On 2012-08-31 06:52, Nakajima, Jun wrote:
> It includes the new VT features for interrupt/APIC virtualization that
> I mentioned at XenSummit and Linux Plumbers Conference.
>
> http://www.intel.com/content/www/us/en/processors/architectures-software-developer-manuals.html
>
Cool features ahead :
On 08/31/2012 02:59 AM, Hugo wrote:
> On Thu, Aug 30, 2012 at 5:22 AM, Xiao Guangrong
> wrote:
>> On 08/28/2012 11:30 AM, Felix wrote:
>>> Xiao Guangrong linux.vnet.ibm.com> writes:
>>>
On 07/31/2012 01:18 AM, Sunil wrote:
> Hello List,
>
> I am a KVM newbie and studying KVM
On Tue, 2012-07-31 at 14:53 -0400, Sunil Agham wrote:
> On Mon, Jul 30, 2012 at 10:49 PM, Xiao Guangrong
> wrote:
> > On 07/31/2012 01:18 AM, Sunil wrote:
> >> Hello List,
> >>
> >> I am a KVM newbie and studying KVM mmu code.
> >>
> >> On the existing guest, I am trying to track all guest writes
This is primarily done so that the guest will think it is running
under vmware when hypervisor=vmware is specified as a property of a
cpu.
Also allow this to work in accel=tcg mode.
The new cpu properties hyper_level, hyper_extra, hyper_extra_a, and
hyper_extra_b can be used to further adjust wha
This is primarily done so that the guest will think it is running
under vmware when hypervisor=vmware is specified as a property of a
cpu.
Also allow this to work in accel=tcg mode.
The new cpu properties hyper_level, hyper_extra, hyper_extra_a, and
hyper_extra_b can be used to further adjust wha
This is primarily done so that the guest will think it is running
under vmware when hypervisor=vmware is specified as a property of a
cpu.
Also allow this to work in accel=tcg mode.
The new cpu properties hyper_level, hyper_extra, hyper_extra_a, and
hyper_extra_b can be used to further adjust wha
This is primarily done so that the guest will think it is running
under vmware when hypervisor=vmware is specified as a property of a
cpu.
Also allow this to work in accel=tcg mode.
The new cpu properties hyper_level, hyper_extra, hyper_extra_a, and
hyper_extra_b can be used to further adjust wha
On Thu, Aug 30, 2012 at 5:22 AM, Xiao Guangrong
wrote:
> On 08/28/2012 11:30 AM, Felix wrote:
>> Xiao Guangrong linux.vnet.ibm.com> writes:
>>
>>>
>>> On 07/31/2012 01:18 AM, Sunil wrote:
Hello List,
I am a KVM newbie and studying KVM mmu code.
On the existing guest, I am
In addition to Andrew's comment about making the stats struct and
functions generic...
On 8/27/12 3:51 AM, Dong Hao wrote:
---8<---
+static void exit_event_decode_key(struct event_key *key, char decode[20])
+{
+ const char *exit_reason = get_exit_reason(key->key);
+
+ snprintf(deco
On Fri, Aug 31, 2012 at 01:09:56AM +0900, Takuya Yoshikawa wrote:
> On Thu, 30 Aug 2012 16:21:31 +0300
> "Michael S. Tsirkin" wrote:
>
> > > +static u32 apic_read_reg(int reg_off, void *bitmap)
> > > +{
> > > + return *((u32 *)(bitmap + reg_off));
> > > +}
> > > +
> >
> > Contrast with apic_set
On Thu, 30 Aug 2012 16:21:31 +0300
"Michael S. Tsirkin" wrote:
> > +static u32 apic_read_reg(int reg_off, void *bitmap)
> > +{
> > + return *((u32 *)(bitmap + reg_off));
> > +}
> > +
>
> Contrast with apic_set_reg which gets apic,
> add fact that all callers invoke REG_POS and you will
> see
Il 30/08/2012 16:53, Michael S. Tsirkin ha scritto:
>> > this series adds multiqueue support to the virtio-scsi driver, based
>> > on Jason Wang's work on virtio-net. It uses a simple queue steering
>> > algorithm that expects one queue per CPU. LUNs in the same target always
>> > use the same qu
On Thu, Aug 30, 2012 at 8:37 AM, santwana wrote:
> Hi All,
>
> Please find the results of upstream testing.
>
> We are evaluating the failures and will be raising the issues with the
> appropriate community.
>
> Environment:
> Host Kernel: 3.5.0-rc6
> KVM Version: 1.1.90
> Date: Thu Aug 30 15:29:0
On Tue, Aug 28, 2012 at 01:54:12PM +0200, Paolo Bonzini wrote:
> Hi all,
>
> this series adds multiqueue support to the virtio-scsi driver, based
> on Jason Wang's work on virtio-net. It uses a simple queue steering
> algorithm that expects one queue per CPU. LUNs in the same target always
> use
https://bugzilla.kernel.org/show_bug.cgi?id=42782
Alan changed:
What|Removed |Added
CC||a...@lxorguk.ukuu.org.uk
Kernel Version|3.2.6
On Thu, Aug 30, 2012 at 01:21:57PM +0200, Sasha Levin wrote:
> Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will use indirect
> descriptors even if we have plenty of space in the ring. This means that
> we take a performance hit at all times due to the overhead of creating
> indirect desc
https://bugzilla.kernel.org/show_bug.cgi?id=42600
Alan changed:
What|Removed |Added
Status|NEW |RESOLVED
CC|
On Thu, Aug 30, 2012 at 01:21:58PM +0200, Sasha Levin wrote:
> Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
> use indirect descriptors and allocate them using a simple
> kmalloc().
>
> This patch adds a cache which will allow indirect buffers under
> a configurable size to be alloca
On Thu, Aug 30, 2012 at 09:30:19PM +0900, Takuya Yoshikawa wrote:
> find_highest_vector() and count_vectors():
> - Instead of using magic values, define and use proper interfaces
>to access registers.
>
> find_highest_vector():
> - Remove likely() which is there only for historical reasons a
find_highest_vector() and count_vectors():
- Instead of using magic values, define and use proper interfaces
to access registers.
find_highest_vector():
- Remove likely() which is there only for historical reasons and not
doing correct branch predictions anymore. Using such heuristics
Hi All,
Please find the results of upstream testing.
We are evaluating the failures and will be raising the issues with the
appropriate community.
Environment:
Host Kernel: 3.5.0-rc6
KVM Version: 1.1.90
Date: Thu Aug 30 15:29:06 2012
Stats: 41 tests executed (26 tests passed, 15 tests failed)
Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will use indirect
descriptors even if we have plenty of space in the ring. This means that
we take a performance hit at all times due to the overhead of creating
indirect descriptors.
Instead, use it only after we're below a configurable offse
Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().
This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.
Signed-off-by: Sasha Levin
---
drivers/bl
On Thu, Aug 30, 2012 at 07:24:39PM +0900, Takuya Yoshikawa wrote:
> On Thu, 30 Aug 2012 13:10:33 +0300
> "Michael S. Tsirkin" wrote:
>
> > > OK, I'll do these on top of this patch.
> >
> > Tweaking these 5 lines for readability across multiple
> > patches is just not worth it.
> > As long as we
On 08/24/2012 03:29 PM, 陳韋任 (Wei-Ren Chen) wrote:
> Hi Guangrong,
>
> I am not familiar with the term used in paging world, so I need to ask
> some dumb questions.
>
>> It is controlled by shadow page table, guest-page-tables are write-protected
>> on shadow pages (the W bit on PTE is cleared).
On 08/29/2012 05:14 PM, Michael S. Tsirkin wrote:
>> > Note that these are simple tests with netperf listening on one end and a
>> > simple
>> > 'netperf -H [host]' within the guest. If there are other tests which may be
>> > interesting please let me know.
> Checking that host CPU utilization did
Commit aea218f3cbbc (KVM: PIC: call ack notifiers for irqs that are
dropped form irr) used an uninitialised variable to track whether an
appropriate apic had been found. This could result in calling the ack
notifier incorrectly.
Cc: Gleb Natapov
Cc: Avi Kivity
Signed-off-by: Jamie Iles
---
ar
On Thu, 30 Aug 2012 13:10:33 +0300
"Michael S. Tsirkin" wrote:
> > OK, I'll do these on top of this patch.
>
> Tweaking these 5 lines for readability across multiple
> patches is just not worth it.
> As long as we do random cleanups of this function it's probably easier
> to just do them all in
On 08/30/2012 04:03 AM, Wen Congyang wrote:
> At 08/29/2012 07:56 PM, Sasha Levin Wrote:
>> On 08/29/2012 07:18 AM, Wen Congyang wrote:
>>> diff --git a/Documentation/virtual/kvm/pv_event.txt
>>> b/Documentation/virtual/kvm/pv_event.txt
>>> new file mode 100644
>>> index 000..bb04de0
>>> --- /
On 08/28/2012 11:30 AM, Felix wrote:
> Xiao Guangrong linux.vnet.ibm.com> writes:
>
>>
>> On 07/31/2012 01:18 AM, Sunil wrote:
>>> Hello List,
>>>
>>> I am a KVM newbie and studying KVM mmu code.
>>>
>>> On the existing guest, I am trying to track all guest writes by
>>> marking page table entry
On Thu, Aug 30, 2012 at 06:50:52PM +0900, Takuya Yoshikawa wrote:
> On Thu, 30 Aug 2012 09:37:02 +0300
> "Michael S. Tsirkin" wrote:
>
> > After staring at your code for a while it does appear to
> > do the right thing, and looks cleaner than what
> > we have now. commit log could be clearer.
> >
On Thu, 30 Aug 2012 09:37:02 +0300
"Michael S. Tsirkin" wrote:
> After staring at your code for a while it does appear to
> do the right thing, and looks cleaner than what
> we have now. commit log could be clearer.
> It should state something like:
>
>
> Clean up code in find_highest_vector:
>
On 08/30/2012 11:48 AM, Pekka Enberg wrote:
> On Thu, Aug 30, 2012 at 12:44 PM, Sasha Levin wrote:
>> On 08/30/2012 09:50 AM, Cyrill Gorcunov wrote:
>>> On Thu, Aug 30, 2012 at 09:36:37AM +0200, Sasha Levin wrote:
+char *new_env[] = { "TERM=linux", "DISPLAY=192.168.33.1:0",
+
On Thu, Aug 30, 2012 at 12:44 PM, Sasha Levin wrote:
> On 08/30/2012 09:50 AM, Cyrill Gorcunov wrote:
>> On Thu, Aug 30, 2012 at 09:36:37AM +0200, Sasha Levin wrote:
>>> +char *new_env[] = { "TERM=linux", "DISPLAY=192.168.33.1:0",
>>> +"HOME=/virt/home", NULL };
>>>
On 08/30/2012 09:50 AM, Cyrill Gorcunov wrote:
> On Thu, Aug 30, 2012 at 09:36:37AM +0200, Sasha Levin wrote:
>> +char *new_env[] = { "TERM=linux", "DISPLAY=192.168.33.1:0",
>> +"HOME=/virt/home", NULL };
>> +
>> +mkdir("/virt/home", 0755);
>
> Please add check
On Thu, Aug 30, 2012 at 11:22 AM, Cyrill Gorcunov wrote:
> Maybe we could enable it via some make option?
> Say make LTO=1 or something?
That is not going to help much in catching LTO issues early.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to major
On Tue, Jun 26, 2012 at 01:32:58PM -0700, Frank Swiderski wrote:
> +static void fill_balloon(struct virtio_balloon *vb, size_t num)
> +{
> + int err;
> +
> + /* We can only do one array worth at a time. */
> + num = min(num, ARRAY_SIZE(vb->pfns));
> +
> + for (vb->num_pfns = 0; vb->
On Thu, Aug 30, 2012 at 10:33:21AM +0200, Sasha Levin wrote:
> >>>
> >>> Ingo, any objections to this?
> >>
> >> No objections if you can live with a 2x-4x increase in build
> >> time - at worst it might cause funnies with the BIOS linker
> >> script and such.
> >
> > Maybe we could enable it vi
On 08/30/2012 10:22 AM, Cyrill Gorcunov wrote:
> On Thu, Aug 30, 2012 at 10:16:54AM +0200, Ingo Molnar wrote:
>>
>> * Pekka Enberg wrote:
>>
>>> On Thu, Aug 30, 2012 at 10:36 AM, Sasha Levin
>>> wrote:
Build with -flto set, which should enable link-time-optimizations.
I'm not sure
On Thu, Aug 30, 2012 at 10:16:54AM +0200, Ingo Molnar wrote:
>
> * Pekka Enberg wrote:
>
> > On Thu, Aug 30, 2012 at 10:36 AM, Sasha Levin
> > wrote:
> > > Build with -flto set, which should enable link-time-optimizations.
> > >
> > > I'm not sure if it provides a significant performance incre
* Pekka Enberg wrote:
> On Thu, Aug 30, 2012 at 10:36 AM, Sasha Levin wrote:
> > Build with -flto set, which should enable link-time-optimizations.
> >
> > I'm not sure if it provides a significant performance increase, but
> > it's probably just worth it for catching issues which it may cause.
On Tue, Aug 28, 2012 at 01:54:12PM +0200, Paolo Bonzini wrote:
> this series adds multiqueue support to the virtio-scsi driver, based
> on Jason Wang's work on virtio-net. It uses a simple queue steering
> algorithm that expects one queue per CPU. LUNs in the same target always
> use the same que
On Thu, Aug 30, 2012 at 10:36 AM, Sasha Levin wrote:
> Build with -flto set, which should enable link-time-optimizations.
>
> I'm not sure if it provides a significant performance increase, but
> it's probably just worth it for catching issues which it may cause.
>
> Signed-off-by: Sasha Levin
I
On Thu, Aug 30, 2012 at 09:36:37AM +0200, Sasha Levin wrote:
> + char *new_env[] = { "TERM=linux", "DISPLAY=192.168.33.1:0",
> + "HOME=/virt/home", NULL };
> +
> + mkdir("/virt/home", 0755);
Please add check for mkdir error code. Frankly, this is a bad habbit
to
Instead of a get/set for config values, just request the address of the
config region, and handle that by simply reading directly from that region.
Signed-off-by: Sasha Levin
---
tools/kvm/include/kvm/virtio.h | 3 +--
tools/kvm/virtio/9p.c | 12 ++--
tools/kvm/virtio/balloon.c
We're not supposed to kill all fids when a new attach request
arrives. This used to cause issues when the guest would send
multiple attach requests.
Signed-off-by: Sasha Levin
---
tools/kvm/virtio/9p.c | 22 --
1 file changed, 22 deletions(-)
diff --git a/tools/kvm/virtio/9p
Build with -flto set, which should enable link-time-optimizations.
I'm not sure if it provides a significant performance increase, but
it's probably just worth it for catching issues which it may cause.
Signed-off-by: Sasha Levin
---
tools/kvm/Makefile | 2 +-
1 file changed, 1 insertion(+), 1
Fix up warnings related to not checking return value of read/write by actually
handling errors there.
Signed-off-by: Sasha Levin
---
tools/kvm/virtio/blk.c | 10 --
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/tools/kvm/virtio/blk.c b/tools/kvm/virtio/blk.c
index 740442a
We still create GSIs and keep them for two reasons:
- They're required by virtio-* devices.
- There's not much overhead since we just create them when starting the
guest, they don't use anything when the guest is running.
Signed-off-by: Sasha Levin
---
tools/kvm/include/kvm/virtio-pci.h | 3
Signed-off-by: Sasha Levin
---
tools/kvm/ioeventfd.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/tools/kvm/ioeventfd.c b/tools/kvm/ioeventfd.c
index 226876f..742b008 100644
--- a/tools/kvm/ioeventfd.c
+++ b/tools/kvm/ioeventfd.c
@@ -44,7 +44,6 @@ static void *ioeventfd__thread(void *param)
Add a HOME env var when booting a hostfs guest. This will point out to a home
dir within the given guest name.
This will make several apps happier when being run under hostfs.
Signed-off-by: Sasha Levin
---
tools/kvm/guest/init.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff -
51 matches
Mail list logo
