On 17/12/12 16:00, Alexander Graf wrote:
On 14.12.2012, at 17:02, Cornelia Huck wrote:
Hi,
here's the virtio-ccw guest support for kvm/next again.
The not-kvm specific patches have made their way upstream via the
s390 tree in the meantime. Patch 2 fixes an inconsistency there.
Patch 3
Il 04/09/2012 17:13, Cornelia Huck ha scritto:
+VirtioCcwBus *virtio_ccw_bus_init(void)
+{
+VirtioCcwBus *cbus;
+BusState *bus;
+DeviceState *dev;
+
+/* Create bridge device */
+dev = qdev_create(NULL, virtio-ccw-bridge);
+qdev_init_nofail(dev);
+
+/* Create
On Sun, Dec 16, 2012 at 01:26:41PM +, Zhang, Yang Z wrote:
Gleb Natapov wrote on 2012-12-13:
On Thu, Dec 13, 2012 at 08:19:01AM +, Zhang, Yang Z wrote:
Gleb Natapov wrote on 2012-12-13:
On Thu, Dec 13, 2012 at 08:03:06AM +, Zhang, Yang Z wrote:
Gleb Natapov wrote on
On Sat, Dec 15, 2012 at 06:34:37AM -0500, Nickolai Zeldovich wrote:
The kvm i8254 emulation for counter 0 (but not for counters 1 and 2)
has at least two bugs in mode 0:
1. The OUT bit, computed by pit_get_out(), is never set high.
2. The counter value, computed by pit_get_count(), wraps
On Thu, Dec 13, 2012 at 01:40:37PM +0100, Paolo Bonzini wrote:
This patch adds three scenarios to the vmexit test. Two are very simple
PIO cases that are handled in the kernel (reading from and writing
to ELCR). The other is an unmapped PIO that is handled in userspace.
The difference
The include/uapi/asm/kvm_para.h includes
include/uapi/asm/epapr_hcalls.h but the correct reference
should be include/asm/epapr_hcalls.h as this is the place
where make install_header installs the header files for
userspace.
Signed-off-by: Bharat Bhushan bharat.bhus...@freescale.com
---
On 18.12.2012, at 12:21, Bharat Bhushan wrote:
The include/uapi/asm/kvm_para.h includes
include/uapi/asm/epapr_hcalls.h but the correct reference
should be include/asm/epapr_hcalls.h as this is the place
where make install_header installs the header files for
userspace.
Signed-off-by:
This patch adds queue steering to virtio-scsi. When a target is sent
multiple requests, we always drive them to the same queue so that FIFO
processing order is kept. However, if a target was idle, we can choose
a queue arbitrarily. In this case the queue is chosen according to the
current VCPU,
Using the new virtio_scsi_add_sg function lets us simplify the queueing
path. In particular, all data protected by the tgt_lock is just gone
(multiqueue will find a new use for the lock).
The speedup is relatively small (2-4%) but it is worthwhile because of
the code simplification---both in
The virtqueue_add_buf function has two limitations:
1) it requires the caller to provide all the buffers in a single call;
2) it does not support chained scatterlists: the buffers must be
provided as an array of struct scatterlist;
Because of these limitations, virtio-scsi has to copy each
This will be needed soon in order to retrieve the per-target
struct.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
drivers/scsi/virtio_scsi.c | 17 +
1 files changed, 9 insertions(+), 8 deletions(-)
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
At the moment when vector is masked virtio will poll it
in userspace, even if it is handled by irqfd.
This is done in order to update pending bits, but
it's not really required until someone reads the pending bits.
On the other hand this read results in extra io thread wakeups.
As we only
At the moment, when irqfd is in use but a vector is masked,
qemu will poll it and handle vector masks in userspace.
Since almost no one ever looks at the pending bits,
it is better to defer this until pending bits
are actually read.
Implement this optimization using the new poll notifier.
For use by poll handler.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci/msix.c | 6 +++---
hw/pci/msix.h | 3 +++
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index 1f31975..9df0ffb 100644
--- a/hw/pci/msix.c
+++ b/hw/pci/msix.c
@@
Update all users.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci/msix.c | 13 -
hw/pci/msix.h | 3 ++-
hw/pci/pci.h| 4
hw/vfio_pci.c | 2 +-
hw/virtio-pci.c | 3 ++-
5 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/hw/pci/msix.c
On Tue, Dec 18, 2012 at 02:20:20PM +0200, Michael S. Tsirkin wrote:
At the moment when vector is masked virtio will poll it
in userspace, even if it is handled by irqfd.
This is done in order to update pending bits, but
it's not really required until someone reads the pending bits.
On the
On Fri, Dec 14, 2012 at 05:02:15PM +0100, Cornelia Huck wrote:
Hi,
here's the virtio-ccw guest support for kvm/next again.
The not-kvm specific patches have made their way upstream via the
s390 tree in the meantime. Patch 2 fixes an inconsistency there.
Patch 3 lost the now unneeded
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull.
Changes include:
- important header fix for UAPI
- Book3S: PR: Enable fake sc 1 instruction for KVM on top of pHyp
Alex
The following changes since commit e11ae1a102b46f76441e328a2743ae5d6e201423:
Gleb Natapov
When running on top of pHyp, the hypercall instruction sc 1 goes
straight into pHyp without trapping in supervisor mode.
So if we want to support PAPR guest in this configuration we need to
add a second way of accessing PAPR hypercalls, preferably with the
exact same semantics except for the
virtio_scsi_target_state is now empty, but we will find new uses
for it in the next few patches. However, dropping the sglist lets
us turn the array-of-pointers into a simple array, which simplifies
the allocation.
However, we do not leave the virtio_scsi_target_state structs in the
flexible
From: Bharat Bhushan r65...@freescale.com
The include/uapi/asm/kvm_para.h includes
include/uapi/asm/epapr_hcalls.h but the correct reference
should be include/asm/epapr_hcalls.h as this is the place
where make install_header installs the header files for
userspace.
Signed-off-by: Bharat Bhushan
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants a BUG(), because it can be guest triggered.
So instead, let's only WARN() the user that this happened.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/kvm/powerpc.c |3 ++-
1
From: Mihai Caraman mihai.cara...@freescale.com
Reflect the uapi folder change in SREGS API documentation.
Signed-off-by: Mihai Caraman mihai.cara...@freescale.com
Reviewed-by: Amos Kong kongjian...@gmail.com
Signed-off-by: Alexander Graf ag...@suse.de
---
Documentation/virtual/kvm/api.txt |
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 the same queue (so that commands are not reordered); queue switching
Some comments without arguing about whether the performance
benefit is worth it.
On Tue, Dec 18, 2012 at 01:32:48PM +0100, Paolo Bonzini wrote:
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index cf8adb1..39d56c4 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
On Tue, Dec 18, 2012 at 01:32:49PM +0100, Paolo Bonzini wrote:
Using the new virtio_scsi_add_sg function lets us simplify the queueing
path. In particular, all data protected by the tgt_lock is just gone
(multiqueue will find a new use for the lock).
vq access still needs some protection:
Il 18/12/2012 14:37, Michael S. Tsirkin ha scritto:
On Tue, Dec 18, 2012 at 01:32:49PM +0100, Paolo Bonzini wrote:
Using the new virtio_scsi_add_sg function lets us simplify the queueing
path. In particular, all data protected by the tgt_lock is just gone
(multiqueue will find a new use for
On Tue, Dec 18, 2012 at 01:32:47PM +0100, 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 the
This series goes on top of my previous one: Fix
emulate_invalid_guest_state=0 part 2. It does not only fixes bugs,
but also does a nice cleanup of VMX real mode emulation. All real mode
segment register mangling is now contained in fix_rmode_seg() function.
Gleb Natapov (5):
KVM: emulator:
According to Intel SDM Vol3 Section 5.5 Privilege Levels and 5.6
Privilege Level Checking When Accessing Data Segments RPL checking is
done during loading of a segment selector, not during data access. We
already do checking during segment selector loading, so drop the check
during data access.
Currently when emulation of invalid guest state is enable
(emulate_invalid_guest_state=1) segment registers are still fixed for
entry to vm86 mode some times. Segment register fixing is avoided in
enter_rmode(), but vmx_set_segment() still does it unconditionally.
The patch fixes it.
Currently it allows entering vm86 mode if segment limit is greater than
0x and db bit is set. Both of those can cause incorrect execution of
instruction by cpu since in vm86 mode limit will be set to 0x and db
will be forced to 0.
Signed-off-by: Gleb Natapov g...@redhat.com
---
Il 18/12/2012 14:36, Michael S. Tsirkin ha scritto:
Some comments without arguing about whether the performance
benefit is worth it.
On Tue, Dec 18, 2012 at 01:32:48PM +0100, Paolo Bonzini wrote:
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index cf8adb1..39d56c4 100644
---
On Tue, Dec 18, 2012 at 01:32:52PM +0100, Paolo Bonzini wrote:
This patch adds queue steering to virtio-scsi. When a target is sent
multiple requests, we always drive them to the same queue so that FIFO
processing order is kept. However, if a target was idle, we can choose
a queue
On Tue, Dec 18, 2012 at 02:43:51PM +0100, Paolo Bonzini wrote:
Il 18/12/2012 14:36, Michael S. Tsirkin ha scritto:
Some comments without arguing about whether the performance
benefit is worth it.
On Tue, Dec 18, 2012 at 01:32:48PM +0100, Paolo Bonzini wrote:
diff --git
Il 18/12/2012 14:57, Michael S. Tsirkin ha scritto:
-static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
+static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
+ struct virtio_scsi_target_state *tgt,
+
Juan Quintela quint...@redhat.com writes:
Hi
Please send in any agenda topics that you have.
I have a conflicting call today so I can't attend.
Regards,
Anthony Liguori
Thanks, Juan.
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to
Juan Quintela quint...@redhat.com wrote:
Hi
Please send in any agenda topics that you have.
As there are no topics, call is cancelled.
Later, Juan.
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at
Il 18/12/2012 14:59, Michael S. Tsirkin ha scritto:
Can't we track state internally to the virtqueue? Exposing it
seems to buy us nothing since you can't call add_buf between
start and end anyway.
I wanted to keep the state for these functions separate from the
rest. I don't think it makes
Hi Alex,
Thank you for helping me debug this issue. Some additional repros showed
that sometimes HW reports only PCI_CAP_ID_SLOTID and PCI_CAP_ID_EXP, and
sometimes it does not report any capability at all. At this point, I am
unable to install all the required components for reproduction on
On Tue, 18 Dec 2012 09:45:27 +0100
Paolo Bonzini pbonz...@redhat.com wrote:
Il 04/09/2012 17:13, Cornelia Huck ha scritto:
+VirtioCcwBus *virtio_ccw_bus_init(void)
+{
+VirtioCcwBus *cbus;
+BusState *bus;
+DeviceState *dev;
+
+/* Create bridge device */
+dev =
On Tue, Dec 18, 2012 at 03:08:08PM +0100, Paolo Bonzini wrote:
Il 18/12/2012 14:57, Michael S. Tsirkin ha scritto:
-static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd
*sc)
+static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
+ struct
Il 18/12/2012 15:58, Cornelia Huck ha scritto:
On Tue, 18 Dec 2012 09:45:27 +0100
Paolo Bonzini pbonz...@redhat.com wrote:
Il 04/09/2012 17:13, Cornelia Huck ha scritto:
+VirtioCcwBus *virtio_ccw_bus_init(void)
+{
+VirtioCcwBus *cbus;
+BusState *bus;
+DeviceState *dev;
+
+
On Tue, Dec 18, 2012 at 03:32:15PM +0100, Paolo Bonzini wrote:
Il 18/12/2012 14:59, Michael S. Tsirkin ha scritto:
Can't we track state internally to the virtqueue? Exposing it
seems to buy us nothing since you can't call add_buf between
start and end anyway.
I wanted to keep the state
Il 18/12/2012 16:03, Michael S. Tsirkin ha scritto:
On Tue, Dec 18, 2012 at 03:08:08PM +0100, Paolo Bonzini wrote:
Il 18/12/2012 14:57, Michael S. Tsirkin ha scritto:
-static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd
*sc)
+static int virtscsi_queuecommand(struct
On Tue, Dec 18, 2012 at 01:38:39PM +0100, Alexander Graf wrote:
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull.
Is this for 3.8 or 3.9?
Changes include:
- important header fix for UAPI
- Book3S: PR: Enable fake sc 1 instruction for KVM on top of pHyp
On Tue, Dec 18, 2012 at 04:51:28PM +0100, Paolo Bonzini wrote:
Il 18/12/2012 16:03, Michael S. Tsirkin ha scritto:
On Tue, Dec 18, 2012 at 03:08:08PM +0100, Paolo Bonzini wrote:
Il 18/12/2012 14:57, Michael S. Tsirkin ha scritto:
-static int virtscsi_queuecommand(struct Scsi_Host *sh,
On 12/18/2012 04:20 PM, Gleb Natapov wrote:
On Tue, Dec 18, 2012 at 01:38:39PM +0100, Alexander Graf wrote:
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull.
Is this for 3.8 or 3.9?
This is for 3.9, except for the UAPI one. That one should go into 3.8
and stable.
Hi.
I'm experiencing weird network problems on a KVM installation.
OS is Ubuntu 12.04, qemu 1.0+noroms-0ubuntu14.3, kernel 3.2.0-34-generic.
eth0 is attached to LAN - br0
eth2 is attached to WAN - br1
Debian config follows:
auto eth0
iface eth0 inet manual
auto br0
iface br0 inet static
On Tue, Dec 18, 2012 at 08:53:42AM +0100, Andreas Färber wrote:
Since the model list is highly macrofied, keep ppc_def_t for now and
save a pointer to it in PowerPCCPUClass. This results in a flat list of
subclasses including aliases, to be refined later.
Move cpu_ppc_init() to
Hello,
I have a iSCSI storage array connected to 4 physical hosts. On these 4 hosts I
have configured 40 odd logical volumes with clvm. each logical volume is the
root volume for a VM.
How should I set up io scheduling with this configuration. Performance is not
so great and I have a feeling
On Tue, Dec 18, 2012 at 4:41 PM, Andrew Holway a.hol...@syseleven.de wrote:
How should I set up io scheduling with this configuration. Performance is not
so great and I have a feeling that all of the io schedulers in my VMs and the
ones on my host are not having a nice party together.
most
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an
error,
but it's nothing that warrants a BUG(), because it can be guest
triggered.
So instead, let's only WARN() the user that this happened.
Signed-off-by: Alexander Graf
On 18.12.2012, at 23:54, Scott Wood wrote:
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants a BUG(), because it can be guest triggered.
So instead, let's only WARN() the user that this
On 12/18/2012 05:01:19 PM, Alexander Graf wrote:
On 18.12.2012, at 23:54, Scott Wood wrote:
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an
error,
but it's nothing that warrants a BUG(), because it can be guest
On 19.12.2012, at 00:05, Scott Wood wrote:
On 12/18/2012 05:01:19 PM, Alexander Graf wrote:
On 18.12.2012, at 23:54, Scott Wood wrote:
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants
Am 16.12.2012 01:13, schrieb Andreas Färber:
Here's a rebased version of the series moving KVM-specific fields from
CPU*State struct (CPU_COMMON macro) to QOM CPUState and avoiding use of
CPU*State in KVM's API.
There was no review feedback on v1, which I'm interpreting as a don't-care.
If
Hello KVM,
I'm seeing something similar to this
(http://thread.gmane.org/gmane.comp.emulators.kvm.devel/100592) as well when
doing live migrations on Ubuntu 12.04 (Host and Guest) with a backported
libvirt 1.0 and qemu-kvm 1.2 (improved performance for live migrations on
guests with large
Am 18.12.2012 08:53, schrieb Andreas Färber:
+static gint ppc_cpu_compare_class_name(gconstpointer a, gconstpointer b)
+{
+ObjectClass *oc = (ObjectClass *)a;
+const char *name = b;
-return NULL;
+if (strncasecmp(name, object_class_get_name(oc), strlen(name)) == 0
+
Hello,
I have a problem when I used perf in Guest, the count of LLC-loads
almost always returns 0.
LLC-loads was a hardware cache event, besides the setting of general
PMU MSR, need to set MSR_OFFCORE_RSP_0 as well, in perf, it would be
the extra_reg and extra_config in hw_perf_event. I add some
Hi, All,
Currently when using kvm from qemu-kvm-1.1.0, I found sometimes after
doing the restart within the guest OS(winxp), the guest machine becomes
extremely slow and the computer info shows the CPU is 'QEMU virtual CPU'
and its frequency is rather low(nearly 350M Hz and changed after each
[I forgot to do TO to Ingo last time]
Ingo,
Could you please take this into x86 tree.
This is
Acked-by: Andrew Jones drjo...@redhat.com
Tested-by: Chegu Vinod chegu_vi...@hp.com
Marcelo, do you want to add your Acked-by/Reviewed-by?
On 12/14/2012 09:10 PM, Raghavendra K T wrote:
Hi Ingo,
The include/uapi/asm/kvm_para.h includes
include/uapi/asm/epapr_hcalls.h but the correct reference
should be include/asm/epapr_hcalls.h as this is the place
where make install_header installs the header files for
userspace.
Signed-off-by: Bharat Bhushan bharat.bhus...@freescale.com
---
On 18.12.2012, at 12:21, Bharat Bhushan wrote:
The include/uapi/asm/kvm_para.h includes
include/uapi/asm/epapr_hcalls.h but the correct reference
should be include/asm/epapr_hcalls.h as this is the place
where make install_header installs the header files for
userspace.
Signed-off-by:
When running on top of pHyp, the hypercall instruction sc 1 goes
straight into pHyp without trapping in supervisor mode.
So if we want to support PAPR guest in this configuration we need to
add a second way of accessing PAPR hypercalls, preferably with the
exact same semantics except for the
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull.
Changes include:
- important header fix for UAPI
- Book3S: PR: Enable fake sc 1 instruction for KVM on top of pHyp
Alex
The following changes since commit e11ae1a102b46f76441e328a2743ae5d6e201423:
Gleb Natapov
From: Bharat Bhushan r65...@freescale.com
The include/uapi/asm/kvm_para.h includes
include/uapi/asm/epapr_hcalls.h but the correct reference
should be include/asm/epapr_hcalls.h as this is the place
where make install_header installs the header files for
userspace.
Signed-off-by: Bharat Bhushan
From: Mihai Caraman mihai.cara...@freescale.com
Reflect the uapi folder change in SREGS API documentation.
Signed-off-by: Mihai Caraman mihai.cara...@freescale.com
Reviewed-by: Amos Kong kongjian...@gmail.com
Signed-off-by: Alexander Graf ag...@suse.de
---
Documentation/virtual/kvm/api.txt |
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants a BUG(), because it can be guest triggered.
So instead, let's only WARN() the user that this happened.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/kvm/powerpc.c |3 ++-
1
On Tue, Dec 18, 2012 at 01:38:39PM +0100, Alexander Graf wrote:
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull.
Is this for 3.8 or 3.9?
Changes include:
- important header fix for UAPI
- Book3S: PR: Enable fake sc 1 instruction for KVM on top of pHyp
On 12/18/2012 04:20 PM, Gleb Natapov wrote:
On Tue, Dec 18, 2012 at 01:38:39PM +0100, Alexander Graf wrote:
Hi Marcelo / Gleb,
This is my current patch queue for ppc. Please pull.
Is this for 3.8 or 3.9?
This is for 3.9, except for the UAPI one. That one should go into 3.8
and stable.
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an
error,
but it's nothing that warrants a BUG(), because it can be guest
triggered.
So instead, let's only WARN() the user that this happened.
Signed-off-by: Alexander Graf
On 18.12.2012, at 23:54, Scott Wood wrote:
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants a BUG(), because it can be guest triggered.
So instead, let's only WARN() the user that this
On 12/18/2012 05:01:19 PM, Alexander Graf wrote:
On 18.12.2012, at 23:54, Scott Wood wrote:
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an
error,
but it's nothing that warrants a BUG(), because it can be guest
On 19.12.2012, at 00:05, Scott Wood wrote:
On 12/18/2012 05:01:19 PM, Alexander Graf wrote:
On 18.12.2012, at 23:54, Scott Wood wrote:
On 12/18/2012 06:38:41 AM, Alexander Graf wrote:
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants
75 matches
Mail list logo