Add device info into list before do context mapping, because device info will
be used by iommu_enable_dev_iotlb function, in this function, pci_enable_ats
would not be called without this patch.
Signed-off-by: Xudong Hao xudong@intel.com
Signed-off-by: Xiantao Zhang xiantao.zh...@intel.com
On 12/19/2011 07:59 PM, Amit Shah wrote:
On (Mon) 19 Dec 2011 [14:59:36], Avi Kivity wrote:
On 12/19/2011 02:52 PM, Amit Shah wrote:
(snip)
S4 needs some treatment, though, as resume after s4 doesn't work with
kvmclock enabled. I didn't realise this series was only handling the
soft lockup
On 12/19/2011 07:50 PM, Marcelo Tosatti wrote:
Maybe it is good (not sure), need to look into schedstats and think of
cases that would break legitimate guest hangs. And it probably also
affects the position of clearing the flag on the guest side as its
currently done in Eric's
On 12/08/2011 07:31 AM, Sasha Levin wrote:
It sounds like Alex is considering KVM PPC's return value in this case (and
updating api.txt if appropriate) -- what say you on this patch? It actually
brings kvmtool's KVM_RUN return val check in line with QEMU's (also 0)
and
nothing PPC
On 12/15/2011 09:42 PM, Eric B Munson wrote:
Now that we have a flag that will tell the guest it was suspended, create an
interface for that communication using a KVM ioctl.
+4.64 KVMCLOCK_GUEST_PAUSED
+
+Capability: basic
+Architechtures: Any that implement pvclocks (currently x86 only)
On 12/15/2011 09:42 PM, Eric B Munson wrote:
+4.64 KVMCLOCK_GUEST_PAUSED
+
+Capability: basic
Capability: basic means that this ioctl is available on any Linux
version that has KVM (apart from 2.6.2[01], before the ABI was
stabilized). You need to define a new KVM_CAP, document it, and
On Thu, 2011-12-22 at 12:03 +0200, Avi Kivity wrote:
On 12/08/2011 07:31 AM, Sasha Levin wrote:
It sounds like Alex is considering KVM PPC's return value in this case
(and
updating api.txt if appropriate) -- what say you on this patch? It
actually
brings kvmtool's KVM_RUN
On 12/22/2011 12:18 PM, Sasha Levin wrote:
On Thu, 2011-12-22 at 12:03 +0200, Avi Kivity wrote:
On 12/08/2011 07:31 AM, Sasha Levin wrote:
It sounds like Alex is considering KVM PPC's return value in this case
(and
updating api.txt if appropriate) -- what say you on this
On Thu, 2011-12-22 at 12:21 +0200, Avi Kivity wrote:
On 12/22/2011 12:18 PM, Sasha Levin wrote:
On Thu, 2011-12-22 at 12:03 +0200, Avi Kivity wrote:
On 12/08/2011 07:31 AM, Sasha Levin wrote:
It sounds like Alex is considering KVM PPC's return value in this
case (and
From: Christian Borntraeger borntrae...@de.ibm.com
On some cpus the overhead for virtualization instructions is in the same
range as a system call. Having to call multiple ioctls to get set registers
will make userspace handled exits more expensive than necessary.
Lets provide two sections in
From: Christian Borntraeger borntrae...@de.ibm.com
The general purpose registers are often necessary to handle SIE exits.
Avoid additional ioctls by providing the guest registers in the r/w
section of the kvm_run structure.
Signed-off-by: Christian Borntraeger borntrae...@de.ibm.com
---
Avi, Marcelo,
currently userspace can access guest registers via several ioctls. Some
of these registers might be useful very often. Here the system call overhead
for ioctl can make an exit more expensive than necessary.
In a discussion with Alex Graf we concluded that it might be beneficial to
From: Christian Borntraeger borntrae...@de.ibm.com
The prefix register is a read-mostly value that is necessary to emulate
memory accesses in an architecture compliant-way. Avoid an additional
ioctl by providing the prefix content in the r/o section of kvm_run.
Signed-off-by: Christian
On Wed, Dec 21, 2011 at 1:00 AM, Minchan Kim minc...@kernel.org wrote:
+static void virtblk_add_buf_wait(struct virtio_blk *vblk,
+ struct virtblk_req *vbr, unsigned long out, unsigned long in)
+{
+ DEFINE_WAIT(wait);
+ bool retry, notify;
+
+ for (;;) {
+
On 12/22/2011 01:56 PM, Christian Borntraeger wrote:
From: Christian Borntraeger borntrae...@de.ibm.com
On some cpus the overhead for virtualization instructions is in the same
range as a system call. Having to call multiple ioctls to get set registers
will make userspace handled exits more
On 12/22/2011 01:56 PM, Christian Borntraeger wrote:
From: Christian Borntraeger borntrae...@de.ibm.com
The general purpose registers are often necessary to handle SIE exits.
Avoid additional ioctls by providing the guest registers in the r/w
section of the kvm_run structure.
This is only
On 12/22/2011 01:56 PM, Christian Borntraeger wrote:
Avi, Marcelo,
currently userspace can access guest registers via several ioctls. Some
of these registers might be useful very often. Here the system call overhead
for ioctl can make an exit more expensive than necessary.
In a discussion
On 22/12/11 13:34, Avi Kivity wrote:
The general purpose registers are often necessary to handle SIE exits.
Avoid additional ioctls by providing the guest registers in the r/w
section of the kvm_run structure.
This is only needed for S390_UCONTROL?
No for the standard path. It was more
On Thu, Dec 22, 2011 at 12:56:49PM +0100, Christian Borntraeger wrote:
From: Christian Borntraeger borntrae...@de.ibm.com
The general purpose registers are often necessary to handle SIE exits.
Avoid additional ioctls by providing the guest registers in the r/w
section of the kvm_run
On Mon, Dec 19, 2011 at 04:13:41PM +0200, Avi Kivity wrote:
@@ -871,7 +899,10 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice
*vdev)
hdev-vqs + i,
i);
}
-vhost_sync_dirty_bitmap(hdev, 0,
On 12/22/2011 02:41 PM, Heiko Carstens wrote:
Index: b/arch/s390/include/asm/kvm_host.h
===
Btw. you may want to set QUILT_NO_DIFF_INDEX to get rid of the
Index lines junk :)
Or just use git, when I switched some years ago I
On Mon, Dec 19, 2011 at 04:13:35PM +0200, Avi Kivity wrote:
+static void vhost_log_start(MemoryListener *listener,
+MemoryRegionSection *section)
+{
+/* FIXME: implement */
+}
+
+static void vhost_log_stop(MemoryListener *listener,
+
On 12/22/2011 02:48 PM, Michael S. Tsirkin wrote:
On Mon, Dec 19, 2011 at 04:13:41PM +0200, Avi Kivity wrote:
@@ -871,7 +899,10 @@ void vhost_dev_stop(struct vhost_dev *hdev,
VirtIODevice *vdev)
hdev-vqs + i,
i);
}
On 12/22/2011 02:50 PM, Michael S. Tsirkin wrote:
On Mon, Dec 19, 2011 at 04:13:35PM +0200, Avi Kivity wrote:
+static void vhost_log_start(MemoryListener *listener,
+MemoryRegionSection *section)
+{
+/* FIXME: implement */
+}
+
+static void
On 12/22/2011 02:49 PM, Christian Borntraeger wrote:
Interesting. Other archs emulate everything to do with registers in the
kernel, so this is not a fast path.
What workload does this benefit?
My main concern was the prefix register (this is a per cpu register that
defines the
On Thu, Dec 22, 2011 at 02:50:27PM +0200, Avi Kivity wrote:
On 12/22/2011 02:50 PM, Michael S. Tsirkin wrote:
On Mon, Dec 19, 2011 at 04:13:35PM +0200, Avi Kivity wrote:
+static void vhost_log_start(MemoryListener *listener,
+MemoryRegionSection *section)
+{
On Wed, Dec 21, 2011 at 1:00 AM, Minchan Kim minc...@kernel.org wrote:
This patch is follow-up of Christohp Hellwig's work
[RFC: -make_request support for virtio-blk].
http://thread.gmane.org/gmane.linux.kernel/1199763
Quote from hch
This patchset allows the virtio-blk driver to support much
On 12/22/2011 02:57 PM, Michael S. Tsirkin wrote:
On Thu, Dec 22, 2011 at 02:50:27PM +0200, Avi Kivity wrote:
On 12/22/2011 02:50 PM, Michael S. Tsirkin wrote:
On Mon, Dec 19, 2011 at 04:13:35PM +0200, Avi Kivity wrote:
+static void vhost_log_start(MemoryListener *listener,
+
On 22/12/11 13:54, Avi Kivity wrote:
My main concern was the prefix register (this is a per cpu register that
defines the address of two pages that are swapped with the pages at 0 for
this cpu).
SMP on s390 is done that way (e.g. interrupt things are stored in page 0 for
this cpu)
The
On 12/22/2011 03:17 PM, Christian Borntraeger wrote:
On 22/12/11 13:54, Avi Kivity wrote:
My main concern was the prefix register (this is a per cpu register that
defines the address of two pages that are swapped with the pages at 0 for
this cpu).
SMP on s390 is done that way (e.g.
On Thu, Dec 15, 2011 at 02:23:16PM +0800, Hamo wrote:
by checking the return value from kvm_init_debug, we
can ensure that the entries under debugfs for KVM have
been created correctly.
Signed-off-by: Yang Bai hamo...@gmail.com
Applied, thanks.
--
To unsubscribe from this list: send the
On Thu, Dec 01, 2011 at 06:40:31PM +0100, Peter Zijlstra wrote:
On Wed, 2011-11-23 at 16:03 +0100, Andrea Arcangeli wrote:
snip
From what I gather what you propose is to periodically unmap all user
memory (or map it !r !w !x, which is effectively the same) and take the
fault. This fault will
On Thu, Dec 01, 2011 at 06:40:31PM +0100, Peter Zijlstra wrote:
On Wed, 2011-11-23 at 16:03 +0100, Andrea Arcangeli wrote:
Hi!
On Mon, Nov 21, 2011 at 07:51:21PM -0600, Anthony Liguori wrote:
Fundamentally, the entity that should be deciding what memory should be
present
and
Am 20.12.2011 13:08, schrieb Sasha Levin:
[..]
Whats wrong?
Are you sure that windows is using the serial device at all?
You're not emulating a keyboard there, you're emulating input from a
serial device.
HI Sasha,
Ive found a better solution:
It is possible to pipe the qemu-monitor:
On Thu, Dec 22, 2011 at 10:05:38AM +0900, Minchan Kim wrote:
[..]
May be using deadline or noop in guest is better to benchmark against
PCI-E based flash.
Good suggestion.
I tested it by deadline on guest side.
The result is not good.
Although gap is within noise, Batch BIO's random
This file, like many others, needs to include linux/export.h.
Signed-off-by: Kyle Moffett kyle.d.moff...@boeing.com
---
arch/powerpc/kvm/e500.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 26d2090..387c383 100644
On Fri, Dec 16, 2011 at 06:13:42PM +0800, Xiao Guangrong wrote:
unsync is only used for the page of level == 1 and unsync_children is only
used in the upper page, so combine them to reduce the size of shadow page
structure
Signed-off-by: Xiao Guangrong xiaoguangr...@linux.vnet.ibm.com
---
On 12/22/2011 05:01 AM, Marcelo Tosatti wrote:
On Thu, Dec 01, 2011 at 06:40:31PM +0100, Peter Zijlstra wrote:
No virt is crap, it needs to die, its horrid, and any solution aimed
squarely at virt only is shit and not worth considering, that simple.
Removing this phrase from context (feel
On Thu, 2011-12-22 at 09:01 -0200, Marcelo Tosatti wrote:
No virt is crap, it needs to die, its horrid, and any solution aimed
squarely at virt only is shit and not worth considering, that simple.
Removing this phrase from context (feel free to object on that basis
to the following
From: Gleb Natapov g...@redhat.com
Signed-off-by: Gleb Natapov g...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
---
target-i386/cpuid.c | 17 +
1 files changed, 13 insertions(+), 4 deletions(-)
diff --git a/target-i386/cpuid.c b/target-i386/cpuid.c
index
From: Vasilis Liaskovitis vasilis.liaskovi...@profitbricks.com
qemu-kvm passes numa/SRAT topology information for smp_cpus to SeaBIOS. However
SeaBIOS always expects to setup max_cpus number of SRAT cpu entries
(MaxCountCPUs variable in build_srat function of Seabios). When qemu-kvm runs
with
From: Jan Kiszka jan.kis...@siemens.com
Keep a per-VCPU xsave buffer for kvm_put/get_xsave instead of
continuously allocating and freeing it on state sync.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
---
target-i386/cpu.h |3 ++-
From: Jan Kiszka jan.kis...@siemens.com
The latter was already commented out, the former is redundant as well.
We always get the latest changes after return from the guest via
kvm_arch_post_run.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
On Thu, Dec 22, 2011 at 11:13:15AM -0600, Anthony Liguori wrote:
On 12/22/2011 05:01 AM, Marcelo Tosatti wrote:
On Thu, Dec 01, 2011 at 06:40:31PM +0100, Peter Zijlstra wrote:
No virt is crap, it needs to die, its horrid, and any solution aimed
squarely at virt only is shit and not worth
On Thu, Dec 22, 2011 at 12:20:01PM +, Stefan Hajnoczi wrote:
virtblk_make_request() checks that the queue is not plugged. Do we
need to do that here too?
biot based drivers don't have a queue that could be plugged.
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body
The following changes since commit 03ecd2c80a64d030a22fe67cc7a60f24e17ff211:
virtio-serial-bus: Ports are expected to implement 'have_data' callback
(2011-12-21 15:00:29 -0600)
are available in the git repository at:
git://git.kernel.org/pub/scm/virt/kvm/qemu-kvm.git uq/master
Gleb Natapov
From: Jan Kiszka jan.kis...@siemens.com
Field 0 (FCW+FSW) and 1 (FTW+FOP) were hard-coded so far.
Signed-off-by: Jan Kiszka jan.kis...@siemens.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
---
target-i386/kvm.c | 14 --
1 files changed, 8 insertions(+), 6 deletions(-)
On Thu, Dec 22, 2011 at 10:45:06AM -0500, Vivek Goyal wrote:
On Thu, Dec 22, 2011 at 10:05:38AM +0900, Minchan Kim wrote:
[..]
May be using deadline or noop in guest is better to benchmark against
PCI-E based flash.
Good suggestion.
I tested it by deadline on guest side.
The
On Thu, Dec 22, 2011 at 12:57:40PM +, Stefan Hajnoczi wrote:
On Wed, Dec 21, 2011 at 1:00 AM, Minchan Kim minc...@kernel.org wrote:
This patch is follow-up of Christohp Hellwig's work
[RFC: -make_request support for virtio-blk].
http://thread.gmane.org/gmane.linux.kernel/1199763
On 12/18/2011 04:59 PM, Avi Kivity wrote:
On 12/16/2011 12:16 PM, Xiao Guangrong wrote:
unsync_child_bitmap is used to record which spte has unsync page or unsync
children, we can set a free bit in the spte instead of it
unsync_child_bitmap takes one cacheline; the shadow page table takes
On 12/18/2011 06:42 PM, Avi Kivity wrote:
On 12/16/2011 12:18 PM, Xiao Guangrong wrote:
It is not used, remove it
Signed-off-by: Xiao Guangrong xiaoguangr...@linux.vnet.ibm.com
---
arch/x86/kvm/mmu.c |1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git
On 12/23/2011 12:06 AM, Marcelo Tosatti wrote:
On Fri, Dec 16, 2011 at 06:13:42PM +0800, Xiao Guangrong wrote:
unsync is only used for the page of level == 1 and unsync_children is only
used in the upper page, so combine them to reduce the size of shadow page
structure
Signed-off-by: Xiao
On 12/22/2011 12:18 PM, Sasha Levin wrote:
On Thu, 2011-12-22 at 12:03 +0200, Avi Kivity wrote:
On 12/08/2011 07:31 AM, Sasha Levin wrote:
It sounds like Alex is considering KVM PPC's return value in this case
(and
updating api.txt if appropriate) -- what say you on this
On Thu, 2011-12-22 at 12:21 +0200, Avi Kivity wrote:
On 12/22/2011 12:18 PM, Sasha Levin wrote:
On Thu, 2011-12-22 at 12:03 +0200, Avi Kivity wrote:
On 12/08/2011 07:31 AM, Sasha Levin wrote:
It sounds like Alex is considering KVM PPC's return value in this
case (and
This file, like many others, needs to include linux/export.h.
Signed-off-by: Kyle Moffett kyle.d.moff...@boeing.com
---
arch/powerpc/kvm/e500.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 26d2090..387c383 100644
55 matches
Mail list logo