On 05/10/2012 11:15 AM, Nikunj A Dadhania wrote:
I am running a 3.4.0-rc4 based kernel(commit: af3a3ab2), guest config
attached.
During my tests, I saw few softlockups inside the guests while running
kernbench inside the guest. I can reproduce this repeatedly.
Test Setup:
- Create 4 VMs
On 05/09/2012 11:12 PM, Michael S. Tsirkin wrote:
On Wed, May 09, 2012 at 01:10:04PM -0700, H. Peter Anvin wrote:
On 05/09/2012 01:07 PM, Michael S. Tsirkin wrote:
In practice ATM any of the above will work. We probably don't even need
to add barrier() calls since what we do
When handling the H_BULK_REMOVE hypercall, we were forgetting to
invalidate and unlock the hashed page table entry (HPTE) in the case
where the page had been paged out. This fixes it by clearing the
first doubleword of the HPTE in that case.
This fixes a regression introduced in commit
Hi,
I'm looking to implement a san storage with ssd drive.
which block device type support trim or scsi unmap ?
I think ide support it (but performance...)
scsi ?
virtio ?
virtio-scsi ?
Regards,
Alexandre Derumier
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body
On Thu, May 10, 2012 at 8:19 PM, Alexandre DERUMIER aderum...@odiso.com wrote:
Hi,
I'm looking to implement a san storage with ssd drive.
which block device type support trim or scsi unmap ?
I think ide support it (but performance...)
scsi ?
virtio ?
virtio-scsi ?
iscsi supports it too
https://bugzilla.kernel.org/show_bug.cgi?id=42980
--- Comment #6 from Avi Kivity a...@redhat.com 2012-05-10 10:53:48 ---
Created an attachment (id=73244)
-- (https://bugzilla.kernel.org/attachment.cgi?id=73244)
Fix
Please test the attached patch.
--
Configure bugmail:
Please pull from:
git://git.kernel.org/pub/scm/virt/kvm/qemu-kvm.git uq/master
to receive a fix for qemu 1.1, fixing dirty tracking with a large host
page size; only applicable to ppc.
David Gibson (1):
kvm: Fix dirty
On 05/10/2012 03:32 AM, Mao, Junjie wrote:
This patch handles PCID/INVPCID for guests.
Process-context identifiers (PCIDs) are a facility by which a logical
processor may cache information for multiple linear-address spaces so that
the processor may retain cached information when software
On 05/10/2012 03:32 AM, Mao, Junjie wrote:
This patch handles PCID/INVPCID for guests.
Process-context identifiers (PCIDs) are a facility by which a logical
processor may cache information for multiple linear-address spaces so that
the processor may retain cached information when software
iscsi supports it too but it requires that your iscsi target supports
these opcodes, and that the filesystem/storage behind it supports it
too.
TGTD with EXT4 and a suitable storage device should do the trick.
I'm using a iscsi solaris target, with scsi UNMAP support.
Drives also support
Currently when you mount a filesystem, you face two issues:
- you have to be root
- if the media is untrusted, it can exploit your kernel
With kvm and fuse, we can have a virtualized kernel mount the
filesystem, and re-export to the host, which mounts it using a fuse
interface. This solves both
On Thu, May 10, 2012 at 03:29:54PM +0300, Avi Kivity wrote:
Currently when you mount a filesystem, you face two issues:
- you have to be root
- if the media is untrusted, it can exploit your kernel
With kvm and fuse, we can have a virtualized kernel mount the
filesystem, and re-export to
On Thu, May 10, 2012 at 10:28 PM, Alexandre DERUMIER
aderum...@odiso.com wrote:
iscsi supports it too but it requires that your iscsi target supports
these opcodes, and that the filesystem/storage behind it supports it
too.
TGTD with EXT4 and a suitable storage device should do the trick.
I'm
On 10 May 2012 13:29, Avi Kivity a...@redhat.com wrote:
Currently when you mount a filesystem, you face two issues:
- you have to be root
- if the media is untrusted, it can exploit your kernel
With kvm and fuse, we can have a virtualized kernel mount the
filesystem, and re-export to the
On Wed, May 09, 2012 at 04:38:02PM -0300, Eduardo Habkost wrote:
On Wed, May 09, 2012 at 12:38:37PM +0300, Gleb Natapov wrote:
On Wed, May 09, 2012 at 11:05:58AM +0200, Alexander Graf wrote:
On 09.05.2012, at 10:51, Gleb Natapov wrote:
On Wed, May 09, 2012 at 10:42:26AM +0200,
On 05/10/2012 03:37 PM, Alex Bradbury wrote:
On 10 May 2012 13:29, Avi Kivity a...@redhat.com wrote:
Currently when you mount a filesystem, you face two issues:
- you have to be root
- if the media is untrusted, it can exploit your kernel
With kvm and fuse, we can have a virtualized
https://bugzilla.kernel.org/show_bug.cgi?id=42980
--- Comment #7 from Luke-Jr luke-jr+linuxb...@utopios.org 2012-05-10
13:17:17 ---
Is there anything I can do to reproduce the problem condition for the test? It
seems to only occur about once every 6 months normally.
--
Configure bugmail:
On 05/10/2012 03:35 PM, Richard W.M. Jones wrote:
On Thu, May 10, 2012 at 03:29:54PM +0300, Avi Kivity wrote:
Currently when you mount a filesystem, you face two issues:
- you have to be root
- if the media is untrusted, it can exploit your kernel
With kvm and fuse, we can have a
On 05/10/2012 02:53 PM, Gleb Natapov wrote:
On Wed, May 09, 2012 at 04:38:02PM -0300, Eduardo Habkost wrote:
On Wed, May 09, 2012 at 12:38:37PM +0300, Gleb Natapov wrote:
On Wed, May 09, 2012 at 11:05:58AM +0200, Alexander Graf wrote:
On 09.05.2012, at 10:51, Gleb Natapov wrote:
On Wed, May
https://bugzilla.kernel.org/show_bug.cgi?id=42980
--- Comment #8 from Avi Kivity a...@redhat.com 2012-05-10 13:30:36 ---
Try running
while :; do :; done
in the nested (L2) guest, and ping -f the L1 guest from the host.
--
Configure bugmail:
On Thu, May 10, 2012 at 03:21:41PM +0200, Alexander Graf wrote:
On 05/10/2012 02:53 PM, Gleb Natapov wrote:
On Wed, May 09, 2012 at 04:38:02PM -0300, Eduardo Habkost wrote:
On Wed, May 09, 2012 at 12:38:37PM +0300, Gleb Natapov wrote:
On Wed, May 09, 2012 at 11:05:58AM +0200, Alexander Graf
On 2012-05-10 09:29, Avi Kivity wrote:
Currently when you mount a filesystem, you face two issues:
- you have to be root
- if the media is untrusted, it can exploit your kernel
With kvm and fuse, we can have a virtualized kernel mount the
filesystem, and re-export to the host, which mounts
On Thu, May 10, 2012 at 04:39:45PM +0300, Gleb Natapov wrote:
On Thu, May 10, 2012 at 03:21:41PM +0200, Alexander Graf wrote:
On 05/10/2012 02:53 PM, Gleb Natapov wrote:
On Wed, May 09, 2012 at 04:38:02PM -0300, Eduardo Habkost wrote:
On Wed, May 09, 2012 at 12:38:37PM +0300, Gleb Natapov
From: Takuya Yoshikawa yoshikawa.tak...@oss.ntt.co.jp
lpage_info is created for each large level even when the memory slot is
not for RAM. This means that when we add one slot for a PCI device, we
end up allocating at least KVM_NR_PAGE_SIZES - 1 pages by vmalloc():
this problem will become
On Tue, May 08, 2012 at 11:39:38AM +0930, Rusty Russell wrote:
On Mon, 7 May 2012 08:30:21 +0300, Michael S. Tsirkin m...@redhat.com
wrote:
Hi Rusty, please also pick two fixes from for_linus tag on my tree
I think they should be sent to Linus for 3.4:
On Thu, 10 May 2012 15:39:04 +0530, Nikunj A Dadhania
nik...@linux.vnet.ibm.com wrote:
On Thu, 10 May 2012 12:22:00 +0300, Avi Kivity a...@redhat.com wrote:
On 05/10/2012 11:15 AM, Nikunj A Dadhania wrote:
I am running a 3.4.0-rc4 based kernel(commit: af3a3ab2), guest config
attached.
It does not work.
Without the patch KVM git experiences emulation error, with the patch
it just locks up.
Also I don't see why would they use movntps for framebuffer. The
graphics is up and running, only reboot hits this unimplemented
opcode.
Thanks
Michal
--
To unsubscribe from this list:
If I have a mix of 2M and 1G pages on the host, how will I be able to pass the
same to the guest?. Does KVM and Libvirtd allow multiple -mem-path options?.
Also, where in the source can I find more info about hugepage support in KVM?
Thanks and regards,
Sriram
--- On Wed, 5/9/12, Avi Kivity
On 05/09/2012 08:45 AM, Michael S. Tsirkin wrote:
diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt
index 27f2b21..b7e3b67 100644
--- a/Documentation/atomic_ops.txt
+++ b/Documentation/atomic_ops.txt
@@ -520,6 +520,25 @@ The __clear_bit_unlock version is non-atomic,
On 04/27/2012 07:51 AM, Benjamin Herrenschmidt wrote:
More recent Power server chips (i.e. based on the 64 bit hash MMU)
support more than just the traditional 4k and 16M page sizes. This
can get quite complicated, because which page sizes are supported,
which combinations are supported within
On 05/10/2012 08:49 PM, Alexander Graf wrote:
+#if defined(TARGET_PPC64)
+if (def-sps)
+memcpy(env-sps, def-sps, sizeof(*def-sps));
I never know if *def-... would dereference def or the complete
construct.
'man operator'
How about sizeof(env-sps)?
How about
env-sps =
On 04/27/2012 07:51 AM, Benjamin Herrenschmidt wrote:
The core tcg/kvm code for ppc64 now has at least the outline
capability to support pagesizes beyond the standard 4k and 16MB. The
CPUState is initialized with information advertising the available
pagesizes and their correct encodings, and
On Wed, 9 May 2012, Michael S. Tsirkin wrote:
kvm needs to update some hypervisor variables atomically
in a sense that the operation can't be interrupted
in the middle. However the hypervisor always runs
on the same CPU so it does not need any memory
barrier or lock prefix.
Add _local
FYI (mea culpa for semi-spamming): On early June LinuxCon Japan will
host a virtualization track w/ some known faces and a parallel oVirt
developer workshop in Japan.
More details:
https://events.linuxfoundation.org/events/linuxcon-japan/schedule
Regards,
Dor
Original Message
Guess it depends on how recent kernel your guest runs.
If you present it as a SCSI disk to the guest, then I have
successfully had Linux Mint 12 guests do UNMAP when accessing /dev/sd*
from within the guest.
Ok, thanks for the info, i'll try it !
- Mail original -
De: ronnie
Instead of the bitmap size, store the maximum of GSIs the kernel
support. Move the GSI limit assertion to the API function
kvm_irqchip_add_route and make it stricter.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
kvm-all.c |8
1 files changed, 4 insertions(+), 4 deletions(-)
Version 3 is mostly a rebase + the final consolidation over the direct
MSI inject mechanism that made it into kvm.git recently. I also
introduced an MSIMessage structure as it will be helpful for the
follow-up work on irqfd-driven MSI injection under KVM. And, finally,
this flips the default for
Will be used for generating and distributing MSI messages, both in
emulation mode and under KVM.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
hw/msi.h |5 +
qemu-common.h |1 +
2 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/hw/msi.h b/hw/msi.h
index
This patch basically adds kvm_irqchip_send_msi, a service for sending
arbitrary MSI messages to KVM's in-kernel irqchip models.
As the current KVI API requires us to establish a static route from a
pseudo GSI to the target MSI message and inject the MSI via toggling
that GSI, we need to play some
Catch writes to the MSI MMIO region in the KVM APIC and forward them to
the kernel. Provide the kernel support GSI routing, this allows to
enable MSI support also for in-kernel irqchip mode.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
hw/apic.c |1 +
hw/kvm/apic.c | 34
Corresponding kvm.git hash: f2569053e0
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
linux-headers/linux/kvm.h | 38 ++
1 files changed, 38 insertions(+), 0 deletions(-)
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index
If the kernel supports KVM_SIGNAL_MSI, we can avoid the route-based
MSI injection mechanism.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
kvm-all.c | 22 +++---
1 files changed, 19 insertions(+), 3 deletions(-)
diff --git a/kvm-all.c b/kvm-all.c
index e7ed510..4e8c8f7
As MSI is now fully supported by KVM (/wrt available features in
upstream), we can finally enable the in-kernel irqchip by default.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
kvm-all.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/kvm-all.c b/kvm-all.c
index
Push msi_supported enabling to the APIC implementations where we can
encapsulate the decision more cleanly, hiding the details from the
generic code.
CC: Stefano Stabellini stefano.stabell...@eu.citrix.com
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
---
hw/apic.c |2 ++
hw/pc.c
On Thu, 2012-05-10 at 20:55 +0300, Avi Kivity wrote:
On 05/10/2012 08:49 PM, Alexander Graf wrote:
+#if defined(TARGET_PPC64)
+if (def-sps)
+memcpy(env-sps, def-sps, sizeof(*def-sps));
I never know if *def-... would dereference def or the complete
construct.
'man
+for (count = 0; count PPC_PAGE_SIZES_MAX_SZ; count++) {
+if (sps-enc[count].page_shift == 0) {
+break;
+}
+}
+if ((p - prop)= (maxcells - 3 - count * 2))
Is this valid C? Can you substract one pointer from another
Replaced Ingo's address with kernel.org one,
On Thu, 03 May 2012 17:47:30 +0200
Peter Zijlstra pet...@infradead.org wrote:
On Thu, 2012-05-03 at 22:00 +0900, Takuya Yoshikawa wrote:
But as I could not see why spin_needbreak() was differently
implemented
depending on CONFIG_PREEMPT, I
On Wed, 2012-05-09 at 13:10 -0700, H. Peter Anvin wrote:
On 05/09/2012 01:07 PM, Michael S. Tsirkin wrote:
In practice ATM any of the above will work. We probably don't even need
to add barrier() calls since what we do afterwards is apic access which
has an optimization barrier anyway.
Andrew Theurer habanero at linux.vnet.ibm.com writes:
On 05/09/2012 08:46 AM, Avi Kivity wrote:
On 05/09/2012 04:05 PM, Chegu Vinod wrote:
Hello,
On an 8 socket Westmere host I am attempting to run a single guest and
characterize the virtualization overhead for a system intensive
On 05/10/2012 03:32 AM, Mao, Junjie wrote:
This patch handles PCID/INVPCID for guests.
Process-context identifiers (PCIDs) are a facility by which a logical
processor
may cache information for multiple linear-address spaces so that the processor
may retain cached information when
When handling the H_BULK_REMOVE hypercall, we were forgetting to
invalidate and unlock the hashed page table entry (HPTE) in the case
where the page had been paged out. This fixes it by clearing the
first doubleword of the HPTE in that case.
This fixes a regression introduced in commit
On 04/27/2012 07:51 AM, Benjamin Herrenschmidt wrote:
More recent Power server chips (i.e. based on the 64 bit hash MMU)
support more than just the traditional 4k and 16M page sizes. This
can get quite complicated, because which page sizes are supported,
which combinations are supported within
On 05/10/2012 08:49 PM, Alexander Graf wrote:
+#if defined(TARGET_PPC64)
+if (def-sps)
+memcpy(env-sps, def-sps, sizeof(*def-sps));
I never know if *def-... would dereference def or the complete
construct.
'man operator'
How about sizeof(env-sps)?
How about
env-sps =
On 04/27/2012 07:51 AM, Benjamin Herrenschmidt wrote:
The core tcg/kvm code for ppc64 now has at least the outline
capability to support pagesizes beyond the standard 4k and 16MB. The
CPUState is initialized with information advertising the available
pagesizes and their correct encodings, and
54 matches
Mail list logo