On 06/09/2010 01:31 PM, Gordan Bobic wrote:
On 06/09/2010 09:56 AM, Paolo Bonzini wrote:
Or is this too crazy an idea?
It should work. Note that the the malloced memory should be aligned in
order to get better sharing.
Within glibc malloc large blocks are mmaped, so they are automatically
On 06/08/10 20:43, Gordan Bobic wrote:
Is this plausible?
I'm trying to work out if it's even worth considering this approach to
enable all memory used by in a system to be open to KSM page merging,
rather than only memory used by specific programs aware of it (e.g.
kvm/qemu).
Something
On 06/10/2010 08:33 AM, Dor Laor wrote:
On 06/09/2010 01:31 PM, Gordan Bobic wrote:
On 06/09/2010 09:56 AM, Paolo Bonzini wrote:
Or is this too crazy an idea?
It should work. Note that the the malloced memory should be aligned in
order to get better sharing.
Within glibc malloc large
On 06/10/2010 06:27 AM, Sheng Yang wrote:
From: Dexuan Cuidexuan@intel.com
This patch enable guest to use XSAVE/XRSTOR instructions.
We assume that host_xcr0 would use all possible bits that OS supported.
And we loaded xcr0 in the same way we handled fpu - do it as late as we can.
On 06/10/2010 08:44 AM, Jes Sorensen wrote:
On 06/08/10 20:43, Gordan Bobic wrote:
Is this plausible?
I'm trying to work out if it's even worth considering this approach to
enable all memory used by in a system to be open to KSM page merging,
rather than only memory used by specific programs
On 06/10/2010 06:27 AM, Sheng Yang wrote:
This patch enable save/restore of xsave state.
Signed-off-by: Sheng Yangsh...@linux.intel.com
---
Documentation/kvm/api.txt | 76 ++
arch/x86/include/asm/kvm.h | 24 ++
arch/x86/kvm/x86.c | 110
On 06/10/2010 12:17 AM, Zachary Amsden wrote:
On 06/09/2010 03:23 AM, Marcelo Tosatti wrote:
On Tue, Jun 08, 2010 at 04:36:16PM -1000, Zachary Amsden wrote:
+pt-timer.function = pit_timer_fn;
I am happy to see this. I thought kvm_timer_fn was a step
backwards; it was too general of a
Linus, please pull from
git://git.kernel.org/pub/scm/virt/kvm/kvm.git kvm-updates/2.6.35
to receive a bunch of KVM fixes for 2.6.35-rc2, including a workaround
for a cpu erratum that can allow a guest to crash the host.
Avi Kivity (1):
KVM: MMU: Remove user access when allowing
On 06/08/2010 06:51 PM, Balbir Singh wrote:
Balloon unmapped page cache pages first
From: Balbir Singhbal...@linux.vnet.ibm.com
This patch builds on the ballooning infrastructure by ballooning unmapped
page cache pages first. It looks for low hanging fruit first and tries
to reclaim clean
Am 09.06.2010 18:22, schrieb Anthony Liguori:
On 06/09/2010 10:31 AM, Daniel P. Berrange wrote:
However, libvirt was counting on this feature and on the snapshot commands
to switch from the text Monitor. We have two options:
1. Ask them to wait one more release (not so good for us)
2.
On 06/10/2010 06:31 AM, Sheng Yang wrote:
+
+#define EXCEPTION_REGION_BEGIN(r, lb) \
+asm volatile(pushq $lb\n\t \
+ mov $2, %0\n\t \
+ : =r(r))
+#define EXCEPTION_REGION_END(r, lb) \
+asm volatile(popq %%rdx\n\t \
+mov $0, %0\n\t \
+
On Thu, 2010-06-10 at 10:21 +0800, Zhang, Yanmin wrote:
. The ABI mostly includes the definition of struct perf_event_attr,
guest_perf_counter,
and hypercalls.
Note that perf_event_attr isn't guaranteed to be stable between kernels,
it can grow.
--
To unsubscribe from this list: send the line
Hi!
How is the guest supposed to halt the hypervisor if KVM_CREATE_IRQCHIP
is being used? The kvm_emulate_halt() function seems to handle the halt
event completely if irqchip_in_kernel() returns true and thus never
exits to the hypervisor.
I see there's a KVM_GET_MP_STATE ioctl that can be
On Thursday 10 June 2010 17:49:16 Avi Kivity wrote:
On 06/10/2010 06:31 AM, Sheng Yang wrote:
+
+#define EXCEPTION_REGION_BEGIN(r, lb) \
+asm volatile(pushq $lb\n\t \
+ mov $2, %0\n\t \
+ : =r(r))
+#define EXCEPTION_REGION_END(r, lb) \
+asm
On 06/10/2010 12:52 PM, Pekka Enberg wrote:
How is the guest supposed to halt the hypervisor if KVM_CREATE_IRQCHIP
is being used? The kvm_emulate_halt() function seems to handle the
halt event completely if irqchip_in_kernel() returns true and thus
never exits to the hypervisor.
The
Hi Avi,
On 06/10/2010 12:52 PM, Pekka Enberg wrote:
How is the guest supposed to halt the hypervisor if KVM_CREATE_IRQCHIP
is being used? The kvm_emulate_halt() function seems to handle the
halt event completely if irqchip_in_kernel() returns true and thus
never exits to the hypervisor.
On
On 06/10/2010 01:15 PM, Pekka Enberg wrote:
On 06/10/2010 12:52 PM, Pekka Enberg wrote:
I see there's a KVM_GET_MP_STATE ioctl that can be used to check if
state is KVM_MP_STATE_HALTED but as we never exit to the hypervisor,
how is this supposed to work? Am I missing something obvious here?
On 06/10/2010 12:55 PM, Sheng Yang wrote:
On Thursday 10 June 2010 17:49:16 Avi Kivity wrote:
On 06/10/2010 06:31 AM, Sheng Yang wrote:
+
+#define EXCEPTION_REGION_BEGIN(r, lb) \
+asm volatile(pushq $lb\n\t \
+ mov $2, %0\n\t \
+ : =r(r))
+#define
No real bugs in this one, the real bug I found is in a separate
patch.
Cc: a...@redhat.com
Cc: kvm@vger.kernel.org
Signed-off-by: Andi Kleen a...@linux.intel.com
---
arch/x86/kvm/paging_tmpl.h |1 +
arch/x86/kvm/vmx.c |3 +--
virt/kvm/assigned-dev.c|2 --
3 files
Real bug fix.
When the user passed in a NULL mask pass this on from the ioctl
handler.
Found by gcc 4.6's new warnings.
Cc: a...@redhat.com
Cc: kvm@vger.kernel.org
Signed-off-by: Andi Kleen a...@linux.intel.com
---
virt/kvm/kvm_main.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Avi Kivity wrote:
I have found out what have happen, current code has 2 serious bugs!
I will sent patches to fix these bugs tomorrow(because my box is broken).
And I will sent this use ro page and don't copy shared page
pathset next week.
Thanks a lot.
Lai
--
To unsubscribe from this list:
On 06/10/10 11:09, Gordan Bobic wrote:
On 06/10/2010 08:44 AM, Jes Sorensen wrote:
Not sure if it is worth it, but you might want to look at ElectricFence
which does malloc wrapping in a somewhat similar way. It might save you
some code :)
I'll look into it, but I don't see this requiring
On 06/10/2010 04:43 AM, Kevin Wolf wrote:
Huh, why this? Seems I still haven't understood all of qcow2 then... I
always thought that there's just a specific offset where VM state
starts, but no explicit end.
A live snapshot can last for a very long time. What happens if you need
to
Am 10.06.2010 14:53, schrieb Anthony Liguori:
On 06/10/2010 04:43 AM, Kevin Wolf wrote:
Huh, why this? Seems I still haven't understood all of qcow2 then... I
always thought that there's just a specific offset where VM state
starts, but no explicit end.
A live snapshot can last for a
Signed-off-by: Sheng Yang sh...@linux.intel.com
Signed-off-by: Avi Kivity a...@redhat.com
---
kvm/test/config-x86-common.mak |2 +
kvm/test/config-x86_64.mak |2 +-
kvm/test/flat.lds |7 ++-
kvm/test/lib/x86/idt.h | 19 +
kvm/test/x86/idt.c |
On 06/10/2010 01:55 PM, Avi Kivity wrote:
Something like =m(blah) can cause access to %rsp, usually when
compiling without frame pointers.
I suggest using a special data section like the kernel.
Kind of more complex...
Makes it more fun. I'll have a go.
Posted. Currently fails due to
On Intel, we call skip_emulated_instruction() even if we injected a #GP,
resulting in the #GP pointing at the wrong address.
Fix by injecting the exception and skipping the instruction at the same place,
so we can do just one or the other.
Signed-off-by: Avi Kivity a...@redhat.com
---
On Intel, we call skip_emulated_instruction() even if we injected a #GP,
resulting in the #GP pointing at the wrong address.
Fix by injecting the exception and skipping the instruction at the same place,
so we can do just one or the other.
Signed-off-by: Avi Kivity a...@redhat.com
---
Three mov cr instructions fail in a similar way when they fault: the
fault rip points at the next instead of faulting instructions. This
patch set fixes the problem.
Avi Kivity (3):
KVM: Fix mov cr0 #GP at wrong instruction
KVM: Fix mov cr4 #GP at wrong instruction
KVM: Fix mov cr3 #GP at
On Intel, we call skip_emulated_instruction() even if we injected a #GP,
resulting in the #GP pointing at the wrong address.
Fix by injecting the exception and skipping the instruction at the same place,
so we can do just one or the other.
Signed-off-by: Avi Kivity a...@redhat.com
---
On 06/10/2010 04:08 PM, Kevin Wolf wrote:
It's just not seen by the guest because
it's saved at a high offset that is after the end of the real disk
content, but otherwise it should behave the same as guest data.
That's very unfriendly towards extending the guest-visible portion of
the
On 06/10/2010 02:10 PM, Andi Kleen wrote:
Real bug fix.
When the user passed in a NULL mask pass this on from the ioctl
handler.
Found by gcc 4.6's new warnings.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the
Am 10.06.2010 16:11, schrieb Avi Kivity:
On 06/10/2010 04:08 PM, Kevin Wolf wrote:
It's just not seen by the guest because
it's saved at a high offset that is after the end of the real disk
content, but otherwise it should behave the same as guest data.
That's very unfriendly towards
On Fri, Jun 04, 2010 at 02:03:16PM -0300, Marcelo Tosatti wrote:
On Wed, Jun 02, 2010 at 09:01:52PM +0300, Michael S. Tsirkin wrote:
vhost net currently keeps running after vmstop,
which causes trouble as qemy does not check
for dirty pages anymore.
The fix is to simply keep vm and vhost
* Avi Kivity a...@redhat.com [2010-06-10 12:43:11]:
On 06/08/2010 06:51 PM, Balbir Singh wrote:
Balloon unmapped page cache pages first
From: Balbir Singhbal...@linux.vnet.ibm.com
This patch builds on the ballooning infrastructure by ballooning unmapped
page cache pages first. It looks
On 06/10/2010 08:08 AM, Kevin Wolf wrote:
Am 10.06.2010 14:53, schrieb Anthony Liguori:
On 06/10/2010 04:43 AM, Kevin Wolf wrote:
Huh, why this? Seems I still haven't understood all of qcow2 then... I
always thought that there's just a specific offset where VM state
starts, but no
On 06/10/2010 09:19 AM, Michael S. Tsirkin wrote:
On Fri, Jun 04, 2010 at 02:03:16PM -0300, Marcelo Tosatti wrote:
On Wed, Jun 02, 2010 at 09:01:52PM +0300, Michael S. Tsirkin wrote:
vhost net currently keeps running after vmstop,
which causes trouble as qemy does not check
for dirty
On Thu, 2010-06-10 at 10:23 +0200, Gerd Hoffmann wrote:
I may have been a bit misleading here. What we really want to do is use the
same matching algorithm as is used by the rest of the device state.
Currently
this is a vmstate name and [arbitrary] numeric id. I don't remember whether
On 06/10/2010 02:10 PM, Andi Kleen wrote:
No real bugs in this one, the real bug I found is in a separate
patch.
Index: linux-2.6.35-rc2-gcc/arch/x86/kvm/vmx.c
===
--- linux-2.6.35-rc2-gcc.orig/arch/x86/kvm/vmx.c
+++
A VF interrupt usually happens in 4-8KHZ. How about the virtio?
I assume virtio will be widely used together w/ leagcy guest with
INTx mode.
True, but in time it will be replaced by MSI.
Note without vhost virtio is also in userspace, so there are lots of
exits anyway for the status
On Thu, 2010-06-10 at 10:23 +0200, Gerd Hoffmann wrote:
I may have been a bit misleading here. What we really want to do is use
the same matching algorithm as is used by the rest of the device
state. Currently this is a vmstate name and [arbitrary] numeric id. I
don't remember whether
On Wed, 2010-06-09 at 21:36 +0100, Paul Brook wrote:
Not really. This identifier is device and bus independent, which is why
I suggested passing the device to qemu_ram_alloc. This can then figure
out how to the identify the device. It should probably do this the same
way that we
On Thu, 2010-06-10 at 15:49 +0100, Paul Brook wrote:
On Thu, 2010-06-10 at 10:23 +0200, Gerd Hoffmann wrote:
I may have been a bit misleading here. What we really want to do is use
the same matching algorithm as is used by the rest of the device
state. Currently this is a vmstate
On Wed, Jun 09, 2010 at 11:17:41AM -1000, Zachary Amsden wrote:
On 06/09/2010 03:23 AM, Marcelo Tosatti wrote:
On Tue, Jun 08, 2010 at 04:36:16PM -1000, Zachary Amsden wrote:
+ pt-timer.function = pit_timer_fn;
I am happy to see this. I thought kvm_timer_fn was a step
backwards; it was
The last thing assign_device() does is call into KVM_ASSIGN_PCI_DEVICE.
If that fails, the device is not assigned, so we shouldn't then try to
deassign it. If you try to assign the same device multiple times, you
can get into a nasty fail-succeed-fail-succeed loop. And we certainly
shouldn't
On Thu, Jun 10, 2010 at 2:31 AM, Avi Kivity a...@redhat.com wrote:
Linus, please pull from
git://git.kernel.org/pub/scm/virt/kvm/kvm.git kvm-updates/2.6.35
to receive a bunch of KVM fixes for 2.6.35-rc2, including a workaround for a
cpu erratum that can allow a guest to crash the host.
* Alex Williamson (alex.william...@redhat.com) wrote:
On Wed, 2010-06-09 at 13:18 +0100, Paul Brook wrote:
to the identify the device. It should probably do this the same way that we
identify the saved state for the device. Currently I think this is an
arbitrary vmstate name/id, but I
to the identify the device. It should probably do this the same way
that we identify the saved state for the device. Currently I think
this is an arbitrary vmstate name/id, but I expect this to change to a
qdev address (e.g. /i440FX-pcihost/pci.0/_addr_04.0).
Ok, that seems
+EXPORT_SYMBOL(uiommu_fdget);
EXPORT_SYMBOL_GPL
.. snip
+EXPORT_SYMBOL(uiommu_put);
ditto.
--
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
On 06/10/2010 07:33 PM, Linus Torvalds wrote:
On Thu, Jun 10, 2010 at 2:31 AM, Avi Kivitya...@redhat.com wrote:
Linus, please pull from
git://git.kernel.org/pub/scm/virt/kvm/kvm.git kvm-updates/2.6.35
to receive a bunch of KVM fixes for 2.6.35-rc2, including a workaround for a
cpu
On Thu, Jun 10, 2010 at 10:34 AM, Avi Kivity a...@redhat.com wrote:
Ok. I've dropped the SRAO patch; this still leaves ~100 changed lines, but
they are almost all due to the erratum 383 workaround, which can result in a
guest killing the host. The rest of the patches are less critical, but
On Thu, Jun 10, 2010 at 11:27:12AM +0800, Sheng Yang wrote:
From: Dexuan Cui dexuan@intel.com
This patch enable guest to use XSAVE/XRSTOR instructions.
We assume that host_xcr0 would use all possible bits that OS supported.
And we loaded xcr0 in the same way we handled fpu - do it as
On 06/10/2010 09:28 PM, Stephen Hemminger wrote:
With current 2.6.35-rc2 and following configuration, my build guest VM will
not start (it was working previously).
Error starting domain: monitor socket did not show up: Connection refused
Surprisingly, other guests work fine. The one
On Thu, 10 Jun 2010 21:44:07 +0300
Avi Kivity a...@redhat.com wrote:
On 06/10/2010 09:28 PM, Stephen Hemminger wrote:
With current 2.6.35-rc2 and following configuration, my build guest VM will
not start (it was working previously).
Error starting domain: monitor socket did not show
As we've discussed previously, here is a series of patches to
fix some of the IRQ routing issues we have in KVM. With this series
in place I was able to successfully kdump a RHEL-5 64-bit, and RHEL-6
32- and 64-bit guest on CPU's other than the BSP. RHEL-5 32-bit kdump still
does not work; it
We really want to kvm_set_irq during the hrtimer callback,
but that is risky because that is during interrupt context.
Instead, offload the work to a workqueue, which is a bit safer
and should provide most of the same functionality.
Signed-off-by: Chris Lalancette clala...@redhat.com
---
Otherwise we might try to deliver a timer interrupt to a cpu that
can't possibly handle it.
Signed-off-by: Chris Lalancette clala...@redhat.com
---
virt/kvm/irq_comm.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index
If the guest wants to accept timer interrupts on a CPU other
than the BSP, we need to remove this gate.
Signed-off-by: Chris Lalancette clala...@redhat.com
---
arch/x86/kvm/lapic.c | 12 +---
1 files changed, 5 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/lapic.c
This is v2 of monitor commands based on Stefan's trace framework :
( http://lists.gnu.org/archive/html/qemu-devel/2010-05/msg02407.html )
This adds the following monitor commands for the 'simple' backend:
- info trace: to view current contents of the trace buffer.
- info tracepoints
For now, I simply export tdb_hash() from qdict.h for use by tracing
framework.
Luiz suggested renaming and exporting it from a location other than
qdict.h . Would qemu-common.h be a better place?
Signed-off-by: Prerna Saxena pre...@linux.vnet.ibm.com
---
qdict.c |2 +-
qdict.h |2 ++
On 06/09/2010 11:24 PM, Avi Kivity wrote:
On 06/10/2010 12:17 AM, Zachary Amsden wrote:
On 06/09/2010 03:23 AM, Marcelo Tosatti wrote:
On Tue, Jun 08, 2010 at 04:36:16PM -1000, Zachary Amsden wrote:
+pt-timer.function = pit_timer_fn;
I am happy to see this. I thought kvm_timer_fn was a
This patch adds support for dynamically enabling/disabling of tracepoints.
Monitor commands added :
1) info tracepoints : to view all available tracepoints and
their state.
2) tracepoint NAME on|off : to enable/disable data logging from a
close() the resource fd when we're done with it. Unregister and munmap the
anonymous memory for the MSIX table.
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
hw/device-assignment.c | 21 +
1 files changed, 21 insertions(+), 0 deletions(-)
diff --git
This introduces the monitor command 'info trace' to display current
contents of trace buffer.
Signed-off-by: Prerna Saxena pre...@linux.vnet.ibm.com
---
configure |3 +++
monitor.c | 12
qemu-monitor.hx |4
simpletrace.c | 12
tracetool
On Thu, 2010-06-10 at 19:55 +0530, Balbir Singh wrote:
I'm not sure victimizing unmapped cache pages is a good idea.
Shouldn't page selection use the LRU for recency information instead
of the cost of guest reclaim? Dropping a frequently used unmapped
cache page can be more expensive than
Bugs item #2832416, was opened at 2009-08-05 09:49
Message generated for change (Comment added) made by haoxudong
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2832416group_id=180599
Please note that this message will contain a full copy of the comment
On Thu, 10 Jun 2010 17:07:32 -0700
Dave Hansen d...@linux.vnet.ibm.com wrote:
On Thu, 2010-06-10 at 19:55 +0530, Balbir Singh wrote:
I'm not sure victimizing unmapped cache pages is a good idea.
Shouldn't page selection use the LRU for recency information instead
of the cost of guest
On Thursday 10 June 2010 10:27:36 am Konrad Rzeszutek Wilk wrote:
+EXPORT_SYMBOL(uiommu_fdget);
EXPORT_SYMBOL_GPL
.. snip
+EXPORT_SYMBOL(uiommu_put);
ditto.
Is there a definitive explanation somewhere of when to use each?
--
To unsubscribe from this list: send the line unsubscribe
On Thu, 2010-06-10 at 11:50 +0200, Peter Zijlstra wrote:
On Thu, 2010-06-10 at 10:21 +0800, Zhang, Yanmin wrote:
. The ABI mostly includes the definition of struct perf_event_attr,
guest_perf_counter,
and hypercalls.
Note that perf_event_attr isn't guaranteed to be stable between
The following patch implements a simple busy-spin detector. It considers
a vcpu as busy-spinning if there are two consecutive exits due to
external interrupt on the same RIP, and sleeps for 100us in that case.
It is very likely that if the vcpu is making progress it will either
exit for other
On Thu, Jun 10, 2010 at 06:58:37PM -0700, Tom Lyon wrote:
On Thursday 10 June 2010 10:27:36 am Konrad Rzeszutek Wilk wrote:
+EXPORT_SYMBOL(uiommu_fdget);
EXPORT_SYMBOL_GPL
.. snip
+EXPORT_SYMBOL(uiommu_put);
ditto.
Is there a definitive explanation somewhere of when to use
This patch enable save/restore of xsave state.
Signed-off-by: Sheng Yang sh...@linux.intel.com
---
Documentation/kvm/api.txt| 74 +
arch/x86/include/asm/kvm.h | 22 ++
arch/x86/include/asm/xsave.h |7 ++-
arch/x86/kvm/x86.c | 145
Signed-off-by: Sheng Yang sh...@linux.intel.com
---
qemu-kvm-x86.c| 109 -
qemu-kvm.c| 24 +++
qemu-kvm.h| 28 +
target-i386/cpu.h |5 ++
target-i386/kvm.c |2 +
* KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com [2010-06-11 10:54:41]:
On Thu, 10 Jun 2010 17:07:32 -0700
Dave Hansen d...@linux.vnet.ibm.com wrote:
On Thu, 2010-06-10 at 19:55 +0530, Balbir Singh wrote:
I'm not sure victimizing unmapped cache pages is a good idea.
Shouldn't page
* Dave Hansen d...@linux.vnet.ibm.com [2010-06-10 17:07:32]:
On Thu, 2010-06-10 at 19:55 +0530, Balbir Singh wrote:
I'm not sure victimizing unmapped cache pages is a good idea.
Shouldn't page selection use the LRU for recency information instead
of the cost of guest reclaim? Dropping
On Fri, 11 Jun 2010 10:16:32 +0530
Balbir Singh bal...@linux.vnet.ibm.com wrote:
* KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com [2010-06-11 10:54:41]:
On Thu, 10 Jun 2010 17:07:32 -0700
Dave Hansen d...@linux.vnet.ibm.com wrote:
On Thu, 2010-06-10 at 19:55 +0530, Balbir Singh
On Fri, 11 Jun 2010 14:05:53 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
I can think of both way in kernel and in user approarh and they should be
complement to each other.
An example of kernel-based approach is.
1. add a shrinker callback(A) for balloon-driver-for-guest
On 06/10/2010 06:27 AM, Sheng Yang wrote:
From: Dexuan Cuidexuan@intel.com
This patch enable guest to use XSAVE/XRSTOR instructions.
We assume that host_xcr0 would use all possible bits that OS supported.
And we loaded xcr0 in the same way we handled fpu - do it as late as we can.
78 matches
Mail list logo