(2013/10/29 11:58), David Ahern wrote:
> On 10/28/13 7:15 AM, Peter Zijlstra wrote:
>>> Any suggestions on how to do this and without impacting performance. I
>>> noticed the MSR path seems to take about twice as long as the current
>>> implementation (which I believe results in rdtsc in the VM for
Hi Alex,
Looks like this patch is not picked by anyone, Are you going to pick this patch?
My vfio/iommu patches have dependency on this patch (this is already tested by
me).
Thanks
-Bharat
> -Original Message-
> From: Linuxppc-dev [mailto:linuxppc-dev-
> bounces+bharat.bhushan=freescale
Hi
Not only lock waiter preemption, but the scheduler may affect VMs' IO
throughput.
Experiments must be taken to figure out the reason.
I am trying to use preempt_notifier and vmexit handler to build a more
efficient scheduler.
Something like priority boosting.
2013/10/29 Gleb Natapov :
> On Tue
On Mon, Oct 28, 2013 at 12:37:56PM -0700, Greg Edwards wrote:
> Using KVM PCI assignment with 1 GiB huge pages trips a BUG in 3.12.0-rc7, e.g.
>
> # qemu-system-x86_64 \
> -m 8192 \
> -mem-path /var/lib/hugetlbfs/pagesize-1GB \
> -mem-prealloc \
> -enable-kvm \
> -devi
> -Original Message-
> From: Don Dutile [mailto:ddut...@redhat.com]
> Sent: Tuesday, October 29, 2013 12:13 PM
> To: Alex Williamson
> Cc: Bhushan Bharat-R65777; Antonios Motakis;
> kvm...@lists.cs.columbia.edu; linux-samsung-...@vger.kernel.org;
> kvm@vger.kernel.org; ag...@suse.de; Yode
On 10/29/2013 07:47 AM, Alex Williamson wrote:
On Mon, 2013-10-28 at 21:29 -0400, Don Dutile wrote:
On 09/30/2013 11:37 AM, Bhushan Bharat-R65777 wrote:
-Original Message-
From: iommu-boun...@lists.linux-foundation.org [mailto:iommu-
boun...@lists.linux-foundation.org] On Behalf Of A
On Wed, Oct 30, 2013 at 12:57:32AM +0530, Raghavendra K T wrote:
> Adding Greg/AI too since we touch debugfs code.
You do?
> [...]
> >>
> >>sudo modprobe kvm_amd
> >>modprobe: ERROR: could not insert 'kvm_amd': Bad address
> >
> >"Bad address"? Christ people, are you guys making up error numbers
On Tue, Oct 29, 2013 at 12:27 PM, Raghavendra K T
wrote:
>
> Could one solution be cascading actual error
> that is lost in fs/debugfs/inode.c:__create_file(), so that we could
> take correct action in case of failure of debugfs_create_dir()?
>
> (ugly side is we increase total number of params fo
Adding Greg/AI too since we touch debugfs code.
[...]
>>
sudo modprobe kvm_amd
modprobe: ERROR: could not insert 'kvm_amd': Bad address
"Bad address"? Christ people, are you guys making up error numbers
with some kind of dice-roll? I can just see it now, somebody sitting
there with a D20, playi
> > > 2. Get the system into the bad state and then do some deeper. Start
> > >with outgoing ping, instrument guest driver and host vhost_net
> > >functions to see what the drivers are doing, inspect the transmit
> > >vring, etc.
Update: have not gotten around to reboot the server for
Ugh. I won't comment on the actual kvm part of this patch, somebody
who knows that code should do so.
But I reacted to this:
On Tue, Oct 29, 2013 at 8:13 AM, Tim Gardner wrote:
>
> sudo modprobe kvm_amd
> modprobe: ERROR: could not insert 'kvm_amd': Bad address
"Bad address"? Christ people, are
So far we've succeeded at making KVM and VFIO mostly unaware of each
other, but areas are cropping up where a connection beyond eventfds
and irqfds needs to be made. This patch introduces a KVM-VFIO device
that is meant to be a gateway for such interaction. The user creates
the device and can add
The setting of the SNP bit in the intel-iommu page tables should not
be dependent on the current capability of the iommu domain. The
current VT-d spec (2.2) indicates the SNP bit is "treated as
reserved[0] by hardware implementations not supporting Snoop Control".
Furthermore, section 3.7.3 indica
The KVM device interface allocates a struct kvm_device and calls
kvm_device_ops.create on it from KVM VM ioctl KVM_CREATE_DEVICE.
This returns a file descriptor to the user for them to set/get/check
further attributes. On closing the file descriptor, one would assume
that kvm_device_ops.destroy is
This series allows QEMU to create a VFIO device in KVM for registering
VFIO groups. The initial user of this interface is to toggle whether
KVM emulates coherency instructions like WBINVD. For this particular
use case I've toyed with the idea of disabling NoSnoop at the device,
but we already hav
Default to operating in coherent mode. This simplifies the logic when
we switch to a model of registering and unregistering noncoherent I/O
with KVM.
Signed-off-by: Alex Williamson
---
arch/ia64/include/asm/kvm_host.h |2 +-
arch/x86/include/asm/kvm_host.h |2 +-
arch/x86/kvm/vmx.c
We currently use some ad-hoc arch variables tied to legacy KVM device
assignment to manage emulation of instructions that depend on whether
non-coherent DMA is present. Create an interface for this, adapting
legacy KVM device assignment and adding VFIO via the KVM-VFIO device.
For now we assume th
> -Original Message-
> From: Antonios Motakis [mailto:a.mota...@virtualopensystems.com]
> Sent: Wednesday, October 02, 2013 6:14 AM
> To: Yoder Stuart-B08248
> Cc: Alex Williamson; kvm...@lists.cs.columbia.edu; iommu@lists.linux-
> foundation.org; linux-samsung-...@vger.kernel.org; kvm@vg
Juan Quintela wrote:
> Hi
>
> Please, send any topic that you are interested in covering.
As there are no topics, no call (lots of stuff got discussed on kvm forum)
See you in two weeks.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger
> -Original Message-
> From: kvm-ow...@vger.kernel.org [mailto:kvm-ow...@vger.kernel.org] On Behalf
> Of
> Alex Williamson
> Sent: Tuesday, October 29, 2013 5:17 PM
> To: Don Dutile
> Cc: Bhushan Bharat-R65777; Antonios Motakis; kvm...@lists.cs.columbia.edu;
> linux-samsung-...@vger.kern
On Mon, Oct 28, 2013 at 08:58:08PM -0600, David Ahern wrote:
> To back out a bit, my end goal is to be able to create and merge perf-events
> from any context on a KVM-based host -- guest userspace, guest kernel space,
> host userspace and host kernel space (userspace events with a perf-clock
> tim
> -Original Message-
> From: Don Dutile [mailto:ddut...@redhat.com]
> Sent: Monday, October 28, 2013 8:30 PM
> To: Bhushan Bharat-R65777
> Cc: Antonios Motakis; kvm...@lists.cs.columbia.edu;
> alex.william...@redhat.com; linux-samsung-...@vger.kernel.org;
> kvm@vger.kernel.org; ag...@suse
Il 29/10/2013 06:39, Arthur Chunqi Li ha scritto:
> What is the dirty page tracking code path? I find a obsoleted flag
> "dirty_page_log_all" in the very previous codes, but I cannot get the
> most recent version of tracking dirty pages.
Basically everything that accesses the dirty_bitmap field of
From: Borislav Petkov
This basically came from the need to be able to boot 32-bit Atom SMP
guests on an AMD host, i.e. a host which doesn't support MOVBE. As a
matter of fact, qemu has since recently received MOVBE support but we
cannot share that with kvm emulation and thus we have to do this in
From: Borislav Petkov
Add initial support for handling three-byte instructions in the
emulator.
Signed-off-by: Borislav Petkov
---
arch/x86/kvm/emulate.c | 30 ++
1 file changed, 30 insertions(+)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 54
On Tue, Oct 29, 2013 at 01:36:03PM +0200, Gleb Natapov wrote:
> git://git.kernel.org/pub/scm/virt/kvm/kvm.git queue branch.
Ok, they still apply.
I'm sending 4 and 5 (5 needed changes too) as a reply to this message.
> That's why we got "max users limit is reached" error! (only for the
> first h
On Mon, 2013-10-28 at 21:29 -0400, Don Dutile wrote:
> On 09/30/2013 11:37 AM, Bhushan Bharat-R65777 wrote:
> >
> >
> >> -Original Message-
> >> From: iommu-boun...@lists.linux-foundation.org [mailto:iommu-
> >> boun...@lists.linux-foundation.org] On Behalf Of Antonios Motakis
> >> Sent: Mo
On Tue, Oct 29, 2013 at 12:28:24PM +0100, Borislav Petkov wrote:
> On Tue, Oct 29, 2013 at 12:35:24PM +0200, Gleb Natapov wrote:
> > If everything still applies patch 4 resend should be fine.
>
> Which tree should they still apply to?
>
git://git.kernel.org/pub/scm/virt/kvm/kvm.git queue branch.
On Tue, Oct 29, 2013 at 12:35:24PM +0200, Gleb Natapov wrote:
> If everything still applies patch 4 resend should be fine.
Which tree should they still apply to?
> Yeah, kvm forum was not at the same building as LinuxCon :(
Yep, I know. We did go to the kvm forum to use the wifi there because
th
On Tue, Oct 29, 2013 at 11:30:03AM +0100, Borislav Petkov wrote:
> On Tue, Oct 29, 2013 at 11:53:00AM +0200, Gleb Natapov wrote:
> > Except a small nitpick for patch 4 this looks good to me. No need to
> > wait for QEMU cpu parsing code to change to apply it.
>
> Ok, want a resend or rather a pull
On Tue, Oct 29, 2013 at 11:53:00AM +0200, Gleb Natapov wrote:
> Except a small nitpick for patch 4 this looks good to me. No need to
> wait for QEMU cpu parsing code to change to apply it.
Ok, want a resend or rather a pull request or only patch 4 resend?
Btw, we kinda missed each other in Edinbu
On Tue, Oct 29, 2013 at 11:04:57AM +0100, Borislav Petkov wrote:
> On Tue, Oct 29, 2013 at 11:50:43AM +0200, Gleb Natapov wrote:
> > There are two three opcode tables, so third_opcode_byte is ambiguous.
>
> Actually there's also 0F_3A and there are also other prefixes besides f0
> and f1. Oh, and
On Tue, Oct 29, 2013 at 11:50:43AM +0200, Gleb Natapov wrote:
> There are two three opcode tables, so third_opcode_byte is ambiguous.
Actually there's also 0F_3A and there are also other prefixes besides f0
and f1. Oh, and those tables are not completely full so I can imagine
more stuff coming in
On Sun, Sep 22, 2013 at 04:44:49PM +0200, Borislav Petkov wrote:
> From: Borislav Petkov
>
> Alriiight,
>
> here's another version of the patchset, hopefully addressing all review
> feedback from last time. 6/6 is the respective qemu patch to handle
> emulated features query, etc.
>
Except a sm
On Sun, Sep 22, 2013 at 04:44:53PM +0200, Borislav Petkov wrote:
> From: Borislav Petkov
>
> Add initial support for handling three-byte instructions in the
> emulator.
>
> Signed-off-by: Borislav Petkov
> ---
> arch/x86/kvm/emulate.c | 30 ++
> 1 file changed, 30 i
On Tue, Oct 29, 2013 at 10:20:37AM +0800, R wrote:
> Hi, everyone
>
> I am a graduate student. And now I have some spare time.
> I notice that KVM uses kernel scheduler to schedule VCPUs.
> But there exists many problem beyond the capability of current
> scheduler. (e.g. Lock Waiter Preemption pro
On Tue, Oct 29, 2013 at 7:50 AM, R <1989012...@gmail.com> wrote:
> Hi, everyone
>
> I am a graduate student. And now I have some spare time.
> I notice that KVM uses kernel scheduler to schedule VCPUs.
> But there exists many problem beyond the capability of current
> scheduler. (e.g. Lock Waiter P
37 matches
Mail list logo