> qemu/hw/apic.c | 17 -
> qemu/hw/pc.c| 11 +++
> qemu/qemu-kvm.c | 12 +---
> user/kvmctl.c | 25 +++--
> user/kvmctl.h |5 +++--
> user/main.c |3 +--
> 6 files changed, 59 insertions(+), 14 deletions(-)
>
>diff --git a/q
Hello
Yeasterday, I noticed a strange behaviour on my WinXP guest (host is kubuntu
7.04).
When the guest is launched, it is *VERY* slow. When looking at the task
manager, the processor is used at 100%, doing quite noting.
After having thought hardly, I arrrived to the conclusion that KVM itself
Hello
Yeasterday, I noticed a strange behaviour on my WinXP guest (host is
kubuntu 7.04).
When the guest is launched, it is *VERY* slow. When looking at the task
manager, the processor is used at 100%, doing quite noting.
Note that the guest's cpu consumption is never accurate using
virtualizati
>+static inline void kvm_iodevice_read(struct kvm_io_device *dev,
>+ gpa_t addr,
>+ int len,
>+ void *val)
>+{
>+ dev->read(dev, addr, len, val);
>+}
>+
>+static inline void kvm_iodevice_write
>>> On Wed, May 9, 2007 at 4:16 AM, in message
<[EMAIL PROTECTED]>,
"Dor Laor" <[EMAIL PROTECTED]> wrote:
> For having the option of using kvm with qemu- apic you can use the
> apic_level variable below and add it to qemu's configuration params.
> This will be valuable while testing your impleme
This release fixes two critical issues:
1) Performance was bad in previous versions (QEMU would stay at 80% + even
when the guest was idle). Root cause was a latent KVM bug that was not
exposed with the original interrupt model. Namely, interrupts were not
checked during light-exit (see
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/vmx.c |6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 19edb34..c701ead 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -1855,9 +1855,6 @@ preempte
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/kvm.h | 60 +++
drivers/kvm/kvm_main.c | 94 ++--
2 files changed, 142 insertions(+), 12 deletions(-)
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/k
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/kvm.h |2 +
drivers/kvm/kvm_main.c | 82
2 files changed, 84 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 0f6cc32..b5bfc91 1006
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/Makefile |2
drivers/kvm/kernint.c | 149 +
drivers/kvm/kvm.h | 35 +
drivers/kvm/kvm_main.c | 179 +-
drivers/kvm/lapic.c| 1412
drivers/kvm/svm.c
The current code is geared towards using a user-mode (A)PIC. This patch adds
an "irqdevice" abstraction, and implements a "userint" model to handle the
duties of the original code. Later, we can develop other irqdevice models
to handle objects like LAPIC, IOAPIC, i8259, etc, as appropriate
Signe
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/vmx.c | 63 +
drivers/kvm/vmx.h |3 +++
2 files changed, 61 insertions(+), 5 deletions(-)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 2b4a9ac..d99 100644
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/irqdevice.h |3 +++
drivers/kvm/kvm.h |1 +
drivers/kvm/lapic.c | 15 +++
3 files changed, 19 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/irqdevice.h b/drivers/kvm/irqdevice.h
index 097d
Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]>
---
drivers/kvm/vmx.c | 32 ++--
1 files changed, 26 insertions(+), 6 deletions(-)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index d99..470494e 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@
The VCPU executes synchronously w.r.t. userspace today, and therefore
interrupt injection is pretty straight forward. However, we will soon need
to be able to inject interrupts asynchronous to the execution of the VCPU
due to the introduction of SMP, paravirtualized drivers, and asynchronous
hyper
>-static inline void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
>-{
>- struct vmcb_control_area *control;
>-
>- control = &vcpu->svm->vmcb->control;
>- control->int_vector = pop_irq(vcpu);
>- control->int_ctl &= ~V_INTR_PRIO_MASK;
>- control->int_ctl |= V_IRQ_MASK |
>-
For your information if another dummy people report my strange behaviour:
the solution was the loading kvm and kvm-amd modules...
Sorry
Bye
Cyril
On 5/9/07, Dor Laor <[EMAIL PROTECTED]> wrote:
Hello
Yeasterday, I noticed a strange behaviour on my WinXP guest (host is
kubuntu 7.04).
When
>>> On Wed, May 9, 2007 at 11:16 AM, in message
<[EMAIL PROTECTED]>,
"Dor Laor" <[EMAIL PROTECTED]> wrote:
>
>>- static inline void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
>>-{
>>- struct vmcb_control_area *control;
>>-
>>- control = &vcpu- >svm- >vmcb- >control;
>>- control- >int_v
>>>+static void do_interrupt_requests(struct kvm_vcpu *vcpu,
>>>+ struct kvm_run *kvm_run)
>>>+{
>>>+int pending = __kvm_vcpu_irq_all_pending(vcpu);
>>>+
>>>+clear_pending_controls(vcpu);
>>>+
>>>+while (pending) {
>>>+kvm_irqpin_t pin = __fls(pe
>-Original Message-
>From: [EMAIL PROTECTED] [mailto:kvm-devel-
>[EMAIL PROTECTED] On Behalf Of Gregory Haskins
>Sent: Wednesday, May 09, 2007 6:19 PM
>To: kvm-devel@lists.sourceforge.net
>Subject: [kvm-devel] [PATCH 4/9] KVM: Adds ability to preempt an
>executingVCPU
>
>The VCPU executes
>>> On Wed, May 9, 2007 at 6:12 PM, in message
<[EMAIL PROTECTED]>,
"Dor Laor" <[EMAIL PROTECTED]> wrote:
>
> I wonder if VMX or SVM have an option of injecting several virq at once.
VMX definitely does not (IIUC). I don't know enough about SVN to say for sure,
but my gut tells me that its not
>>> On Wed, May 9, 2007 at 6:28 PM, in message
<[EMAIL PROTECTED]>,
"Dor Laor" <[EMAIL PROTECTED]> wrote:
>
>>- Original Message-
>>From: kvm- devel- [EMAIL PROTECTED] [mailto:kvm- devel-
>>[EMAIL PROTECTED] On Behalf Of Gregory Haskins
>>Sent: Wednesday, May 09, 2007 6:19 PM
>>To: kvm-
22 matches
Mail list logo