This patch enable per-vector mask for assigned devices using MSI-X.
This patch provided two new APIs: one is for guest to specific device's MSI-X
table address in MMIO, the other is for userspace to get information about mask
bit.
All the mask bit operation are kept in kernel, in order to acceler
On Fri, Nov 05, 2010 at 01:39:18PM +0800, Xiao Guangrong wrote:
> On 11/04/2010 06:35 PM, Gleb Natapov wrote:
> > On Thu, Nov 04, 2010 at 06:32:42PM +0800, Xiao Guangrong wrote:
> >> nonpaing guest's 'direct_map' is also true, retry #PF for those
> >> guests is useless, so use 'tdp_enabled' instead
On 11/05/2010 03:45 PM, Gleb Natapov wrote:
>>
>> It looks like something broken: apfs can generated in L2 guest (nested ntp
>> guest)
>> and be retried in L1 guest.
>>
> Why is this a problem? apf will be generate on direct map even when L2
> guest is running so it should be OK to prefault it in
On Fri, Nov 05, 2010 at 10:44:19AM +0800, Sheng Yang wrote:
> > > +};
> > > +
> > > +This ioctl would enable in-kernel MSI-X emulation, which would handle
> > > MSI-X +mask bit in the kernel.
> >
> > What happens on repeated calls when it's already enabled?
> > How does one disable after it's enab
On Fri, Nov 05, 2010 at 10:50:08AM +0800, Jason Wang wrote:
> For device that supports VIRTIO_NET_F_STATUS, there's no need to
> assume the link is up and we need to call nerif_carrier_off() before
> querying device status, otherwise we may get wrong operstate after
> diver was loaded because the l
On Fri, Nov 05, 2010 at 11:00:53AM +0800, Jason Wang wrote:
> Jason Wang writes:
>
> CC netdev missed in the original patch.
You'll have to repost it properly. Patches with a >
at start can't be applied :)
You can add my ack when you do.
> > For device that supports VIRTIO_NET_F_STATUS, there's
On Fri, Nov 05, 2010 at 03:16:23PM +0800, Sheng Yang wrote:
> This patch enable per-vector mask for assigned devices using MSI-X.
>
> This patch provided two new APIs: one is for guest to specific device's MSI-X
> table address in MMIO, the other is for userspace to get information about
> mask
>
On Fri, Nov 05, 2010 at 10:59:23AM +0800, Sheng Yang wrote:
> > We are trying to move away from using ifdefs. Stub these out instead?
>
> Example?
37859f054986fab6b4094cd5950266ae56a6ca6a and
889e30cc18e21f2091b77267dca8096d7dd34f8b that depends on it.
> --
> regards
> Yang, Sheng
--
To unsubscr
On Fri, Nov 05, 2010 at 11:14:48AM +0800, Sheng Yang wrote:
> On Thursday 04 November 2010 18:04:08 Michael S. Tsirkin wrote:
> > On Thu, Nov 04, 2010 at 02:18:21PM +0800, Sheng Yang wrote:
> > > This patch emulated MSI-X per vector mask bit on assigned device.
> > >
> > > Signed-off-by: Sheng Yan
On Fri, Nov 05, 2010 at 11:20:37AM +0800, Sheng Yang wrote:
> On Thursday 04 November 2010 17:44:27 Michael S. Tsirkin wrote:
>
> Thanks very much for reviewing this! Seems nobody cares about userspace one
> before...
>
> > On Thu, Nov 04, 2010 at 02:18:21PM +0800, Sheng Yang wrote:
> > > This p
Hi,
As already posted, I experience disk I/O stucks with KVM, which make the guest
systems alsmost unusable. These stucks come periodically, e.g. every 2 to 10
seconds and last between 3 and sometimes over 120 seconds, which trigger
kernel messages like this:
INFO: task postgres:2195 blocked fo
For device that supports VIRTIO_NET_F_STATUS, there's no need to
assume the link is up and we need to call nerif_carrier_off() before
querying device status, otherwise we may get wrong operstate after
diver was loaded because the link watch event was not fired as
expected.
For device that does not
On Fri, Nov 05, 2010 at 04:03:28PM +0800, Xiao Guangrong wrote:
> On 11/05/2010 03:45 PM, Gleb Natapov wrote:
>
> >>
> >> It looks like something broken: apfs can generated in L2 guest (nested ntp
> >> guest)
> >> and be retried in L1 guest.
> >>
> > Why is this a problem? apf will be generate on
On Friday 05 November 2010 16:43:33 Michael S. Tsirkin wrote:
> On Fri, Nov 05, 2010 at 10:44:19AM +0800, Sheng Yang wrote:
> > > > +};
> > > > +
> > > > +This ioctl would enable in-kernel MSI-X emulation, which would
> > > > handle MSI-X +mask bit in the kernel.
> > >
> > > What happens on repeat
On Friday 05 November 2010 16:51:33 Michael S. Tsirkin wrote:
> On Fri, Nov 05, 2010 at 03:16:23PM +0800, Sheng Yang wrote:
> > This patch enable per-vector mask for assigned devices using MSI-X.
> >
> > This patch provided two new APIs: one is for guest to specific device's
> > MSI-X table addres
On Friday 05 November 2010 17:05:32 Michael S. Tsirkin wrote:
> On Fri, Nov 05, 2010 at 11:20:37AM +0800, Sheng Yang wrote:
> > On Thursday 04 November 2010 17:44:27 Michael S. Tsirkin wrote:
> >
> > Thanks very much for reviewing this! Seems nobody cares about userspace
> > one before...
> >
> >
On Friday 05 November 2010 18:53:50 Sheng Yang wrote:
> On Friday 05 November 2010 16:43:33 Michael S. Tsirkin wrote:
> > On Fri, Nov 05, 2010 at 10:44:19AM +0800, Sheng Yang wrote:
> > > > > +};
> > > > > +
> > > > > +This ioctl would enable in-kernel MSI-X emulation, which would
> > > > > handle
Hi Joe,
> diff --git a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
> b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c index a101abf..3b894f5
> 100644
> --- a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
> +++ b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
> @@ -36,10 +36,9 @@ static int
On Fri, Nov 05, 2010 at 06:53:50PM +0800, Sheng Yang wrote:
> On Friday 05 November 2010 16:43:33 Michael S. Tsirkin wrote:
> > On Fri, Nov 05, 2010 at 10:44:19AM +0800, Sheng Yang wrote:
> > > > > +};
> > > > > +
> > > > > +This ioctl would enable in-kernel MSI-X emulation, which would
> > > > > h
On Fri, Nov 05, 2010 at 08:01:53PM +0800, Sheng Yang wrote:
> > Go back to me if someone want to implement MSI device assignment on
> > big-endian machine.
>
> Sorry, just realized it's very likely that I don't have an big endian machine
> to
> test it even at that time...
>
> I think it's real
On Fri, Nov 05, 2010 at 07:02:02PM +0800, Sheng Yang wrote:
> On Friday 05 November 2010 17:05:32 Michael S. Tsirkin wrote:
> > On Fri, Nov 05, 2010 at 11:20:37AM +0800, Sheng Yang wrote:
> > > On Thursday 04 November 2010 17:44:27 Michael S. Tsirkin wrote:
> > >
> > > Thanks very much for reviewi
Gleb Natapov writes:
> On Thu, Nov 04, 2010 at 03:22:50PM +0100, Markus Armbruster wrote:
>> Gleb Natapov writes:
>>
>> > On Thu, Nov 04, 2010 at 09:46:57AM +0100, Markus Armbruster wrote:
>> >> > But why order of device creation is important? It shouldn't be if we
>> >> > want to move HW descr
Gleb Natapov writes:
> On Thu, Nov 04, 2010 at 03:58:03PM +0100, Markus Armbruster wrote:
>> Gleb Natapov writes:
>>
>> > On Thu, Nov 04, 2010 at 10:20:18AM +0100, Markus Armbruster wrote:
>> >> Gleb Natapov writes:
>> >>
>> >> > Add "deriver_name" to DeviceInfo to use in device path building
On Fri, Nov 05, 2010 at 03:14:20PM +0100, Markus Armbruster wrote:
> Gleb Natapov writes:
>
> > On Thu, Nov 04, 2010 at 03:58:03PM +0100, Markus Armbruster wrote:
> >> Gleb Natapov writes:
> >>
> >> > On Thu, Nov 04, 2010 at 10:20:18AM +0100, Markus Armbruster wrote:
> >> >> Gleb Natapov write
On Fri, Nov 05, 2010 at 03:04:05PM +0100, Markus Armbruster wrote:
[skip]
> >> Passing bus numbers explicitly isn't hard either. Programmer is free to
> >> pass nonsensical numbers. For the most common case of one bus, the bus
> >> number parameter is just noise.
> > If programmer makes an error
Gleb Natapov writes:
> On Fri, Nov 05, 2010 at 03:14:20PM +0100, Markus Armbruster wrote:
>> Gleb Natapov writes:
>>
>> > On Thu, Nov 04, 2010 at 03:58:03PM +0100, Markus Armbruster wrote:
>> >> Gleb Natapov writes:
>> >>
>> >> > On Thu, Nov 04, 2010 at 10:20:18AM +0100, Markus Armbruster wro
Gleb Natapov writes:
> On Fri, Nov 05, 2010 at 03:04:05PM +0100, Markus Armbruster wrote:
[...]
>> >> >> There has been quite some discussion on "canonical path" on the list,
>> >> >> but no consensus. Ironically, one of the places where we got stuck was
>> >> >> ISA. You cut right through that
Hi,
I already tried to get some help on the KVM list for my problem but had no
success, so the problem could be not KVM related at all, therefore maybe
someone here has an idea:
I experience strange disk I/O stucks on my Linux Host + Guest with KVM, which
make the system (especially the guests)
We're currently masking out virtualized bits when updating both
physical device registers and vconfig. I think we really want
vconfig to track virtualized bits, otherwise they're not much
different that unwritable bits.
Signed-off-by: Alex Williamson
---
drivers/vfio/vfio_pci_config.c | 118 +
Tom,
Since we use INTX_DISABLE internally for PCI 2.3 devices, it's probably
not a good idea to allow vfio users direct access to it. In trying to
virtualize it, I stumbled on some config space virtualization issues.
I think we want vconfig and the value written to hardware to be different
when t
As we use this internally for interrupt control, it's dangerous
to let the user manipulate it. Instead, virtualize it. Also,
de-assert INTX_DISABLE when device is opened, the device reset
doesn't seem to clear this.
Signed-off-by: Alex Williamson
---
drivers/vfio/vfio_intrs.c | 38
On Fri, Nov 05, 2010 at 05:24:01PM +0100, Markus Armbruster wrote:
> Gleb Natapov writes:
>
> > On Fri, Nov 05, 2010 at 03:14:20PM +0100, Markus Armbruster wrote:
> >> Gleb Natapov writes:
> >>
> >> > On Thu, Nov 04, 2010 at 03:58:03PM +0100, Markus Armbruster wrote:
> >> >> Gleb Natapov write
On Fri, Nov 05, 2010 at 05:31:38PM +0100, Markus Armbruster wrote:
> Gleb Natapov writes:
>
> > On Fri, Nov 05, 2010 at 03:04:05PM +0100, Markus Armbruster wrote:
> [...]
> >> >> >> There has been quite some discussion on "canonical path" on the list,
> >> >> >> but no consensus. Ironically, one
This is an update to the original QEMU VFIO driver I sent several
months ago. Since then, I've ported it to the qemu-kvm.git tree,
and back, incorporated common msix and msi code, added irqfd
support, created an irqfd-like mechanism for EOIs, and likely
numerous other things that I've forgotten.
[Replying to my own email]
04.11.2010 00:16, Michael Tokarev wrote:
> 03.11.2010 22:44, Khaled El Mously wrote:
>> The host kernel is on Ubuntu: 2.6.32-25-generic
>>
>> The guest kernel is 2.6.34-something.
>>
>> I have figured out what the problem is. When I first attempted to run kvm,
>> it said
On Thu, Nov 04, 2010 at 02:15:16PM +0800, Sheng Yang wrote:
> Here is the latest series of MSI-X mask supporting patches.
>
> The bigest change from last version is, in order to reduce the complexity, I
> moved all mask bit operation to kernel, including disabled entries. This
> addressed two conc
On Fri, Nov 05, 2010 at 06:53:50PM +0800, Sheng Yang wrote:
> On Friday 05 November 2010 16:43:33 Michael S. Tsirkin wrote:
> > On Fri, Nov 05, 2010 at 10:44:19AM +0800, Sheng Yang wrote:
> > > > > +};
> > > > > +
> > > > > +This ioctl would enable in-kernel MSI-X emulation, which would
> > > > > h
Linus, please pull from
git://git.kernel.org/pub/scm/virt/kvm/kvm.git kvm-updates/2.6.37
To receive the following updates:
Jan Kiszka (1):
KVM: x86: Issue smp_call_function_many with preemption disabled
Marcelo Tosatti (1):
KVM: MMU: fix rmap_remove on non present sptes
Michae
The following changes since commit d33ea50a958b2e050d2b28e5f17e3b55e91c6d74:
scsi-disk: Fix immediate failure of bdrv_aio_* (2010-11-04 13:54:37 +0100)
are available in the git repository at:
git://git.kernel.org/pub/scm/virt/kvm/qemu-kvm.git uq/master
Gleb Natapov (1):
Add support for
The following changes since commit d33ea50a958b2e050d2b28e5f17e3b55e91c6d74:
scsi-disk: Fix immediate failure of bdrv_aio_* (2010-11-04 13:54:37 +0100)
are available in the git repository at:
git://git.kernel.org/pub/scm/virt/kvm/qemu-kvm.git uq/master
Gleb Natapov (1):
Add support for
From: Gleb Natapov
Add save/restore of MSR for migration and cpuid bit.
Signed-off-by: Gleb Natapov
Signed-off-by: Marcelo Tosatti
---
target-i386/cpu.h |1 +
target-i386/cpuid.c |2 +-
target-i386/kvm.c | 14 ++
target-i386/machine.c | 26 +++
From: Gleb Natapov
Add save/restore of MSR for migration and cpuid bit.
Signed-off-by: Gleb Natapov
Signed-off-by: Marcelo Tosatti
---
target-i386/cpu.h |1 +
target-i386/cpuid.c |2 +-
target-i386/kvm.c | 14 ++
target-i386/machine.c | 26 +++
On Sat, Nov 06, 2010 at 01:32:20AM +0300, Michael Tokarev wrote:
> [Replying to my own email]
> 04.11.2010 00:16, Michael Tokarev wrote:
> > 03.11.2010 22:44, Khaled El Mously wrote:
> >> The host kernel is on Ubuntu: 2.6.32-25-generic
> >>
> >> The guest kernel is 2.6.34-something.
> >>
> >> I ha
Hello
Ack_flush function () is not used anywhere in the code and apparently has no
function currently defined.
Unless there are plans to use it in the future, I took it out via this patch
code for readability.
Signed-off-by: Andre Luis Pereira dos Santos
---
Signed-off-by: Andre Luis Pereir
44 matches
Mail list logo