On Mon, 2016-11-07 at 18:09 +0100, Paolo Bonzini wrote:
>
> On 06/11/2016 08:06, Michael S. Tsirkin wrote:
> >
> > On Sat, Nov 05, 2016 at 03:19:51AM -0400, Chao Peng wrote:
> > >
> > > >
> > > > This patch introduces a light weight machine type which shares
> > > > the
> > > > same codebase wi
On Sun, Nov 13, 2016 at 4:20 AM, wrote:
> Hi,
>
> Your series seems to have some coding style problems. See output below for
> more information:
>
> Type: series
> Subject: [Qemu-devel] [PATCH v2 0/5] [RFC] Add HAX support
> Message-id: cover.1478863621.git.vpala...@chromium.org
>
> === TEST SCRI
> +static uint64_t pnv_xscom_addr(const PnvChip *chip, uint32_t pcba)
> +{
> +uint64_t addr = chip->xscom_base;
> +
> +if (chip->chip_type == PNV_CHIP_POWER9) {
> +return addr | ((uint64_t) pcba << 3);
> +} else {
> +return addr | (((uint64_t) pcba << 4) & ~0xfful) |
T
On 14/11/2016 09:21, Vincent Palatin wrote:
> On Sun, Nov 13, 2016 at 4:20 AM, wrote:
>> Hi,
>>
>> Your series seems to have some coding style problems. See output below for
>> more information:
>>
>> Type: series
>> Subject: [Qemu-devel] [PATCH v2 0/5] [RFC] Add HAX support
>> Message-id: cove
On 11/14/16 09:21, Vincent Palatin wrote:
On Sun, Nov 13, 2016 at 4:20 AM, wrote:
=== OUTPUT BEGIN ===
fatal: unrecognized argument: --no-patch
Checking PATCH 1/5: ...
fatal: unrecognized argument: --no-patch
Checking PATCH 2/5: ...
fatal: unrecognized argument: --no-patch
Checking PATCH 3/5:
On 11/12/2016 3:13 PM, Greg Kurz wrote:
On Fri, 11 Nov 2016 03:54:27 -0500
Pradeep Jagadeesh wrote:
Uses throttling APIs to limit I/O bandwidth and number of operations on the
devices which use 9p-local driver.
Signed-off-by: Pradeep Jagadeesh
Reviewed-by: Alberto Garcia"
---
Hi Pradeep,
Hello,
Here is a little serie adding some fixes for the XSCOM registers of
the POWER9 cores and a unit test.
Changes since v1 :
- fixed pnv_xscom_addr() for 32bit host systems
- replace hweight_long() by ctpop64()
Tested on a 32-bit LE system and on 64-bit LE and BE systems.
Thanks,
C.
Cé
The XSCOM addresses for the core registers are encoded in a slightly
different way on POWER8 and POWER9.
Signed-off-by: Cédric Le Goater
---
hw/ppc/pnv.c | 8 +++-
include/hw/ppc/pnv.h | 1 +
include/hw/ppc/pnv_xscom.h | 5 ++---
3 files changed, 10 insertions(+), 4 delet
From: David Gibson
If the pnv machine type is compiled on a 32-bit host, the unsigned long
(host) type is 32-bit. This means that the hweight_long() used to
calculate the number of allowed cores only considers the low 32 bits of
the cores_mask variable, and can thus return 0 in some circumstance
High addresses can overflow the uint32_t pcba variable after the 8byte
shift.
Signed-off-by: Cédric Le Goater
---
hw/ppc/pnv_xscom.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/hw/ppc/pnv_xscom.c b/hw/ppc/pnv_xscom.c
index f46646141a96..8da271872f59 100644
--- a/h
Add a couple of tests on the XSCOM bus of the PowerNV machine for the
the POWER8 and POWER9 CPUs. The first tests reads the CFAM identifier
of the chip. The second test goes further in the XSCOM address space
and reaches the cores to read their DTS registers.
Signed-off-by: Cédric Le Goater
---
Hi,
Your series seems to have some coding style problems. See output below for
more information:
Type: series
Subject: [Qemu-devel] [PATCH v2 0/4] ppc/pnv: XSCOM fixes and unit tests
Message-id: 1479114778-3881-1-git-send-email-...@kaod.org
=== TEST SCRIPT BEGIN ===
#!/bin/bash
BASE=base
n=1
t
On Mon, Nov 14, 2016 at 9:55 AM, Stefan Weil wrote:
> On 11/14/16 09:21, Vincent Palatin wrote:
>>
>> On Sun, Nov 13, 2016 at 4:20 AM, wrote:
>>>
>>>
>>> === OUTPUT BEGIN ===
>>> fatal: unrecognized argument: --no-patch
>>> Checking PATCH 1/5: ...
>>> fatal: unrecognized argument: --no-patch
>>>
Am 11.11.2016 um 12:28 schrieb Vincent Palatin:
[...]
>
> Signed-off-by: Vincent Palatin
> ---
> hax-stub.c | 74 +++
> include/sysemu/hax.h| 66 ++
> target-i386/hax-all.c | 1490
> +++
Git warns about a whitespace issu
* Russell King - ARM Linux (li...@armlinux.org.uk) wrote:
> On Fri, Nov 11, 2016 at 09:23:43PM +, David Woodhouse wrote:
> > It's also *fairly* unlikely that the kernel in the guest has developed
> > a bug and isn't setting gso_size sanely. I'm more inclined to suspect
> > that qemu isn't prope
Richard,
I have studied your V2 patch
https://lists.nongnu.org/archive/html/qemu-devel/2016-02/msg02969.html
. Though I have not tested this patch on Loongson machine, I feel this
patch has implemented MIPS64 ISA very completely, including big/little
endian, N32 and N64 ABI. The use of #if is m
On Mon, Nov 14, 2016 at 10:29 AM, Stefan Weil wrote:
> Am 11.11.2016 um 12:28 schrieb Vincent Palatin:
> [...]
>>
>> Signed-off-by: Vincent Palatin
>> ---
>> hax-stub.c | 74 +++
>> include/sysemu/hax.h| 66 ++
>> target-i386/hax-all.c | 1490
>> ++
On Mon, Nov 14, 2016 at 01:32:56PM +0800, Dave Young wrote:
> On 11/09/16 at 04:38pm, Laszlo Ersek wrote:
> > On 11/09/16 15:47, Daniel P. Berrange wrote:
> > > On Wed, Nov 09, 2016 at 01:20:51PM +0100, Andrew Jones wrote:
> > >> On Wed, Nov 09, 2016 at 11:58:19AM +, Daniel P. Berrange wrote:
>
Am 24.10.2016 um 22:32 hat Eric Blake geschrieben:
> On 10/21/2016 08:14 AM, Ed Swierk wrote:
> > On Thu, Oct 20, 2016 at 6:38 PM, Eric Blake wrote:
> >> On 10/20/2016 07:24 PM, Ed Swierk wrote:
> >>> Changing max_transfer in the normal write case to
> >>> MIN_NON_ZERO(alignment, MAX_WRITE_ZEROES_
On Fri, Nov 11, 2016 at 01:55:49PM -0600, Wei Huang wrote:
>
>
> On 11/11/2016 01:43 AM, Andrew Jones wrote:
> > On Tue, Nov 08, 2016 at 12:17:14PM -0600, Wei Huang wrote:
> >> From: Christopher Covington
> >>
> >> Ensure that reads of the PMCCNTR_EL0 are monotonically increasing,
> >> even for
Hi,
Further investigation to the issue revealed that this happens before the
guest OS get to execute. KVM is not able to emulate a PF happened during a
jump to 0x4000.
Folowing is the trace of instructions at which the emulation error is
happening.
IN:
CR3: b859
On Mon, Nov 14, 2016 at 01:32:56PM +0800, Dave Young wrote:
> On 11/09/16 at 04:38pm, Laszlo Ersek wrote:
> > On 11/09/16 15:47, Daniel P. Berrange wrote:
> > > On Wed, Nov 09, 2016 at 01:20:51PM +0100, Andrew Jones wrote:
> > >> On Wed, Nov 09, 2016 at 11:58:19AM +, Daniel P. Berrange wrote:
>
On 11/11/2016 12:28, Vincent Palatin wrote:
> +
> +memcpy(env->xmm_regs, fpu.mmx_1, sizeof(fpu.mmx_1));
> +memcpy((ZMMReg *) (env->xmm_regs) + 8, fpu.mmx_2, sizeof(fpu.mmx_2));
HAX will only support SSE (128-bit) registers, while env->xmm_regs
supports AVX512 (512-bit) so you have to cop
On 09/11/2016 17:01, Daniel P. Berrange wrote:
> On Wed, Nov 09, 2016 at 04:38:36PM +0100, Laszlo Ersek wrote:
>> On 11/09/16 15:47, Daniel P. Berrange wrote:
> That doesn't help with trying to diagnose a crash during boot up, since
> the guest agent isn't running till fairly late. I'm al
On 14/11/2016 11:10, Daniel P. Berrange wrote:
> There's already patches posted to create a virtio-pstore device for
> QEMU, which is what led me to suggest this as an option:
>
> https://lists.nongnu.org/archive/html/qemu-devel/2016-09/msg00381.html
It's also possible to use UEFI as a pstore
On Mon, Nov 14, 2016 at 11:28:04AM +0100, Paolo Bonzini wrote:
>
>
> On 14/11/2016 11:10, Daniel P. Berrange wrote:
> > There's already patches posted to create a virtio-pstore device for
> > QEMU, which is what led me to suggest this as an option:
> >
> > https://lists.nongnu.org/archive/html
On 09/11/2016 16:28, Dave Anderson wrote:
> I'm not sure whether this "guest userspace agent" is still in play here,
> but if there were such a thing, it could theoretically do the same
> thing that crash currently does when running on a live system.
>
> Both of those are available or calculatab
On 14/11/2016 11:08, Anand J wrote:
> Hi,
>
> Further investigation to the issue revealed that this happens before the
> guest OS get to execute. KVM is not able to emulate a PF happened during a
> jump to 0x4000.
>
> Folowing is the trace of instructions at which the emulation error is
> h
On 11/14/16 11:33, Daniel P. Berrange wrote:
> On Mon, Nov 14, 2016 at 11:28:04AM +0100, Paolo Bonzini wrote:
>>
>>
>> On 14/11/2016 11:10, Daniel P. Berrange wrote:
>>> There's already patches posted to create a virtio-pstore device for
>>> QEMU, which is what led me to suggest this as an option:
On 14/11/2016 11:33, Daniel P. Berrange wrote:
> On Mon, Nov 14, 2016 at 11:28:04AM +0100, Paolo Bonzini wrote:
>>
>>
>> On 14/11/2016 11:10, Daniel P. Berrange wrote:
>>> There's already patches posted to create a virtio-pstore device for
>>> QEMU, which is what led me to suggest this as an opti
On 11/11/2016 12:28, Vincent Palatin wrote:
> +/*
> + * In Hax, the qemu allocate the virtual address, and HAX kernel
> + * populate the memory with physical memory. Currently we have no
> + * paging, so user should make sure enough free memory in a
On 11/11/2016 12:28, Vincent Palatin wrote:
> +
> +memcpy(env->xmm_regs, fpu.mmx_1, sizeof(fpu.mmx_1));
> +memcpy((ZMMReg *) (env->xmm_regs) + 8, fpu.mmx_2, sizeof(fpu.mmx_2));
HAX will only support SSE (128-bit) registers, while env->xmm_regs
supports AVX512 (512-bit) so you have to cop
On Mon, Nov 14, 2016 at 11:15 AM, Paolo Bonzini wrote:
>
>
> On 11/11/2016 12:28, Vincent Palatin wrote:
>> +
>> +memcpy(env->xmm_regs, fpu.mmx_1, sizeof(fpu.mmx_1));
>> +memcpy((ZMMReg *) (env->xmm_regs) + 8, fpu.mmx_2, sizeof(fpu.mmx_2));
>
> HAX will only support SSE (128-bit) registers
On Mon, Nov 14, 2016 at 12:56 PM, Paolo Bonzini wrote:
>
>
> On 11/11/2016 12:28, Vincent Palatin wrote:
>> +/*
>> + * In Hax, the qemu allocate the virtual address, and HAX kernel
>> + * populate the memory with physical memory. Currently we have
>> no
>> +
Am 11.11.2016 um 12:28 schrieb Vincent Palatin:
> I took a stab at trying to rebase/upstream the support for Intel HAXM.
> (Hardware Accelerated Execution Manager).
> Intel HAX is kernel-based hardware acceleration module for Windows and MacOSX.
>
> I have based my work on the last version of the
On Mon, Nov 14, 2016 at 1:21 PM, Stefan Weil wrote:
> Am 11.11.2016 um 12:28 schrieb Vincent Palatin:
>> I took a stab at trying to rebase/upstream the support for Intel HAXM.
>> (Hardware Accelerated Execution Manager).
>> Intel HAX is kernel-based hardware acceleration module for Windows and
>>
From: Li Qiang
Currently, the backend of VirtFS doesn't have a cleanup
function. This will lead resource leak issues if the backed
driver allocates resources. This patch addresses this issue.
Signed-off-by: Li Qiang
---
fsdev/file-op-9p.h | 1 +
hw/9pfs/9p.c | 3 +++
2 files changed, 4 i
From: Li Qiang
In the init operation of handle backend dirver, it allocates a
handle_data struct and opens a mount file. We should free these
resources when the 9pfs device is unrealized. This is what this
patch does.
Signed-off-by: Li Qiang
---
hw/9pfs/9p-handle.c | 8
1 file changed
From: Li Qiang
Currently, the backend of VirtFS doesn't have a cleanup
function. This will leak some resources in handle and proxy
backend driver. This patchset addresses this issue.
Li Qiang (3):
9pfs: add cleanup operation in FileOperations
9pfs: add cleanup operation for handle backend dr
Am 14.11.2016 um 13:33 schrieb Vincent Palatin:
> On Mon, Nov 14, 2016 at 1:21 PM, Stefan Weil wrote:
>>
>> A full build for Windows needs the patch below to
>> fix missing declarations, otherwise it fails with
>> compiler warnings and linker errors.
> Thanks for filing the gaps. That's very helpf
On Thu, Nov 10, 2016 at 06:57:21PM +0100, Paolo Bonzini wrote:
>
>
> On 10/11/2016 12:48, Marcelo Tosatti wrote:
> > Destination has to run the following logic:
> >
> > If (source has KVM_CAP_ADVANCE_CLOCK)
> > use KVM_GET_CLOCK value
> > Else
> >read pvclock from guest
> >
> > To suppo
Am 11.11.2016 um 12:28 schrieb Vincent Palatin:
[...]
> I have tested the end result on a Windows 10 Pro machine (with UG support)
> with the Intel HAXM module 6.0.4 and a large ChromiumOS x86_64 image to
> exercise various code paths. It looks stable.
> I also did a quick regression testing of the
From: Li Qiang
In the init operation of proxy backend dirver, it allocates a
V9fsProxy struct and some other resources. We should free these
resources when the 9pfs device is unrealized. This is what this
patch does.
Signed-off-by: Li Qiang
---
hw/9pfs/9p-proxy.c | 10 ++
1 file change
See patches for details.
From: ZhuangYanying
After "ivshmem: Split ivshmem-plain, ivshmem-doorbell off ivshmem",
ivshmem_64bit renamed to not_legacy_32bit, and changed the implementation of
this property.
Then use64 = not_legacy_32bit = 1, then PCI attribute configuration ~
PCI_BASE_ADDRESS_MEM_TYPE_64 (default for iv
Import KVM_CLOCK_TSC_STABLE.
Signed-off-by: Marcelo Tosatti
diff --git a/include/standard-headers/linux/input.h
b/include/standard-headers/linux/input.h
index 7361a16..b472b85 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -245,6 +245,7 @@ st
I have a question about qemu.is it a bug in qemu version 1.2?
in qemu version 1.2 ,it set avail event by the code :
if (vq->vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
vring_avail_event(vq, vring_avail_idx(vq));
}
and in version 2.7 the code is
if (virtio_vdev_has_fe
Check for KVM_CAP_ADJUST_CLOCK capability KVM_CLOCK_TSC_STABLE, which
indicates that KVM_GET_CLOCK returns a value as seen by the guest at
that moment.
For new machine types, use this value rather than reading
from guest memory.
This reduces kvmclock difference on migration from 5s to 0.1s
(when
Hi,
I have observed a virtual server with an e1000 network card loosing network
connectivity
after live migration (not reproducible so far). In the log of the vServer I
found several messages like:
kernel: [13833656.832108] e1000 :00:05.0 eth2: Reset adapter
When I restarted the vServer
On Mon, Nov 14, 2016 at 1:36 PM, Stefan Weil wrote:
> Am 11.11.2016 um 12:28 schrieb Vincent Palatin:
> [...]
>> I have tested the end result on a Windows 10 Pro machine (with UG support)
>> with the Intel HAXM module 6.0.4 and a large ChromiumOS x86_64 image to
>> exercise various code paths. It
On 11/11/2016 22:03, Alex Williamson wrote:
> On Fri, 11 Nov 2016 21:24:33 +0100
> Paolo Bonzini wrote:
>> If you can post a backtrace of all threads at the time of the hang, from
>> origin/master (so without vhost, and not at ad07cd6) that could help.
>
> Yes, it occurs with all of the vfio de
On Sun, Nov 13, 2016 at 11:55:16AM +, Brian Candler wrote:
> On 12/11/2016 10:44, Samuel Thibault wrote:
> > Oops, sorry, my patch was completely bogus, here is a proper one.
>
> Excellent.
>
> I've run the original build process 18 times (each run takes about 25
> minutes) without valgrind,
On Fri, 11/11 13:59, Karl Rister wrote:
>
> Stefan
>
> I ran some quick tests with your patches and got some pretty good gains,
> but also some seemingly odd behavior.
>
> These results are for a 5 minute test doing sequential 4KB requests from
> fio using O_DIRECT, libaio, and IO depth of 1. T
On 14/11/2016 13:36, Marcelo Tosatti wrote:
> +/* local (running VM) restore */
> +if (s->clock_valid) {
> +/*
> + * if host does not support reliable KVM_GET_CLOCK,
> + * read kvmclock value from memory
> + */
> +if (!kv
On Mon, Nov 14, 2016 at 10:36:45AM +0800, Hailiang Zhang wrote:
> ping ?
>
> Anyone pick this up?
The original patch that added these lines went through Amit Shah and
David Gilbert. I have CCed them.
Stefan
signature.asc
Description: PGP signature
On Sat, Nov 12, 2016 at 04:43:21PM +0800, zhun...@gmail.com wrote:
> Thanks,the expression is not the key problem,I just write it wrong,the key
> problem is that what I get from the code is everytime dirver add a sg ,it
> will call virtqueue_kick,such as network driver,in start_xmit function ,it
On Mon, Nov 14, 2016 at 02:54:38PM +0100, Paolo Bonzini wrote:
>
>
> On 14/11/2016 13:36, Marcelo Tosatti wrote:
> > +/* local (running VM) restore */
> > +if (s->clock_valid) {
> > +/*
> > + * if host does not support reliable KVM_GET_CLOCK,
> > +
Marcelo Tosatti wrote:
> Check for KVM_CAP_ADJUST_CLOCK capability KVM_CLOCK_TSC_STABLE, which
> indicates that KVM_GET_CLOCK returns a value as seen by the guest at
> that moment.
>
> For new machine types, use this value rather than reading
> from guest memory.
>
> This reduces kvmclock differe
Paolo Bonzini wrote:
> On 14/11/2016 13:36, Marcelo Tosatti wrote:
>> +/* local (running VM) restore */
>> +if (s->clock_valid) {
>> +/*
>> + * if host does not support reliable KVM_GET_CLOCK,
>> + * read kvmclock value from memory
>> +
On Fri, Nov 11, 2016 at 02:13:31PM +0100, Andrew Jones wrote:
> On Fri, Nov 11, 2016 at 11:13:46AM +, Andre Przywara wrote:
> > Hi,
> >
> > more a comment loosely related to this patch ...
> >
> > > diff --git a/arm/unittests.cfg b/arm/unittests.cfg
> > > index 3f6fa45c587e..68bf5cd6008f 1006
On 14/11/2016 15:00, Marcelo Tosatti wrote:
> On Mon, Nov 14, 2016 at 02:54:38PM +0100, Paolo Bonzini wrote:
>>
>>
>> On 14/11/2016 13:36, Marcelo Tosatti wrote:
>>> +/* local (running VM) restore */
>>> +if (s->clock_valid) {
>>> +/*
>>> + * if host does n
When running with KVM enabled, you can choose between emulating the
gic in kernel or user space. If the kernel supports in-kernel virtualization
of the interrupt controller, it will default to that. If not, if will
default to user space emulation.
Unfortunately when running in user mode gic emulat
When running with KVM enabled, you can choose between emulating the
gic in kernel or user space. If the kernel supports in-kernel virtualization
of the interrupt controller, it will default to that. If not, if will
default to user space emulation.
Unfortunately when running in user mode gic emulat
This patch updates the Linux headers to include the in-progress user
space ARM timer patches. It is explicitly RFC, as the patches are not
merged yet.
---
linux-headers/asm-arm/kvm.h | 1 +
linux-headers/asm-arm64/kvm.h | 1 +
linux-headers/linux/kvm.h | 6 ++
3 files changed, 8 insertio
On Mon, Nov 14, 2016 at 03:22:02PM +0100, Paolo Bonzini wrote:
>
>
> On 14/11/2016 15:00, Marcelo Tosatti wrote:
> > On Mon, Nov 14, 2016 at 02:54:38PM +0100, Paolo Bonzini wrote:
> >>
> >>
> >> On 14/11/2016 13:36, Marcelo Tosatti wrote:
> >>> +/* local (running VM) restore */
> >>> +
On 11/14/2016 07:53 AM, Fam Zheng wrote:
> On Fri, 11/11 13:59, Karl Rister wrote:
>>
>> Stefan
>>
>> I ran some quick tests with your patches and got some pretty good gains,
>> but also some seemingly odd behavior.
>>
>> These results are for a 5 minute test doing sequential 4KB requests from
>> f
On 11/09/2016 06:13 PM, Stefan Hajnoczi wrote:
> Recent performance investigation work done by Karl Rister shows that the
> guest->host notification takes around 20 us. This is more than the "overhead"
> of QEMU itself (e.g. block layer).
>
> One way to avoid the costly exit is to use polling ins
On 11/09/2016 06:13 PM, Stefan Hajnoczi wrote:
> Recent performance investigation work done by Karl Rister shows that the
> guest->host notification takes around 20 us. This is more than the "overhead"
> of QEMU itself (e.g. block layer).
>
> One way to avoid the costly exit is to use polling ins
On 14/11/2016 15:50, Marcelo Tosatti wrote:
> Well, i didnt want to mix the meaning of the variables:
>
> +/* whether machine supports reliable KVM_GET_CLOCK */
> +bool mach_use_reliable_get_clock;
> +
> +/* whether source host supported reliable KVM_GET_CLOCK */
> +bool src_use_
On Wed, Sep 28, 2016 at 10:45 PM, Stefan Hajnoczi wrote:
> On Tue, Sep 27, 2016 at 09:09:49PM -0700, Ashish Mittal wrote:
>
> Review of .bdrv_open() and .bdrv_aio_writev() code paths.
>
> The big issues I see in this driver and libqnio:
>
> 1. Showstoppers like broken .bdrv_open() and leaking memo
On Mon, Nov 07, 2016 at 04:59:44PM -0800, Ashish Mittal wrote:
> Source code for the qnio library that this code loads can be downloaded from:
> https://github.com/MittalAshish/libqnio.git
>
> Sample command line using the JSON syntax:
> ./qemu-system-x86_64 -name instance-0008 -S -vnc 0.0.0.0
Hi Drew, Wei,
On 11/14/2016 05:05 AM, Andrew Jones wrote:
> On Fri, Nov 11, 2016 at 01:55:49PM -0600, Wei Huang wrote:
>>
>>
>> On 11/11/2016 01:43 AM, Andrew Jones wrote:
>>> On Tue, Nov 08, 2016 at 12:17:14PM -0600, Wei Huang wrote:
From: Christopher Covington
Ensure that reads o
On Fri, Nov 11, 2016 at 04:31:36PM +, Andre Przywara wrote:
> Hi,
>
> On 10/11/16 17:21, Andrew Jones wrote:
> > Signed-off-by: Andrew Jones
> >
> > ---
> > v5: use modern register names [Andre]
> > v4:
> > - only take defines from kernel we need now [Andre]
> > - simplify enable by not ca
On Fri, Nov 11, 2016 at 01:59:25PM -0600, Karl Rister wrote:
> On 11/09/2016 11:13 AM, Stefan Hajnoczi wrote:
> > Recent performance investigation work done by Karl Rister shows that the
> > guest->host notification takes around 20 us. This is more than the
> > "overhead"
> > of QEMU itself (e.g.
On 14/11/2016 16:26, Stefan Hajnoczi wrote:
> On Fri, Nov 11, 2016 at 01:59:25PM -0600, Karl Rister wrote:
>> QEMU_AIO_POLL_MAX_NS IOPs
>>unset31,383
>>146,860
>>246,440
>>435,246
>>
On 11/14/2016 09:26 AM, Stefan Hajnoczi wrote:
> On Fri, Nov 11, 2016 at 01:59:25PM -0600, Karl Rister wrote:
>> On 11/09/2016 11:13 AM, Stefan Hajnoczi wrote:
>>> Recent performance investigation work done by Karl Rister shows that the
>>> guest->host notification takes around 20 us. This is more
On Mon, 14 Nov 2016 13:22:08 +0530
Kirti Wankhede wrote:
> On 11/9/2016 2:58 AM, Alex Williamson wrote:
> > On Wed, 9 Nov 2016 01:29:19 +0530
> > Kirti Wankhede wrote:
> >
> >> On 11/8/2016 11:16 PM, Alex Williamson wrote:
> >>> On Tue, 8 Nov 2016 21:56:29 +0530
> >>> Kirti Wankhede wrote:
On Fri, Nov 11, 2016 at 09:01:41PM +0800, Fam Zheng wrote:
> The following changes since commit 6bbcb76301a72dc80c8d29af13d40bb9a759c9c6:
>
> MAINTAINERS: Remove obsolete stable branches (2016-11-10 15:29:59 +)
>
> are available in the git repository at:
>
> g...@github.com:famz/qemu tag
On Fri, Nov 11, 2016 at 04:21:10PM +0100, Igor Mammedov wrote:
>
> Commit 080ac219cc7d9c55adf925c3545b7450055ad625
>pc: Add 'etc/boot-cpus' fw_cfg file for machine with more than 255 CPUs
>
> added "etc/boot-cpus" fw_cfg file durung 2.8 merge window, however
> QEMU alredy had similar legacy F
On Mon, Nov 14, 2016 at 04:00:38PM +0100, Paolo Bonzini wrote:
>
>
> On 14/11/2016 15:50, Marcelo Tosatti wrote:
> > Well, i didnt want to mix the meaning of the variables:
> >
> > +/* whether machine supports reliable KVM_GET_CLOCK */
> > +bool mach_use_reliable_get_clock;
> > +
> > +
Added APIs for pining and unpining set of pages. These call back into
backend iommu module to actually pin and unpin pages.
Added two new callback functions to struct vfio_iommu_driver_ops. Backend
IOMMU module that supports pining and unpinning pages for mdev devices
should provide these functions
This series adds Mediated device support to Linux host kernel. Purpose
of this series is to provide a common interface for mediated device
management that can be used by different devices. This series introduces
Mdev core module that creates and manages mediated devices, VFIO based
driver for media
Added task structure as input argument to vfio_lock_acct() function.
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I5d3673cc9d3786bb436b395d5f74537f1a36da80
---
drivers/vfio/vfio_iommu_type1.c | 30 --
1 file changed, 16 insertions(+), 14 deletions(
On Mon, Nov 14, 2016 at 03:09:46PM +0100, Juan Quintela wrote:
> Marcelo Tosatti wrote:
> > Check for KVM_CAP_ADJUST_CLOCK capability KVM_CLOCK_TSC_STABLE, which
> > indicates that KVM_GET_CLOCK returns a value as seen by the guest at
> > that moment.
> >
> > For new machine types, use this value
Add file Documentation/vfio-mediated-device.txt that include details of
mediated device framework.
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I137dd646442936090d92008b115908b7b2c7bc5d
---
Documentation/vfio-mediated-device.txt | 298 +
driver
This change rearrange functions to have common function to increment
container_users
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Reviewed-by: Jike Song
Change-Id: I8bdeb352bc8439b107ffd519480fd4dc238677f2
---
drivers/vfio/vfio.c | 34 +-
1 file changed
Update arguments of vaddr_get_pfn() to take struct mm_struct *mm as input
argument.
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I885fd4cd4a9f66f4ee2c1caf58267464ec239f52
---
drivers/vfio/vfio_iommu_type1.c | 32
1 file changed, 24 insertions(
Design for Mediated Device Driver:
Main purpose of this driver is to provide a common interface for mediated
device management that can be used by different drivers of different
devices.
This module provides a generic interface to create the device, add it to
mediated bus, add device to IOMMU grou
Added details of sysfs ABI for mediated device framework
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: Icb0fd4ed58a2fa793fbcb1c3d5009a4403c1f3ac
---
Documentation/ABI/testing/sysfs-bus-vfio-mdev | 111 ++
1 file changed, 111 insertions(+)
create mode 1
Add find_iommu_group()
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Reviewed-by: Jike Song
Reviewed-by: Dong Jia Shi
Change-Id: I9d372f1ebe9eb01a5a21374b8a2b03f7df73601f
---
drivers/vfio/vfio_iommu_type1.c | 57 -
1 file changed, 33 insertions(
Added blocking notifier to IOMMU TYPE1 driver to notify vendor drivers
about DMA_UNMAP.
Exported two APIs vfio_register_notifier() and vfio_unregister_notifier().
Notifier should be registered, if external user wants to use
vfio_pin_pages()/vfio_unpin_pages() APIs to pin/unpin pages.
Vendor driver
vfio_mdev driver registers with mdev core driver.
mdev core driver creates mediated device and calls probe routine of
vfio_mdev driver for each device.
Probe routine of vfio_mdev driver adds mediated device to VFIO core module
This driver forms a shim layer that pass through VFIO devices operation
Adding myself as a maintainer of mediated device framework,
a sub module of VFIO.
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I58f6717783e0d4008ca31f4a5c4494696bae8571
---
MAINTAINERS | 9 +
1 file changed, 9 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
inde
Defined device API strings. Vendor driver using mediated device
framework should use corresponding string for device_api attribute.
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I42d29f475f02a7132ce13297fbf2b48f1da10995
---
include/uapi/linux/vfio.h | 10 ++
1 file cha
This patch rearranges functions to get vfio_group from device
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Reviewed-by: Jike Song
Change-Id: I1f93262bdbab75094bc24b087b29da35ba70c4c6
---
drivers/vfio/vfio.c | 23 ---
1 file changed, 16 insertions(+), 7 deletions(-)
The Sample driver creates mdev device that simulates serial port over PCI
card.
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I857f8f12f8b275f2498dfe8c628a5cdc7193b1b2
---
Documentation/vfio-mediated-device.txt | 103 ++-
samples/vfio-mdev/Makefile | 13 +
sampl
Updated vfio_pci.c file to use vfio_set_irqs_validate_and_prepare()
Signed-off-by: Kirti Wankhede
Signed-off-by: Neo Jia
Change-Id: I9f3daba89d8dba5cb5b01a8cff420412f30686c7
---
drivers/vfio/pci/vfio_pci.c | 34 +++---
1 file changed, 7 insertions(+), 27 deletions(-)
Add task structure to vfio_dma structure.
During DMA_UNMAP, same task who mapped it or other task who shares same
address space is allowed to unmap, otherwise unmap fails.
QEMU maps few iova ranges initially, then fork threads and from the child
thread calls DMA_UNMAP on previously mapped iova. Sin
On Mon, 11/14 15:07, Stefan Hajnoczi wrote:
> On Mon, Nov 07, 2016 at 04:59:44PM -0800, Ashish Mittal wrote:
> > diff --git a/block/vxhs.c b/block/vxhs.c
> > new file mode 100644
> > index 000..8913e8f
> > --- /dev/null
> > +++ b/block/vxhs.c
> > @@ -0,0 +1,689 @@
> > +/*
> > + * QEMU Block dri
Vendor driver using mediated device framework should use
vfio_info_add_capability() to add capabilities.
Introduced this function to reduce code duplication in vendor drivers.
vfio_info_cap_shift() manipulated a data buffer to add an offset to each
element in a chain. This data buffer is documente
1 - 100 of 277 matches
Mail list logo
