Bugs item #1819768, was opened at 2007-10-25 15:25
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting:
https://sourceforge.net/tracker/?func=detail&atid=893831&aid=1819768&group_id=180599
Please note that this message will contain a full copy
Hi,
Here is the testing result for latest KVM commits, kernel
948c098f17a7a64a067d25f9e95651fef4bfc34e, userspace,
f33b8d57e92d7ce82a7b30fc5bdc274552f6ad63.
One new issue
1. xp and win2k3 guest crashes on pae host:
https://sourceforge.net/tracker/?func=detail&atid=893831&aid=1819768&gro
up_i
This patch lets GCC to determine which registers to save when we
switch to/from a VCPU in the case of AMD x86_64.
* Original code saves following registers:
rbx, rcx, rdx, rsi, rdi, rbp,
r8, r9, r10, r11, r12, r13, r14, r15
* Patched code:
- informs GCC that we modify following regist
This patch lets GCC to determine which registers to save when we
switch to/from a VCPU in the case of AMD i386
* Original code saves following registers:
ebx, ecx, edx, esi, edi, ebp
* Patched code:
- informs GCC that we modify following registers
using the clobber description:
e
This patch lets GCC to determine which registers to save when we
switch to/from a VCPU in the case of intel x86_64.
* Original code saves following registers:
rax, rbx, rcx, rdx, rsi, rdi, rbp,
r8, r9, r10, r11, r12, r13, r14, r15
* Patched code:
- informs GCC that we modify following
This patch lets GCC to determine which registers to save when we
switch to/from a VCPU.
[PATCH 1/4] Let gcc to choose which registers to save (vmx-x86_64)
drivers/kvm/vmx.c | 21 +
1 files changed, 9 insertions(+), 12 deletions(-)
This patch lets GCC to determine
This patch lets GCC to determine which registers to save when we
switch to/from a VCPU in the case of intel i386.
>>> I don't know if its patch is really usefull as it replaces <<<
>>> a popa/pusha by several pop/push. <<<
* Original code saves following registers:
As a quick test I added a printk to the loop, right after the while():
while (atomic_read(&completed) != needed) {
printk("kvm_flush_remote_tlbs: completed = %d, needed = %d\n",
atomic_read(&completed), needed);
cpu_relax();
barrier();
}
This is the output r
david ahern wrote:
> As a quick test I added a printk to the loop, right after the while():
>
> while (atomic_read(&completed) != needed) {
> printk("kvm_flush_remote_tlbs: completed = %d, needed = %d\n",
> atomic_read(&completed), needed);
> cpu_relax();
> barrier(
I'll give your suggestions I try. I need to move to a server that I can
forcibly reboot remotely (to recover), so it will be a while.
david
Avi Kivity wrote:
> david ahern wrote:
>> As a quick test I added a printk to the loop, right after the while():
>>
>> while (atomic_read(&completed)
This patch adds a target "tar" in the Makefile of kvm-userspace
to create a tarball of kvm, including kvm kernel modules sources.
Use "make tar"
or "make LINUX=/usr/src/linux-2.6 tar" to create kvm-snapshot-.tar.gz
with module sources from /usr/src/linux-2.6
or "make VERSION=latest" to creat
This patch splits kvm_vm_ioctl into archtecture independent parts, and
x86 specific parts which go to kvm_arch_vcpu_ioctl in x86.c.
Common ioctls for all architectures are:
KVM_CREATE_VCPU, KVM_GET_DIRTY_LOG, KVM_SET_USER_MEMORY_REGION
KVM_SET_USER_MEMORY_REGION is actually implemented in x86.c
On Thu, 2007-10-25 at 17:48 +0200, Carsten Otte wrote:
> This patch splits kvm_vm_ioctl into archtecture independent parts, and
> x86 specific parts which go to kvm_arch_vcpu_ioctl in x86.c.
>
> Common ioctls for all architectures are:
> KVM_CREATE_VCPU, KVM_GET_DIRTY_LOG, KVM_SET_USER_MEMORY_REG
On Thu, 2007-10-25 at 17:48 +0200, Izik Eidus wrote:
> On Thu, 2007-10-25 at 17:48 +0200, Carsten Otte wrote:
> > This patch splits kvm_vm_ioctl into archtecture independent parts, and
> > x86 specific parts which go to kvm_arch_vcpu_ioctl in x86.c.
> >
> > Common ioctls for all architectures are
On Thu, 2007-10-25 at 11:22 -0500, Hollis Blanchard wrote:
> On Thu, 2007-10-25 at 17:48 +0200, Izik Eidus wrote:
> > On Thu, 2007-10-25 at 17:48 +0200, Carsten Otte wrote:
> > > This patch splits kvm_vm_ioctl into archtecture independent parts, and
> > > x86 specific parts which go to kvm_arch_vcp
This is a request for testing of an experimental kvm feature that
dramatically accelerates some Windows releases (when running with the
ACPI HAL, and especially with guest SMP). The feature detects accesses
by the guest to the Task Priority Register (TPR) and patches them at
runtime to a kvm-f
On compilation I get the following error.
../qemu-kvm.h:41: error: redefinition of 'kvm_log_tpr'
../qemu-kvm.h:41: error: previous definition of 'kvm_log_tpr' was here
make[2]: *** [i8259.o] Error 1
make[2]: Leaving directory
`/root/Download/software/tpr-opt-1/qemu/x86_64-softmmu'
make[1]: *** [su
Haydn Solomon wrote:
> On compilation I get the following error.
>
> ../qemu-kvm.h:41: error: redefinition of 'kvm_log_tpr'
> ../qemu-kvm.h:41: error: previous definition of 'kvm_log_tpr' was here
> make[2]: *** [i8259.o] Error 1
> make[2]: Leaving directory
> `/root/Download/software/tpr-opt-1/qe
Thanks, that was quick.
On 10/25/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
>
> Haydn Solomon wrote:
> > On compilation I get the following error.
> >
> > ../qemu-kvm.h:41: error: redefinition of 'kvm_log_tpr'
> > ../qemu-kvm.h:41: error: previous definition of 'kvm_log_tpr' was here
> > make[2]: *
Avi Kivity wrote:
> Jan Kiszka wrote:
>> Got it! It's wbinvd from smm_init in rombios32.c! Anyone any comments on
>> this?
>>
>
> Ha! A real life 300usec instruction!
>
> Unfortunately, it cannot be trapped on Intel (it can be trapped on
> AMD). Looks like a minor hole in VT, as a guest can
Avi Kivity wrote:
This is a request for testing of an experimental kvm feature that
dramatically accelerates some Windows releases (when running with the
ACPI HAL, and especially with guest SMP). The feature detects accesses
by the guest to the Task Priority Register (TPR) and patches them at
Jan Kiszka wrote:
> Avi Kivity wrote:
>
>> Jan Kiszka wrote:
>>
>>> Got it! It's wbinvd from smm_init in rombios32.c! Anyone any comments on
>>> this?
>>>
>>>
>> Ha! A real life 300usec instruction!
>>
>> Unfortunately, it cannot be trapped on Intel (it can be trapped on
>> AMD)
Anthony Liguori wrote:
> Avi Kivity wrote:
>> This is a request for testing of an experimental kvm feature that
>> dramatically accelerates some Windows releases (when running with the
>> ACPI HAL, and especially with guest SMP). The feature detects
>> accesses by the guest to the Task Priority
On Thu, 25 Oct 2007 13:39:33 -0400
"Haydn Solomon" <[EMAIL PROTECTED]> wrote:
> Thanks, that was quick.
Finally, this (pre)release solved the long standing Java IE Plugin
lockup problem for me. Thanks a lot!
--
Jindrich Makovicka
Avi Kivity wrote:
> Anthony Liguori wrote:
>> Avi Kivity wrote:
>>> This is a request for testing of an experimental kvm feature that
>>> dramatically accelerates some Windows releases (when running with
>>> the ACPI HAL, and especially with guest SMP). The feature detects
>>> accesses by the g
Anthony Liguori wrote:
> Avi Kivity wrote:
>> Anthony Liguori wrote:
>>> Avi Kivity wrote:
This is a request for testing of an experimental kvm feature that
dramatically accelerates some Windows releases (when running with
the ACPI HAL, and especially with guest SMP). The feature
Jindrich Makovicka wrote:
> On Thu, 25 Oct 2007 13:39:33 -0400
> "Haydn Solomon" <[EMAIL PROTECTED]> wrote:
>
>
>> Thanks, that was quick.
>>
>
> Finally, this (pre)release solved the long standing Java IE Plugin
> lockup problem for me. Thanks a lot!
>
>
No, this release is meant to ca
[EMAIL PROTECTED] wrote:
> This is the acutally the 3rd attempt.
>
> These patches consolidate the make files & tests in user director for x86.
> This
> is to allow other architectures easier integration into the kvm source.
>
>
Food fight seems to have died down, so I applied both. But pleas
Hy
somthing new about the shared memory support between VMs? or VM and host?
bye
-
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems? Stop.
Now Search log events and configuration
I also had a problem installing windows xp. Got the following error
localhost kernel: [ cut here ]
Message from syslogd@ at Thu Oct 25 13:59:27 2007 ...
localhost kernel: invalid opcode: [1] SMP
Installed windows xp with the following options
/usr/local/kvm/bin/qemu
Dor Laor wrote:
> [PATCH] Make kvm Sleep if eflag is unset.
>
> The main loop checks whether a sleep is needed (kvm_main_loop_wait).
> If there is a need to sleep it polls 10msec for signals and
> select input from the devices.
> Otherwise it enters guest mode.
>
> In case halt is on and there is p
Haydn Solomon wrote:
> I also had a problem installing windows xp. Got the following error
I guess I'll have to test that too.
--
error compiling committee.c: too many arguments to function
-
This SF.net email is sponsore
Avi Kivity wrote:
> This is a request for testing of an experimental kvm feature that
> dramatically accelerates some Windows releases (when running with the
> ACPI HAL, and especially with guest SMP). The feature detects accesses
> by the guest to the Task Priority Register (TPR) and patches t
The issue appears to be with the RHEL5 kernel (host OS is rhel5). I tried your
suggestions below -- no effect; still hit the softlockup.
I then moved the host to the 2.6.23.1 kernel but with the kvm-48 code base.
Surprisingly, I had no issues starting my guest with '-smp 4'.
david
Avi Kivity
Anthony Liguori wrote:
> Avi Kivity wrote:
>
>> This is a request for testing of an experimental kvm feature that
>> dramatically accelerates some Windows releases (when running with the
>> ACPI HAL, and especially with guest SMP). The feature detects accesses
>> by the guest to the Task Pri
david ahern wrote:
> The issue appears to be with the RHEL5 kernel (host OS is rhel5). I tried
> your suggestions below -- no effect; still hit the softlockup.
>
> I then moved the host to the 2.6.23.1 kernel but with the kvm-48 code base.
> Surprisingly, I had no issues starting my guest with '-
Avi, what do you think about breaking the kvm-userspace repository into
separate kvm-qemu, kvmctl, and libkvm repositories?
--
Hollis Blanchard
IBM Linux Technology Center
-
This SF.net email is sponsored by: Splunk Inc.
St
Avi Kivity wrote:
> Haydn Solomon wrote:
>
>> I also had a problem installing windows xp. Got the following error
>>
>
>
> I guess I'll have to test that too.
>
I hit it again, this time about half-way through the second stage
install of Windows XP (last time it was almost immediately)
Carlo Marcelo Arenas Belon wrote:
> The following patch implement a configure passthrough for qemu and
> migrate all currently implemented qemu specific configuration flags
> (enable-alsa, disable-vnc-tls and disable-gcc-check) to use it.
>
> It uses qemu's configure to get a list of hints for ad
Hollis Blanchard wrote:
> Avi, what do you think about breaking the kvm-userspace repository into
> separate kvm-qemu, kvmctl, and libkvm repositories?
>
>
Firstly, I think kvmctl and libkvm should stay together.
I'm not thrilled about breaking up the repositories even more; it makes
bisectin
Anthony Liguori wrote:
> Avi Kivity wrote:
>> Haydn Solomon wrote:
>>
>>> I also had a problem installing windows xp. Got the following error
>>>
>>
>>
>> I guess I'll have to test that too.
>>
>
> I hit it again, this time about half-way through the second stage
> install of Windows XP
Avi Kivity wrote:
> Anthony Liguori wrote:
>> Avi Kivity wrote:
>>> Haydn Solomon wrote:
>>>
I also had a problem installing windows xp. Got the following error
>>>
>>>
>>> I guess I'll have to test that too.
>>>
>>
>> I hit it again, this time about half-way through the second
Hey,
> Avi Kivity wrote:
> > Haydn Solomon wrote:
> >
> >> I also had a problem installing windows xp. Got the following error
> >>
> >
> >
> > I guess I'll have to test that too.
> >
>
> I hit it again, this time about half-way through the second stage
> install of Windows XP (last t
Yang, Sheng wrote:
>>
>> Exporting an ioctl handler isn't very pretty. Izik is working on a
>> patch that also requires an internal memory slot, so he will add an
>>
> API
>
>> for it.
>>
>
> OK, that's my hope :-)
> I will wait for that.
>
I've just merged and pushed that bit.
On Thu, 2007-10-25 at 20:40 +0200, Avi Kivity wrote:
> Hollis Blanchard wrote:
> > Avi, what do you think about breaking the kvm-userspace repository into
> > separate kvm-qemu, kvmctl, and libkvm repositories?
>
> Firstly, I think kvmctl and libkvm should stay together.
Why? As far as I can see,
Anthony Liguori wrote:
>>
>>> static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
>>> {
>>> int r;
>>>
>>> kvm_mmu_free_some_pages(vcpu);
>>> r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache,
>>>pte_chain_cache, 4);
>>> if (r)
>>> goto out;
>>>
Hollis Blanchard wrote:
> On Thu, 2007-10-25 at 20:40 +0200, Avi Kivity wrote:
>
>> Hollis Blanchard wrote:
>>
>>> Avi, what do you think about breaking the kvm-userspace repository into
>>> separate kvm-qemu, kvmctl, and libkvm repositories?
>>>
>> Firstly, I think kvmctl and libkvm
Francesco Cipollone wrote:
> Hy
> somthing new about the shared memory support between VMs? or VM and host?
> bye
>
beside moving the memory allocation to userspace (this is first step in
share memory between VMs using smart file system)
there is not much advance.
about sharing memory between
I was able to complete an installation of windows xp using -smp 1. However,
I would like to test on an existing virtual machine with applications
already installed on it. Changing the HAL to ACPI should be enough for me to
test the windows optimization right feature right?
On 10/25/07, Avi Kivity
Haydn Solomon wrote:
> I was able to complete an installation of windows xp using -smp 1.
> However, I would like to test on an existing virtual machine with
> applications already installed on it. Changing the HAL to ACPI should
> be enough for me to test the windows optimization right feature
Hollis Blanchard wrote:
> On Thu, 2007-10-25 at 17:48 +0200, Izik Eidus wrote:
>
>> On Thu, 2007-10-25 at 17:48 +0200, Carsten Otte wrote:
>>
>>> This patch splits kvm_vm_ioctl into archtecture independent parts, and
>>> x86 specific parts which go to kvm_arch_vcpu_ioctl in x86.c.
>>>
>>>
- Original Message -
From: "Francesco Cipollone" <[EMAIL PROTECTED]>
To: "Izik Eidus" <[EMAIL PROTECTED]>
Sent: Thursday, October 25, 2007 10:43 PM
Subject: Re: [kvm-devel] somthing new for shared memory???
>
> - Original Message -
> From: "Izik Eidus" <[EMAIL PROTECTED]>
> To:
Francesco Cipollone wrote:
> - Original Message -
> From: "Francesco Cipollone" <[EMAIL PROTECTED]>
> To: "Izik Eidus" <[EMAIL PROTECTED]>
> Sent: Thursday, October 25, 2007 10:43 PM
> Subject: Re: [kvm-devel] somthing new for shared memory???
>
>
>
>> - Original Message -
>> F
Hollis Blanchard wrote:
> On Fri, 2007-10-26 at 00:12 +0200, Izik Eidus wrote:
>
>> ok i was thinking,
>> maybe we can rewrite the way kvm hold memory so more code would be shared,
>> lets say we throw away all the slots and arch depended stuff, and we let kvm
>> just hold the userspace allocate
Avi Kivity wrote:
> Anthony Liguori wrote:
>>>
static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
{
int r;
kvm_mmu_free_some_pages(vcpu);
r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache,
pte_chain_cache, 4);
if
On Fri, 2007-10-26 at 00:12 +0200, Izik Eidus wrote:
> ok i was thinking,
> maybe we can rewrite the way kvm hold memory so more code would be shared,
> lets say we throw away all the slots and arch depended stuff, and we let kvm
> just hold the userspace allocated memory address,
With that approa
Izik Eidus wrote:
> Hollis Blanchard wrote:
>> On Fri, 2007-10-26 at 00:12 +0200, Izik Eidus wrote:
>>
>>> ok i was thinking,
>>> maybe we can rewrite the way kvm hold memory so more code would be
>>> shared,
>>> lets say we throw away all the slots and arch depended stuff, and we
>>> let kvm
>
It appears to be a problem with the kernel proper (ie., not a Red Hat patch). I
hit the soft lockup problem with kvm-48 and the 2.6.18.4 kernel which is the
base for RHEL5. That suggests a delivery between 2.6.18.4 (November 2006) and
2.6.23.1 fixed it.
david
Avi Kivity wrote:
> david ahern w
Avi Kivity wrote:
Anthony Liguori wrote:
static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
{
int r;
kvm_mmu_free_some_pages(vcpu);
r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache,
pte_chain_cache, 4);
if (r)
goto out;
r = mmu_topup_
Carsten Otte wrote:
> This patch splits kvm_vm_ioctl into archtecture independent parts, and
> x86 specific parts which go to kvm_arch_vcpu_ioctl in x86.c.
>
> Common ioctls for all architectures are:
> KVM_CREATE_VCPU, KVM_GET_DIRTY_LOG, KVM_SET_USER_MEMORY_REGION
>
> KVM_SET_USER_MEMORY_REGION
I've been running windows xp sp2 all day with acpi uniprocessor HAL and it's
noticeable much faster...blazing fast. I can imagine how much faster it will
be when -smp 2 works. Once it did hang up on me after installing an office
application and prompted for registration online. Other than that it's
>
> There's a two-liner required to make it work. I'll add it soon.
>
But you still needs to issue WBINVD to all pCPUs which just move
non-response time from one place to another, not?
Eddie
-
This SF.net email is sponsore
Kvm cannot be compiled on fc6 which doesn't define CONFIG_HAS_IOMEM.
Here is the error messages:
[EMAIL PROTECTED] kvm-userspace]# make
make -C kernel
make[1]: Entering directory `/root/kvm-userspace/kernel'
make -C /lib/modules/2.6.18-1.2798.fc6/build M=`pwd` "$@"
make[2]: Entering directory `/us
> BTW, is it wise to enable this by default for all guests?
> Ignoring the
> fact that we're modifying guest's memory without its knowledge, if a
> guest unmaps the VA mappings for the BIOS then all sorts of problems
> could occur.
>
Good movement!
But, Vista won't work with patching. The memor
>From ebfc23b71051e5ab19d22fb3f9c3d57721566ea9 Mon Sep 17 00:00:00 2001
From: Sheng Yang <[EMAIL PROTECTED]>
Date: Fri, 26 Oct 2007 13:41:28 +0800
Subject: [PATCH] KVM: x86_emulator: Decode the memory operand for 'mov'
For the following TPR patch, we must get gva for executing instructions.
Most
m
>From 2fc9eedaaaf4034c2b84ee0b3b0c8153f775545d Mon Sep 17 00:00:00 2001
From: Sheng Yang <[EMAIL PROTECTED]>
Date: Fri, 26 Oct 2007 13:43:11 +0800
Subject: [PATCH] KVM: VMX: Enable memory mapped TPR shadow(FlexPriority)
This patch based on CR8/TPR patch, and enable the TPR
shadow(FlexPriority)
for
Yang, Sheng wrote:
>
> +static int alloc_apic_access_page(struct kvm *kvm)
> +{
> + struct kvm_userspace_memory_region kvm_userspace_mem;
> + int r;
> +
> + r = -EFAULT;
> + /* Top memslot for apic access page */
> + if (kvm->nmemslots == KVM_MEMORY_SLOTS)
> + retu
Izik Eidus wrote:
> Yang, Sheng wrote:
>>
>> +static int alloc_apic_access_page(struct kvm *kvm) +{
>> +struct kvm_userspace_memory_region kvm_userspace_mem; + int r;
>> +
>> +r = -EFAULT;
>> +/* Top memslot for apic access page */
>> +if (kvm->nmemslots == KVM_MEMORY_SLOTS)
>> +
Resend, with private memslot for apic access page.
>From 95225627954e125da965096633a1020f8072091d Mon Sep 17 00:00:00 2001
From: Sheng Yang <[EMAIL PROTECTED]>
Date: Fri, 26 Oct 2007 13:43:11 +0800
Subject: [PATCH] KVM: VMX: Enable memory mapped TPR shadow(FlexPriority)
This patch based on CR8/TP
69 matches
Mail list logo
