From: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
To: svt-core@virtuozzo.com
Cc: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Subject: [PATCH QEMU HCI-8.1 v5 00/36] vfio: support qemu-update with passed through GPU's and vGPU's #VSTOR-103860
Date: Fri, 23 Oct 2026 19:53:37 +0300 [thread overview]
Message-ID: <20261023-vfio_v1-v5-0-ba0bf3c6d122@virtuozzo.com> (raw)
v4 -> v5:
Live migration of a vGPU VM with the default downtime limit (#VSTOR-150595).
- Patch 35 (NEW) ("VZ: migration: keep the estimate and wait over starved
windows"): the bandwidth, and so the pending size allowed for the
switchover, was measured over the windows the sender had run out of
dirty pages in, collapsing to a fraction of the link rate; meanwhile
the migration thread spun re-syncing the dirty logs
- Patch 36 (NEW) ("VZ: migration: don't wait for stop-copy-only device
state"): the vGPU's stop-copy state (2 GB for NVIDIA) never fits the
limit, so the migration never switched over; switch over once the rest
is within the limit plus as much again, as waiting can't help
Fixes of the issues found by Sashiko AI review.
- Patch 4 ("migration/cpr-exec: require a file or exec migration URI"):
CPR.rst says the URI must be a file or exec one
- Patch 5 ("migration: close the CPR state if the outgoing channel fails
to open"): the message no longer claims the cpr-exec memfd is closed,
see patch 6
- Patch 6 (NEW) ("migration/cpr-exec: close the persisted state if the
channel fails to open"): the memfd dup'd for the exec and the
environment variable pointing at it were leaked when the file or exec
URI couldn't be opened
- Patch 7 (NEW) ("migration: don't refuse a blocker over a migration of
another mode"): a blocker for cpr-transfer only was refused while a
normal migration runs, failing the operation adding it
- Patch 26 (NEW) ("vfio/migration: don't assume the device is running on
CPR incoming"): after CPR of a paused VM, 'cont' found the cached
device state already RUNNING and skipped the transition, leaving the
device stopped
- Patch 29 -> 32 ("VZ: vfio/region: preserve BAR mappings across
cpr-exec"): a preserved mapping of a different size is reported and
exits, instead of asserting
v4: http://lore.virtuozzo.com/20261020-vfio_v1-v4-0-83a5668230e5@virtuozzo.com
---
Akihiko Odaki (1):
vfio/pci: Grow buffer in vfio_pci_host_match()
Andrey Drobyshev (22):
VZ: migration/cpr-exec: fix Error leak in preserve_ram()
migration/cpr-exec: restore RAM write access if exec fails
vfio/region: create BAR dma-bufs with O_CLOEXEC
migration/cpr-exec: require a file or exec migration URI
migration: close the CPR state if the outgoing channel fails to open
migration/cpr-exec: close the persisted state if the channel fails to open
migration: don't refuse a blocker over a migration of another mode
kvm: tolerate ioctls after kvm_close()
kvm: fix coalesced MMIO flush racing with kvm_close()
migration/cpr: add cpr_is_in_progress()
vfio/migration: don't migrate device state during CPR
vfio/migration: don't assume the device is running on CPR incoming
vfio/listener: skip dirty page tracking during CPR
VZ: vfio/cpr: don't close KVM on cpr-exec
VZ: migration/cpr-exec: abort cpr-exec if memory can't be preserved
VZ: migration/cpr-exec: take the vhost-net devices back if exec fails
VZ: migration/cpr-exec: don't exec if a vhost-net device can't be released
VZ: vfio/region: preserve BAR mappings across cpr-exec #VSTOR-103860
VZ: migration/cpr-exec: allow cpr-exec with VFIO devices #VSTOR-103860
VZ: vfio/container: lift the CPR blocker for mdev devices #VSTOR-103860
VZ: migration: keep the estimate and wait over starved windows #VSTOR-150595
VZ: migration: don't wait for stop-copy-only device state #VSTOR-150595
Arun Menon (1):
migration: Fix regression of passing error_fatal into vmstate_load_state()
Cédric Le Goater (2):
vfio/pci: Reject invalid MSI-X Table and PBA BIR values
vfio/pci: Fix information leak in vfio_rom_read()
Fabiano Rosas (3):
migration: yank: Move register instance earlier
migration: Free cpr-transfer MigrationAddress along with gsource
migration: Move CPR HUP watch to cpr-transfer.c
Igor Mammedov (1):
q35: Fix migration of SMRAM state
Mario Casquero (1):
vfio/pci: Initialize rom_read_failed in vfio_pci_load_rom()
Markus Armbruster (1):
migration: Plug memory leaks after migrate_set_error()
Peter Xu (1):
migration: Fix crash on second migration when cancel early
Tycho Andersen (AMD) (1):
hw/vfio: Fix liveness check in vfio_connect_kvm_msi_virq()
Vladimir Sementsov-Ogievskiy (1):
migration: vmstate_save_state_v: fix double error_setg
Yanfei Xu (1):
migration: ensure APIC is loaded prior to VFIO PCI devices
accel/kvm/kvm-all.c | 24 ++++++-
docs/devel/migration/CPR.rst | 8 +--
hw/display/virtio-gpu.c | 22 ++++--
hw/intc/apic_common.c | 1 +
hw/net/vhost_net.c | 62 +++++++++++++++-
hw/pci-host/q35.c | 25 +++----
hw/pci/pci.c | 15 +++-
hw/s390x/virtio-ccw.c | 17 ++++-
hw/scsi/spapr_vscsi.c | 10 ++-
hw/vfio/container-legacy.c | 13 ----
hw/vfio/cpr.c | 11 +--
hw/vfio/device.c | 29 ++++++--
hw/vfio/listener.c | 6 ++
hw/vfio/migration-multifd.c | 2 +
hw/vfio/migration.c | 59 ++++++++++++++-
hw/vfio/pci.c | 25 ++++---
hw/vfio/region.c | 51 ++++++++++++-
hw/virtio/virtio-mmio.c | 15 +++-
hw/virtio/virtio-pci.c | 15 +++-
hw/virtio/virtio.c | 10 ++-
include/hw/vfio/vfio-cpr.h | 2 +-
include/hw/vfio/vfio-device.h | 2 -
include/hw/virtio/vhost.h | 2 +
include/migration/cpr.h | 7 ++
include/migration/vmstate.h | 1 +
include/net/vhost_net.h | 3 +-
migration/cpr-exec.c | 44 ++++++++++--
migration/cpr-transfer.c | 33 +++++++++
migration/cpr.c | 22 ++++++
migration/migration.c | 164 ++++++++++++++++++++++++++----------------
migration/migration.h | 11 +++
migration/multifd.c | 2 +
migration/savevm.c | 15 +++-
migration/savevm.h | 5 +-
migration/vmstate.c | 7 +-
tests/qtest/q35-test.c | 6 --
36 files changed, 586 insertions(+), 160 deletions(-)
---
base-commit: f3c1d9ef263edfab8d2a273078493bb766dcf8f8
change-id: 20261009-vfio_v1-a176cddd6b64
Best regards,
--
Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
next reply other threads:[~2026-10-23 16:54 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-23 16:53 Andrey Drobyshev [this message]
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 01/36] VZ: migration/cpr-exec: fix Error leak in preserve_ram() Andrey Drobyshev
2026-10-23 16:58 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 02/36] migration/cpr-exec: restore RAM write access if exec fails Andrey Drobyshev
2026-10-23 16:58 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 03/36] vfio/region: create BAR dma-bufs with O_CLOEXEC Andrey Drobyshev
2026-10-23 17:00 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 04/36] migration/cpr-exec: require a file or exec migration URI Andrey Drobyshev
2026-10-23 17:00 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 05/36] migration: close the CPR state if the outgoing channel fails to open Andrey Drobyshev
2026-10-23 17:01 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 06/36] migration/cpr-exec: close the persisted state if the " Andrey Drobyshev
2026-10-23 17:01 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 07/36] migration: don't refuse a blocker over a migration of another mode Andrey Drobyshev
2026-10-23 17:03 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 08/36] migration: Plug memory leaks after migrate_set_error() Andrey Drobyshev
2026-10-23 17:02 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 09/36] hw/vfio: Fix liveness check in vfio_connect_kvm_msi_virq() Andrey Drobyshev
2026-10-23 17:04 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 10/36] vfio/pci: Reject invalid MSI-X Table and PBA BIR values Andrey Drobyshev
2026-10-23 17:03 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 11/36] vfio/pci: Fix information leak in vfio_rom_read() Andrey Drobyshev
2026-10-23 17:04 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 12/36] vfio/pci: Initialize rom_read_failed in vfio_pci_load_rom() Andrey Drobyshev
2026-10-23 17:05 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 13/36] vfio/pci: Grow buffer in vfio_pci_host_match() Andrey Drobyshev
2026-10-23 17:05 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 14/36] q35: Fix migration of SMRAM state Andrey Drobyshev
2026-10-23 17:07 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 15/36] migration: ensure APIC is loaded prior to VFIO PCI devices Andrey Drobyshev
2026-10-23 17:06 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 16/36] migration: Fix regression of passing error_fatal into vmstate_load_state() Andrey Drobyshev
2026-10-23 17:09 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 17/36] migration: vmstate_save_state_v: fix double error_setg Andrey Drobyshev
2026-10-23 17:11 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 18/36] migration: yank: Move register instance earlier Andrey Drobyshev
2026-10-23 17:13 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 19/36] migration: Free cpr-transfer MigrationAddress along with gsource Andrey Drobyshev
2026-10-23 17:12 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 20/36] migration: Move CPR HUP watch to cpr-transfer.c Andrey Drobyshev
2026-10-23 17:12 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 21/36] migration: Fix crash on second migration when cancel early Andrey Drobyshev
2026-10-23 17:17 ` no-reply
2026-10-23 16:53 ` [PATCH QEMU HCI-8.1 v5 22/36] kvm: tolerate ioctls after kvm_close() Andrey Drobyshev
2026-10-23 17:17 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 23/36] kvm: fix coalesced MMIO flush racing with kvm_close() Andrey Drobyshev
2026-10-23 17:19 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 24/36] migration/cpr: add cpr_is_in_progress() Andrey Drobyshev
2026-10-23 17:19 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 25/36] vfio/migration: don't migrate device state during CPR Andrey Drobyshev
2026-10-23 17:26 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 26/36] vfio/migration: don't assume the device is running on CPR incoming Andrey Drobyshev
2026-10-23 17:23 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 27/36] vfio/listener: skip dirty page tracking during CPR Andrey Drobyshev
2026-10-23 17:27 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 28/36] VZ: vfio/cpr: don't close KVM on cpr-exec Andrey Drobyshev
2026-10-23 17:29 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 29/36] VZ: migration/cpr-exec: abort cpr-exec if memory can't be preserved Andrey Drobyshev
2026-10-23 17:29 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 30/36] VZ: migration/cpr-exec: take the vhost-net devices back if exec fails Andrey Drobyshev
2026-10-23 17:31 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 31/36] VZ: migration/cpr-exec: don't exec if a vhost-net device can't be released Andrey Drobyshev
2026-10-23 17:30 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 32/36] VZ: vfio/region: preserve BAR mappings across cpr-exec #VSTOR-103860 Andrey Drobyshev
2026-10-23 17:36 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 33/36] VZ: migration/cpr-exec: allow cpr-exec with VFIO devices #VSTOR-103860 Andrey Drobyshev
2026-10-23 17:32 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 34/36] VZ: vfio/container: lift the CPR blocker for mdev " Andrey Drobyshev
2026-10-23 17:34 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 35/36] VZ: migration: keep the estimate and wait over starved windows #VSTOR-150595 Andrey Drobyshev
2026-10-23 17:38 ` no-reply
2026-10-23 16:54 ` [PATCH QEMU HCI-8.1 v5 36/36] VZ: migration: don't wait for stop-copy-only device state #VSTOR-150595 Andrey Drobyshev
2026-10-23 17:40 ` no-reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261023-vfio_v1-v5-0-ba0bf3c6d122@virtuozzo.com \
--to=andrey.drobyshev@virtuozzo.com \
--cc=svt-core@virtuozzo.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox