On Sat, Oct 09, 2010 at 08:30:18PM +0200, Avi Kivity wrote:
On 10/07/2010 07:47 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 11:50:08AM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
If a guest accesses swapped out memory do not swap it in from vcpu thread
On Sat, Oct 09, 2010 at 08:32:14PM +0200, Avi Kivity wrote:
On 10/09/2010 08:30 PM, Avi Kivity wrote:
So that info cpu will interfere with apf? Migration should work
in regular way. apf state should not be migrated since it has no meaning
on the destination. I'll make sure synthetic halt
On Sat, Oct 09, 2010 at 08:42:00PM +0200, Avi Kivity wrote:
On 10/07/2010 07:21 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 02:29:07PM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
When page is swapped in it is mapped into guest memory only after guest
tries
On Sat, Oct 09, 2010 at 08:48:15PM +0200, Avi Kivity wrote:
On 10/07/2010 08:03 PM, Gleb Natapov wrote:
Host side keeps track of outstanding apfs and will not send apf for the
same phys address twice. It will halt vcpu instead.
What about different pages, running the scheduler
On 10/08/2010 06:44 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 09:49:17PM -0300, Marcelo Tosatti wrote:
On Thu, Oct 07, 2010 at 07:56:55PM +0200, Gleb Natapov wrote:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b8499f5..8800713 100644
---
Hi Marcelo / Avi,
Scott has found some bugs in the BookE implementation of KVM, so please pull
the fixes for them to the kvm tree.
The following changes since commit 3c4504636ab1ff41ec162980bf85121aee14e58f:
Huang Ying (1):
KVM: MCE: Send SRAR SIGBUS directly
are available in the git
From: Scott Wood scottw...@freescale.com
It is not legal to call mutex_lock() with interrupts disabled.
This will assert with debug checks enabled.
If there's a real need to disable interrupts here, it could be done
after the mutex is acquired -- but I don't see why it's needed at all.
From: Scott Wood scottw...@freescale.com
The VCPU uninit calls some TLB functions, and the TLB uninit function
frees the memory used by them.
Signed-off-by: Scott Wood scottw...@freescale.com
Acked-by: Liu Yu yu@freescale.com
Signed-off-by: Alexander Graf ag...@suse.de
---
From: Scott Wood scottw...@freescale.com
This was preventing the guest from setting any bits in the
hardware MSR which aren't forced on, such as MSR[SPE].
Signed-off-by: Scott Wood scottw...@freescale.com
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/kvm/booke_interrupts.S |2
Hi,
More importantly: anyone's going to work on this?
I'd like to work on this. Might need some assistance though.
Thanks,
Dragos
--
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
On Sun, Oct 10, 2010 at 01:37:45PM +0200, Dragos Tatulea wrote:
Hi,
More importantly: anyone's going to work on this?
I'd like to work on this. Might need some assistance though.
Thanks,
Dragos
Cool, you can add this info to the wiki.
Thanks!
--
MST
--
To unsubscribe from this list:
On Thu, Oct 07, 2010 at 03:10:27PM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
When async PF capability is detected hook up special page fault handler
that will handle async page fault events and bypass other page faults to
regular page fault handler. Also add async
On 10/10/2010 02:32 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 03:10:27PM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
When async PF capability is detected hook up special page fault handler
that will handle async page fault events and bypass other page
On 10/10/2010 09:56 AM, Gleb Natapov wrote:
On Sat, Oct 09, 2010 at 08:48:15PM +0200, Avi Kivity wrote:
On 10/07/2010 08:03 PM, Gleb Natapov wrote:
Host side keeps track of outstanding apfs and will not send apf for the
same phys address twice. It will halt vcpu instead.
On 10/07/2010 07:53 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 02:42:06PM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
Guest enables async PF vcpu functionality using this MSR.
return NON_PRESENT;
+
+MSR_KVM_ASYNC_PF_EN:
On 10/07/2010 07:23 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 06:20:53PM +0200, Avi Kivity wrote:
On 10/07/2010 06:03 PM, Gleb Natapov wrote:
Isn't SET_USER_MEMORY_REGION so slow that calling it 2^32 times
isn't really feasible?
Assuming it takes 1ms, it
On Sun, Oct 10, 2010 at 02:38:58PM +0200, Avi Kivity wrote:
On 10/10/2010 02:32 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 03:10:27PM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
When async PF capability is detected hook up special page fault handler
that
On Sun, Oct 10, 2010 at 02:47:43PM +0200, Avi Kivity wrote:
On 10/07/2010 07:53 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 02:42:06PM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
Guest enables async PF vcpu functionality using this MSR.
On Wed, Oct 06, 2010 at 12:41:32PM +0200, Gleb Natapov wrote:
On Tue, Oct 05, 2010 at 04:51:50PM -0300, Marcelo Tosatti wrote:
On Mon, Oct 04, 2010 at 05:56:32PM +0200, Gleb Natapov wrote:
If async page fault is received by idle task or when preemp_count is
not zero guest cannot
Due to a depedency on kvm's msix support, msix.c was changed to be a target
dependent file. This patch set changes it back.
v2: make the msix.c-kvm.c interface at a finer granularity, removing the need
for kvm code to know about PCIDevice.
Avi Kivity (8):
msix: avoid leaking kvm data on
Move initialization after we're certain to succeed, so we don't leak
memory on failure.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/msix.c | 13 +++--
1 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/hw/msix.c b/hw/msix.c
index 9663b17..162faa7 100644
--- a/hw/msix.c
kvm_irq_routing_entry cannot be used when CONFIG_KVM is disabled; add a new
interface to the kvm support code that uses scalars instead.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/msix.c| 35 ++-
qemu-kvm.c | 44
To allow msix to build without kvm support, add stubs for these functions.
Move the declarations to kvm.h so they are accessible when kvm support is not
built.
Signed-off-by: Avi Kivity a...@redhat.com
---
kvm-stub.c | 35 +++
kvm.h | 13 +
Now that the kvm support is properly stubbed, we can build the msix/kvm glue
unconditionally.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/msix.c | 10 --
1 files changed, 0 insertions(+), 10 deletions(-)
diff --git a/hw/msix.c b/hw/msix.c
index c752e90..f6ab686 100644
---
- don't include qemu-kvm.h when NEED_CPU_H not defined
- move a couple of declarations around
Signed-off-by: Avi Kivity a...@redhat.com
---
kvm.h | 11 +++
1 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/kvm.h b/kvm.h
index 2f12851..d484a3f 100644
--- a/kvm.h
+++ b/kvm.h
Now that hw/msix.c does not depend on CONFIG_KVM, remove it from
Makefile.target and put it back in Makefile.objs.
Signed-off-by: Avi Kivity a...@redhat.com
---
Makefile.objs |4 +---
Makefile.target |4
2 files changed, 1 insertions(+), 7 deletions(-)
diff --git a/Makefile.objs
The kvm_context parameter serves no useful purpose since it's a global (and
all callers reference that global); on the other hand it prevents the build
when kvm is not configured in since the kvm_context symbol is not defined.
Remove the parameter and replace it by the global kvm_context in
This structure is not available when !CONFIG_KVM. While an incomplete type
works if it's not used, you can't do address arithmetic on it.
Use a new type kvm_msix_message instead.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/msix.c | 60
Hi,
I would like to use a resolution 1920x1080 for my Windows XP Guest.
However I only see 1680x1050 and 19520x1200 with nothing in between.I
did see a message that resolution 1920x1080 was added to to vga bios.
Anyone knows how I can activate the 1920x1080 resolution? I'm using
Debian sid.
On Sun, Oct 10, 2010 at 04:41:59PM +0200, Avi Kivity wrote:
Due to a depedency on kvm's msix support, msix.c was changed to be a target
dependent file. This patch set changes it back.
Nothing to object to here :). FWIW
Acked-by: Michael S. Tsirkin m...@redhat.com
v2: make the msix.c-kvm.c
On Sun, Oct 10, 2010 at 10:45:45AM +0200, Avi Kivity wrote:
On 10/08/2010 06:44 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 09:49:17PM -0300, Marcelo Tosatti wrote:
On Thu, Oct 07, 2010 at 07:56:55PM +0200, Gleb Natapov wrote:
diff --git a/virt/kvm/kvm_main.c
On 10/10/2010 09:29 AM, Gleb Natapov wrote:
On Sat, Oct 09, 2010 at 08:30:18PM +0200, Avi Kivity wrote:
On 10/07/2010 07:47 PM, Gleb Natapov wrote:
On Thu, Oct 07, 2010 at 11:50:08AM +0200, Avi Kivity wrote:
On 10/04/2010 05:56 PM, Gleb Natapov wrote:
If a guest accesses swapped
On 10/10/2010 05:55 PM, Avi Kivity wrote:
There is special completion that tells guest to wake all sleeping tasks
on vcpu. It is delivered after migration on the destination.
Yes, I saw.
What if you can't deliver it? is it possible that some other vcpu
will start receiving apfs that
On Sun, Oct 10, 2010 at 05:55:25PM +0200, Avi Kivity wrote:
@@ -5112,6 +5122,13 @@ static int vcpu_enter_guest(struct kvm_vcpu
*vcpu)
if (unlikely(r))
goto out;
+ kvm_check_async_pf_completion(vcpu);
+ if
On Sun, Oct 10, 2010 at 05:56:31PM +0200, Avi Kivity wrote:
On 10/10/2010 05:55 PM, Avi Kivity wrote:
There is special completion that tells guest to wake all sleeping tasks
on vcpu. It is delivered after migration on the destination.
Yes, I saw.
What if you can't deliver it? is it
On Fri, Oct 1, 2010 at 7:29 AM, Avi Kivity a...@redhat.com wrote:
On 10/01/2010 08:16 AM, Neo Jia wrote:
On Wed, Sep 29, 2010 at 1:38 AM, Avi Kivitya...@redhat.com wrote:
On 09/28/2010 08:40 PM, Neo Jia wrote:
I found the instruction that caused this problem:
emulation failed
Hi Marcelo / Avi,
Scott has found some bugs in the BookE implementation of KVM, so please pull
the fixes for them to the kvm tree.
The following changes since commit 3c4504636ab1ff41ec162980bf85121aee14e58f:
Huang Ying (1):
KVM: MCE: Send SRAR SIGBUS directly
are available in the git
From: Scott Wood scottw...@freescale.com
It is not legal to call mutex_lock() with interrupts disabled.
This will assert with debug checks enabled.
If there's a real need to disable interrupts here, it could be done
after the mutex is acquired -- but I don't see why it's needed at all.
From: Scott Wood scottw...@freescale.com
The VCPU uninit calls some TLB functions, and the TLB uninit function
frees the memory used by them.
Signed-off-by: Scott Wood scottw...@freescale.com
Acked-by: Liu Yu yu@freescale.com
Signed-off-by: Alexander Graf ag...@suse.de
---
39 matches
Mail list logo
