On 07/02/2023 2:56, Juan Quintela wrote:
External email: Use caution opening links or attachments
We split the function into to:
- state_pending_estimate: We estimate the remaining state size without
stopping the machine.
- state pending_exact: We calculate the exact amount of remaining
On 08/02/2023 19:25, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
On 2/6/23 13:31, Avihai Horon wrote:
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2 protocol.
Signed
On 08/02/2023 19:22, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Wed, 8 Feb 2023 15:08:15 +0200
Avihai Horon wrote:
On 08/02/2023 0:34, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 6 Feb 2023 14:31:30
On 08/02/2023 18:44, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
On 2/8/23 14:08, Avihai Horon wrote:
On 08/02/2023 0:34, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 6 Feb 2023 14:31:30 +0200
Avihai Horon
On 08/02/2023 1:49, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 6 Feb 2023 14:31:37 +0200
Avihai Horon wrote:
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2
On 08/02/2023 1:42, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 6 Feb 2023 14:31:33 +0200
Avihai Horon wrote:
@@ -523,6 +745,41 @@ static int vfio_save_iterate(QEMUFile *f, void *opaque)
return 0;
}
+static int vfio_save_complete_precopy
On 08/02/2023 0:34, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 6 Feb 2023 14:31:30 +0200
Avihai Horon wrote:
Currently VFIO migration doesn't implement some kind of intermediate
quiescent state in which P2P DMAs are quiesced before stopping
Now that v2 protocol implementation has been added, remove the
deprecated v1 implementation.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw/vfio/vfio-common.h | 5 -
hw/vfio/common.c | 17 +-
hw/vfio/migration.c | 703
is made optional in v2 protocol. Support for pre-copy will be
added later on.
Detailed information about VFIO migration protocol v2 and its difference
compared to v1 protocol can be found here [1].
[1]
https://lore.kernel.org/all/20220224142024.147653-10-yish...@nvidia.com/
Signed-off-by: Avihai
time.
Until such support is added, block migration of multiple devices.
Signed-off-by: Avihai Horon
---
include/hw/vfio/vfio-common.h | 2 ++
hw/vfio/common.c | 51 +++
hw/vfio/migration.c | 6 +
3 files changed, 59 insertions(+)
diff
device pending data size.
Avoid these unnecessary queries by issuing them in a RAM pre-copy
notifier instead of vfio_save_pending().
This way the VFIO device is queried only when RAM pending data is
below the threshold, when there is an actual chance for migration to
converge.
Signed-off-by: Avihai
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2 protocol.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
docs/devel/vfio-migration.rst | 68 ---
1 file changed, 30
Sort the migration section of VFIO trace events file alphabetically
and move two misplaced traces to common.c section.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
hw/vfio/trace-events | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git
are in running state [1]. No functional changes
intended.
[1] Note that checking if migration is in setup or active states and if
all VFIO devices are in running state doesn't guarantee that we are in
pre-copy phase, thus we check if migration is only in active state.
Signed-off-by: Avihai Horon
Reviewed
Move vfio_dev_get_region_info() logic from vfio_migration_probe() to
vfio_migration_init(). This logic is specific to v1 protocol and moving
it will make it easier to add the v2 protocol implementation later.
No functional changes intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later in VFIO migration code.
Signed-off-by: Avihai Horon
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Cédric Le Goater
---
migration/qemu-file.h
compatibility
API and prevent migration regressions caused by the lack of VFIO IOMMU
dirty tracking support.
[1]
https://lore.kernel.org/kvm/0-v6-a196d26f289e+11787-iommufd_...@nvidia.com/
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
hw/vfio/common.c| 20 ++--
hw
To avoid name collisions, rename functions and structs related to VFIO
migration protocol v1. This will allow the two protocols to co-exist
when v2 protocol is added, until v1 is removed. No functional changes
intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw
From: Juan Quintela
So remove it everywhere.
Signed-off-by: Juan Quintela
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Dr. David Alan Gilbert
---
include/migration/register.h | 3 +--
migration/savevm.h | 3 +--
hw/s390x/s390-stattrib.c | 2 +-
ration and vfio_vmstate_change() error flow is taken, as
MigrationState->to_dst_file is not set at that time.
Fix it by checking that MigrationState->to_dst_file is set before using
it.
Fixes: 02a7e71b1e5b ("vfio: Add VM state change handler to know state of VM")
Signed-off-by:
19072-1-avih...@nvidia.com/
[10]
https://lore.kernel.org/qemu-devel/20221003031600.20084-1-quint...@redhat.com/T/
[11]
https://lore.kernel.org/all/20221016085752.32740-1-avih...@nvidia.com/
[12]
https://lore.kernel.org/all/20220512154320.19697-1-avih...@nvidia.com/
Avihai Horon (13):
linux-header
Update to commit 1b929c02afd3 ("Linux 6.2-rc1").
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
Reviewed-by: Michael S. Tsirkin
---
include/standard-headers/drm/drm_fourcc.h | 63 +++-
include/standard-headers/linux/ethtool.h | 81 -
include/standard-hea
On 26/01/2023 2:00, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Sun, 22 Jan 2023 12:31:33 +0200
Avihai Horon wrote:
On 21/01/2023 1:07, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 16 Jan 2023 16:11:31
On 21/01/2023 1:07, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 16 Jan 2023 16:11:31 +0200
Avihai Horon wrote:
Implement the basic mandatory part of VFIO migration protocol v2.
This includes all functionality that is necessary to support
On 21/01/2023 1:06, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Mon, 16 Jan 2023 16:11:26 +0200
Avihai Horon wrote:
Currently, if IOMMU of a VFIO container doesn't support dirty page
tracking, migration is blocked. This is because a DMA-able VFIO
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2 protocol.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
docs/devel/vfio-migration.rst | 68 ---
1 file changed, 30
Now that v2 protocol implementation has been added, remove the
deprecated v1 implementation.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw/vfio/vfio-common.h | 5 -
hw/vfio/common.c | 19 +-
hw/vfio/migration.c | 703
device pending data size.
Avoid these unnecessary queries by issuing them in a RAM pre-copy
notifier instead of vfio_save_pending().
This way the VFIO device is queried only when RAM pending data is
below the threshold, when there is an actual chance for migration to
converge.
Signed-off-by: Avihai
is made optional in v2 protocol. Support for pre-copy will be
added later on.
Detailed information about VFIO migration protocol v2 and its difference
compared to v1 protocol can be found here [1].
[1]
https://lore.kernel.org/all/20220224142024.147653-10-yish...@nvidia.com/
Signed-off-by: Avihai
Sort the migration section of VFIO trace events file alphabetically
and move two misplaced traces to common.c section.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
hw/vfio/trace-events | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git
compatibility
API and prevent migration regressions caused by the lack of VFIO IOMMU
dirty tracking support.
[1]
https://lore.kernel.org/kvm/0-v6-a196d26f289e+11787-iommufd_...@nvidia.com/
Signed-off-by: Avihai Horon
---
hw/vfio/common.c| 20 ++--
hw/vfio/migration.c | 3 +--
2
From: Juan Quintela
So remove it everywhere.
Signed-off-by: Juan Quintela
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Dr. David Alan Gilbert
---
include/migration/register.h | 3 +--
migration/savevm.h | 3 +--
hw/s390x/s390-stattrib.c | 2 +-
Update to commit 1b929c02afd3 ("Linux 6.2-rc1").
Signed-off-by: Avihai Horon
---
include/standard-headers/drm/drm_fourcc.h | 63 +++-
include/standard-headers/linux/ethtool.h | 81 -
include/standard-headers/linux/fuse.h | 20 +-
.../linux/input-eve
Move vfio_dev_get_region_info() logic from vfio_migration_probe() to
vfio_migration_init(). This logic is specific to v1 protocol and moving
it will make it easier to add the v2 protocol implementation later.
No functional changes intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le
ration and vfio_vmstate_change() error flow is taken, as
MigrationState->to_dst_file is not set at that time.
Fix it by checking that MigrationState->to_dst_file is set before using
it.
Fixes: 02a7e71b1e5b ("vfio: Add VM state change handler to know state of VM")
Signed-off-by:
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later in VFIO migration code.
Signed-off-by: Avihai Horon
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Cédric Le Goater
---
migration/qemu-file.h
To avoid name collisions, rename functions and structs related to VFIO
migration protocol v1. This will allow the two protocols to co-exist
when v2 protocol is added, until v1 is removed. No functional changes
intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw
are in running state [1]. No functional changes
intended.
[1] Note that checking if migration is in setup or active states and if
all VFIO devices are in running state doesn't guarantee that we are in
pre-copy phase, thus we check if migration is only in active state.
Signed-off-by: Avihai Horon
Reviewed
kernel.org/all/20221016085752.32740-1-avih...@nvidia.com/
[10]
https://lore.kernel.org/all/20220512154320.19697-1-avih...@nvidia.com/
Avihai Horon (12):
linux-headers: Update to v6.2-rc1
vfio/migration: Fix NULL pointer dereference bug
vfio/migration: Allow migration without VFIO IOMMU dirty tracking
On 16/01/2023 12:55, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
Hello Avihai,
On 1/15/23 19:35, Avihai Horon wrote:
Implement the basic mandatory part of VFIO migration protocol v2.
This includes all functionality that is necessary to support
On 13/01/2023 18:13, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
On 1/12/23 09:50, Avihai Horon wrote:
Implement the basic mandatory part of VFIO migration protocol v2.
This includes all functionality that is necessary to support
VFIO_MIGRATION_STOP_COPY
ration and vfio_vmstate_change() error flow is taken, as
MigrationState->to_dst_file is not set at that time.
Fix it by checking that MigrationState->to_dst_file is set before using
it.
Fixes: 02a7e71b1e5b ("vfio: Add VM state change handler to know state of VM")
Signed-off-by:
Sort the migration section of VFIO trace events file alphabetically
and move two misplaced traces to common.c section.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
hw/vfio/trace-events | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2 protocol.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
docs/devel/vfio-migration.rst | 68 ---
1 file changed, 30
compatibility
API and prevent migration regressions caused by the lack of VFIO IOMMU
dirty tracking support.
[1]
https://lore.kernel.org/kvm/0-v6-a196d26f289e+11787-iommufd_...@nvidia.com/
Signed-off-by: Avihai Horon
---
hw/vfio/common.c| 20 ++--
hw/vfio/migration.c | 3 +--
2
device pending data size.
Avoid these unnecessary queries by issuing them in a RAM pre-copy
notifier instead of vfio_save_pending().
This way the VFIO device is queried only when RAM pending data is
below the threshold, when there is an actual chance for migration to
converge.
Signed-off-by: Avihai
is made optional in v2 protocol. Support for pre-copy will be
added later on.
Detailed information about VFIO migration protocol v2 and its difference
compared to v1 protocol can be found here [1].
[1]
https://lore.kernel.org/all/20220224142024.147653-10-yish...@nvidia.com/
Signed-off-by: Avihai
Move vfio_dev_get_region_info() logic from vfio_migration_probe() to
vfio_migration_init(). This logic is specific to v1 protocol and moving
it will make it easier to add the v2 protocol implementation later.
No functional changes intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le
Now that v2 protocol implementation has been added, remove the
deprecated v1 implementation.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw/vfio/vfio-common.h | 5 -
hw/vfio/common.c | 19 +-
hw/vfio/migration.c | 703
To avoid name collisions, rename functions and structs related to VFIO
migration protocol v1. This will allow the two protocols to co-exist
when v2 protocol is added, until v1 is removed. No functional changes
intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw
are in running state [1]. No functional changes
intended.
[1] Note that checking if migration is in setup or active states and if
all VFIO devices are in running state doesn't guarantee that we are in
pre-copy phase, thus we check if migration is only in active state.
Signed-off-by: Avihai Horon
Reviewed
-1-avih...@nvidia.com/
[7]
https://lore.kernel.org/qemu-devel/20221003031600.20084-1-quint...@redhat.com/T/
[8]
https://lore.kernel.org/all/20221016085752.32740-1-avih...@nvidia.com/
[9]
https://lore.kernel.org/all/20220512154320.19697-1-avih...@nvidia.com/
Avihai Horon (12):
linux-headers: Update to
Update to commit 1b929c02afd3 ("Linux 6.2-rc1").
Signed-off-by: Avihai Horon
---
include/standard-headers/drm/drm_fourcc.h | 63 +++-
include/standard-headers/linux/ethtool.h | 81 -
include/standard-headers/linux/fuse.h | 20 +-
.../linux/input-eve
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later in VFIO migration code.
Signed-off-by: Avihai Horon
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Cédric Le Goater
---
migration/qemu-file.h
From: Juan Quintela
So remove it everywhere.
Signed-off-by: Juan Quintela
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Dr. David Alan Gilbert
---
include/migration/register.h | 3 +--
migration/savevm.h | 3 +--
hw/s390x/s390-stattrib.c | 2 +-
are in running state [1]. No functional changes
intended.
[1] Note that checking if migration is in setup or active states and if
all VFIO devices are in running state doesn't guarantee that we are in
pre-copy phase, thus we check if migration is only in active state.
Signed-off-by: Avihai Horon
---
hw
ration and vfio_vmstate_change() error flow is taken, as
MigrationState->to_dst_file is not set at that time.
Fix it by checking that MigrationState->to_dst_file is set before using
it.
Fixes: 02a7e71b1e5b ("vfio: Add VM state change handler to know state of VM")
Signed-off-by:
To avoid name collisions, rename functions and structs related to VFIO
migration protocol v1. This will allow the two protocols to co-exist
when v2 protocol is added, until v1 is removed. No functional changes
intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le Goater
---
include/hw
Sort the migration section of VFIO trace events file alphabetically
and move two misplaced traces to common.c section.
Signed-off-by: Avihai Horon
---
hw/vfio/trace-events | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/hw/vfio/trace-events b/hw/vfio
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later in VFIO migration code.
Signed-off-by: Avihai Horon
Reviewed-by: Vladimir Sementsov-Ogievskiy
---
migration/qemu-file.h | 1 +
migration/qemu-file.c
is made optional in v2 protocol. Support for pre-copy will be
added later on.
Detailed information about VFIO migration protocol v2 and its difference
compared to v1 protocol can be found here [1].
[1]
https://lore.kernel.org/all/20220224142024.147653-10-yish...@nvidia.com/
Signed-off-by: Avihai
compatibility
API and prevent migration regressions caused by the lack of VFIO IOMMU
dirty tracking support.
[1]
https://lore.kernel.org/kvm/0-v6-a196d26f289e+11787-iommufd_...@nvidia.com/
Signed-off-by: Avihai Horon
---
hw/vfio/common.c| 20 ++--
hw/vfio/migration.c | 3 +--
2
Move vfio_dev_get_region_info() logic from vfio_migration_probe() to
vfio_migration_init(). This logic is specific to v1 protocol and moving
it will make it easier to add the v2 protocol implementation later.
No functional changes intended.
Signed-off-by: Avihai Horon
Reviewed-by: Cédric Le
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2 protocol.
Signed-off-by: Avihai Horon
---
docs/devel/vfio-migration.rst | 68 ---
1 file changed, 30 insertions(+), 38 deletions
device pending data size.
Avoid these unnecessary queries by issuing them in a RAM pre-copy
notifier instead of vfio_save_pending().
This way the VFIO device is queried only when RAM pending data is
below the threshold, when there is an actual chance for migration to
converge.
Signed-off-by: Avihai
Now that v2 protocol implementation has been added, remove the
deprecated v1 implementation.
Signed-off-by: Avihai Horon
---
include/hw/vfio/vfio-common.h | 5 -
hw/vfio/common.c | 19 +-
hw/vfio/migration.c | 703 +-
hw/vfio/trace
om/
[4]
https://lore.kernel.org/qemu-devel/20221103161620.13120-1-avih...@nvidia.com/
[5]
https://lore.kernel.org/all/20220530170739.19072-1-avih...@nvidia.com/
[6]
https://lore.kernel.org/qemu-devel/20221003031600.20084-1-quint...@redhat.com/T/
[7]
https://lore.kernel.org/all/20221016085752.32
From: Juan Quintela
So remove it everywhere.
Signed-off-by: Juan Quintela
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Dr. David Alan Gilbert
---
include/migration/register.h | 3 +--
migration/savevm.h | 3 +--
hw/s390x/s390-stattrib.c | 2 +-
Update to commit 1b929c02afd3 ("Linux 6.2-rc1").
Signed-off-by: Avihai Horon
---
include/standard-headers/drm/drm_fourcc.h | 63 +++-
include/standard-headers/linux/ethtool.h | 81 -
include/standard-headers/linux/fuse.h | 20 +-
.../linux/input-eve
On 10/01/2023 18:19, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
Hello Avihai
On 1/10/23 15:08, Avihai Horon wrote:
On 09/01/2023 20:36, Jason Gunthorpe wrote:
On Mon, Jan 09, 2023 at 06:27:21PM +0100, Cédric Le Goater wrote:
also
On 09/01/2023 20:36, Jason Gunthorpe wrote:
On Mon, Jan 09, 2023 at 06:27:21PM +0100, Cédric Le Goater wrote:
also, in vfio_migration_query_flags() :
+static int vfio_migration_query_flags(VFIODevice *vbasedev, uint64_t
*mig_flags)
+{
+uint64_t buf[DIV_ROUND_UP(sizeof(struct
On 09/01/2023 13:20, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
On 12/29/22 12:03, Avihai Horon wrote:
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later
On 09/01/2023 12:20, Cédric Le Goater wrote:
External email: Use caution opening links or attachments
Hello Avihai,
On 12/29/22 12:03, Avihai Horon wrote:
+static int vfio_save_setup(QEMUFile *f, void *opaque)
+{
+ VFIODevice *vbasedev = opaque;
+ VFIOMigration *migration
On 06/01/2023 23:56, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Thu, 29 Dec 2022 13:03:36 +0200
Avihai Horon wrote:
Currently, if IOMMU of a VFIO container doesn't support dirty page
tracking, migration is blocked. This is because a DMA-able VFIO
On 06/01/2023 19:56, Alex Williamson wrote:
External email: Use caution opening links or attachments
On Thu, 29 Dec 2022 13:03:34 +0200
Avihai Horon wrote:
From: Juan Quintela
IMHO, there should always be a commit log description. Why is this a
simplification?
Yes. It just rephrases
On 03/01/2023 13:13, Dr. David Alan Gilbert wrote:
External email: Use caution opening links or attachments
* Avihai Horon (avih...@nvidia.com) wrote:
As part of its error flow, vfio_vmstate_change() accesses
MigrationState->to_dst_file without any checks. This can cause a NULL
poin
compatibility
API and prevent migration regressions caused by the lack of VFIO IOMMU
dirty tracking support.
[1]
https://lore.kernel.org/kvm/0-v6-a196d26f289e+11787-iommufd_...@nvidia.com/
Signed-off-by: Avihai Horon
---
hw/vfio/common.c| 100 ++--
hw
Now that VFIO migration protocol v2 has been implemented and v1 protocol
has been removed, update the documentation according to v2 protocol.
Signed-off-by: Avihai Horon
---
docs/devel/vfio-migration.rst | 68 ---
1 file changed, 30 insertions(+), 38 deletions
device pending data size.
Avoid these unnecessary queries by issuing them in a RAM pre-copy
notifier instead of vfio_save_pending().
This way the VFIO device is queried only when RAM pending data is
below the threshold, when there is an actual chance for migration to
converge.
Signed-off-by: Avihai
Now that v2 protocol implementation has been added, remove the
deprecated v1 implementation.
Signed-off-by: Avihai Horon
---
include/hw/vfio/vfio-common.h | 5 -
hw/vfio/common.c | 19 +-
hw/vfio/migration.c | 701 +-
hw/vfio/trace
Sort the migration section of VFIO trace events file alphabetically
and move two misplaced traces to common.c section.
Signed-off-by: Avihai Horon
---
hw/vfio/trace-events | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/hw/vfio/trace-events b/hw/vfio
Move vfio_dev_get_region_info() logic from vfio_migration_probe() to
vfio_migration_init(). This logic is specific to v1 protocol and moving
it will make it easier to add the v2 protocol implementation later.
No functional changes intended.
Signed-off-by: Avihai Horon
---
hw/vfio/migration.c
are in running state [1]. No functional changes
intended.
[1] Note that checking if migration is in setup or active states and if
all VFIO devices are in running state doesn't guarantee that we are in
pre-copy phase, thus we check if migration is only in active state.
Signed-off-by: Avihai Horon
---
hw
is made optional in v2 protocol. Support for pre-copy will be
added later on.
Detailed information about VFIO migration protocol v2 and its difference
compared to v1 protocol can be found here [1].
[1]
https://lore.kernel.org/all/20220224142024.147653-10-yish...@nvidia.com/
Signed-off-by: Avihai
From: Juan Quintela
So remove it everywhere.
Signed-off-by: Juan Quintela
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Dr. David Alan Gilbert
---
include/migration/register.h | 3 +--
migration/savevm.h | 3 +--
hw/s390x/s390-stattrib.c | 2 +-
Update to commit 1b929c02afd3 ("Linux 6.2-rc1").
Signed-off-by: Avihai Horon
---
include/standard-headers/drm/drm_fourcc.h | 63 +++-
include/standard-headers/linux/ethtool.h | 81 -
include/standard-headers/linux/fuse.h | 20 +-
.../linux/input-eve
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later in VFIO migration code.
Signed-off-by: Avihai Horon
Reviewed-by: Vladimir Sementsov-Ogievskiy
---
migration/qemu-file.h | 1 +
migration/qemu-file.c
ration and vfio_vmstate_change() error flow is taken, as
MigrationState->to_dst_file is not set at that time.
Fix it by checking that MigrationState->to_dst_file is set before using
it.
Fixes: 02a7e71b1e5b ("vfio: Add VM state change handler to know state of VM")
Signed-off-by:
To avoid name collisions, rename functions and structs related to VFIO
migration protocol v1. This will allow the two protocols to co-exist
when v2 protocol is added, until v1 is removed. No functional changes
intended.
Signed-off-by: Avihai Horon
---
include/hw/vfio/vfio-common.h | 2 +-
hw
From: Juan Quintela
Signed-off-by: Juan Quintela
Signed-off-by: Avihai Horon
---
migration/migration.c | 25 +
1 file changed, 13 insertions(+), 12 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index 9795d0ec5c..61b9ce0fe8 100644
1620.13120-1-avih...@nvidia.com/
[5]
https://lore.kernel.org/all/20220530170739.19072-1-avih...@nvidia.com/
[6]
https://lore.kernel.org/all/20221016085752.32740-1-avih...@nvidia.com/
[7]
https://lore.kernel.org/all/20220512154320.19697-1-avih...@nvidia.com/
Avihai Horon (12):
linux-headers: Upd
Move vfio_dev_get_region_info() logic from vfio_migration_probe() to
vfio_migration_init(). This logic is specific to v1 protocol and moving
it will make it easier to add the v2 protocol implementation later.
No functional changes intended.
Signed-off-by: Avihai Horon
---
hw/vfio/migration.c
Now that v2 protocol implementation has been added, remove the
deprecated v1 implementation.
Signed-off-by: Avihai Horon
---
hw/vfio/common.c | 19 +-
hw/vfio/migration.c | 695 +-
hw/vfio/trace-events | 8 -
include/hw/vfio
From: Juan Quintela
So remove it everywhere.
Signed-off-by: Juan Quintela
Reviewed-by: Vladimir Sementsov-Ogievskiy
Reviewed-by: Dr. David Alan Gilbert
---
hw/s390x/s390-stattrib.c | 2 +-
hw/vfio/migration.c| 3 +--
include/migration/register.h | 3 +--
device pending data size.
Avoid these unnecessary queries by issuing them in a RAM pre-copy
notifier instead of vfio_save_pending().
This way the VFIO device is queried only when RAM pending data is
below the threshold, when there is an actual chance for migration to
converge.
Signed-off-by: Avihai
Add new function qemu_file_get_to_fd() that allows reading data from
QEMUFile and writing it straight into a given fd.
This will be used later in VFIO migration code.
Signed-off-by: Avihai Horon
Reviewed-by: Vladimir Sementsov-Ogievskiy
---
migration/qemu-file.c | 34
Use VFIO_DEVICE_FEATURE_MIG_DATA_SIZE ioctl to query the device stop
copy data size and report this value in vfio_save_pending() instead of
the hardcoded value that is currently used.
Use this ioctl in vfio_save_setup() as well, to adjust the migration
data buffer size.
Signed-off-by: Avihai
To avoid name collisions, rename functions and structs related to VFIO
migration protocol v1. This will allow the two protocols to co-exist
when v2 protocol is added, until v1 is removed. No functional changes
intended.
Signed-off-by: Avihai Horon
---
hw/vfio/common.c | 6 +-
hw
are in running state [1]. No functional changes
intended.
[1] Note that checking if migration is in setup or active states and if
all VFIO devices are in running state doesn't guarantee that we are in
pre-copy phase, thus we check if migration is only in active state.
Signed-off-by: Avihai Horon
---
hw
compared to v1 can be found here [1].
[1]
https://lore.kernel.org/all/20220224142024.147653-10-yish...@nvidia.com/
Signed-off-by: Avihai Horon
---
hw/vfio/common.c | 19 +-
hw/vfio/migration.c | 420 +++---
hw/vfio/trace-events | 6
1 - 100 of 142 matches
Mail list logo