From: Wanpeng Li
CC i386-softmmu/target-i386/translate.o
/home/kernel/qemu/target-i386/translate.c: In function ‘gen_sse’:
/home/kernel/qemu/target-i386/translate.c:3571:27: error: assignment from
incompatible pointer type [-Werror]
/home/kernel/qemu/target-i386/translate.c:3573:17: error
u!
>
>2012/7/4 Wanpeng Li :
>> From: Wanpeng Li
>>
>> CC i386-softmmu/target-i386/translate.o
>> /home/kernel/qemu/target-i386/translate.c: In function ‘gen_sse’:
>> /home/kernel/qemu/target-i386/translate.c:3571:27: error: assignment from
>> incompatible
From: Wanpeng Li
Since function pc_vga_init doesn't need to return DeviceState any more,
just cleanup.
Signed-off-by: Wanpneg Li
---
hw/pc.c | 18 +++---
hw/pc.h |2 +-
2 files changed, 8 insertions(+), 12 deletions(-)
diff --git a/hw/pc.c b/hw/pc.c
index c7e9ab3..f3
) during guest os boot
no --enable-kvm has -m 1024 guest os will block during guest os boot
has --enable-kvm no -m guest os will block during guest os boot
has --enable-kvm has -m 1024 run normally
Regards,
Wanpeng Li
desired
when several cooperating threads/task is running in guest.
Is there a plane for this work?
Please refer to gang scheduler.
Regards,
Wanpeng Li
Thanks,
Zhang Haoyu
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kerne
Hi all:
I am confused with what's the meaning of main-system-bus, it emulates
physical bus like FSB(front side bus) or just a virtual bus as the root
of device tree.
Regards,
Wanpeng Li
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
memory.c | 94 ++
memory.h |8 +
2 files changed, 78 insertions(+), 24 deletions(-)
diff --git a/memory.c b/memory.c
index 22b0352
ional.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/hpet.c | 39 ++-
hw/hpet_emul.h | 41 +
hw/i8254_internal.h |2 +-
hw/mc146818rtc.c| 26 -
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/pci_host.c | 26 ++
hw/pci_host.h |5 +
2 files changed, 31 insertions(+), 0 deletions(-)
diff --git a/hw/pci_host.c b/hw/pci_host.c
index 44c6c20..44d7e55 100644
--- a
children are visible in the device model. This lets you set properties
of the parent and its children.
realize() (which is still called DeviceState::init today) will be called right
before the guest starts up for the first time.
Signed-off-by: Anthony Liguori
Signed-off-by: Wa
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/pc.c | 22 +++---
hw/pc.h | 26 --
2 files changed, 11 insertions(+), 37 deletions(-)
diff --git a/hw/pc.c b/hw/pc.c
index d5a557e..5f93643 100644
--- a/hw/pc.c
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
Makefile.target |1 -
hw/pc.c | 816 +--
hw/pc.h | 20 +-
hw/pc_piix.c| 762
PMC
is contained within the i440fx which we will now reflect in composition in the
next few changesets.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
Makefile.target |2 +-
hw/i440fx.c | 431 +++
hw/i440fx.h | 78 +++
hw/p
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/pci_host.c | 26 ++
hw/pci_host.h |5 +
2 files changed, 31 insertions(+), 0 deletions(-)
diff --git a/hw/pci_host.c b/hw/pci_host.c
index 44c6c20..44d7e55 100644
--- a
On Mon, Mar 26, 2012 at 10:06:45AM +0800, Wanpeng Li wrote:
>
>From: Anthony Liguori
>
>
>Signed-off-by: Anthony Liguori
>Signed-off-by: Wanpeng Li
>
>---
> hw/pci_host.c | 26 ++
> hw/pci_host.h |5 +
> 2 files changed, 31 inse
On Mon, Mar 26, 2012 at 02:47:19PM +0200, Andreas Färber wrote:
>Am 26.03.2012 04:06, schrieb Wanpeng Li:
>> From: Anthony Liguori
>
>Resending an old cover letter is not a good idea. This looks like a v2,
>so please mark it as such in the subjects; it's missing a Change
Hi all:
Consider of the options parsing process in main function of vl.c is too long.
It should be module into single function to clear Ideas, strengthen the source
code
management, and increase code readability.
Regards,
Wanpeng Li
--
LTC China, IBM, Shanghai
Hi all:
Are there any materials introduce how to use the scripts under scripts/
?
Regards,
Wanpeng Li
--
LTC China, IBM, Shanghai
On Fri, Mar 30, 2012 at 11:28:53AM +0200, Andreas Färber wrote:
>Am 30.03.2012 09:11, schrieb Wanpeng Li:
>> Are there any materials introduce how to use the scripts under scripts/
>> ?
>
>Is this a general question about improving our scripts' documentation,
>or are
order to not influence command-line invocations.
Signed-off-by: Wanpeng Li
---
vl.c | 159 ++---
1 files changed, 83 insertions(+), 76 deletions(-)
diff --git a/vl.c b/vl.c
index 0fccf50..fa4d0a9 100644
--- a/vl.c
+++ b/vl.c
On Fri, Mar 30, 2012 at 01:53:14PM +0100, Daniel P. Berrange wrote:
>On Fri, Mar 30, 2012 at 08:36:43PM +0800, Wanpeng Li wrote:
>> Consider of the options parse process in main function of vl.c is too
>> long.It should be module into single function to clear ideas, strengthen
>
This comment is useless, just removes it and makes the codes clear.
Signed-off-by: Wanpeng Li
---
dma.h |1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/dma.h b/dma.h
index 20e86d2..5bd1fc8 100644
--- a/dma.h
+++ b/dma.h
@@ -11,7 +11,6 @@
#define DMA_H
#include
On Sat, Apr 07, 2012 at 02:23:43PM +, Blue Swirl wrote:
>On Fri, Apr 6, 2012 at 07:52, Wanpeng Li wrote:
>> This comment is useless, just removes it and makes the codes clear.
>>
>> Signed-off-by: Wanpeng Li
>
>Thanks, applied. Patches like these could be directe
Hi all:
I know i8042 is a chip in southbridge which control keyboard and mouse.
Keboard is emulated by i8042 in qemu and mouse is emulated by vmmouse.
But what are port92 and vmport, what's the relationship among these four
stuff ?
Regards,
Wanpeng Li
--
LTC China, IBM, Shanghai
Signed-off-by: Wanpeng Li
---
hw/ps2.h | 29 +
1 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/hw/ps2.h b/hw/ps2.h
index 32a4231..d19c226 100644
--- a/hw/ps2.h
+++ b/hw/ps2.h
@@ -1,3 +1,30 @@
+/*
+ * QEMU PS/2 keyboard/mouse emulation
Signed-off-by: Wanpeng Li
---
hw/ps2.h | 29 +
1 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/hw/ps2.h b/hw/ps2.h
index 32a4231..d19c226 100644
--- a/hw/ps2.h
+++ b/hw/ps2.h
@@ -1,3 +1,30 @@
+/*
+ * QEMU PS/2 keyboard/mouse emulation
PCI_CLASS_DISPLAY_VGA has already defined in hw/pci_ids.h, so use the
macro definition instead of a simple digit.
Signed-off-by: Wanpeng Li
---
hw/pci.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/hw/pci.c b/hw/pci.c
index fe71666..274d86d 100644
--- a/hw/pci.c
PCI_CLASS_DISPLAY_VGA has already defined in hw/pci_ids.h, so use the
macro definition instead of a simple digit.
Signed-off-by: Wanpeng Li
---
hw/pci.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/hw/pci.c b/hw/pci.c
index fe71666..274d86d 100644
--- a/hw/pci.c
ioport write/read, I have traced this function, but I haven't found it
has
any relationship with pci read/write configuration space functions like
i440fx_write_config and piix3_write_config.So how does it emulate pci
configuration space access when not use passthrough?
thanks
Wanpeng Li
LTC
ISA bus only use IRQ 0~15, so don't need to give an array qemu_irq 0~24, just
array qemu_irq i8259 is ok.
Signed-off-by: Wanpeng Li
---
hw/pc_piix.c |3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/hw/pc_piix.c b/hw/pc_piix.c
index 63dba4e..52f7cf8 100644
---
ISA bus only use IRQ 0~15, so don't need to give an array qemu_irq 0~23, just
array qemu_irq i8259 is ok.
Signed-off-by: Wanpeng Li
---
hw/pc_piix.c |3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/hw/pc_piix.c b/hw/pc_piix.c
index 63dba4e..52f7cf8 100644
---
On Sun, Mar 11, 2012 at 08:46:38AM +0100, Jan Kiszka wrote:
>On 2012-03-11 08:04, Wanpeng Li wrote:
>> ISA bus only use IRQ 0~15, so don't need to give an array qemu_irq 0~23, just
>> array qemu_irq i8259 is ok.
>>
>> Signed-off-by: Wanpeng Li
>> ---
&
c NUMA
balancing) that either the policy for schednuma or autonuma can be
rebased on implemented by Mel has already merged.
Regards,
Wanpeng Li
>
>Thanks,
>Wanlong Gao
>
>
>
>> Hi,
>>
>> We just met a problem of QEMU memory allocation.
>> Here is the de
Add xsaves related definition, it also add corresponding part to
kvm_get/put, and vmstate.
Signed-off-by: Wanpeng Li
---
target-i386/cpu.h | 2 ++
target-i386/kvm.c | 15 +++
target-i386/machine.c | 3 ++-
3 files changed, 19 insertions(+), 1 deletion(-)
diff --git a
Add xsaves related definition, it also adds corresponding part
to kvm_get/put, and vmstate.
Signed-off-by: Wanpeng Li
---
v1 -> v2:
* use a subsection instead of bumping the version number.
target-i386/cpu.h | 2 ++
target-i386/kvm.c | 15 +++
target-i386/machine.c |
Add xsaves related definition, it also adds corresponding part
to kvm_get/put, and vmstate.
Signed-off-by: Wanpeng Li
---
v1 -> v2:
* use a subsection instead of bumping the version number.
target-i386/cpu.h | 2 ++
target-i386/kvm.c | 15 +++
target-i386/machine.c |
ynIC message slot and triggering the corresponding
> synthetic interrupt.
Could you post a link for this specification?
Regards,
Wanpeng Li
2015-11-26 16:34 GMT+08:00 Andrey Smetanin :
>
>
> On 11/26/2015 08:28 AM, Wanpeng Li wrote:
>>
>> 2015-11-25 23:20 GMT+08:00 Andrey Smetanin :
>>>
>>> Per Hyper-V specification (and as required by Hyper-V-aware guests),
>>> SynIC provides 4 per-v
2015-11-26 16:34 GMT+08:00 Andrey Smetanin :
>
>
> On 11/26/2015 08:28 AM, Wanpeng Li wrote:
>>
>> 2015-11-25 23:20 GMT+08:00 Andrey Smetanin :
>>>
>>> Per Hyper-V specification (and as required by Hyper-V-aware guests),
>>> SynIC provides 4 per-v
This series aggressively refactors the PC machine initialization to be more
modelled and less ad-hoc. The highlights of this series are:
1) Things like -m and -bios-name are now device model properties
2) The i440fx and piix3 are now modelled in a thorough fashion
3) i440fx_init is trivialized
Take advantage of Andreas's pci-host patchset, add instance_init function
to fully implement convert pci-host to QOM.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/pci_host.c |9 +
1 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/hw/pci_host.c
convert RTC as piix3 proper QOM child.
RTC creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/mc146818rtc.c | 29
convert PCSPK as piix3 proper QOM child.
PCSPK creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/pcspk.c | 19 +--
hw/pcspk.h | 19
convert i8042 as piix3 proper QOM child.
I8042 creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/pc.c|9 ++---
hw/pckbd.c | 24 +---
hw
convert VMPORT as piix3 proper QOM child.
VMPORT creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/pc.c |1 -
hw/pc.h |5 -
hw/piix3.c | 11
convert VMMOUSE as piix3 proper QOM child.
VMMOUSE creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/pc.c | 15 ++-
hw/piix3.c | 10 ++
hw
convert IOAPIC as piix3 proper QOM child.
IOAPIC creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/ioapic.c |2 +-
hw/ioapic.h |2 --
hw
just made things
worse. Making things proper objects and using composition is the right way
to share common devices.
By pulling these files back together, we can start to fix some of this mess.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i386/Makefile.objs |1
convert HPET as piix3 proper QOM child.
HPET creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/hpet.c | 35
convert PORT92 as piix3 proper QOM child.
PORT92 creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/pc.c| 25 -
hw/pc.h|3 +++
hw/piix3
child device in the PIIX3 ::init
function.
Anthony Liguori (3):
convert RTC as piix3 proper QOM child
convert HPET as piix3 proper QOM child
convert PIT as piix3 proper QOM child
Wanpeng Li (7):
convert PCSPK as piix3 proper QOM child
convert PORT92 as piix3 proper QOM child
convert I8042 as
convert PIT as piix3 proper QOM child.
PIT creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i8254.c |2 +-
hw/i8254_internal.h
convert IDE as piix3 proper QOM child.
IDE creation for the PIIX3 is done by calling object_init() with
qdev_init() being called for each child device in the PIIX3 ::init
function.
Signed-off-by: Wanpeng Li
---
hw/i440fx.c |6 ++
hw/ide.h |6 --
hw/ide
On Thu, Nov 08, 2012 at 01:36:09PM +0800, Wanpeng Li wrote:
>This series aggressively refactors the PC machine initialization to be more
>modelled and less ad-hoc. The highlights of this series are:
>
>1) Things like -m and -bios-name are now device model properties
>
>2) The i4
R_CRASH in this patchset. :(
Regards,
Wanpeng Li
in power states (which
we do not even emulate IIRC). In that case, the OS is under risk of
sleeping forever, thus need to look for a different wakeup source.
HPET will always be the default broadcast event device I think.
Regards,
Wanpeng Li
Live-migration or VM pausing are external effects on al
[CCing ML]
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/pci_host.c | 26 ++
hw/pci_host.h |5 +
2 files changed, 31 insertions(+), 0 deletions(-)
diff --git a/hw/pci_host.c b/hw/pci_host.c
index 8041778..095bfe3
[CCing ML]
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
memory.c | 94 ++
memory.h |8 +
2 files changed, 78 insertions(+), 24 deletions(-)
diff --git a/memory.c b/memory.c
index
IX is rational.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/hpet.c | 39 ++-
hw/hpet_emul.h | 41 +
hw/i8254.c |2 +-
hw/i8254_internal.h |2 +-
hw/mc146818rtc.c|
t
that the PMC is contained within the i440fx which we will now reflect in
composition in the next few changesets.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i386/Makefile.objs |2 +-
hw/i440fx.c | 434 +++
hw/i440fx.h
e in the device model. This lets you set properties
of the parent and its children.
realize() (which is still called DeviceState::init today) will be called right
before the guest starts up for the first time.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
Change in v4:
*rebase
[CCing ML]
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i386/Makefile.objs |1 -
hw/pc.c | 753 +++--
hw/pc.h | 46 +---
hw/pc_piix.c | 661
On Thu, Jul 19, 2012 at 03:23:32PM -0500, Anthony Liguori wrote:
>Wanpeng Li writes:
>
>> [CCing ML]
>>
>> From: Anthony Liguori
>
>Each of these devices should be a separate patch.
>
>Please don't just send patches from branches of mine. Spend so
iceState::init today) will be called right
before the guest starts up for the first time.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
Change in v5:
* drop patch "convert MemoryRegion to QOM" and
"prepare to create HPET, RTC and i8254 through composition"
* add And
From: Anthony Liguori
makes pci_host a proper QOM type.
Changelog:
* against Andreas pci_host branch
* make host bridge TypeInfos const
* use PCI_HOST_BRIDGE() where appropriate
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i440fx.c |6 +++---
hw/pc.c |2
From: Anthony Liguori
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i386/Makefile.objs |1 -
hw/pc.c | 695 +
hw/pc.h | 46 +---
hw/pc_piix.c | 661
at the PMC is contained within the i440fx which we will now reflect in
composition in the next few changesets.
Signed-off-by: Anthony Liguori
Signed-off-by: Wanpeng Li
---
hw/i386/Makefile.objs |2 +-
hw/i440fx.c | 434 +++
hw/i440fx.h
On Mon, Jul 23, 2012 at 02:57:20PM +0200, Andreas Färber wrote:
>Am 23.07.2012 14:35, schrieb Wanpeng Li:
>> From: Anthony Liguori
>>
>> makes pci_host a proper QOM type.
>>
>> Changelog:
>> * against Andreas pci_host branch
>> * make host bridge Typ
From: Wanpeng Li
The CPUID.01H:ECX[bit 3] ought to mirror the value of the MSR
IA32_MISC_ENABLE MWAIT bit and as userspace has control of them
both, it is userspace's job to configure both bits to match on
the initial setup.
Cc: Eduardo Habkost
Cc: Paolo Bonzini
Cc: Radim Krčmář
S
ncrease
downtime when acquire the benefit of reducing total time, maybe it
will be more acceptable if there is no downside for downtime.
Regards,
Wanpeng Li
#x27;
>> perception than total time, however, this feature will increase downtime
>> when acquire the benefit of reducing total time, maybe it will be more
>> acceptable if there is no downside for downtime.
>>
>> Regards,
>> Wanpeng Li
>
> In theory, there is no fac
From: Wanpeng Li
Add -kernel_irqchip=split
./x86-run x86/eventinj.flat
qemu-system-x86_64 -enable-kvm -machine kernel_irqchip=split -cpu host
-device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc
none -serial stdio -device pci-testdev -kernel x86/eventinj.flat
enabling apic
ic: fix touch LAPIC when irqchip is split...
>> ERROR: suspect code indent for conditional statements (4, 9)
>> #90: FILE: hw/i386/pc.c:164:
>> +if (!kvm_irqchip_in_kernel()) {
>> + intno = apic_get_interrupt(cpu->apic_state);
> ^
> Should be 4 spaces here.
>
>>
>> ERROR: suspect code indent for conditional statements (9, 13)
>> #92: FILE: hw/i386/pc.c:166:
>> + if (intno >= 0) {
>> + return intno;
>
> Then this and later will be indented back by 1 column.
You are right, thanks Fam.
Regards,
Wanpeng Li
From: Wanpeng Li
Add -kernel_irqchip=split
./x86-run x86/eventinj.flat
qemu-system-x86_64 -enable-kvm -machine kernel_irqchip=split -cpu host
-device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc
none -serial stdio -device pci-testdev -kernel x86/eventinj.flat
enabling apic
From: Wanpeng Li
Introduce a new APIC macro to replace APIC_COMMON macro in
hw/intc/apic.c in order to capture access LAPIC in qemu
even if LAPIC is emulated in kvm.
Suggested-by: Paolo Bonzini
Cc: Paolo Bonzini
Cc: Radim Krčmář
Cc: Michael S. Tsirkin
Cc: Eduardo Habkost
Signed-off-by
by TYPE_APIC.
Will do, thanks for your review.
Regards,
Wanpeng Li
From: Wanpeng Li
Introduce a new APIC macro to replace APIC_COMMON macro in
hw/intc/apic.c in order to capture access LAPIC in qemu
even if LAPIC is emulated in kvm.
Suggested-by: Paolo Bonzini
Reviewed-by: Michael S. Tsirkin
Cc: Paolo Bonzini
Cc: Radim Krčmář
Cc: Michael S. Tsirkin
Cc
From: Wanpeng Li
This patch adds async pf flag to KVM_GET/SET_VCPU_EVENTS interface.
Signed-off-by: Wanpeng Li
---
linux-headers/asm-x86/kvm.h | 2 ++
target/i386/cpu.h | 1 +
target/i386/kvm.c | 6 +-
3 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/linux
From: Wanpeng Li
This patch adds async page fault flag to KVM_GET/SET_VCPU_EVENTS interface.
Cc: Paolo Bonzini
Cc: Radim Krčmář
Signed-off-by: Wanpeng Li
---
v1 -> v2:
* reuse the pad for async_page_fault
* cleanup coding style
linux-headers/asm-x86/kvm.h | 3 ++-
target/i386/cp
2017-06-22 0:28 GMT+08:00 Radim Krčmář :
> 2017-06-20 20:14-0700, Wanpeng Li:
>> From: Wanpeng Li
>>
>> This patch adds async pf flag to KVM_GET/SET_VCPU_EVENTS interface.
>>
>> Signed-off-by: Wanpeng Li
>> ---
>> diff --git a/linux-header
> If you are correlating the clocks, then yes.
>
> Older Linux guests get upset (marking the TSC clocksource unstable
> because the watchdog checks TSC vs kvmclock), but there is a workaround for it
> in newer guests
> (kvmclock interface to notify watchdog to not complain).
Could
LOG_DIRTY_PAGES) &&
>> - !(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
>> - kvm_mmu_zap_collapsible_sptes(kvm, new);
This is an unlikely branch(unless guest live migration fails and
continue to run on the source machine) instead of hot path, do you
ha
2017-05-11 21:43 GMT+08:00 Wanpeng Li :
> 2017-05-11 20:24 GMT+08:00 Paolo Bonzini :
>>
>>
>> On 11/05/2017 14:07, Zhoujian (jay) wrote:
>>> -* Scan sptes if dirty logging has been stopped, dropping those
>>> -* which can be collapse
2017-05-11 22:18 GMT+08:00 Zhoujian (jay) :
> Hi Wanpeng,
>
>> 2017-05-11 21:43 GMT+08:00 Wanpeng Li :
>> > 2017-05-11 20:24 GMT+08:00 Paolo Bonzini :
>> >>
>> >>
>> >> On 11/05/2017 14:07, Zhoujian (jay) wrote:
>> >>> -
# 9.52% of all iTLB
> cache hits (16.67%)
> 1,152,784 iTLB-loads
> (33.32%)
>
> 10.000703078 seconds time elapsed
> **
Could you comment out the original "lazy collapse small sptes into
la
etup:
>
> 1) set up 1G hugetlbfs hugepages and use those for the guest's memory
>
> 2) test both without and with the above patch.
>
In addition, we can compare /sys/kernel/debug/kvm/largepages w/ and
w/o the patch. IIRC, /sys/kernel/debug/kvm/largepages will drop during
live migration, it will keep a small value if live migration fails and
w/o "lazy collapse small sptes into large sptes" codes, however, it
will increase gradually if w/ the "lazy collapse small sptes into
large sptes" codes.
Regards,
Wanpeng Li
From: Wanpeng Li
This patch adds async page fault flag to KVM_GET/SET_VCPU_EVENTS interface.
Cc: Paolo Bonzini
Cc: Radim Krčmář
Signed-off-by: Wanpeng Li
---
v2 -> v3:
* nested_apf for vcpu events
v1 -> v2:
* reuse the pad for async_page_fault
* cleanup coding style
linux-heade
been merged in kvm/qemu?
Regards,
Wanpeng Li
>
> Removed: xop, fma4, tbm
>
> Cc: Paolo Bonzini
> Cc: Richard Henderson
> Cc: Eduardo Habkost
> Cc: Tom Lendacky
> Signed-off-by: Brijesh Singh
> ---
>
> Changes since v2:
> * limit the xlevel to 0x800a
&g
clear INIT in pending_events
> considering migration, just at level >= KVM_PUT_RESET_STATE,
> add KVM_VCPUEVENT_VALID_SMM in events.flags.I think it is better to
> modify in qemu.
Do it in qemu just avoids to trigger the bug instead of fixing it. Why
we touch INIT pen
On Fri, 19 May 2017 at 16:10, Jay Zhou wrote:
>
> Hi Paolo and Wanpeng,
>
> On 2017/5/17 16:38, Wanpeng Li wrote:
> > 2017-05-17 15:43 GMT+08:00 Paolo Bonzini :
> >>> Recently, I have tested the performance before migration and after
> >>> migrat
On Wed, 20 Jun 2018 at 10:41, Michael S. Tsirkin wrote:
>
> On Wed, Jun 20, 2018 at 08:46:10AM +0800, Wanpeng Li wrote:
> > On Wed, 20 Jun 2018 at 08:07, Michael S. Tsirkin wrote:
> > >
> > > On Tue, Jun 19, 2018 at 05:07:46PM -0500, Eric Blake wrote:
> &g
%92.72% 67.15us ( +- 7.93% )
After patch:
IO Port Access Samples Samples% Time%Avg time
0x70:POUT1750945.42%42.08% 6.37us ( +- 20.37% )
Thanks to Peng Hao's initial patch.
Cc: Paolo Bonzini
Cc: Radim Krčmář
Cc: Eduardo Habkost
Signed-off-by: Wanpeng Li
---
: Wanpeng Li
---
v1 -> v2:
* add the original author
accel/kvm/kvm-all.c | 56 +++
hw/timer/mc146818rtc.c| 8 +++
include/exec/memattrs.h | 1 +
include/exec/memory.h | 5 +
include/sysemu/kvm.h | 8 +++
linux-head
Ping,
On Tue, 3 Jul 2018 at 05:43, Eduardo Habkost wrote:
>
> On Mon, Jul 02, 2018 at 06:22:51PM +0800, Wanpeng Li wrote:
> > From: Wanpeng Li
> >
> > Adds PV_SEND_IPI CPUID feature bit.
> >
>
> Thanks!
>
> Paolo, Radim: can I assume the bit is already
Hi Eduardo,
On Tue, 3 Jul 2018 at 05:43, Eduardo Habkost wrote:
>
> On Mon, Jul 02, 2018 at 06:22:51PM +0800, Wanpeng Li wrote:
> > From: Wanpeng Li
> >
> > Adds PV_SEND_IPI CPUID feature bit.
> >
>
> Thanks!
>
> Paolo, Radim: can I assume the bit is a
From: Wanpeng Li
Adds PV_SEND_IPI CPUID feature bit.
Cc: Paolo Bonzini
Cc: Eduardo Habkost
Cc: Radim Krčmář
Cc: Vitaly Kuznetsov
Signed-off-by: Wanpeng Li
---
target/i386/cpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index
u-pm=on' reads reasonably well.
>
> Yes but host resource what? I feel it says nothing at all about what
> one can expect to find in this flag.
>
> > About the only other noun I could think of would be '-feature cpu-pm=on'.
>
> If we have nothing at all to say about what is grouping these things,
> we don't need a new flag. We can make it a machine property.
>
> It's user's hint that some host resource is dedicated to a VM.
The commit 633711e82 (kvm: rename KVM_HINTS_DEDICATED to
KVM_HINTS_REALTIME) should be reverted according to several threads
discussion I think.
Regards,
Wanpeng Li
From: Wanpeng Li
The qemu will crash when info ioapic through hmp if irqchip
is split. Below message is splat:
KVM_GET_IRQCHIP failed: Unknown error -6
This patch fix it by dumping the ioapic state from the qemu
emulated ioapic if irqchip is split.
Cc: Paolo Bonzini
Cc: Richard Henderson
From: Wanpeng Li
Commit 96193c22a "target-i386: Move xsave component mask to features array"
leverages features array to handle XCR0 processor state component bits,
however, it introduces a regression:
warning: host doesn't support requested feature: CPUID.0DH:EAX [bit 0]
warnin
2016-09-28 15:54 GMT+08:00 Paolo Bonzini :
[...]
> I think the right place to add the test is x86_cpu_get_migratable_flags.
I just sent out v2 to handle this, thanks for pointing out.
Regards,
Wanpeng Li
1 - 100 of 139 matches
Mail list logo
