On 2021/3/26 21:18, Tarun Gupta wrote:
> Document interfaces used for VFIO device migration. Added flow of state
> changes
> during live migration with VFIO device. Tested by building docs with the new
> vfio-migration.rst file.
>
> v3:
> - Add introductory line about VM migration in general.
> -
On 2021/3/9 6:51, Alex Williamson wrote:
> [Cc +Intel]
>
> On Mon, 8 Mar 2021 21:39:49 +0530
> Tarun Gupta wrote:
>
>> VFIO migration support in QEMU is experimental as of now, which was done to
>> provide soak time and resolve concerns regarding bit-stream.
>> But, with the patches discussed in
the priority of the VFIO VM state change handler
explicitly (like virtio devices) to ensure it is called before the
GIC's in saving.
Signed-off-by: Shenming Lu
Reviewed-by: Kirti Wankhede
Reviewed-by: Cornelia Huck
---
hw/vfio/migration.c | 3 ++-
1 file changed, 2 insertions(+), 1 del
h 3.
v2 -> v3:
- Nit fixes.
- Set error in migration stream for migration to fail in Patch 1.
- Tested Patch 3 with a Windows guest.
Thanks,
Shenming
Shenming Lu (3):
vfio: Move the saving of the config space to the right place in VFIO
migration
vfio: Set the priority of the VFIO VM
asked vectors one by one without
disabling.
Signed-off-by: Shenming Lu
---
hw/vfio/pci.c | 20 +---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index f74be78209..fece8c2504 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -569,6 +
according to
their priorities.
As for the possible dependence of the device specific migration
data on it's config space, we can let the vendor driver to
include any config info it needs in its own data stream.
Signed-off-by: Shenming Lu
Reviewed-by: Kirti Wankhede
---
hw/vfio/migration.c
llocated(pdev); nr++) {
if (!msix_is_masked(pdev, nr)) {
max_vec = nr;
}
}
}
Thanks,
Shenming
> Thanks,
>
> Alex
>
> On Tue, 23 Feb 2021 10:22:25 +0800
> Shenming Lu wrote:
>
>> In VFIO migration resume phase and some guest startups, there are
&g
Hi Alex,
Does this series need any further modification? Wish you can pick it up. :-)
On 2021/2/23 10:22, Shenming Lu wrote:
> This patch set includes two fixes and one optimization for VFIO migration
> as blew:
>
> Patch 1-2:
> - Fix two ordering problems in migratio
according to
their priorities.
As for the possible dependence of the device specific migration
data on it's config space, we can let the vendor driver to
include any config info it needs in its own data stream.
Signed-off-by: Shenming Lu
---
hw/vfio/migration.c | 25 +++--
1
the priority of the VFIO VM state change handler
explicitly (like virtio devices) to ensure it is called before the
GIC's in saving.
Signed-off-by: Shenming Lu
Reviewed-by: Kirti Wankhede
Reviewed-by: Cornelia Huck
---
hw/vfio/migration.c | 3 ++-
1 file changed, 2 insertions(+), 1 del
to fail in Patch 1.
- Tested Patch 3 with a Windows guest.
Thanks,
Shenming
Shenming Lu (3):
vfio: Move the saving of the config space to the right place in VFIO
migration
vfio: Set the priority of the VFIO VM state change handler explicitly
vfio: Avoid disabling and enabling vect
asked vectors one by one without
disabling.
Signed-off-by: Shenming Lu
---
hw/pci/msix.c | 2 +-
hw/vfio/pci.c | 20 +---
include/hw/pci/msix.h | 1 +
3 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index ae9331cd0b..e0579
On 2021/2/18 22:42, Kirti Wankhede wrote:
>
>
> On 12/9/2020 1:39 PM, Shenming Lu wrote:
>> On ARM64 the VFIO SET_IRQS ioctl is dependent on the VM interrupt
>> setup, if the restoring of the VFIO PCI device config space is
>> before the VGIC, an error might occur in t
On 2021/1/27 22:21, Alex Williamson wrote:
> On Wed, 27 Jan 2021 19:27:35 +0800
> Shenming Lu wrote:
>
>> On 2021/1/27 5:36, Alex Williamson wrote:
>>> On Wed, 9 Dec 2020 16:09:19 +0800
>>> Shenming Lu wrote:
>>>
>>>> Different f
On 2021/1/27 22:20, Alex Williamson wrote:
> On Wed, 27 Jan 2021 19:20:06 +0800
> Shenming Lu wrote:
>
>> On 2021/1/27 5:36, Alex Williamson wrote:
>>> On Wed, 9 Dec 2020 16:09:18 +0800
>>> Shenming Lu wrote:
>>>
>>>> In the VFIO VM state
On 2021/1/27 5:36, Alex Williamson wrote:
> On Wed, 9 Dec 2020 16:09:19 +0800
> Shenming Lu wrote:
>
>> Different from the normal situation when the guest starts, we can
>> know the max unmasked vetctor (at the beginning) after msix_load()
>> in VFIO migration. So in o
On 2021/1/27 5:36, Alex Williamson wrote:
> On Wed, 9 Dec 2020 16:09:18 +0800
> Shenming Lu wrote:
>
>> In the VFIO VM state change handler, VFIO devices are transitioned
>> in the _SAVING state, which should keep them from sending interrupts.
>
> Is this comment acc
On 2020/12/9 16:09, Shenming Lu wrote:
> This patch set includes two fixes and one optimization for VFIO migration
> as blew:
> Patch 1-2:
> - Fix two ordering problems in migration.
>
> Patch 3:
> - Optimize the enabling process of the MSI-X vectors in migration.
>
Hi,
On 2020/12/9 20:45, Cornelia Huck wrote:
> On Wed, 9 Dec 2020 16:09:18 +0800
> Shenming Lu wrote:
>
>> In the VFIO VM state change handler, VFIO devices are transitioned
>> in the _SAVING state, which should keep them from sending interrupts.
>> Then we can sav
On 2020/12/10 2:34, Alex Williamson wrote:
> On Wed, 9 Dec 2020 13:29:47 +0100
> Cornelia Huck wrote:
>
>> On Wed, 9 Dec 2020 16:09:17 +0800
>> Shenming Lu wrote:
>>
>>> On ARM64 the VFIO SET_IRQS ioctl is dependent on the VM interrupt
>>> setup, i
handler
explicitly (like virtio devices) to ensure it is called before the
GIC's in saving.
Signed-off-by: Shenming Lu
Reviewed-by: Kirti Wankhede
---
hw/vfio/migration.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
these unmasked vectors one by one without disabling.
Signed-off-by: Shenming Lu
---
hw/pci/msix.c | 17 +
hw/vfio/pci.c | 10 --
include/hw/pci/msix.h | 2 ++
3 files changed, 27 insertions(+), 2 deletions(-)
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
This patch set includes two fixes and one optimization for VFIO migration
as blew:
Patch 1-2:
- Fix two ordering problems in migration.
Patch 3:
- Optimize the enabling process of the MSI-X vectors in migration.
Thanks,
Shenming
Shenming Lu (3):
vfio: Move the saving of the config space to
ff-by: Shenming Lu
---
hw/vfio/migration.c | 25 +++--
1 file changed, 15 insertions(+), 10 deletions(-)
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 00daa50ed8..3b9de1353a 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -575,11 +575,6 @@ stati
On 2020/12/2 18:55, Dr. David Alan Gilbert wrote:
> * Shenming Lu (lushenm...@huawei.com) wrote:
>> Hi,
>>
>> After reading everyone's opinions, we have a rough idea for this issue.
>>
>> One key point is whether it is necessary to setup the config space b
On 2020/12/2 6:21, Alex Williamson wrote:
> On Tue, 1 Dec 2020 14:37:52 +0800
> Shenming Lu wrote:
>
>> On 2020/12/1 1:03, Alex Williamson wrote:
>>> On Thu, 26 Nov 2020 14:56:17 +0800
>>> Shenming Lu wrote:
>>>
>>>> Hi,
>>>>
On 2020/12/1 1:03, Alex Williamson wrote:
> On Thu, 26 Nov 2020 14:56:17 +0800
> Shenming Lu wrote:
>
>> Hi,
>>
>> After reading everyone's opinions, we have a rough idea for this issue.
>>
>> One key point is whether it is necessary to setup the
Hi,
After reading everyone's opinions, we have a rough idea for this issue.
One key point is whether it is necessary to setup the config space before
the device can accept further migration data. I think it is decided by
the vendor driver, so we can simply ask the vendor driver about it in
.save_
On 2020/11/24 3:33, Neo Jia wrote:
> On Mon, Nov 23, 2020 at 11:14:38AM +0800, Shenming Lu wrote:
>> External email: Use caution opening links or attachments
>>
>>
>> On 2020/11/21 6:01, Alex Williamson wrote:
>>> On Fri, 20 Nov 2020 22:05:49 +0800
>>>
On 2020/11/21 6:01, Alex Williamson wrote:
> On Fri, 20 Nov 2020 22:05:49 +0800
> Shenming Lu wrote:
>
>> On 2020/11/20 1:41, Alex Williamson wrote:
>>> On Thu, 19 Nov 2020 14:13:24 +0530
>>> Kirti Wankhede wrote:
>>>
>>>> On 11/14/2020
On 2020/11/20 1:41, Alex Williamson wrote:
> On Thu, 19 Nov 2020 14:13:24 +0530
> Kirti Wankhede wrote:
>
>> On 11/14/2020 2:47 PM, Shenming Lu wrote:
>>> When running VFIO migration, I found that the restoring of VFIO PCI device’s
>>> config space is before VG
(like virtio devices) to ensure it is called before GIC's
in saving.
Signed-off-by: Shenming Lu
---
hw/vfio/migration.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 55261562d4..d0d30864ba 100644
--- a/hw/vfio/migrat
VGIC
according to their priorities.
Signed-off-by: Shenming Lu
---
hw/vfio/migration.c | 22 ++
1 file changed, 6 insertions(+), 16 deletions(-)
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 3ce285ea39..028da35a25 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio
On 6/23/2020 1:58 AM, Alex Williamson wrote:
>> +} else if (interrupt_type == VFIO_INT_MSIX) {
>> +uint16_t offset;
>> +
>> +offset = pci_default_read_config(pdev,
>> + pdev->msix_cap + PCI_MSIX_FLAGS + 1,
>> 2);
>> +/* load enable
34 matches
Mail list logo
