On Tue, 2007-10-23 at 16:19 +0200, Avi Kivity wrote:
Jan Kiszka wrote:
Avi,
[somehow your mails do not get through to my private account, so I'm
switching]
Avi Kivity wrote:
Jan Kiszka wrote:
Clarification: I can't precisely tell what code is executed in VM mode,
as
On Fri, 2007-10-19 at 16:17 +0200, Back, Michael (ext) wrote:
Are you referring to the -rt patch?
Yes, I take the patch from
http://www.kernel.org/pub/linux/kernel/projects/rt/
Ah, yes. There were problems in the past with running KVM on -rt if you
have the full kit enabled. Its
Hi Michael,
On Fri, 2007-10-19 at 15:32 +0200, Back, Michael (ext) wrote:
2.6.31.1 should be 2.6.23.1 - sorry
_
Von:Back, Michael (ext)
Gesendet: Friday, October 19, 2007 3:16 PM
An: 'kvm-devel@lists.sourceforge.net'
On Thu, 2007-10-04 at 18:33 +0200, Farkas Levente wrote:
hi,
what's the real reason that kvm can't be compiled gcc-4.x?
wouldn't it be better to be able to compile with the current compilers too?
Its actually an issue with QEMUs cpu emulation code. It takes advantage
of compiler traits that
On Thu, 2007-10-04 at 19:27 +0200, Farkas Levente wrote:
ok but now as qemu code was imported into kvm, then it's probably would
be better to witch gcc-4.x?
Sure. Are you volunteering? ;) I'm sure both upstream QEMU developers,
KVM developers, and the community using either would be most
On Thu, 2007-10-04 at 21:49 +0200, Farkas Levente wrote:
Gregory Haskins wrote:
On Thu, 2007-10-04 at 19:27 +0200, Farkas Levente wrote:
ok but now as qemu code was imported into kvm, then it's probably would
be better to witch gcc-4.x?
Sure. Are you volunteering? ;) I'm sure both
On Mon, 2007-10-01 at 17:23 -0600, Cam Macdonell wrote:
Actually, I looking into doing a PhD dissertation :) I'm just trying to
get a better working understanding of how kvm (and other VMMs) handle
instructions like int80 that should trap into the OS, but of course in a
VM need to trap
On Fri, 2007-08-24 at 21:08 +0800, Dong, Eddie wrote:
Avi:
apic-lock is used in many place to avoid race condition with apic
timer call back
function which may run on different pCPU. This patch migrate the
apic timer to
same CPU with the one VP runs on, thus the lock is no
On Fri, 2007-08-24 at 22:24 +0800, Dong, Eddie wrote:
[EMAIL PROTECTED] wrote:
Gregory Haskins wrote:
On Fri, 2007-08-24 at 21:08 +0800, Dong, Eddie wrote:
Avi:
apic-lock is used in many place to avoid race condition with
apic timer call back function which may run
The following series implements v4 of the PV-IO series.
Changes since v3:
1)Rebased on top of kvm.git HEAD
2)Forward ported Ingo's/Dor's baseline work for paravirtualization (Dropped
ballon and net driver)
3)Fixed numerous bugs: You can now pass packets via the IOQNET loopback.
I am on
Author: Ingo Molnar [EMAIL PROTECTED]
Author: Dor Laor [EMAIL PROTECTED]
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
include/asm-i386/hypercall.h | 138
include/asm-x86_64/hypercall.h | 100 +
2 files changed, 238
Author: Ingo Molnar [EMAIL PROTECTED]
Author: Dor Laor [EMAIL PROTECTED]
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
include/linux/kvm.h | 20
1 files changed, 20 insertions(+), 0 deletions(-)
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 1d5a49c
IOQ is a generic shared-memory-queue mechanism that happens to be friendly
to virtualization boundaries. Note that it is not virtualization specific
due to its flexible transport layer.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
include/linux/ioq.h | 176
if the
entire core is not operating with PVOPS. Therefore, we introduce a separate
interface to deal with the devices.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
arch/i386/Kconfig|2 +
arch/x86_64/Kconfig |2 +
drivers/Makefile |1
drivers
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/net/Kconfig | 10 +
drivers/net/Makefile|2
drivers/net/ioqnet/Makefile | 11 +
drivers/net/ioqnet/driver.c | 678 +++
include/linux/ioqnet.h | 44 +++
5 files
We can add a IOQNET loop-back device and register it with the PVBUS to test
many aspects of the system (IOQ, PVBUS, and IOQNET itself).
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/net/Kconfig | 10 +
drivers/net/ioqnet/Makefile |3
drivers/net/ioqnet
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
arch/x86_64/kernel/io_apic.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index f57f8b9..f8d2508 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig | 16 ++
drivers/kvm/Makefile |2
drivers/kvm/ioq.h | 39 +
drivers/kvm/ioq_guest.c | 196 +++
drivers/kvm/pvbus.h | 63 +++
drivers/kvm/pvbus_guest.c
From: Dor Laor [EMAIL PROTECTED]
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h | 11 +++
drivers/kvm/kvm_main.c | 153 +++-
drivers/kvm/svm.c | 11 +++
drivers/kvm/svm.h |2 -
drivers/kvm/vmx.c
IOQ is a shared-memory-queue interface for implmenting PV driver
communication.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig|5 +
drivers/kvm/Makefile |3
drivers/kvm/ioq.h | 12 +-
drivers/kvm/ioq_host.c | 365
PVBUS allows VMM agnostic PV drivers to discover/configure virtual resources
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig |2
drivers/kvm/Makefile |1
drivers/kvm/kvm.h|3
drivers/kvm/kvm_main.c |4
drivers/kvm/pvbus_host.c
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig | 10 +
drivers/kvm/Makefile |4
drivers/kvm/ioqnet_host.c | 578 +
3 files changed, 591 insertions(+), 1 deletions(-)
diff --git a/drivers/kvm/Kconfig b
On Fri, 2007-08-24 at 17:22 -0700, Dor Laor wrote:
Cheers and enjoy the vacation
Thanks!
(your not going to Tuscon Arizona are you...)
While I can't quite say I'd rather be in AZ than on vacation with the
family ;), I am disappointed that the timing will prevent me from
joining you guys.
On Thu, 2007-08-23 at 10:46 +0300, Avi Kivity wrote:
repository: /home/avi/kvm/linux-2.6
branch: lapic5
commit 8ed05c33d82a394c90b5dd830513416e59ffcf68
Author: Yang, Sheng [EMAIL PROTECTED]
Date: Wed Aug 22 15:03:15 2007 +0300
KVM: VMX: Use shadow TPR/cr8 for 64-bits guests
On Tue, 2007-08-21 at 17:58 +1000, Rusty Russell wrote:
Partly the horror of the code, but mainly because it is an in-order
ring. You'll note that we use a reply ring, so we don't need to know
how much the other side has consumed (and it needn't do so in order).
I have certainly been known
On Tue, 2007-08-21 at 15:25 +0300, Avi Kivity wrote:
Gregory Haskins wrote:
On Tue, 2007-08-21 at 17:58 +1000, Rusty Russell wrote:
Partly the horror of the code, but mainly because it is an in-order
ring. You'll note that we use a reply ring, so we don't need to know
how much
On Tue, 2007-08-21 at 23:47 +1000, Rusty Russell wrote:
Hi Gregory,
The main current use is disk drivers: they process out-of-order.
Maybe for you ;) I am working on the networking/IVMC side.
I think the use of rings for the tx-path in of
itself is questionable unless you can
On Tue, 2007-08-21 at 10:06 -0400, Gregory Haskins wrote:
On Tue, 2007-08-21 at 23:47 +1000, Rusty Russell wrote:
In the guest - host direction, an interface like virtio is designed
for batching, with the explicit distinction between add_buf sync.
Right. IOQ has iter_push
On Tue, 2007-08-21 at 20:12 +0300, Avi Kivity wrote:
No, sync() means make the other side aware that there's work to be done.
Ok, but still the important thing isn't the kick per se, but the
resulting completetion. Can we do interrupt driven reclamation? Some
of those virtio_net emails I
On Sun, 2007-08-19 at 12:24 +0300, Avi Kivity wrote:
Rusty Russell wrote:
2) We either need huge descriptors or some chaining mechanism to
handle scatter-gather.
Or, my preference, have a small sglist in the descriptor;
Define small ;)
There a certainly patterns
On Mon, 2007-08-20 at 07:03 -0700, Dor Laor wrote:
2) We either need huge descriptors or some chaining
mechanism to
handle scatter-gather.
Or, my preference, have a small sglist in the descriptor;
Define small ;)
There a certainly patterns that cannot/will-not
On Fri, 2007-08-17 at 17:43 +1000, Rusty Russell wrote:
Sure, these discussions can get pretty esoteric. The question is
whether you want a point-to-point transport (as we discuss here), or an
N-way. Lguest has N-way, but I'm not convinced it's worthwhile, as
there's some overhead
Here is the v3 release of the patch series for a generalized PV-IO
infrastructure. It has v2 plus the following changes:
1) The big changes is that PVBUS is now based on the bus/device_register
APIs. The code is inspired by the lguest_bus except it has been decoupled
from the hypervisor.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/net/Kconfig | 10 +
drivers/net/Makefile|2
drivers/net/ioqnet/Makefile | 11 +
drivers/net/ioqnet/driver.c | 658 +++
include/linux/ioqnet.h | 44 +++
5 files
We can add a IOQNET loop-back device and register it with the PVBUS to test
many aspects of the system (IOQ, PVBUS, and IOQNET itself).
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/net/Kconfig | 10 +
drivers/net/ioqnet/Makefile |3
drivers/net/ioqnet
Hi Rusty,
Comments inline...
On Fri, 2007-08-17 at 11:25 +1000, Rusty Russell wrote:
Transport has several parts. What the hypervisor knows about (usually
shared memory and some interrupt mechanism and possibly DMA) and what
is convention between users (eg. ringbuffer layouts). Whether
On Wed, 2007-08-15 at 11:07 +0300, Avi Kivity wrote:
Farkas Levente wrote:
this rise another question if swapping will be used the it moves the
guest memory to the guest's swap or the host's swap? if to the host's
swap then this implies i should have to allocate large enough swap for
the
On Wed, 2007-08-15 at 00:52 -0700, Dor Laor wrote:
If the above is followed, any enhancement will be appriciated.
Since I am close, I will probably make at least one more v3 drop as is
with the new lguest_bus inspired pvbus (with hotplug, etc). From there,
we can (virtually) get together and
On Wed, 2007-08-15 at 00:13 -0400, Gregory Haskins wrote:
On Wed, 2007-08-15 at 06:58 +0300, Avi Kivity wrote:
since it wants to be hypervisor agnostic, it cannot specify an ABI (as
some already have ABIs, for example Xen).
I see, and that is a good point. By only being an API, virtio
On Wed, 2007-08-15 at 15:52 +0200, Farkas Levente wrote:
Gregory Haskins wrote:
On thing that is interesting about this (to me) is that, in a way it
kind of is a poor mans swap for the guests memory on the host. E.g.
you could give your guests a really small amount of physical ram (say
On Wed, 2007-08-15 at 15:37 -0700, Dor Laor wrote:
If you'll be quick enough you can rip the lguest_bus into a very light
weight
virtio_bus. Please keep it thin as possible, Rusty's code is 217 lines
long, half
of it comments. I'm planing to have a flexible use of this bus while one
can
On Tue, 2007-08-14 at 12:43 +0530, Amit Shah wrote:
On Tuesday 14 August 2007 09:37:45 Gregory Haskins wrote:
There are several things about this patch which aren't nice:
- It implicitly does a kmap_atomic. That's a bad thing for procedures that
might sleep after calling this
- It's prone
On Tue, 2007-08-14 at 00:44 -0700, Dor Laor wrote:
Can you provide performance figures? What’s the tcp/udp between guest host?
None yet :( Its pretty much pseudo code that compiles at this
point. ;) I still have to work out several issues before I can even
begin testing. Interrupt management
On Tue, 2007-08-14 at 01:01 -0700, Dor Laor wrote:
Why not use the standard naming for guest/host or front/backend?
I was trying to stress that this isn't virtualization specific. For
instance, you could use an IOQ on something like an AMP or RDMA based
system too. However, that being said I
On Tue, 2007-08-14 at 07:44 -0400, Gregory Haskins wrote:
On Tue, 2007-08-14 at 01:01 -0700, Dor Laor wrote:
Instead of the above code I would call to iter_seek and do everything inside
then return a proper error code if needed.
Im not sure I fully understand your point. But if I do get
On Tue, 2007-08-14 at 15:50 +0300, Avi Kivity wrote:
Farkas Levente wrote:
hi,
i try to setup a centos host server with kvm and a few guest os for the
first time. imho there is only a very limited docs about kvm (even if i
try to read them:-). so there are a few general questions:
-
This series incorporates all of v1 plus the following changes based on
feedback to date:
*) s/ioq_iter/ioq_iter_init
*) removed unecessary desc-offset
*) utilized create_irq() to actually assign interrupt resource
*) removed inadvertant cleanup of whitespace from series
*) added memory
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
arch/x86_64/kernel/io_apic.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index d8bfe31..6bf8794 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch
if the
entire core is not operating with PVOPS. Therefore, we introduce a separate
interface to deal with the devices.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
include/linux/pvbus.h | 43 +++
kernel/Makefile |2 +-
kernel/pvbus.c
IOQ is a shared-memory-queue interface for implmenting PV driver
communication.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig|5 +
drivers/kvm/Makefile |3
drivers/kvm/ioq.h | 12 +-
drivers/kvm/ioq_host.c | 365
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/net/Kconfig|4
drivers/net/Makefile |2
drivers/net/ioqnet.c | 631
include/linux/ioqnet.h | 42 +++
4 files changed, 679 insertions(+), 0 deletions(-)
diff --git
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h |1 +
drivers/kvm/mmu.c | 12
2 files changed, 13 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 9934f11..05d5be1 100755
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig | 27 +-
drivers/kvm/Makefile |3 -
drivers/kvm/ioq.h | 39 +
drivers/kvm/ioq_guest.c | 192 +
drivers/kvm/pvbus.h | 41
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig |5
drivers/kvm/Makefile |2
drivers/kvm/ioqnet_host.c | 566 +
3 files changed, 573 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/Kconfig b
On Wed, 2007-08-15 at 05:50 +0300, Avi Kivity wrote:
Gregory Haskins wrote:
This series incorporates all of v1 plus the following changes based on
feedback to date:
Are you positioning this as an alternative to virtio?
Absolutely not! I really just want to see a decent PV-IO
On Mon, 2007-08-13 at 11:50 +0300, Avi Kivity wrote:
This patch keep track of the pending irqs and inject them back to guest
eventually
even the guest may be descheduled. This is also what we did in Xen.
BTW, This policy will also be applied to future kernel PIT, I just do it
step by
IOQ is a shared-memory-queue interface for implmenting PV driver
communication.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig|5 +
drivers/kvm/Makefile |3
drivers/kvm/ioq.h | 12 +-
drivers/kvm/ioq_host.c | 365
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig | 27 +-
drivers/kvm/Makefile |3 -
drivers/kvm/ioq.h | 39 +
drivers/kvm/ioq_guest.c | 190 +
drivers/kvm/pvbus.h | 41
This patch series represents the state of my current work w.r.t. PV and KVM.
It is still a work in progress and so far has only been compile tested (though
earlier versions had a test harness that ironed many bugs out). I submit it
now as an RFC on the directions I am taking and to solicit
PVBUS allows VMM agnostic PV drivers to discover/configure virtual resources
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/Kconfig | 10 +
drivers/kvm/Makefile |3
drivers/kvm/kvm.h|4
drivers/kvm/kvm_main.c |4
drivers/kvm/pvbus_host.c
if the
entire core is not operating with PVOPS. Therefore, we introduce a separate
interface to deal with the devices.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
include/linux/pvbus.h | 43 +++
kernel/Makefile |2 +-
kernel/pvbus.c
IOQ is a generic shared-memory-queue mechanism that happens to be friendly
to virtualization boundaries. Note that it is not virtualization specific
due to its flexible transport layer.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
include/linux/ioq.h | 178
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h |1 +
drivers/kvm/mmu.c | 12
2 files changed, 13 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 9934f11..05d5be1 100755
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm
On Fri, 2007-08-10 at 19:59 +0300, Avi Kivity wrote:
Note that passing a virtual address is highly discouraged as its meaning
can change from vcpu to vcpu, it might not be mapped, translation is
slow, etc. Just let the guest do the translation.
Yeah, Hollis and Anthony straighted me out
On Fri, 2007-08-10 at 09:32 -0500, Anthony Liguori wrote:
Gregory Haskins wrote:
Hi All,
I am working on some PV stuff and had some questions about the ability
to share memory across the Guest/Host boundary.
It seems that most examples of how to do this always involve starting
Hi All,
I am working on some PV stuff and had some questions about the ability
to share memory across the Guest/Host boundary.
It seems that most examples of how to do this always involve starting
with a *page, converting it to a gfn via page_to_gfn(), and using that
as a gpa to pass across the
On Wed, 2007-08-01 at 09:56 +0300, Avi Kivity wrote:
Gregory Haskins wrote:
Hi Team,
I don't know if anyone here also subscribes to linux-rt-users, but it
seems as though Ingo et. al. rejected my modifications which ran the
smp_call() in a thread (VFCIPI).
It's not surprising. 650
On Tue, 2007-07-31 at 17:18 +0800, Dong, Eddie wrote:
I may miss something, why does that matter?
As it turns out, it doesn't ;) So we have dropped the patch. But not
for the reason you are suggesting.
__vcpu_clear will eventually
get executed though it is a little bit delayed. vmclear
Hi Team,
I don't know if anyone here also subscribes to linux-rt-users, but it
seems as though Ingo et. al. rejected my modifications which ran the
smp_call() in a thread (VFCIPI). So FYI: KVM is still broken on RT and
needs to be addressed.
In a nutshell, kvm_lock cannot be used as it us
. It also allows
code that was written to expect spin_locks to work properly, even though
they may have converted to rt_mutex under the hood. In summary, this
subsystem does for FCIPI interrupts what PREEMPT_HARDIRQs does for normal
interrupts.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED
On Fri, 2007-07-27 at 16:53 +1000, Rusty Russell wrote:
On Thu, 2007-07-26 at 14:45 -0400, Gregory Haskins wrote:
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
OK, in anticipation that you would do it, I've done a trivial
s/svm()/to-svm()/ and s/vmx()/to_vmx()/ patch and put my patch
On Fri, 2007-07-27 at 07:58 +0300, Avi Kivity wrote:
Gregory Haskins wrote:
We need to provide locking around the current_vmcs/VMCS interactions to
protect against race conditions.
We agreed the race was benign? Do you no longer think so?
No, I agree (see 0/3 note). I was just
On Fri, 2007-07-27 at 07:56 +0300, Avi Kivity wrote:
Gregory Haskins wrote:
Hi guys,
While working with the -rt kernel, I have noticed a problem in KVM.
Specifically, when you stop a VM you sometimes get a sleep while
atomic oopses. It turns out that the issue is related
(Note the last v3 I sent out was a duplicate v3...it should have been v4)
This series includes the following changes from v4(v3)
Patch #1: I have folded Rusty's cleanup in (thanks Rusty!)
Patch #2: Rebased on Rusty's changes
Patch #3: Dropped
Signed-off-by: Gregory Haskins [EMAIL PROTECTED
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h | 31
drivers/kvm/kvm_main.c | 26 +--
drivers/kvm/kvm_svm.h |3
drivers/kvm/svm.c | 394
drivers/kvm/vmx.c | 249
On Fri, 2007-07-27 at 17:09 -0700, Nakajima, Jun wrote:
Gregory Haskins wrote:
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/vmx.c | 71
+++-- 1 files
changed, 58
insertions(+), 13 deletions(-)
diff --git
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/vmx.c | 70 +++--
1 files changed, 57 insertions(+), 13 deletions(-)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 5f0a7fd..d6354ca 100644
--- a/drivers/kvm/vmx.c
+++ b
and
linux.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
-
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems? Stop.
Now Search log events and configuration files using AJAX
On Thu, 2007-07-26 at 15:33 +0300, Avi Kivity wrote:
The suggestion I liked best (Anthony's) was
struct vmx_vcpu {
struct kvm_vcpu vcpu;
void *vmcs;
// other vmx-specific data
};
to move from a kvm_vcpu to a vmx_vcpu, you use container_of() (inside
your
On Fri, 2007-07-27 at 09:27 +1000, Rusty Russell wrote:
So the in-kernel apic code has to traverse every element in the array?
That is clearly better because?
I can't speak for Eddie's implementation, but the one that I had worked
on did in fact take advantage of the array. Not for
We need to provide locking around the current_vmcs/VMCS interactions to
protect against race conditions.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/vmx.c | 25 +++--
1 files changed, 19 insertions(+), 6 deletions(-)
diff --git a/drivers/kvm/vmx.c b
On Thu, 2007-07-26 at 19:31 +0300, Avi Kivity wrote:
Avi Kivity wrote:
Sure. It can happen with two VMs are running simultaneously. Lets call
them VM-a and VM-b. Assume the scenario: VM-a is on CPU-x, gets
migrated to CPU-y, and VM-b gets scheduled in on CPU-x. There is a race
on
On Thu, 2007-07-26 at 10:04 -0500, Anthony Liguori wrote:
Gregory Haskins wrote:
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h | 31 -
drivers/kvm/kvm_main.c | 26 +---
drivers/kvm/kvm_svm.h |3
drivers/kvm/svm.c | 322
(v2)
Incorporates all feedback except for the arch-pointer stuff which is still
being discussed.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h | 31 -
drivers/kvm/kvm_main.c | 26 +---
drivers/kvm/kvm_svm.h |3
drivers/kvm/svm.c | 322
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h | 31 -
drivers/kvm/kvm_main.c | 26 +---
drivers/kvm/kvm_svm.h |3
drivers/kvm/svm.c | 322 +---
drivers/kvm/vmx.c | 236
On Thu, 2007-07-26 at 16:37 +0300, Avi Kivity wrote:
Gregory Haskins wrote:
On Thu, 2007-07-26 at 15:33 +0300, Avi Kivity wrote:
The suggestion I liked best (Anthony's) was
struct vmx_vcpu {
struct kvm_vcpu vcpu;
void *vmcs;
// other vmx-specific
On Thu, 2007-07-26 at 18:35 +0300, Avi Kivity wrote:
A race indeed, good catch.
I think the race is only on the per_cpu(current_vmcs) variable, no? The
actual vmcs ptr (as loaded by vmptrld) is handled by the processor.
Correct.
Disabling interrupts was chosen as the sync-primitive,
We need to provide locking around the current_vmcs/VMCS interactions to
protect against race conditions.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/vmx.c | 77 -
1 files changed, 64 insertions(+), 13 deletions(-)
diff
This is a cleanup patch to de-VMX the general code. It was developed in the
preempt-hooks branch, but it should apply elsewhere as well.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h | 33 +
drivers/kvm/kvm_main.c | 12 +-
drivers/kvm/kvm_svm.h |3
is not held.
Signed-off-by: Gregory Haskins [EMAIL PROTECTED]
---
drivers/kvm/kvm.h |1 +
drivers/kvm/kvm_main.c |3 +++
2 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 03f374e..d18537c 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers
On Tue, 2007-07-24 at 22:02 +, Chris Clayton wrote:
I've been doing some more digging around here and thought I'd report my
findings. I've found that under kvm 31 and 33, qemu-system-x86_64 always
fails with a seg fault when the (__thread) variable vcpu_env (declared at
line 33 of
On Wed, 2007-07-25 at 06:20 +0300, Avi Kivity wrote:
I'd rather wait for the real fix, especially as this is an experimental
branch. Can you provide details of the issue?
Sure. Keep in mind I am working with the RT kernel, so things might be
tighter and/or different than the vanilla
On Wed, 2007-07-25 at 07:13 +0300, Avi Kivity wrote:
Preemption disabled yes, but interrupts?
How do you think I found this? ;)
From smp_call_function_single in -rt:
WARN_ON(irqs_disabled());
IIRC I picked the place where
sched_in is called to have interrupts enabled, but maybe -rt
Hi Rusty,
I was curious if there are any implementations of your virtio
substrate for KVM yet? And if not, I can offer help to get this done as
I have an immediate need for a ring-buffer like PV channel.
Regards,
-Greg
-
On Tue, 2007-07-17 at 23:16 +1000, Rusty Russell wrote:
I have shied away from touching x86_emulate.c (it could definitely use
some love, but it is forked from the Xen code, and it would be more
productive to cross-merge fixes).
On this topic, here's an idea I have been kicking around for a
On Tue, 2007-07-17 at 06:31 -0700, Dor Laor wrote:
You're welcome to rip my ring code ;)
Point me at the code, if you would. I would be happy to use it as a
base. :)
-
This SF.net email is sponsored by DB2 Express
On Sun, 2007-07-15 at 10:39 +0300, Avi Kivity wrote:
When applied to current HEAD, this doesn't work. Booting windows or
Linux, quite soon during boot everything freezes.
Crap. Not sure whats happening as I definitely tested that during
development. Ill have to take a look.
-Greg
Is there a way I can see a list of commits that are related only to KVM
since 2.6.22 without seeing all the stuff from upstream?
-Greg
-
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE
On Fri, 2007-07-13 at 16:41 +0300, Avi Kivity wrote:
I tested FC6 i386 about found no difference with or without the patch.
Dave, can you diff the guest dmesg with kvm-27 and kvm-28 userspace?
Maybe that will tell us something.
I can say this: It would seem that the IDE enable bits
On Fri, 2007-07-13 at 16:46 +0200, Luca wrote:
On 7/13/07, Gregory Haskins [EMAIL PROTECTED] wrote:
Just to clarify: you are suggesting that the old IDE driver used to
see that the controller was disabled and reprogrammed it by itself
(fast mode); now it sees it's enabled and leaves whatever
1 - 100 of 354 matches
Mail list logo