin wrote:
> > We perform ISR lookups twice: during interrupt
> > injection and on EOI. Typical workloads only have
> > a single bit set there. So we can avoid ISR scans by
>
On Tue, May 22, 2012 at 05:05:47PM +0300, Michael S. Tsirkin wrote:
> Implementation of PV EOI using shared memory.
> This reduces the number of exits an interrupt
> causes as much as by half.
>
> The idea is simple: there's a bit, per APIC, in guest memory,
> that tells the guest that it does not
Hi Lucas,
F17 is not working on xen hypervisor without some changes. I'm going to prepare
fixes for xen handling.
Mirek
- Original Message -
> From: "Lucas Meneghel Rodrigues"
> To: autot...@test.kernel.org
> Cc: kvm@vger.kernel.org
> Sent: Wednesday, May 30, 2012 11:20:55 PM
> Subject:
On 05/30/2012 11:03 PM, Marcelo Tosatti wrote:
> On Sun, May 20, 2012 at 04:49:27PM +0300, Avi Kivity wrote:
>> Instead of using a atomic operation per active request, use just one
>> to get all requests at once, then check them with local ops. This
>> probably isn't any faster, since simultaneous
On Thu, May 31, 2012 at 11:47:17AM +0300, Michael S. Tsirkin wrote:
> On Thu, May 31, 2012 at 06:35:08PM +1000, Stephen Rothwell wrote:
> > Hi all,
> >
> > On Wed, 30 May 2012 19:41:47 +0930 Rusty Russell
> > wrote:
> > >
> > > On Mon, 28 May 2012 15:53:25 +0300, "Michael S. Tsirkin"
> > > wro
On Thu, May 31, 2012 at 06:35:08PM +1000, Stephen Rothwell wrote:
> Hi all,
>
> On Wed, 30 May 2012 19:41:47 +0930 Rusty Russell
> wrote:
> >
> > On Mon, 28 May 2012 15:53:25 +0300, "Michael S. Tsirkin"
> > wrote:
> > > On Wed, Apr 04, 2012 at 12:19:54PM +0300, Michael S. Tsirkin wrote:
> > >
Hi all,
On Wed, 30 May 2012 19:41:47 +0930 Rusty Russell wrote:
>
> On Mon, 28 May 2012 15:53:25 +0300, "Michael S. Tsirkin"
> wrote:
> > On Wed, Apr 04, 2012 at 12:19:54PM +0300, Michael S. Tsirkin wrote:
> > > disable_cb is just an optimization: it
> > > can not guarantee that there are no ca
From: Raghavendra K T
Thanks Alex for KVM_HC_FEATURES inputs and Jan for VAPIC_POLL_IRQ
Signed-off-by: Raghavendra K T
---
diff --git a/Documentation/virtual/kvm/hypercalls.txt
b/Documentation/virtual/kvm/hypercalls.txt
new file mode 100644
index 000..c79335a
--- /dev/null
+++ b/Document
24 matches
Mail list logo