On Tue, Apr 16, 2013 at 08:38:56PM -0400, Sasha Levin wrote:
> > select NET
> > select NETDEVICES
> > select PCI
> > select BLOCK
> > select BLK_DEV
> > select NETWORK_FILESYSTEMS
> > select INET
> > select EXPERIMENTAL
> > select TTY
> > select SERIAL_8250
>
On Tue, 16 Apr 2013 16:25:10 -0700, Christoffer Dall
wrote:
> The following changes since commit
> 31880c37c11e28cb81c70757e38392b42e695dc6:
>
> Linux 3.9-rc6 (2013-04-07 20:49:54 -0700)
>
> are available in the git repository at:
>
> git://github.com/columbia/linux-kvm-arm.git kvm-arm-fixe
On Wed, Apr 17, 2013 at 02:10:01AM -0700, Christoffer Dall wrote:
> On Wed, Apr 17, 2013 at 1:05 AM, Marc Zyngier wrote:
>
> > On Tue, 16 Apr 2013 16:25:10 -0700, Christoffer Dall
> > wrote:
> > > The following changes since commit
> > > 31880c37c11e28cb81c70757e38392b42e695dc6:
> > >
> > > Li
Il 16/04/2013 19:28, Gleb Natapov ha scritto:
> > This does highlight a weakness in CPU_GET_SUPPORTED_CPUID, but I think
> > this is not a problem in practice.
> >
> > With a management layer such as oVirt it's not a problem. For example,
> > oVirt has its own library of processors. It doesn't c
On Wed, Apr 17, 2013 at 12:28:15PM +0200, Alexander Graf wrote:
>
> On 17.04.2013, at 12:17, Christoffer Dall wrote:
>
> >
> >
> >
> > On Wed, Apr 17, 2013 at 2:20 AM, Gleb Natapov wrote:
> > On Wed, Apr 17, 2013 at 02:10:01AM -0700, Christoffer Dall wrote:
> > > On Wed, Apr 17, 2013 at 1:05
On Tue, Apr 16, 2013 at 08:42:36PM +0300, Gleb Natapov wrote:
> > Right, and this is what we have, AFAICT. And if userspace does that what
> > you exemplify above, you get exactly that - a feature bit not set in
> > CPUID but KVM reporting it set means, it is emulated. There's no room
> > for other
On Wed, Apr 17, 2013 at 3:45 AM, Gleb Natapov wrote:
> Marcelo has sent pull request yesterday and Linus pulled it
> already. Sorry if I was not clear. Generally specking we should not wait
> so late into the release to send fixes to Linus, exceptions happen of
> course.
I know, the reason everyt
On Wed, Apr 17, 2013 at 09:29:53AM +0800, Asias He wrote:
> On Tue, Apr 16, 2013 at 08:58:27PM +0300, Michael S. Tsirkin wrote:
> > On Tue, Apr 16, 2013 at 05:16:51PM +0800, Asias He wrote:
> > > This patch makes vhost_scsi_flush() wait for all the pending requests
> > > issued before the flush ope
On 17.04.2013, at 13:05, Christoffer Dall wrote:
> On Wed, Apr 17, 2013 at 3:45 AM, Gleb Natapov wrote:
>> Marcelo has sent pull request yesterday and Linus pulled it
>> already. Sorry if I was not clear. Generally specking we should not wait
>> so late into the release to send fixes to Linus, e
On Wed, Apr 17, 2013 at 4:08 AM, Alexander Graf wrote:
>
> On 17.04.2013, at 13:05, Christoffer Dall wrote:
>
>> On Wed, Apr 17, 2013 at 3:45 AM, Gleb Natapov wrote:
>>> Marcelo has sent pull request yesterday and Linus pulled it
>>> already. Sorry if I was not clear. Generally specking we should
On Wed, Apr 17, 2013 at 04:05:31AM -0700, Christoffer Dall wrote:
> On Wed, Apr 17, 2013 at 3:45 AM, Gleb Natapov wrote:
> > Marcelo has sent pull request yesterday and Linus pulled it
> > already. Sorry if I was not clear. Generally specking we should not wait
> > so late into the release to send
Il 16/04/2013 00:10, Andrew Honig ha scritto:
>
> The motivation for this patch is to fix a 20KB leak of memory in vmx.c
> when a VM is created and destroyed.
>
> On x86/vmx platforms KVM needs 5 pages of userspace memory per VM for
> architecture specific reasons. It currently allocates the pa
Il 16/04/2013 19:26, Alexander Graf ha scritto:
> Quite a bit of code in KVM has been conditionalized on availability of
> IOAPIC emulation. However, most of it is generically applicable to
> platforms that don't have an IOPIC, but a different type of irq chip.
>
> Introduce a new define to distin
This series of patches implements shadow-vmcs capability for nested VMX.
Shadow-vmcs - background and overview:
In Intel VMX, vmread and vmwrite privileged instructions are used by the
hypervisor to read and modify the guest and host specifications (VMCS). In a
nested virtualization environmen
Il 16/04/2013 19:26, Alexander Graf ha scritto:
> The current irq_comm.c file contains pieces of code that are generic
> across different irqchip implementations, as well as code that is
> fully IOAPIC specific.
>
> Split the generic bits out into irqchip.c.
>
> Signed-off-by: Alexander Graf
> -
Add definitions for all the vmcs control fields/bits
required to enable vmcs-shadowing
Signed-off-by: Abel Gordon
---
arch/x86/include/asm/vmx.h|3 +++
arch/x86/include/uapi/asm/msr-index.h |2 ++
2 files changed, 5 insertions(+)
--- .before/arch/x86/include/asm/vmx.h 2013-
Il 16/04/2013 19:26, Alexander Graf ha scritto:
> The concept of routing interrupt lines to an irqchip is nothing
> that is IOAPIC specific. Every irqchip has a maximum number of pins
> that can be linked to irq lines.
>
> So let's add a new define that allows us to reuse generic code for
> non-IO
Add logic required to detect if shadow-vmcs is supported by the
processor. Introduce a new kernel module parameter to specify if L0 should use
shadow vmcs (or not) to run L1.
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 25 -
1 file changed, 24 insertions(+), 1 d
Prepare vmread and vmwrite bitmaps according to a pre-specified list of fields.
These lists are intended to specifiy most frequent accessed fields so we can
minimize the number of fields that are copied from/to the software controlled
VMCS12 format to/from to processor-specific shadow vmcs. The lis
Refactor existent code so we re-use vmcs12_write_any to copy fields from the
shadow vmcs specified by the link pointer (used by the processor,
implementation-specific) to the VMCS12 software format used by L0 to hold
the fields in L1 memory address space.
Signed-off-by: Abel Gordon
---
arch/x86/
On 17.04.2013, at 13:49, Paolo Bonzini wrote:
> Il 16/04/2013 19:26, Alexander Graf ha scritto:
>> Quite a bit of code in KVM has been conditionalized on availability of
>> IOAPIC emulation. However, most of it is generically applicable to
>> platforms that don't have an IOPIC, but a different ty
Allocate a shadow vmcs used by the processor to shadow part of the fields
stored in the software defined VMCS12 (let L1 access fields without causing
exits). Note we keep a shadow vmcs only for the current vmcs12. Once a vmcs12
becomes non-current, its shadow vmcs is released.
Signed-off-by: Abe
Unmap vmcs12 and release the corresponding shadow vmcs
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 23 +++
1 file changed, 15 insertions(+), 8 deletions(-)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 14:20:50.0 +0300
+++ .after/arch/x86/kvm/vmx.c 2013-04-
On 17.04.2013, at 13:50, Paolo Bonzini wrote:
> Il 16/04/2013 19:26, Alexander Graf ha scritto:
>> The current irq_comm.c file contains pieces of code that are generic
>> across different irqchip implementations, as well as code that is
>> fully IOAPIC specific.
>>
>> Split the generic bits out
Introduce a function used to copy fields from the processor-specific shadow
vmcs to the software controlled VMCS12
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 35 +++
1 file changed, 35 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 14:20:51.0
Introduce a function used to copy fields from the software controlled VMCS12
to the processor-specific shadow vmcs
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 45 +++
1 file changed, 45 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 14
Synchronize between the VMCS12 software controlled structure and the
processor-specific shadow vmcs
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 24
1 file changed, 24 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 14:20:51.0 +0300
+++ .after/
Il 17/04/2013 13:53, Alexander Graf ha scritto:
>>> >> arch/x86/include/uapi/asm/kvm.h |1 +
>>> >> include/linux/kvm_host.h|4 ++--
>>> >> include/uapi/linux/kvm.h|2 +-
>>> >> virt/kvm/eventfd.c |6 +++---
>>> >> 4 files changed, 7 insertions(+), 6 deletio
Once L1 loads VMCS12 we enable shadow-vmcs capability and copy all the VMCS12
shadowed fields to the shadow vmcs. When we release the VMCS12, we also
disable shadow-vmcs capability.
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 11 +++
1 file changed, 11 insertions(+)
--- .befo
On 17.04.2013, at 13:54, Paolo Bonzini wrote:
> Il 17/04/2013 13:53, Alexander Graf ha scritto:
>> arch/x86/include/uapi/asm/kvm.h |1 +
>> include/linux/kvm_host.h|4 ++--
>> include/uapi/linux/kvm.h|2 +-
>> virt/kvm/eventfd.c |6 +++---
Il 16/04/2013 19:26, Alexander Graf ha scritto:
> +#ifdef kvm_irqchip
> TP_printk("irqchip %s pin %u",
> __print_symbolic(__entry->irqchip, kvm_irqchips),
>__entry->pin)
> +#else
> + TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin)
> +#endif
On 17.04.2013, at 14:05, Paolo Bonzini wrote:
> Il 16/04/2013 19:26, Alexander Graf ha scritto:
>> +#ifdef kvm_irqchip
>> TP_printk("irqchip %s pin %u",
>>__print_symbolic(__entry->irqchip, kvm_irqchips),
>> __entry->pin)
>> +#else
>> +TP_printk("irqchip %d
Il 17/04/2013 13:59, Alexander Graf ha scritto:
>> > Well, we just got a patch to make it at least compile,
> That was really just Yang (blindly?) fixing an issue I pointed out on
> ARM. There is no kvm user space support for IA64. The kernel side has
> been KConfig depending on BROKEN for a year a
On Wed, Apr 17, 2013 at 01:07:56PM +0300, Michael S. Tsirkin wrote:
> On Wed, Apr 17, 2013 at 09:29:53AM +0800, Asias He wrote:
> > On Tue, Apr 16, 2013 at 08:58:27PM +0300, Michael S. Tsirkin wrote:
> > > On Tue, Apr 16, 2013 at 05:16:51PM +0800, Asias He wrote:
> > > > This patch makes vhost_scsi
On 17.04.2013, at 14:06, Paolo Bonzini wrote:
> Il 17/04/2013 13:59, Alexander Graf ha scritto:
Well, we just got a patch to make it at least compile,
>> That was really just Yang (blindly?) fixing an issue I pointed out on
>> ARM. There is no kvm user space support for IA64. The kernel side
Il 17/04/2013 14:10, Alexander Graf ha scritto:
>>> Still, __KVM_HAVE_IRQCHIP is clearly a subset of
>>> __KVM_HAVE_IOAPIC; defining one without the other makes no sense
>>> and will cause compilation or link errors for trace_kvm_ack_irq.
>>>
>>> Either we drop it altogether, or we should not brea
On 17.04.2013, at 14:15, Paolo Bonzini wrote:
> Il 17/04/2013 14:10, Alexander Graf ha scritto:
Still, __KVM_HAVE_IRQCHIP is clearly a subset of
__KVM_HAVE_IOAPIC; defining one without the other makes no sense
and will cause compilation or link errors for trace_kvm_ack_irq.
>
On Mon, Apr 15, 2013 at 03:10:32PM -0700, Andrew Honig wrote:
>
> The motivation for this patch is to fix a 20KB leak of memory in vmx.c
> when a VM is created and destroyed.
>
> On x86/vmx platforms KVM needs 5 pages of userspace memory per VM for
> architecture specific reasons. It currently
On Mon, Apr 15, 2013 at 11:30:13PM -0300, Marcelo Tosatti wrote:
>
> ** Untested **.
>
> Emulation of xcr0 writes zero guest_xcr0_loaded variable so that
> subsequent VM-entry reloads CPU's xcr0 with guests xcr0 value.
>
> However, this is incorrect because guest_xcr0_loaded variable is
> read
On Wed, Apr 17, 2013 at 12:42:30PM +0200, Paolo Bonzini wrote:
> Il 16/04/2013 19:28, Gleb Natapov ha scritto:
> > > This does highlight a weakness in CPU_GET_SUPPORTED_CPUID, but I think
> > > this is not a problem in practice.
> > >
> > > With a management layer such as oVirt it's not a problem.
On Wed, Apr 17, 2013 at 01:04:34PM +0200, Borislav Petkov wrote:
> On Tue, Apr 16, 2013 at 08:42:36PM +0300, Gleb Natapov wrote:
> > > Right, and this is what we have, AFAICT. And if userspace does that what
> > > you exemplify above, you get exactly that - a feature bit not set in
> > > CPUID but
On Wed, Apr 17, 2013 at 02:51:40PM +0300, Abel Gordon wrote:
> Add logic required to detect if shadow-vmcs is supported by the
> processor. Introduce a new kernel module parameter to specify if L0 should use
> shadow vmcs (or not) to run L1.
>
> Signed-off-by: Abel Gordon
> ---
> arch/x86/kvm/vm
On Tue, Apr 16, 2013 at 09:49:20AM +0200, Martin Wawro wrote:
> On 04/16/2013 07:49 AM, Stefan Hajnoczi wrote:
> > Besides the kvm_stat, general performance data from the host is useful
> > when dealing with high load averages.
> >
> > Do you have vmstat or sar data for periods of time when the mac
On Tue, Apr 16, 2013 at 03:54:15PM +0800, Wenchao Xia wrote:
> δΊ 2013-4-16 13:51, Stefan Hajnoczi ει:
> >On Mon, Apr 15, 2013 at 09:03:36PM +0800, Wenchao Xia wrote:
> >> I'd like to add/export an function which allow userspace program
> >>to take snapshot for a region of memory. Since it is not
On Wed, Apr 17, 2013 at 04:38:29PM +0300, Gleb Natapov wrote:
> Yes, but it is "good" emulation. You want to have it for performance
> even if host does not have x2apic. x2apic is emulated no matter if
> host cpu has it or not. movbe is different, you want to emulate it
> only if your guest require
On Tue, Apr 16, 2013 at 04:30:17PM -0400, Mason Turner wrote:
> We have an in-house app, written in c, that is not performing as well as we'd
> hoped it would when moving to a VM. We've tried all the common tuning
> recommendations (virtio, tap interface, cpu pining), without any change in
> per
On Wed, Apr 17, 2013 at 10:55:26AM +0800, Xiao Guangrong wrote:
> On 04/17/2013 02:08 AM, Robin Holt wrote:
> > On Tue, Apr 16, 2013 at 09:07:20PM +0800, Xiao Guangrong wrote:
> >> On 04/16/2013 07:43 PM, Robin Holt wrote:
> >>> Argh. Taking a step back helped clear my head.
> >>>
> >>> For the -s
On Wed, Apr 17, 2013 at 02:53:10PM +0300, Abel Gordon wrote:
> Allocate a shadow vmcs used by the processor to shadow part of the fields
> stored in the software defined VMCS12 (let L1 access fields without causing
> exits). Note we keep a shadow vmcs only for the current vmcs12. Once a vmcs12
> b
On Fri, Apr 12, 2013 at 04:10:50PM -0700, Nicholas A. Bellinger wrote:
> Hi MST,
>
> Ping on this series for use with vhost-scsi-pci code..?
>
> They will need to be heading into target-pending/for-next soon to make
> the v3.10 window opening in t-minus 9 days. ;)
>
> --nab
>
> On Tue, 2013-04
Gleb Natapov wrote on 17/04/2013 04:51:16 PM:
> > +static inline bool cpu_has_vmx_shadow_vmcs(void)
> > +{
> > + u64 vmx_msr;
> > + rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
> > + /* check if the cpu supports writing r/o exit information fields */
> > + if (!(vmx_msr & (1u << 29)))
> I think
On Wed, Apr 17, 2013 at 02:55:10PM +0300, Abel Gordon wrote:
> Synchronize between the VMCS12 software controlled structure and the
> processor-specific shadow vmcs
>
> Signed-off-by: Abel Gordon
> ---
> arch/x86/kvm/vmx.c | 24
> 1 file changed, 24 insertions(+)
>
>
On Wed, Apr 17, 2013 at 02:55:40PM +0300, Abel Gordon wrote:
> Once L1 loads VMCS12 we enable shadow-vmcs capability and copy all the VMCS12
> shadowed fields to the shadow vmcs. When we release the VMCS12, we also
> disable shadow-vmcs capability.
>
> Signed-off-by: Abel Gordon
> ---
> arch/x8
Gleb Natapov wrote on 17/04/2013 05:10:28 PM:
> On Wed, Apr 17, 2013 at 02:53:10PM +0300, Abel Gordon wrote:
> > Allocate a shadow vmcs used by the processor to shadow part of the
fields
> > stored in the software defined VMCS12 (let L1 access fields without
causing
> > exits). Note we keep a
On Wed, Apr 17, 2013 at 05:41:19PM +0300, Abel Gordon wrote:
>
>
> Gleb Natapov wrote on 17/04/2013 05:10:28 PM:
>
>
> > On Wed, Apr 17, 2013 at 02:53:10PM +0300, Abel Gordon wrote:
> > > Allocate a shadow vmcs used by the processor to shadow part of the
> fields
> > > stored in the software d
Gleb Natapov wrote on 17/04/2013 05:34:49 PM:
> > @@ -5716,6 +5725,10 @@ static void nested_vmx_failValid(struct
> > X86_EFLAGS_SF | X86_EFLAGS_OF))
> > | X86_EFLAGS_ZF);
> > get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
> > + /*
> > +* We don'
Gleb Natapov wrote on 17/04/2013 05:41:07 PM:
> On Wed, Apr 17, 2013 at 02:55:40PM +0300, Abel Gordon wrote:
> > Once L1 loads VMCS12 we enable shadow-vmcs capability and copy allthe
VMCS12
> > shadowed fields to the shadow vmcs. When we release the VMCS12, we
also
> > disable shadow-vmcs capa
Freeing the memory in kvm_arch_free_memslot is as good as anywhere
else in KVM. The problem is that this memory is in the user space
process mm. This codepath could be called after the mm is destroyed
in the case of an process exit without closing the fd, which will
result in a panic on vm_munmap
On Wed, Apr 17, 2013 at 06:18:27PM +0300, Abel Gordon wrote:
>
>
> Gleb Natapov wrote on 17/04/2013 05:41:07 PM:
>
> > On Wed, Apr 17, 2013 at 02:55:40PM +0300, Abel Gordon wrote:
> > > Once L1 loads VMCS12 we enable shadow-vmcs capability and copy allthe
> VMCS12
> > > shadowed fields to the s
I'm happy to not add a new API and use __kvm_set_memory_region to
unregister private memory regions, but I thought chaning the API was
the approach you asked for when I sent a previous patch. See the end
of: http://article.gmane.org/gmane.comp.emulators.kvm.devel/107753
Did I misunderstand your c
On Wed, Apr 17, 2013 at 08:24:21AM -0700, Andrew Honig wrote:
> I'm happy to not add a new API and use __kvm_set_memory_region to
> unregister private memory regions, but I thought chaning the API was
> the approach you asked for when I sent a previous patch. See the end
> of: http://article.gmane
Alright, I'll send that soon. Sorry for the mixup.
On Wed, Apr 17, 2013 at 8:30 AM, Gleb Natapov wrote:
> On Wed, Apr 17, 2013 at 08:24:21AM -0700, Andrew Honig wrote:
>> I'm happy to not add a new API and use __kvm_set_memory_region to
>> unregister private memory regions, but I thought chaning
On Wed, Apr 17, 2013 at 05:59:50PM +0300, Abel Gordon wrote:
>
>
> Gleb Natapov wrote on 17/04/2013 05:34:49 PM:
>
> > > @@ -5716,6 +5725,10 @@ static void nested_vmx_failValid(struct
> > > X86_EFLAGS_SF | X86_EFLAGS_OF))
> > > | X86_EFLAGS_ZF);
> > > get_vmcs12(vcpu
Gleb Natapov wrote on 17/04/2013 06:39:01 PM:
> On Wed, Apr 17, 2013 at 05:59:50PM +0300, Abel Gordon wrote:
> >
> >
> > Gleb Natapov wrote on 17/04/2013 05:34:49 PM:
> >
> > > > @@ -5716,6 +5725,10 @@ static void nested_vmx_failValid(struct
> > > > X86_EFLAGS_SF | X86_EFLAGS_OF)
This series of patches implements shadow-vmcs capability for nested VMX.
Shadow-vmcs - background and overview:
In Intel VMX, vmread and vmwrite privileged instructions are used by the
hypervisor to read and modify the guest and host specifications (VMCS). In a
nested virtualization environmen
Add definitions for all the vmcs control fields/bits
required to enable vmcs-shadowing
Signed-off-by: Abel Gordon
---
arch/x86/include/asm/vmx.h|3 +++
arch/x86/include/uapi/asm/msr-index.h |2 ++
2 files changed, 5 insertions(+)
--- .before/arch/x86/include/asm/vmx.h 2013-
Add logic required to detect if shadow-vmcs is supported by the
processor. Introduce a new kernel module parameter to specify if L0 should use
shadow vmcs (or not) to run L1.
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 25 -
1 file changed, 24 insertions(+), 1 d
Prepare vmread and vmwrite bitmaps according to a pre-specified list of fields.
These lists are intended to specifiy most frequent accessed fields so we can
minimize the number of fields that are copied from/to the software controlled
VMCS12 format to/from to processor-specific shadow vmcs. The lis
Il 17/04/2013 17:19, Andrew Honig ha scritto:
> Freeing the memory in kvm_arch_free_memslot is as good as anywhere
> else in KVM. The problem is that this memory is in the user space
> process mm. This codepath could be called after the mm is destroyed
> in the case of an process exit without clo
Refactor existent code so we re-use vmcs12_write_any to copy fields from the
shadow vmcs specified by the link pointer (used by the processor,
implementation-specific) to the VMCS12 software format used by L0 to hold
the fields in L1 memory address space.
Signed-off-by: Abel Gordon
---
arch/x86/
Allocate a shadow vmcs used by the processor to shadow part of the fields
stored in the software defined VMCS12 (let L1 access fields without causing
exits). Note we keep a shadow vmcs only for the current vmcs12. Once a vmcs12
becomes non-current, its shadow vmcs is released.
Signed-off-by: Abe
Unmap vmcs12 and release the corresponding shadow vmcs
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 20
1 file changed, 12 insertions(+), 8 deletions(-)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 19:58:32.0 +0300
+++ .after/arch/x86/kvm/vmx.c 2013-04-17
Introduce a function used to copy fields from the processor-specific shadow
vmcs to the software controlled VMCS12
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 35 +++
1 file changed, 35 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 19:58:33.0
Introduce a function used to copy fields from the software controlled VMCS12
to the processor-specific shadow vmcs
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 45 +++
1 file changed, 45 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 19
Synchronize between the VMCS12 software controlled structure and the
processor-specific shadow vmcs
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 32
1 file changed, 32 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2013-04-17 19:58:33.0 +0300
+++
Once L1 loads VMCS12 we enable shadow-vmcs capability and copy all the VMCS12
shadowed fields to the shadow vmcs. When we release the VMCS12, we also
disable shadow-vmcs capability.
Signed-off-by: Abel Gordon
---
arch/x86/kvm/vmx.c | 11 +++
1 file changed, 11 insertions(+)
--- .befo
From: Prasad Joshi
SVM lock features allows software from preventing update to EFER.SVME.
Enable the SVM lock in guest if it is supported on host machine.
Signed-off-by: Prasad Joshi
---
arch/x86/kvm/svm.c |4
1 file changed, 4 insertions(+)
diff --git a/arch/x86/kvm/svm.c b/arch/x86
If userspace creates and destroys multiple VMs within the same process
we leak 20k of memory in the userspace process context per VM. This
patch frees the memory in kvm_arch_destroy_vm. If the process exits
without closing the VM file descriptor or the file descriptor has been
shared with anothe
On 04/17/13 00:04, Stephen Rothwell wrote:
> Hi all,
>
> Changes since 20130416:
>
on i386, SMP is disabled, X86_UP_APIC is not enabled, but
CONFIG_KVM_APIC_ARCHITECTURE=y:
arch/x86/kvm/vmx.c: In function 'vmx_deliver_posted_interrupt':
arch/x86/kvm/vmx.c:3950:3: error: 'apic' undeclared (firs
On 04/17/2013 10:10 PM, Robin Holt wrote:
> On Wed, Apr 17, 2013 at 10:55:26AM +0800, Xiao Guangrong wrote:
>> On 04/17/2013 02:08 AM, Robin Holt wrote:
>>> On Tue, Apr 16, 2013 at 09:07:20PM +0800, Xiao Guangrong wrote:
On 04/16/2013 07:43 PM, Robin Holt wrote:
> Argh. Taking a step back
On Thu, Apr 18, 2013 at 02:41:31AM +0800, Xiao Guangrong wrote:
> On 04/17/2013 10:10 PM, Robin Holt wrote:
> > On Wed, Apr 17, 2013 at 10:55:26AM +0800, Xiao Guangrong wrote:
> >> On 04/17/2013 02:08 AM, Robin Holt wrote:
> >>> On Tue, Apr 16, 2013 at 09:07:20PM +0800, Xiao Guangrong wrote:
>
On 04/18/2013 02:45 AM, Robin Holt wrote:
>>> For the v3.10 release, we should work on making this more
>>> correct and completely documented.
>>
>> Better document is always welcomed.
>>
>> Double call ->release is not bad, like i mentioned it in the changelog:
>>
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull for 3.10.
Changes include:
- KVM: PPC: Fix in-kernel MMIO loads
- KVM: PPC: BookE: Fix 64-bit guest kernels with SMP
Alex
The following changes since commit 79558f112fc0352e057f7b5e158e3d88b8b62c60:
Alexander Graf (
From: Stuart Yoder
Signed-off-by: Stuart Yoder
Signed-off-by: Alexander Graf
---
arch/powerpc/kvm/emulate.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 7a73b6f..631a265 100644
--- a/arch/powerpc/kvm/emu
From: Bharat Bhushan
This patch adds the one_reg interface to get the special instruction
to be used for setting software breakpoint from userspace.
Signed-off-by: Bharat Bhushan
Signed-off-by: Alexander Graf
---
arch/powerpc/include/asm/kvm_book3s.h |2 ++
arch/powerpc/include/asm/kvm_bo
From: Scott Wood
complete_mmio_load writes back the mmio result into the
destination register. Doing this on a store results in
register corruption.
Signed-off-by: Scott Wood
Signed-off-by: Alexander Graf
---
arch/powerpc/kvm/powerpc.c |1 -
1 files changed, 0 insertions(+), 1 deletions(
From: Marc Zyngier
In the very unlikely event where a guest would be foolish enough to
*read* from a write-only cache maintainance register, we end up
with preemption disabled, due to a misplaced get_cpu().
Just move the "is_write" test outside of the critical section.
Signed-off-by: Marc Zyngi
On Wed, Apr 17, 2013 at 11:03:33PM +0530, prasadjoshi.li...@gmail.com wrote:
> From: Prasad Joshi
>
> SVM lock features allows software from preventing update to EFER.SVME.
> Enable the SVM lock in guest if it is supported on host machine.
>
> Signed-off-by: Prasad Joshi
> ---
> arch/x86/kvm/s
Hi Stefan,
> The host is interesting too if you suspect KVM is involved in the
> performance issue (rather than it being purely an application issue
> inside the guest). For example, pidstat (from the sysstat package) on
> the host can tell you the guest mode CPU utilization percentage. That's
>
On Wed, Apr 17, 2013 at 10:54 AM, Andrew Honig wrote:
>
> If userspace creates and destroys multiple VMs within the same process
> we leak 20k of memory in the userspace process context per VM. This
> patch frees the memory in kvm_arch_destroy_vm. If the process exits
> without closing the VM fi
On Fri, Mar 22, 2013 at 09:15:24PM +0200, Gleb Natapov wrote:
> On Fri, Mar 22, 2013 at 08:37:33PM +0800, Xiao Guangrong wrote:
> > On 03/22/2013 08:12 PM, Gleb Natapov wrote:
> > > On Fri, Mar 22, 2013 at 08:03:04PM +0800, Xiao Guangrong wrote:
> > >> On 03/22/2013 07:47 PM, Gleb Natapov wrote:
>
Il 17/04/2013 19:54, Andrew Honig ha scritto:
>
> If userspace creates and destroys multiple VMs within the same process
> we leak 20k of memory in the userspace process context per VM. This
> patch frees the memory in kvm_arch_destroy_vm. If the process exits
> without closing the VM file descr
Il 17/04/2013 18:03, Abel Gordon ha scritto:
>> > Right, not a big deal if this is the only case when it happens. When we
>> > discussed accessors vs sync_shadow_vmcs flag approach I said that flag
>> > will work only if no vmcs12 fields are changed not as part of vmexit or
>> > vmwrite emulations.
On Wed, 17 Apr 2013, Randy Dunlap wrote:
> On 04/17/13 00:04, Stephen Rothwell wrote:
> > Hi all,
> >
> > Changes since 20130416:
> >
>
>
> on i386, SMP is disabled, X86_UP_APIC is not enabled, but
> CONFIG_KVM_APIC_ARCHITECTURE=y:
>
> arch/x86/kvm/vmx.c: In function 'vmx_deliver_posted_inter
I don't have a significant objection to freeing the memory in
kvm_arch_free_memslot, although I think it's a little harder to
understand. I like the idea of being symmetric (memory is allocated
by calling kvm_set_memory_region and freed using the same technique).
That way if someone changes from v
The build fails when CONFIG_SMP is disabled:
arch/x86/kvm/vmx.c: In function 'vmx_deliver_posted_interrupt':
arch/x86/kvm/vmx.c:3950:3: error: 'apic' undeclared (first use in this
function)
Fix it by including the necessary header.
Reported-by: Randy Dunlap
Signed-off-by: David
On Fri, Apr 12, 2013 at 01:27:36PM +0200, Kevin Wolf wrote:
> This adds a small script that allows to conveniently run all test cases and
> that reports back one "PASS" or "FAIL" line for each test case; it also
> creates
> a test.log file with the full output.
>
> It parses the unittests.cfg fil
On Tue, Apr 16, 2013 at 06:15:21PM +0200, Paolo Bonzini wrote:
> Il 16/04/2013 07:08, prasadjoshi.li...@gmail.com ha scritto:
> > From: Prasad Joshi
> >
> > The SVM test 'cr3 read intercept emulate' when ran on uniprocessor
> > system does not finish and blocks all the tests scheduled to be ran
>
On Sun, Apr 14, 2013 at 12:44:09PM +0200, Jan Kiszka wrote:
> From: Jan Kiszka
>
> As we may emulate the loading of EFER on VM-entry and VM-exit, implement
> the checks that VMX performs on the guest and host values on vmlaunch/
> vmresume. Factor out kvm_valid_efer for this purpose which checks
On Tue, Apr 16, 2013 at 06:18:52PM +0200, Borislav Petkov wrote:
> On Sun, Apr 14, 2013 at 01:03:20PM +0200, Borislav Petkov wrote:
> > On Sun, Apr 14, 2013 at 12:31:12PM +0300, Pekka Enberg wrote:
> > > I obviously support having something like this in mainline. I wonder
> > > though if we could j
On Tue, Apr 16, 2013 at 02:32:45PM +0800, Xiao Guangrong wrote:
> Invalid rmaps is the rmap of the invalid memslot which is being
> deleted, especially, we can treat all rmaps are invalid when
> kvm is being destroyed since all memslot will be deleted soon.
> MMU should remove all sptes on these rm
1 - 100 of 137 matches
Mail list logo