Add Vitastor support

Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>

.gitignore

@@ -0,0 +1,7 @@
+/*.build
+/*.buildinfo
+/*.changes
+/*.deb
+/*.dsc
+/*.tar*
+/pve-qemu-kvm-*.*/

Makefile

@@ -1,60 +1,90 @@
-include /usr/share/dpkg/pkg-info.mk
-include /usr/share/dpkg/architecture.mk
+include /usr/share/dpkg/default.mk
 
 PACKAGE = pve-qemu-kvm
 
 SRCDIR := qemu
-BUILDDIR ?= ${PACKAGE}-${DEB_VERSION_UPSTREAM}
+BUILDDIR ?= $(PACKAGE)-$(DEB_VERSION_UPSTREAM)
+ORIG_SRC_TAR=$(PACKAGE)_$(DEB_VERSION_UPSTREAM).orig.tar.gz
 
 GITVERSION := $(shell git rev-parse HEAD)
 
-DEB = ${PACKAGE}_${DEB_VERSION_UPSTREAM_REVISION}_${DEB_BUILD_ARCH}.deb
-DEB_DBG = ${PACKAGE}-dbg_${DEB_VERSION_UPSTREAM_REVISION}_${DEB_BUILD_ARCH}.deb
+DSC=$(PACKAGE)_$(DEB_VERSION_UPSTREAM_REVISION).dsc
+DEB = $(PACKAGE)_$(DEB_VERSION_UPSTREAM_REVISION)_$(DEB_BUILD_ARCH).deb
+DEB_DBG = $(PACKAGE)-dbgsym_$(DEB_VERSION_UPSTREAM_REVISION)_$(DEB_BUILD_ARCH).deb
 DEBS = $(DEB) $(DEB_DBG)
 
 all: $(DEBS)
 
 .PHONY: submodule
 submodule:
-	test -f "${SRCDIR}/configure" || git submodule update --init --recursive
+ifeq ($(shell test -f "$(SRCDIR)/configure" && echo 1 || echo 0), 0)
+	git submodule update --init --recursive
+	cd $(SRCDIR); meson subprojects download
+endif
 
-$(BUILDDIR): keycodemapdb | submodule
+PC_BIOS_FW_PURGE_LIST_IN = \
+	hppa-firmware.img \
+	hppa-firmware64.img \
+	openbios-ppc \
+	openbios-sparc32 \
+	openbios-sparc64 \
+	palcode-clipper \
+	s390-ccw.img \
+	s390-netboot.img \
+	u-boot.e500 \
+	.*[a-zA-Z0-9]\.dtb \
+	.*[a-zA-Z0-9]\.dts \
+	qemu_vga.ndrv \
+	slof.bin \
+	opensbi-riscv.*-generic-fw_dynamic.bin \
+
+BLOB_PURGE_SED_CMDS = $(foreach FILE,$(PC_BIOS_FW_PURGE_LIST_IN),-e "/$(FILE)/d")
+BLOB_PURGE_FILTER = $(foreach FILE,$(PC_BIOS_FW_PURGE_LIST_IN),-e "$(FILE)")
+
+$(BUILDDIR): submodule
 	# check if qemu/ was used for a build
 	# if so, please run 'make distclean' in the submodule and try again
 	test ! -f $(SRCDIR)/build/config.status
-	rm -rf $(BUILDDIR)
-	cp -a $(SRCDIR) $(BUILDDIR)
-	cp -a debian $(BUILDDIR)/debian
-	rm -rf $(BUILDDIR)/ui/keycodemapdb
-	cp -a keycodemapdb $(BUILDDIR)/ui/
-	echo "git clone git://git.proxmox.com/git/pve-qemu.git\\ngit checkout $(GITVERSION)" > $(BUILDDIR)/debian/SOURCE
+	rm -rf $@.tmp $@
+	cp -a $(SRCDIR) $@.tmp
+	cp -a debian $@.tmp/debian
+	rm -rf $@.tmp/roms/edk2 # packaged separately
+	find $@.tmp/pc-bios -type f | grep $(BLOB_PURGE_FILTER) | xargs rm -f
+	sed -i $(BLOB_PURGE_SED_CMDS) $@.tmp/pc-bios/meson.build
+	echo "git clone git://git.proxmox.com/git/pve-qemu.git\\ngit checkout $(GITVERSION)" > $@.tmp/debian/SOURCE
+	mv $@.tmp $@
 
 .PHONY: deb kvm
 deb kvm: $(DEBS)
 $(DEB_DBG): $(DEB)
 $(DEB): $(BUILDDIR)
-	cd $(BUILDDIR); dpkg-buildpackage -b -us -uc -j
+	cd $(BUILDDIR); dpkg-buildpackage -b -us -uc -j32
 	lintian $(DEBS)
 
-.PHONY: update
-update:
-	cd $(SRCDIR) && git submodule deinit ui/keycodemapdb || true
-	rm -rf $(SRCDIR)/ui/keycodemapdb
-	mkdir $(SRCDIR)/ui/keycodemapdb
-	cd $(SRCDIR) && git submodule update --init ui/keycodemapdb
-	rm -rf keycodemapdb
-	mkdir keycodemapdb
-	cp -R $(SRCDIR)/ui/keycodemapdb/* keycodemapdb/
-	git add keycodemapdb
+sbuild: $(DSC)
+	sbuild $(DSC)
+
+$(ORIG_SRC_TAR): $(BUILDDIR)
+	tar czf $(ORIG_SRC_TAR) --exclude="$(BUILDDIR)/debian" $(BUILDDIR)
+
+.PHONY: dsc
+dsc:
+	rm -rf *.dsc $(BUILDDIR)
+	$(MAKE) $(DSC)
+	lintian $(DSC)
+
+$(DSC): $(ORIG_SRC_TAR) $(BUILDDIR)
+	cd $(BUILDDIR); dpkg-buildpackage -S -us -uc -d
 
 .PHONY: upload
+upload: UPLOAD_DIST ?= $(DEB_DISTRIBUTION)
 upload: $(DEBS)
-	tar cf - ${DEBS} | ssh repoman@repo.proxmox.com upload --product pve --dist bullseye
+	tar cf - $(DEBS) | ssh repoman@repo.proxmox.com upload --product pve --dist $(UPLOAD_DIST)
 
 .PHONY: distclean clean
 distclean: clean
 clean:
-	rm -rf $(BUILDDIR) $(PACKAGE)*.deb *.buildinfo *.changes
+	rm -rf $(PACKAGE)-[0-9]*/ $(PACKAGE)*.tar* *.deb *.dsc *.build *.buildinfo *.changes
 
 .PHONY: dinstall
 dinstall: $(DEBS)

debian/changelog

@@ -1,3 +1,302 @@
+pve-qemu-kvm (9.0.0-2+vitastor1) bookworm; urgency=medium
+
+  * Add Vitastor support
+
+ -- Vitaliy Filippov <vitalif@yourcmc.ru>  Mon, 20 May 2024 19:53:28 +0300
+
+pve-qemu-kvm (9.0.0-2) bookworm; urgency=medium
+
+  * fix #5409: backup: fix copy-before-write timeout
+
+  * backup: improve error when copy-before-write fails for fleecing
+
+  * fix forwards and backwards migration with VirtIO-GPU display
+
+  * fix a regression in pflash device introduced in 8.2
+
+  * revert a commit for VirtIO PCI devices that turned out to cause more
+    potential security issues than what it fixed
+
+  * move compatibility flags for a new VirtIO-net feature to the correct
+    machine type. The feature was introduced in QEMU 8.2, but the
+    compatibility flags got added to machine version 8.0 instead of 8.1. This
+    breaks backwards migration with machine version 8.1 from a 8.2/9.0 binary
+    to an 8.1 binary, in cases where the guest kernel enables the feature
+    (e.g. Ubuntu 23.10).
+    While that breaks migration with machine version 8.1 from an unpatched to
+    a patched binary, Proxmox VE only ever had 8.2 on the test repository and
+    9.0 not yet in any public repository.
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 17 May 2024 17:04:52 +0200
+
+pve-qemu-kvm (9.0.0-1) bookworm; urgency=medium
+
+  * update submodule and patches to QEMU 9.0.0
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 29 Apr 2024 10:51:37 +0200
+
+pve-qemu-kvm (8.2.2-1) bookworm; urgency=medium
+
+  * update submodule and patches to QEMU 8.2.2
+
+ -- Proxmox Support Team <support@proxmox.com>  Sat, 27 Apr 2024 12:44:30 +0200
+
+pve-qemu-kvm (8.1.5-5) bookworm; urgency=medium
+
+  * implement support for backup fleecing
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 11 Apr 2024 17:46:48 +0200
+
+pve-qemu-kvm (8.1.5-4) bookworm; urgency=medium
+
+  * fix live-import for certain kinds of VMDK images that rely on padding
+
+  * backup: avoid bubbling up first error if it's an ECANCELED one, as those
+    are often a result of cancling the job due to running into an actual
+    issue.
+
+  * backup: factor out & clean up gathering device info into helper
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 12 Mar 2024 14:08:40 +0100
+
+pve-qemu-kvm (8.1.5-3) bookworm; urgency=medium
+
+  * backport fix for potential deadlock during QMP stop command if the VM has
+    disks attached through VirtIO-Block and IO-Thread enabled
+
+  * fix #4507: add patch to automatically increase NOFILE soft limit
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 21 Feb 2024 20:11:23 +0100
+
+pve-qemu-kvm (8.1.5-2) bookworm; urgency=medium
+
+  * work around for a situation where guest IO might get stuck, if the VM is
+    configure  with iothread and VirtIO block/SCSI
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 02 Feb 2024 19:41:27 +0100
+
+pve-qemu-kvm (8.1.5-1) bookworm; urgency=medium
+
+  * update to 8.1.5 stable release, including more relevant fixes like:
+    - virtio-net: correctly copy vnet header when flushing TX
+    - hw/pflash: implement update buffer for block writes
+    - Fixes to i386 emulation and ARM emulation.
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 02 Feb 2024 19:08:13 +0100
+
+pve-qemu-kvm (8.1.2-6) bookworm; urgency=medium
+
+  * revert attempted fix to avoid rare issue with stuck guest IO when using
+    iothread, because it caused a much more common issue with iothreads
+    consuming too much CPU
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 15 Dec 2023 14:22:06 +0100
+
+pve-qemu-kvm (8.1.2-5) bookworm; urgency=medium
+
+  * backport workaround for stuck guest IO with iothread and VirtIO block/SCSI
+    in some rare edge cases
+
+  * backport fix for potential deadlock when issuing the "resize" QMP command
+    for a disk that is using iothread
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 11 Dec 2023 16:58:27 +0100
+
+pve-qemu-kvm (8.1.2-4) bookworm; urgency=medium
+
+  * fix vnc clipboard in the host to guest direction
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 22 Nov 2023 14:28:21 +0100
+
+pve-qemu-kvm (8.1.2-3) bookworm; urgency=medium
+
+  * fix #5054: backport fix for software reset with SATA, avoiding breakage
+    with, e.g., some FreeBSD VMs
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 20 Nov 2023 10:24:50 +0100
+
+pve-qemu-kvm (8.1.2-2) bookworm; urgency=medium
+
+  * revert "x86: acpi: workaround Windows not handling name references in
+    Package properly" as that seems to have broken networking (and possibly
+    other things) one some localized variants of Windows (e.g., the German
+    versions).
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 17 Nov 2023 11:55:23 +0100
+
+pve-qemu-kvm (8.1.2-1) bookworm; urgency=medium
+
+  * update submodule and patches to QEMU 8.1.2
+
+  * use QEMU's keycode-map-db again instead of our static copy from QEMU 6.0
+
+  * disable graph locking, newly introduced in the 8.1 release, as it has
+    still various deadlock issuess, e.g., during canceling backup jobs.
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 24 Oct 2023 13:42:45 +0200
+
+pve-qemu-kvm (8.0.2-7) bookworm; urgency=medium
+
+  * fix #2874: SATA: avoid unsolicited write to sector 0 during reset
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 04 Oct 2023 08:33:35 +0200
+
+pve-qemu-kvm (8.0.2-6) bookworm; urgency=medium
+
+  * fix #1534: vma: add extract-filter for disk images allowing users to pass
+    a comma separated list of the disks they want to extract from an archive.
+
+  * backup: create jobs in a drained section to avoid subtle bugs where
+    something interferes with the block-copy-state bitmap on initialization
+
+  * backup: drop experimental, and since a while also fully broken, directory
+    backup format (BACKUP_FORMAT_DIR). This format was never exposed via the
+    Proxmox VE API, but only available via QMP, as its broken since QEMU 8 and
+    we got zero reports about that, it's safe to assume that there are no
+    public users, so just remove it completely.
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 06 Sep 2023 17:03:59 +0200
+
+pve-qemu-kvm (8.0.2-5) bookworm; urgency=medium
+
+  * improve memory footprint after backup by not keeping as much memory
+    resident.
+
+  * fix file descriptor leak for vhost (used by default by vNICs).
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 16 Aug 2023 11:52:24 +0200
+
+pve-qemu-kvm (8.0.2-4) bookworm; urgency=medium
+
+  * fix resume for snapshot and hibernate in combination with iothread and
+    dirty bitmap
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 28 Jul 2023 12:58:22 +0200
+
+pve-qemu-kvm (8.0.2-3) bookworm; urgency=medium
+
+  * fix regression in QEMU 8.0 for drive mirror with bitmap
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 15 Jun 2023 13:57:46 +0200
+
+pve-qemu-kvm (8.0.2-2) bookworm; urgency=medium
+
+  * drop custom get_link_status QMP command, was never really used.
+
+  * drop custom & deprecated drive snapshot QMP commands, we use a better
+    alternative since a while.
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 09 Jun 2023 07:57:56 +0200
+
+pve-qemu-kvm (8.0.2-1) bookworm; urgency=medium
+
+  * update to QEMU stable release 8.0.2
+
+  * update patches for avoiding issues with DMA reentrancy to current,
+    slightly optimized version.
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 06 Jun 2023 16:34:50 +0200
+
+pve-qemu-kvm (8.0.0-1) bookworm; urgency=medium
+
+  * update to QEMU stable release 8.0.0
+
+  * re-build for Proxmox VE 8 / Debian 12 Bookworm
+
+  * adapt to the local virtiofsd C variant being dropped, it has been
+    rewritten in Rust and is now hosted in a separate source repository.
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 22 May 2023 13:45:49 +0200
+
+pve-qemu-kvm (7.2.0-8) bullseye; urgency=medium
+
+  * backport fix for ACPI CPU hotplug issue with TCG
+
+  * cherry-pick TCG-related stable fixes for 7.2 for users that turned off KVM
+    HW acceleration
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 17 Mar 2023 15:47:08 +0100
+
+pve-qemu-kvm (7.2.0-7) bullseye; urgency=medium
+
+  * improve fix for potential deadlock with trim for IDE/SATA and draining
+
+  * backport stable fixes:
+    - hw/nvme: fix missing endian conversions for doorbell buffers
+    - hw/smbios: fix field corruption in type 4 table
+    - virtio-rng-pci: fix transitional migration compat for vectors
+    - hw/timer/hpet: Fix expiration time overflow
+    - vhost/vdpa: stop all svq on device deletion
+    - vhost: avoid a potential use of an uninitialized variable in the call to
+      vhost_svq_poll
+    - chardev/char-socket: set s->listener = NULL in char_socket_finalize to
+      fix a potential crash after live-migration
+    - intel-iommu: fail MAP notifier without caching mode
+    - intel-iommu: fail DEVIOTLB_UNMAP without dt mode
+
+  * fix a regression for when the LSI SCSI controller is used
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 13 Mar 2023 17:42:49 +0100
+
+pve-qemu-kvm (7.2.0-6) bullseye; urgency=medium
+
+  * fix 7.2 regression for Linux boot failures with megasas SCSI
+
+  * fix 7.0 regression for a potential deadlock with trim for IDE/SATA and
+    draining
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 08 Mar 2023 14:32:17 +0100
+
+pve-qemu-kvm (7.2.0-5) bullseye; urgency=medium
+
+  * fix #4476: savevm-async: avoid looping without progress
+
+  * savevm-async: decrease the boundary for free space for (memory) state left
+    on target from 30 MiB to 100 MiB, improving the heuristic for when to
+    enter the final "pause and sync" stage.
+
+  * QMP backup: use correct error number when getting blockdrive length fails
+
+  * backport fix for some DMA reentrancy issues, better protecting against
+    malicious guests
+
+  * backport fix for iSCSI double free issue leading to crashes
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 21 Feb 2023 13:49:43 +0100
+
+pve-qemu-kvm (7.2.0-4) bullseye; urgency=medium
+
+  * backport fix for a 7.2 regression when using VirtIO disk with
+    detect-zeroes=unmap
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 27 Jan 2023 09:37:49 +0100
+
+pve-qemu-kvm (7.2.0-3) bullseye; urgency=medium
+
+  * add fix for live-migration with virtio-rng devices, which regressed in
+    QEMU 7.2.0.
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 12 Jan 2023 13:13:14 +0100
+
+pve-qemu-kvm (7.2.0-2) bullseye; urgency=medium
+
+  * enable slirp again for now, as in qemu-server, user networking is
+    supported (via CLI/API) when no bridge is set on a virtual NIC
+
+  * cherry-pick stable fixes for 7.2. Two for virtio-mem and one for vIOMMU.
+    Both features are not yet exposed in PVE's qemu-server, but there's work
+    going on to change that.
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 10 Jan 2023 15:47:48 +0100
+
+pve-qemu-kvm (7.2.0-1) bullseye; urgency=medium
+
+  * update to QEMU stable release 7.2.0
+
+  * drop 'slirp' networking
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 16 Dec 2022 13:18:21 +0100
+
 pve-qemu-kvm (7.1.0-4) bullseye; urgency=medium
 
   * cherry-pick "block/block-backend: blk_set_enable_write_cache is IO_CODE"

debian/compat

@@ -1 +0,0 @@
-10

debian/control

@@ -2,9 +2,8 @@ Source: pve-qemu-kvm
 Section: admin
 Priority: optional
 Maintainer: Proxmox Support Team <support@proxmox.com>
-Build-Depends: autotools-dev,
+Build-Depends: debhelper-compat (= 13),
                check,
-               debhelper (>= 9),
                libacl1-dev,
                libaio-dev,
                libattr1-dev,
@@ -16,21 +15,21 @@ Build-Depends: autotools-dev,
                libglusterfs-dev (>= 5.2-2),
                libgnutls28-dev,
                libiscsi-dev (>= 1.12.0),
-               libjemalloc-dev,
                libjpeg-dev,
                libjson-perl,
                libnuma-dev,
                libpci-dev,
                libpixman-1-dev,
-               libproxmox-backup-qemu0-dev (>= 1.3.0-1),
+               libproxmox-backup-qemu0-dev (>= 1.3.0),
                librbd-dev (>= 0.48),
                libsdl1.2-dev,
                libseccomp-dev,
+               libslirp-dev,
                libspice-protocol-dev (>= 0.12.14~),
                libspice-server-dev (>= 0.14.0~),
                libsystemd-dev,
                liburing-dev,
-               libusb-1.0-0-dev (>= 1.0.17-1),
+               libusb-1.0-0-dev (>= 1.0.17),
                libusbredirparser-dev (>= 0.6-2),
                libvirglrenderer-dev,
                libzstd-dev,
@@ -38,9 +37,8 @@ Build-Depends: autotools-dev,
                python3-minimal,
                python3-sphinx,
                python3-sphinx-rtd-theme,
+               python3-venv,
                quilt,
-               texi2html,
-               texinfo,
                uuid-dev,
                xfslibs-dev,
 Standards-Version: 3.7.2
@@ -57,16 +55,16 @@ Depends: ceph-common (>= 0.48),
          libglusterfs-dev | glusterfs-common (>= 5.6),
          libglusterfs0 | glusterfs-common (>= 5.6),
          libiscsi4 (>= 1.12.0) | libiscsi7,
-         libjemalloc2,
          libjpeg62-turbo,
          libspice-server1 (>= 0.14.0~),
          libusb-1.0-0 (>= 1.0.17-1),
          libusbredirparser1 (>= 0.6-2),
+         vitastor-client (>= 0.9.4),
          libuuid1,
          ${misc:Depends},
          ${shlibs:Depends},
-Recommends: numactl
-Suggests: libgl1
+Recommends: numactl,
+Suggests: libgl1,
 Conflicts: kvm,
            pve-kvm,
            pve-qemu-kvm-2.6.18,
@@ -74,22 +72,17 @@ Conflicts: kvm,
            qemu-kvm,
            qemu-system-arm,
            qemu-system-common,
+           qemu-system-data,
            qemu-system-x86,
            qemu-utils,
-Provides: qemu-system-arm, qemu-system-x86, qemu-utils
+Provides: qemu-system-arm, qemu-system-x86, qemu-utils,
 Replaces: pve-kvm,
           pve-qemu-kvm-2.6.18,
           qemu-system-arm,
           qemu-system-x86,
           qemu-utils,
+Breaks: qemu-server (<= 8.0.6)
 Description: Full virtualization on x86 hardware
  Using KVM, one can run multiple virtual PCs, each running unmodified Linux or
  Windows images. Each virtual machine has private virtualized hardware: a
  network card, disk, graphics adapter, etc.
-
-Package: pve-qemu-kvm-dbg
-Architecture: any
-Section: debug
-Depends: pve-qemu-kvm (= ${binary:Version})
-Description: pve qemu debugging symbols
- This package contains the debugging symbols for pve-qemu-kvm.

debian/parse-machines.pl

@@ -24,4 +24,5 @@ while (<STDIN>) {
 
 die "no QEMU machine types detected from STDIN input" if scalar (@$machines) <= 0;
 
-print to_json($machines, { utf8 => 1 }) or die "$!\n";
+print to_json($machines, { utf8 => 1, canonical => 1 })
+    or die "failed to encode detected machines as JSON - $!\n";

debian/patches/bitmap-mirror/0001-drive-mirror-add-support-for-sync-bitmap-mode-never.patch

@@ -27,16 +27,18 @@ Signed-off-by: Ma Haocong <mahaocong@didichuxing.com>
 Signed-off-by: John Snow <jsnow@redhat.com>
 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: rebased for 8.2.2]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
- block/mirror.c                         | 98 +++++++++++++++++++++-----
- blockdev.c                             | 39 +++++++++-
+ block/mirror.c                         | 99 ++++++++++++++++++++------
+ blockdev.c                             | 38 +++++++++-
  include/block/block_int-global-state.h |  4 +-
- qapi/block-core.json                   | 29 ++++++--
+ qapi/block-core.json                   | 25 ++++++-
  tests/unit/test-block-iothread.c       |  4 +-
- 5 files changed, 145 insertions(+), 29 deletions(-)
+ 5 files changed, 142 insertions(+), 28 deletions(-)
 
 diff --git a/block/mirror.c b/block/mirror.c
-index 3c4ab1159d..f2eca983f1 100644
+index 1bdce3b657..0c5c72df2e 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
 @@ -51,7 +51,7 @@ typedef struct MirrorBlockJob {
@@ -48,7 +50,7 @@ index 3c4ab1159d..f2eca983f1 100644
      BlockMirrorBackingMode backing_mode;
      /* Whether the target image requires explicit zero-initialization */
      bool zero_target;
-@@ -65,6 +65,8 @@ typedef struct MirrorBlockJob {
+@@ -73,6 +73,8 @@ typedef struct MirrorBlockJob {
      size_t buf_size;
      int64_t bdev_length;
      unsigned long *cow_bitmap;
@@ -57,9 +59,9 @@ index 3c4ab1159d..f2eca983f1 100644
      BdrvDirtyBitmap *dirty_bitmap;
      BdrvDirtyBitmapIter *dbi;
      uint8_t *buf;
-@@ -696,7 +698,8 @@ static int mirror_exit_common(Job *job)
-     bdrv_child_refresh_perms(mirror_top_bs, mirror_top_bs->backing,
+@@ -722,7 +724,8 @@ static int mirror_exit_common(Job *job)
                               &error_abort);
+ 
      if (!abort && s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
 -        BlockDriverState *backing = s->is_none_mode ? src : s->base;
 +        BlockDriverState *backing;
@@ -67,7 +69,7 @@ index 3c4ab1159d..f2eca983f1 100644
          BlockDriverState *unfiltered_target = bdrv_skip_filters(target_bs);
  
          if (bdrv_cow_bs(unfiltered_target) != backing) {
-@@ -794,6 +797,16 @@ static void mirror_abort(Job *job)
+@@ -819,6 +822,16 @@ static void mirror_abort(Job *job)
      assert(ret == 0);
  }
  
@@ -84,7 +86,7 @@ index 3c4ab1159d..f2eca983f1 100644
  static void coroutine_fn mirror_throttle(MirrorBlockJob *s)
  {
      int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-@@ -973,7 +986,8 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
+@@ -1015,7 +1028,8 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
      mirror_free_init(s);
  
      s->last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
@@ -94,7 +96,7 @@ index 3c4ab1159d..f2eca983f1 100644
          ret = mirror_dirty_init(s);
          if (ret < 0 || job_is_cancelled(&s->common.job)) {
              goto immediate_exit;
-@@ -1212,6 +1226,7 @@ static const BlockJobDriver mirror_job_driver = {
+@@ -1304,6 +1318,7 @@ static const BlockJobDriver mirror_job_driver = {
          .run                    = mirror_run,
          .prepare                = mirror_prepare,
          .abort                  = mirror_abort,
@@ -102,7 +104,7 @@ index 3c4ab1159d..f2eca983f1 100644
          .pause                  = mirror_pause,
          .complete               = mirror_complete,
          .cancel                 = mirror_cancel,
-@@ -1228,6 +1243,7 @@ static const BlockJobDriver commit_active_job_driver = {
+@@ -1322,6 +1337,7 @@ static const BlockJobDriver commit_active_job_driver = {
          .run                    = mirror_run,
          .prepare                = mirror_prepare,
          .abort                  = mirror_abort,
@@ -110,7 +112,7 @@ index 3c4ab1159d..f2eca983f1 100644
          .pause                  = mirror_pause,
          .complete               = mirror_complete,
          .cancel                 = commit_active_cancel,
-@@ -1593,7 +1609,10 @@ static BlockJob *mirror_start_job(
+@@ -1714,7 +1730,10 @@ static BlockJob *mirror_start_job(
                               BlockCompletionFunc *cb,
                               void *opaque,
                               const BlockJobDriver *driver,
@@ -122,9 +124,9 @@ index 3c4ab1159d..f2eca983f1 100644
                               bool auto_complete, const char *filter_node_name,
                               bool is_mirror, MirrorCopyMode copy_mode,
                               Error **errp)
-@@ -1605,10 +1624,39 @@ static BlockJob *mirror_start_job(
-     uint64_t target_perms, target_shared_perms;
-     int ret;
+@@ -1728,10 +1747,39 @@ static BlockJob *mirror_start_job(
+ 
+     GLOBAL_STATE_CODE();
  
 -    if (granularity == 0) {
 -        granularity = bdrv_get_default_bitmap_granularity(target);
@@ -164,7 +166,7 @@ index 3c4ab1159d..f2eca983f1 100644
      assert(is_power_of_2(granularity));
  
      if (buf_size < 0) {
-@@ -1740,7 +1788,9 @@ static BlockJob *mirror_start_job(
+@@ -1871,7 +1919,9 @@ static BlockJob *mirror_start_job(
      s->replaces = g_strdup(replaces);
      s->on_source_error = on_source_error;
      s->on_target_error = on_target_error;
@@ -174,10 +176,10 @@ index 3c4ab1159d..f2eca983f1 100644
 +    s->bitmap_mode = bitmap_mode;
      s->backing_mode = backing_mode;
      s->zero_target = zero_target;
-     s->copy_mode = copy_mode;
-@@ -1761,6 +1811,18 @@ static BlockJob *mirror_start_job(
-         bdrv_disable_dirty_bitmap(s->dirty_bitmap);
-     }
+     qatomic_set(&s->copy_mode, copy_mode);
+@@ -1897,6 +1947,18 @@ static BlockJob *mirror_start_job(
+      */
+     bdrv_disable_dirty_bitmap(s->dirty_bitmap);
  
 +    if (s->sync_bitmap) {
 +        bdrv_dirty_bitmap_set_busy(s->sync_bitmap, true);
@@ -191,10 +193,10 @@ index 3c4ab1159d..f2eca983f1 100644
 +        }
 +    }
 +
+     bdrv_graph_wrlock();
      ret = block_job_add_bdrv(&s->common, "source", bs, 0,
                               BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE |
-                              BLK_PERM_CONSISTENT_READ,
-@@ -1838,6 +1900,9 @@ fail:
+@@ -1979,6 +2041,9 @@ fail:
          if (s->dirty_bitmap) {
              bdrv_release_dirty_bitmap(s->dirty_bitmap);
          }
@@ -204,7 +206,7 @@ index 3c4ab1159d..f2eca983f1 100644
          job_early_fail(&s->common.job);
      }
  
-@@ -1855,31 +1920,25 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
+@@ -2001,35 +2066,28 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                    BlockDriverState *target, const char *replaces,
                    int creation_flags, int64_t speed,
                    uint32_t granularity, int64_t buf_size,
@@ -229,8 +231,12 @@ index 3c4ab1159d..f2eca983f1 100644
 -                   MirrorSyncMode_str(mode));
 -        return;
 -    }
+-
+     bdrv_graph_rdlock_main_loop();
 -    is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
      base = mode == MIRROR_SYNC_MODE_TOP ? bdrv_backing_chain_next(bs) : NULL;
+     bdrv_graph_rdunlock_main_loop();
+ 
      mirror_start_job(job_id, bs, creation_flags, target, replaces,
                       speed, granularity, buf_size, backing_mode, zero_target,
                       on_source_error, on_target_error, unmap, NULL, NULL,
@@ -241,7 +247,7 @@ index 3c4ab1159d..f2eca983f1 100644
  }
  
  BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
-@@ -1906,7 +1965,8 @@ BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
+@@ -2056,7 +2114,8 @@ BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
                       job_id, bs, creation_flags, base, NULL, speed, 0, 0,
                       MIRROR_LEAVE_BACKING_CHAIN, false,
                       on_error, on_error, true, cb, opaque,
@@ -252,33 +258,32 @@ index 3c4ab1159d..f2eca983f1 100644
                       errp);
      if (!job) {
 diff --git a/blockdev.c b/blockdev.c
-index 9230888e34..9a1a3118ed 100644
+index 057601dcf0..8682814a7a 100644
 --- a/blockdev.c
 +++ b/blockdev.c
-@@ -2951,6 +2951,10 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
+@@ -2776,6 +2776,9 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
                                     BlockDriverState *target,
-                                    bool has_replaces, const char *replaces,
+                                    const char *replaces,
                                     enum MirrorSyncMode sync,
-+                                   bool has_bitmap,
 +                                   const char *bitmap_name,
 +                                   bool has_bitmap_mode,
 +                                   BitmapSyncMode bitmap_mode,
                                     BlockMirrorBackingMode backing_mode,
                                     bool zero_target,
                                     bool has_speed, int64_t speed,
-@@ -2970,6 +2974,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
+@@ -2794,6 +2797,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
  {
      BlockDriverState *unfiltered_bs;
      int job_flags = JOB_DEFAULT;
 +    BdrvDirtyBitmap *bitmap = NULL;
  
-     if (!has_speed) {
-         speed = 0;
-@@ -3024,6 +3029,29 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
+     GLOBAL_STATE_CODE();
+     GRAPH_RDLOCK_GUARD_MAINLOOP();
+@@ -2848,6 +2852,29 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
          sync = MIRROR_SYNC_MODE_FULL;
      }
  
-+    if (has_bitmap) {
++    if (bitmap_name) {
 +        if (granularity) {
 +            error_setg(errp, "Granularity and bitmap cannot both be set");
 +            return;
@@ -301,53 +306,53 @@ index 9230888e34..9a1a3118ed 100644
 +        }
 +    }
 +
-     if (!has_replaces) {
+     if (!replaces) {
          /* We want to mirror from @bs, but keep implicit filters on top */
          unfiltered_bs = bdrv_skip_implicit_filters(bs);
-@@ -3070,8 +3098,8 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
+@@ -2889,8 +2916,8 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
       * and will allow to check whether the node still exist at mirror completion
       */
      mirror_start(job_id, bs, target,
--                 has_replaces ? replaces : NULL, job_flags,
+-                 replaces, job_flags,
 -                 speed, granularity, buf_size, sync, backing_mode, zero_target,
-+                 has_replaces ? replaces : NULL, job_flags, speed, granularity,
-+                 buf_size, sync, bitmap, bitmap_mode, backing_mode, zero_target,
++                 replaces, job_flags, speed, granularity, buf_size, sync,
++                 bitmap, bitmap_mode, backing_mode, zero_target,
                   on_source_error, on_target_error, unmap, filter_node_name,
                   copy_mode, errp);
  }
-@@ -3216,6 +3244,8 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
+@@ -3034,6 +3061,8 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
  
-     blockdev_mirror_common(arg->has_job_id ? arg->job_id : NULL, bs, target_bs,
-                            arg->has_replaces, arg->replaces, arg->sync,
-+                           arg->has_bitmap, arg->bitmap,
+     blockdev_mirror_common(arg->job_id, bs, target_bs,
+                            arg->replaces, arg->sync,
++                           arg->bitmap,
 +                           arg->has_bitmap_mode, arg->bitmap_mode,
                             backing_mode, zero_target,
                             arg->has_speed, arg->speed,
                             arg->has_granularity, arg->granularity,
-@@ -3237,6 +3267,8 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
+@@ -3053,6 +3082,8 @@ void qmp_blockdev_mirror(const char *job_id,
                           const char *device, const char *target,
-                          bool has_replaces, const char *replaces,
+                          const char *replaces,
                           MirrorSyncMode sync,
-+                         bool has_bitmap, const char *bitmap,
++                         const char *bitmap,
 +                         bool has_bitmap_mode, BitmapSyncMode bitmap_mode,
                           bool has_speed, int64_t speed,
                           bool has_granularity, uint32_t granularity,
                           bool has_buf_size, int64_t buf_size,
-@@ -3286,7 +3318,8 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
+@@ -3093,7 +3124,8 @@ void qmp_blockdev_mirror(const char *job_id,
      }
  
-     blockdev_mirror_common(has_job_id ? job_id : NULL, bs, target_bs,
--                           has_replaces, replaces, sync, backing_mode,
-+                           has_replaces, replaces, sync, has_bitmap,
+     blockdev_mirror_common(job_id, bs, target_bs,
+-                           replaces, sync, backing_mode,
++                           replaces, sync,
 +                           bitmap, has_bitmap_mode, bitmap_mode, backing_mode,
                             zero_target, has_speed, speed,
                             has_granularity, granularity,
                             has_buf_size, buf_size,
 diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h
-index b49f4eb35b..9d744db618 100644
+index d2201e27f4..cc1387ae02 100644
 --- a/include/block/block_int-global-state.h
 +++ b/include/block/block_int-global-state.h
-@@ -149,7 +149,9 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
+@@ -158,7 +158,9 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                    BlockDriverState *target, const char *replaces,
                    int creation_flags, int64_t speed,
                    uint32_t granularity, int64_t buf_size,
@@ -359,31 +364,26 @@ index b49f4eb35b..9d744db618 100644
                    BlockdevOnError on_source_error,
                    BlockdevOnError on_target_error,
 diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 2173e7734a..e1857e7094 100644
+index 746d1694c2..45ab548dfe 100644
 --- a/qapi/block-core.json
 +++ b/qapi/block-core.json
-@@ -2000,10 +2000,19 @@
- #        (all the disk, only the sectors allocated in the topmost image, or
- #        only new I/O).
+@@ -2174,6 +2174,15 @@
+ #     destination (all the disk, only the sectors allocated in the
+ #     topmost image, or only new I/O).
  #
-+# @bitmap: The name of a bitmap to use for sync=bitmap mode. This argument must
-+#          be present for bitmap mode and absent otherwise. The bitmap's
-+#          granularity is used instead of @granularity (since 4.1).
++# @bitmap: The name of a bitmap to use for sync=bitmap mode. This
++#     argument must be present for bitmap mode and absent otherwise.
++#     The bitmap's granularity is used instead of @granularity (Since
++#     4.1).
 +#
-+# @bitmap-mode: Specifies the type of data the bitmap should contain after
-+#               the operation concludes. Must be present if sync is "bitmap".
-+#               Must NOT be present otherwise. (Since 4.1)
++# @bitmap-mode: Specifies the type of data the bitmap should contain
++#     after the operation concludes. Must be present if sync is
++#     "bitmap". Must NOT be present otherwise. (Since 4.1)
 +#
- # @granularity: granularity of the dirty bitmap, default is 64K
- #               if the image format doesn't have clusters, 4K if the clusters
- #               are smaller than that, else the cluster size.  Must be a
--#               power of 2 between 512 and 64M (since 1.4).
-+#               power of 2 between 512 and 64M. Must not be specified if
-+#               @bitmap is present (since 1.4).
- #
- # @buf-size: maximum amount of data in flight from source to
- #            target (since 1.4).
-@@ -2043,7 +2052,9 @@
+ # @granularity: granularity of the dirty bitmap, default is 64K if the
+ #     image format doesn't have clusters, 4K if the clusters are
+ #     smaller than that, else the cluster size.  Must be a power of 2
+@@ -2216,7 +2225,9 @@
  { 'struct': 'DriveMirror',
    'data': { '*job-id': 'str', 'device': 'str', 'target': 'str',
              '*format': 'str', '*node-name': 'str', '*replaces': 'str',
@@ -394,28 +394,23 @@ index 2173e7734a..e1857e7094 100644
              '*speed': 'int', '*granularity': 'uint32',
              '*buf-size': 'int', '*on-source-error': 'BlockdevOnError',
              '*on-target-error': 'BlockdevOnError',
-@@ -2322,10 +2333,19 @@
- #        (all the disk, only the sectors allocated in the topmost image, or
- #        only new I/O).
+@@ -2496,6 +2507,15 @@
+ #     destination (all the disk, only the sectors allocated in the
+ #     topmost image, or only new I/O).
  #
-+# @bitmap: The name of a bitmap to use for sync=bitmap mode. This argument must
-+#          be present for bitmap mode and absent otherwise. The bitmap's
-+#          granularity is used instead of @granularity (since 4.1).
++# @bitmap: The name of a bitmap to use for sync=bitmap mode. This
++#     argument must be present for bitmap mode and absent otherwise.
++#     The bitmap's granularity is used instead of @granularity (since
++#     4.1).
 +#
-+# @bitmap-mode: Specifies the type of data the bitmap should contain after
-+#               the operation concludes. Must be present if sync is "bitmap".
-+#               Must NOT be present otherwise. (Since 4.1)
++# @bitmap-mode: Specifies the type of data the bitmap should contain
++#     after the operation concludes. Must be present if sync is
++#     "bitmap". Must NOT be present otherwise. (Since 4.1)
 +#
- # @granularity: granularity of the dirty bitmap, default is 64K
- #               if the image format doesn't have clusters, 4K if the clusters
- #               are smaller than that, else the cluster size.  Must be a
--#               power of 2 between 512 and 64M
-+#               power of 2 between 512 and 64M . Must not be specified if
-+#               @bitmap is present.
- #
- # @buf-size: maximum amount of data in flight from source to
- #            target
-@@ -2375,7 +2395,8 @@
+ # @granularity: granularity of the dirty bitmap, default is 64K if the
+ #     image format doesn't have clusters, 4K if the clusters are
+ #     smaller than that, else the cluster size.  Must be a power of 2
+@@ -2544,7 +2564,8 @@
  { 'command': 'blockdev-mirror',
    'data': { '*job-id': 'str', 'device': 'str', 'target': 'str',
              '*replaces': 'str',
@@ -426,10 +421,10 @@ index 2173e7734a..e1857e7094 100644
              '*buf-size': 'int', '*on-source-error': 'BlockdevOnError',
              '*on-target-error': 'BlockdevOnError',
 diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c
-index 8b55eccc89..f4650be8e5 100644
+index 3766d5de6b..afa44cbd34 100644
 --- a/tests/unit/test-block-iothread.c
 +++ b/tests/unit/test-block-iothread.c
-@@ -753,8 +753,8 @@ static void test_propagate_mirror(void)
+@@ -755,8 +755,8 @@ static void test_propagate_mirror(void)
  
      /* Start a mirror job */
      mirror_start("job0", src, target, NULL, JOB_DEFAULT, 0, 0, 0,
@@ -439,4 +434,4 @@ index 8b55eccc89..f4650be8e5 100644
 +                 false, BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
                   false, "filter_node", MIRROR_COPY_MODE_BACKGROUND,
                   &error_abort);
-     job = job_get("job0");
+ 

debian/patches/bitmap-mirror/0002-drive-mirror-add-support-for-conditional-and-always-.patch

@@ -24,10 +24,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 18 insertions(+), 6 deletions(-)
 
 diff --git a/block/mirror.c b/block/mirror.c
-index f2eca983f1..b6475d50ad 100644
+index 0c5c72df2e..37fee3fa25 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -673,8 +673,6 @@ static int mirror_exit_common(Job *job)
+@@ -693,8 +693,6 @@ static int mirror_exit_common(Job *job)
          bdrv_unfreeze_backing_chain(mirror_top_bs, target_bs);
      }
  
@@ -36,9 +36,9 @@ index f2eca983f1..b6475d50ad 100644
      /* Make sure that the source BDS doesn't go away during bdrv_replace_node,
       * before we can call bdrv_drained_end */
      bdrv_ref(src);
-@@ -775,6 +773,18 @@ static int mirror_exit_common(Job *job)
-     block_job_remove_all_bdrv(bjob);
-     bdrv_replace_node(mirror_top_bs, mirror_top_bs->backing->bs, &error_abort);
+@@ -800,6 +798,18 @@ static int mirror_exit_common(Job *job)
+     bdrv_drained_end(target_bs);
+     bdrv_unref(target_bs);
  
 +    if (s->sync_bitmap) {
 +        if (s->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS ||
@@ -55,7 +55,7 @@ index f2eca983f1..b6475d50ad 100644
      bs_opaque->job = NULL;
  
      bdrv_drained_end(src);
-@@ -1634,10 +1644,6 @@ static BlockJob *mirror_start_job(
+@@ -1757,10 +1767,6 @@ static BlockJob *mirror_start_job(
                         " sync mode",
                         MirrorSyncMode_str(sync_mode));
              return NULL;
@@ -66,7 +66,7 @@ index f2eca983f1..b6475d50ad 100644
          }
      } else if (bitmap) {
          error_setg(errp,
-@@ -1654,6 +1660,12 @@ static BlockJob *mirror_start_job(
+@@ -1777,6 +1783,12 @@ static BlockJob *mirror_start_job(
              return NULL;
          }
          granularity = bdrv_dirty_bitmap_granularity(bitmap);

debian/patches/bitmap-mirror/0003-mirror-add-check-for-bitmap-mode-without-bitmap.patch

@@ -16,10 +16,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 3 insertions(+)
 
 diff --git a/blockdev.c b/blockdev.c
-index 9a1a3118ed..a57b0af2e7 100644
+index 8682814a7a..5b75a085ee 100644
 --- a/blockdev.c
 +++ b/blockdev.c
-@@ -3050,6 +3050,9 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
+@@ -2873,6 +2873,9 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
          if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_ALLOW_RO, errp)) {
              return;
          }
@@ -28,4 +28,4 @@ index 9a1a3118ed..a57b0af2e7 100644
 +        return;
      }
  
-     if (!has_replaces) {
+     if (!replaces) {

debian/patches/bitmap-mirror/0004-mirror-switch-to-bdrv_dirty_bitmap_merge_internal.patch

@@ -16,10 +16,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 4 insertions(+), 7 deletions(-)
 
 diff --git a/block/mirror.c b/block/mirror.c
-index b6475d50ad..8b3342f9ec 100644
+index 37fee3fa25..6b3cce1007 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -779,8 +779,8 @@ static int mirror_exit_common(Job *job)
+@@ -804,8 +804,8 @@ static int mirror_exit_common(Job *job)
               job->ret == 0 && ret == 0)) {
              /* Success; synchronize copy back to sync. */
              bdrv_clear_dirty_bitmap(s->sync_bitmap, NULL);
@@ -30,7 +30,7 @@ index b6475d50ad..8b3342f9ec 100644
          }
      }
      bdrv_release_dirty_bitmap(s->dirty_bitmap);
-@@ -1828,11 +1828,8 @@ static BlockJob *mirror_start_job(
+@@ -1964,11 +1964,8 @@ static BlockJob *mirror_start_job(
      }
  
      if (s->sync_mode == MIRROR_SYNC_MODE_BITMAP) {
@@ -43,4 +43,4 @@ index b6475d50ad..8b3342f9ec 100644
 +                                         NULL, true);
      }
  
-     ret = block_job_add_bdrv(&s->common, "source", bs, 0,
+     bdrv_graph_wrlock();

debian/patches/bitmap-mirror/0006-mirror-move-some-checks-to-qmp.patch

@@ -12,6 +12,8 @@ uniform w.r.t. backup block jobs.
 
 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: rebase for 8.2.2]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  block/mirror.c             | 28 +++------------
  blockdev.c                 | 29 +++++++++++++++
@@ -19,12 +21,12 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  3 files changed, 70 insertions(+), 59 deletions(-)
 
 diff --git a/block/mirror.c b/block/mirror.c
-index 8b3342f9ec..1d4ff0efad 100644
+index 6b3cce1007..2f1223852b 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -1634,31 +1634,13 @@ static BlockJob *mirror_start_job(
-     uint64_t target_perms, target_shared_perms;
-     int ret;
+@@ -1757,31 +1757,13 @@ static BlockJob *mirror_start_job(
+ 
+     GLOBAL_STATE_CODE();
  
 -    if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
 -        error_setg(errp, "Sync mode '%s' not supported",
@@ -60,17 +62,17 @@ index 8b3342f9ec..1d4ff0efad 100644
  
          if (bitmap_mode != BITMAP_SYNC_MODE_NEVER) {
 diff --git a/blockdev.c b/blockdev.c
-index a57b0af2e7..ce62a9b439 100644
+index 5b75a085ee..d27d8c38ec 100644
 --- a/blockdev.c
 +++ b/blockdev.c
-@@ -3029,7 +3029,36 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
+@@ -2852,7 +2852,36 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
          sync = MIRROR_SYNC_MODE_FULL;
      }
  
 +    if ((sync == MIRROR_SYNC_MODE_BITMAP) ||
 +        (sync == MIRROR_SYNC_MODE_INCREMENTAL)) {
 +        /* done before desugaring 'incremental' to print the right message */
-+        if (!has_bitmap) {
++        if (!bitmap_name) {
 +            error_setg(errp, "Must provide a valid bitmap name for "
 +                       "'%s' sync mode", MirrorSyncMode_str(sync));
 +            return;
@@ -91,7 +93,7 @@ index a57b0af2e7..ce62a9b439 100644
 +        bitmap_mode = BITMAP_SYNC_MODE_ON_SUCCESS;
 +    }
 +
-     if (has_bitmap) {
+     if (bitmap_name) {
 +        if (sync != MIRROR_SYNC_MODE_BITMAP) {
 +            error_setg(errp, "Sync mode '%s' not supported with bitmap.",
 +                       MirrorSyncMode_str(sync));

debian/patches/extra/0001-monitor-qmp-fix-race-with-clients-disconnecting-earl.patch

@@ -48,7 +48,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  6 files changed, 59 insertions(+), 5 deletions(-)
 
 diff --git a/include/monitor/monitor.h b/include/monitor/monitor.h
-index a4b40e8391..d64ae8f34e 100644
+index 965f5d5450..e04bd059b6 100644
 --- a/include/monitor/monitor.h
 +++ b/include/monitor/monitor.h
 @@ -16,6 +16,7 @@ extern QemuOptsList qemu_mon_opts;
@@ -60,10 +60,10 @@ index a4b40e8391..d64ae8f34e 100644
  void monitor_init_globals(void);
  void monitor_init_globals_core(void);
 diff --git a/monitor/monitor-internal.h b/monitor/monitor-internal.h
-index caa2e90ef2..e1596f79ab 100644
+index 252de85681..8db28f9272 100644
 --- a/monitor/monitor-internal.h
 +++ b/monitor/monitor-internal.h
-@@ -152,6 +152,13 @@ typedef struct {
+@@ -151,6 +151,13 @@ typedef struct {
      QemuMutex qmp_queue_lock;
      /* Input queue that holds all the parsed QMP requests */
      GQueue *qmp_requests;
@@ -78,10 +78,10 @@ index caa2e90ef2..e1596f79ab 100644
  
  /**
 diff --git a/monitor/monitor.c b/monitor/monitor.c
-index 86949024f6..c306cadcf4 100644
+index 01ede1babd..5681bca346 100644
 --- a/monitor/monitor.c
 +++ b/monitor/monitor.c
-@@ -135,6 +135,21 @@ bool monitor_cur_is_qmp(void)
+@@ -117,6 +117,21 @@ bool monitor_cur_is_qmp(void)
      return cur_mon && monitor_is_qmp(cur_mon);
  }
  
@@ -104,10 +104,10 @@ index 86949024f6..c306cadcf4 100644
   * Is @mon is using readline?
   * Note: not all HMP monitors use readline, e.g., gdbserver has a
 diff --git a/monitor/qmp.c b/monitor/qmp.c
-index 092c527b6f..6b8cfcf6d8 100644
+index a239945e8d..589c9524f8 100644
 --- a/monitor/qmp.c
 +++ b/monitor/qmp.c
-@@ -141,6 +141,8 @@ static void monitor_qmp_dispatch(MonitorQMP *mon, QObject *req)
+@@ -165,6 +165,8 @@ static void monitor_qmp_dispatch(MonitorQMP *mon, QObject *req)
      QDict *rsp;
      QDict *error;
  
@@ -116,7 +116,7 @@ index 092c527b6f..6b8cfcf6d8 100644
      rsp = qmp_dispatch(mon->commands, req, qmp_oob_enabled(mon),
                         &mon->common);
  
-@@ -156,7 +158,17 @@ static void monitor_qmp_dispatch(MonitorQMP *mon, QObject *req)
+@@ -180,7 +182,17 @@ static void monitor_qmp_dispatch(MonitorQMP *mon, QObject *req)
          }
      }
  
@@ -135,7 +135,7 @@ index 092c527b6f..6b8cfcf6d8 100644
      qobject_unref(rsp);
  }
  
-@@ -444,6 +456,7 @@ static void monitor_qmp_event(void *opaque, QEMUChrEvent event)
+@@ -461,6 +473,7 @@ static void monitor_qmp_event(void *opaque, QEMUChrEvent event)
  
      switch (event) {
      case CHR_EVENT_OPENED:
@@ -144,7 +144,7 @@ index 092c527b6f..6b8cfcf6d8 100644
          monitor_qmp_caps_reset(mon);
          data = qmp_greeting(mon);
 diff --git a/qapi/qmp-dispatch.c b/qapi/qmp-dispatch.c
-index 0990873ec8..e605003771 100644
+index f3488afeef..2624eb3470 100644
 --- a/qapi/qmp-dispatch.c
 +++ b/qapi/qmp-dispatch.c
 @@ -117,16 +117,28 @@ typedef struct QmpDispatchBH {
@@ -180,13 +180,13 @@ index 0990873ec8..e605003771 100644
      aio_co_wake(data->co);
  }
  
-@@ -231,6 +243,7 @@ QDict *qmp_dispatch(const QmpCommandList *cmds, QObject *request,
+@@ -250,6 +262,7 @@ QDict *coroutine_mixed_fn qmp_dispatch(const QmpCommandList *cmds, QObject *requ
              .ret        = &ret,
              .errp       = &err,
              .co         = qemu_coroutine_self(),
 +            .conn_nr    = monitor_get_connection_nr(cur_mon),
          };
-         aio_bh_schedule_oneshot(qemu_get_aio_context(), do_qmp_dispatch_bh,
+         aio_bh_schedule_oneshot(iohandler_get_aio_context(), do_qmp_dispatch_bh,
                                  &data);
 diff --git a/stubs/monitor-core.c b/stubs/monitor-core.c
 index afa477aae6..d3ff124bf3 100644

debian/patches/extra/0002-block-io_uring-revert-Use-io_uring_register_ring_fd-.patch

@@ -1,76 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Sam Li <faithilikerun@gmail.com>
-Date: Sat, 24 Sep 2022 22:48:15 +0800
-Subject: [PATCH] block/io_uring: revert "Use io_uring_register_ring_fd() to
- skip fd operations"
-
-Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1193
-
-The commit "Use io_uring_register_ring_fd() to skip fd operations" broke
-when booting a guest with iothread and io_uring. That is because the
-io_uring_register_ring_fd() call is made from the main thread instead of
-IOThread where io_uring_submit() is called. It can not be guaranteed
-to register the ring fd in the correct thread or unregister the same ring
-fd if the IOThread is disabled. This optimization is not critical so we
-will revert previous commit.
-
-This reverts commit e2848bc574fe2715c694bf8fe9a1ba7f78a1125a
-and 77e3f038af1764983087e3551a0fde9951952c4d.
-
-Signed-off-by: Sam Li <faithilikerun@gmail.com>
----
- block/io_uring.c | 13 +------------
- meson.build      |  1 -
- 2 files changed, 1 insertion(+), 13 deletions(-)
-
-diff --git a/block/io_uring.c b/block/io_uring.c
-index a1760152e0..973e15d876 100644
---- a/block/io_uring.c
-+++ b/block/io_uring.c
-@@ -11,7 +11,6 @@
- #include "qemu/osdep.h"
- #include <liburing.h>
- #include "block/aio.h"
--#include "qemu/error-report.h"
- #include "qemu/queue.h"
- #include "block/block.h"
- #include "block/raw-aio.h"
-@@ -19,7 +18,6 @@
- #include "qapi/error.h"
- #include "trace.h"
- 
--
- /* io_uring ring size */
- #define MAX_ENTRIES 128
- 
-@@ -432,17 +430,8 @@ LuringState *luring_init(Error **errp)
-     }
- 
-     ioq_init(&s->io_q);
--#ifdef CONFIG_LIBURING_REGISTER_RING_FD
--    if (io_uring_register_ring_fd(&s->ring) < 0) {
--        /*
--         * Only warn about this error: we will fallback to the non-optimized
--         * io_uring operations.
--         */
--        warn_report("failed to register linux io_uring ring file descriptor");
--    }
--#endif
--
-     return s;
-+
- }
- 
- void luring_cleanup(LuringState *s)
-diff --git a/meson.build b/meson.build
-index 20fddbd707..d5230eadd6 100644
---- a/meson.build
-+++ b/meson.build
-@@ -1793,7 +1793,6 @@ config_host_data.set('CONFIG_LIBNFS', libnfs.found())
- config_host_data.set('CONFIG_LIBSSH', libssh.found())
- config_host_data.set('CONFIG_LINUX_AIO', libaio.found())
- config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found())
--config_host_data.set('CONFIG_LIBURING_REGISTER_RING_FD', cc.has_function('io_uring_register_ring_fd', prefix: '#include <liburing.h>', dependencies:linux_io_uring))
- config_host_data.set('CONFIG_LIBPMEM', libpmem.found())
- config_host_data.set('CONFIG_NUMA', numa.found())
- config_host_data.set('CONFIG_OPENGL', opengl.found())

debian/patches/extra/0002-scsi-megasas-Internal-cdbs-have-16-byte-length.patch

@@ -0,0 +1,69 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Guenter Roeck <linux@roeck-us.net>
+Date: Tue, 28 Feb 2023 09:11:29 -0800
+Subject: [PATCH] scsi: megasas: Internal cdbs have 16-byte length
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Host drivers do not necessarily set cdb_len in megasas io commands.
+With commits 6d1511cea0 ("scsi: Reject commands if the CDB length
+exceeds buf_len") and fe9d8927e2 ("scsi: Add buf_len parameter to
+scsi_req_new()"), this results in failures to boot Linux from affected
+SCSI drives because cdb_len is set to 0 by the host driver.
+Set the cdb length to its actual size to solve the problem.
+
+Signed-off-by: Guenter Roeck <linux@roeck-us.net>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+(picked-up from https://lists.nongnu.org/archive/html/qemu-devel/2023-02/msg08653.html)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/scsi/megasas.c | 14 ++------------
+ 1 file changed, 2 insertions(+), 12 deletions(-)
+
+diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c
+index 2d0c607177..97e51733af 100644
+--- a/hw/scsi/megasas.c
++++ b/hw/scsi/megasas.c
+@@ -1781,7 +1781,7 @@ static int megasas_handle_io(MegasasState *s, MegasasCmd *cmd, int frame_cmd)
+     uint8_t cdb[16];
+     int len;
+     struct SCSIDevice *sdev = NULL;
+-    int target_id, lun_id, cdb_len;
++    int target_id, lun_id;
+ 
+     lba_count = le32_to_cpu(cmd->frame->io.header.data_len);
+     lba_start_lo = le32_to_cpu(cmd->frame->io.lba_lo);
+@@ -1790,7 +1790,6 @@ static int megasas_handle_io(MegasasState *s, MegasasCmd *cmd, int frame_cmd)
+ 
+     target_id = cmd->frame->header.target_id;
+     lun_id = cmd->frame->header.lun_id;
+-    cdb_len = cmd->frame->header.cdb_len;
+ 
+     if (target_id < MFI_MAX_LD && lun_id == 0) {
+         sdev = scsi_device_find(&s->bus, 0, target_id, lun_id);
+@@ -1805,15 +1804,6 @@ static int megasas_handle_io(MegasasState *s, MegasasCmd *cmd, int frame_cmd)
+         return MFI_STAT_DEVICE_NOT_FOUND;
+     }
+ 
+-    if (cdb_len > 16) {
+-        trace_megasas_scsi_invalid_cdb_len(
+-            mfi_frame_desc(frame_cmd), 1, target_id, lun_id, cdb_len);
+-        megasas_write_sense(cmd, SENSE_CODE(INVALID_OPCODE));
+-        cmd->frame->header.scsi_status = CHECK_CONDITION;
+-        s->event_count++;
+-        return MFI_STAT_SCSI_DONE_WITH_ERROR;
+-    }
+-
+     cmd->iov_size = lba_count * sdev->blocksize;
+     if (megasas_map_sgl(s, cmd, &cmd->frame->io.sgl)) {
+         megasas_write_sense(cmd, SENSE_CODE(TARGET_FAILURE));
+@@ -1824,7 +1814,7 @@ static int megasas_handle_io(MegasasState *s, MegasasCmd *cmd, int frame_cmd)
+ 
+     megasas_encode_lba(cdb, lba_start, lba_count, is_write);
+     cmd->req = scsi_req_new(sdev, cmd->index,
+-                            lun_id, cdb, cdb_len, cmd);
++                            lun_id, cdb, sizeof(cdb), cmd);
+     if (!cmd->req) {
+         trace_megasas_scsi_req_alloc_failed(
+             mfi_frame_desc(frame_cmd), target_id, lun_id);

debian/patches/extra/0003-ide-avoid-potential-deadlock-when-draining-during-tr.patch

@@ -0,0 +1,100 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Tue, 7 Mar 2023 15:03:02 +0100
+Subject: [PATCH] ide: avoid potential deadlock when draining during trim
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+The deadlock can happen as follows:
+1. ide_issue_trim is called, and increments the in_flight counter.
+2. ide_issue_trim_cb calls blk_aio_pdiscard.
+3. Somebody else starts draining (e.g. backup to insert the cbw node).
+4. ide_issue_trim_cb is called as the completion callback for
+   blk_aio_pdiscard.
+5. ide_issue_trim_cb issues yet another blk_aio_pdiscard request.
+6. The request is added to the wait queue via blk_wait_while_drained,
+   because draining has been started.
+7. Nobody ever decrements the in_flight counter and draining can't
+   finish. This would be done by ide_trim_bh_cb, which is called after
+   ide_issue_trim_cb has issued its last request, but
+   ide_issue_trim_cb is not called anymore, because it's the
+   completion callback of blk_aio_pdiscard, which waits on draining.
+
+Quoting Hanna Czenczek:
+> The point of 7e5cdb345f was that we need any in-flight count to
+> accompany a set s->bus->dma->aiocb. While blk_aio_pdiscard() is
+> happening, we don’t necessarily need another count. But we do need
+> it while there is no blk_aio_pdiscard().
+> ide_issue_trim_cb() returns in two cases (and, recursively through
+> its callers, leaves s->bus->dma->aiocb set):
+> 1. After calling blk_aio_pdiscard(), which will keep an in-flight
+>    count,
+> 2. After calling replay_bh_schedule_event() (i.e.
+>    qemu_bh_schedule()), which does not keep an in-flight count.
+
+Thus, even after moving the blk_inc_in_flight to above the
+replay_bh_schedule_event call, the invariant "ide_issue_trim_cb
+returns with an accompanying in-flight count" is still satisfied.
+
+However, the issue 7e5cdb345f fixed for canceling resurfaces, because
+ide_cancel_dma_sync assumes that it just needs to drain once. But now
+the in_flight count is not consistently > 0 during the trim operation.
+So, change it to drain until !s->bus->dma->aiocb, which means that the
+operation finished (s->bus->dma->aiocb is cleared by ide_set_inactive
+via the ide_dma_cb when the end of the transfer is reached).
+
+Discussion here:
+https://lists.nongnu.org/archive/html/qemu-devel/2023-03/msg02506.html
+
+Fixes: 7e5cdb345f ("ide: Increment BB in-flight counter for TRIM BH")
+Suggested-by: Hanna Czenczek <hreitz@redhat.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/ide/core.c | 12 ++++++------
+ 1 file changed, 6 insertions(+), 6 deletions(-)
+
+diff --git a/hw/ide/core.c b/hw/ide/core.c
+index e8cb2dac92..3b21acf651 100644
+--- a/hw/ide/core.c
++++ b/hw/ide/core.c
+@@ -456,7 +456,7 @@ static void ide_trim_bh_cb(void *opaque)
+     iocb->bh = NULL;
+     qemu_aio_unref(iocb);
+ 
+-    /* Paired with an increment in ide_issue_trim() */
++    /* Paired with an increment in ide_issue_trim_cb() */
+     blk_dec_in_flight(blk);
+ }
+ 
+@@ -516,6 +516,8 @@ static void ide_issue_trim_cb(void *opaque, int ret)
+ done:
+     iocb->aiocb = NULL;
+     if (iocb->bh) {
++        /* Paired with a decrement in ide_trim_bh_cb() */
++        blk_inc_in_flight(s->blk);
+         replay_bh_schedule_event(iocb->bh);
+     }
+ }
+@@ -528,9 +530,6 @@ BlockAIOCB *ide_issue_trim(
+     IDEDevice *dev = s->unit ? s->bus->slave : s->bus->master;
+     TrimAIOCB *iocb;
+ 
+-    /* Paired with a decrement in ide_trim_bh_cb() */
+-    blk_inc_in_flight(s->blk);
+-
+     iocb = blk_aio_get(&trim_aiocb_info, s->blk, cb, cb_opaque);
+     iocb->s = s;
+     iocb->bh = qemu_bh_new_guarded(ide_trim_bh_cb, iocb,
+@@ -754,8 +753,9 @@ void ide_cancel_dma_sync(IDEState *s)
+      */
+     if (s->bus->dma->aiocb) {
+         trace_ide_cancel_dma_sync_remaining();
+-        blk_drain(s->blk);
+-        assert(s->bus->dma->aiocb == NULL);
++        while (s->bus->dma->aiocb) {
++            blk_drain(s->blk);
++        }
+     }
+ }
+ 

debian/patches/extra/0003-virtiofsd-use-g_date_time_get_microsecond-to-get-sub.patch

@@ -1,51 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Yusuke Okada <okada.yusuke@jp.fujitsu.com>
-Date: Thu, 18 Aug 2022 14:46:19 -0400
-Subject: [PATCH] virtiofsd: use g_date_time_get_microsecond to get subsecond
-
-The "%f" specifier in g_date_time_format() is only available in glib
-2.65.2 or later. If combined with older glib, the function returns null
-and the timestamp displayed as "(null)".
-
-For backward compatibility, g_date_time_get_microsecond should be used
-to retrieve subsecond.
-
-In this patch the g_date_time_format() leaves subsecond field as "%06d"
-and let next snprintf to format with g_date_time_get_microsecond.
-
-Signed-off-by: Yusuke Okada <okada.yusuke@jp.fujitsu.com>
-Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
-Message-id: 20220818184618.2205172-1-yokada.996@gmail.com
-Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
-(cherry-picked from commit f16d15c9276bd8f501f861c39cbd4adc812d0c1d)
-Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
----
- tools/virtiofsd/passthrough_ll.c | 7 +++++--
- 1 file changed, 5 insertions(+), 2 deletions(-)
-
-diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c
-index 371a7bead6..20f0f41f99 100644
---- a/tools/virtiofsd/passthrough_ll.c
-+++ b/tools/virtiofsd/passthrough_ll.c
-@@ -4185,6 +4185,7 @@ static void setup_nofile_rlimit(unsigned long rlimit_nofile)
- static void log_func(enum fuse_log_level level, const char *fmt, va_list ap)
- {
-     g_autofree char *localfmt = NULL;
-+    char buf[64];
- 
-     if (current_log_level < level) {
-         return;
-@@ -4197,9 +4198,11 @@ static void log_func(enum fuse_log_level level, const char *fmt, va_list ap)
-                                        fmt);
-         } else {
-             g_autoptr(GDateTime) now = g_date_time_new_now_utc();
--            g_autofree char *nowstr = g_date_time_format(now, "%Y-%m-%d %H:%M:%S.%f%z");
-+            g_autofree char *nowstr = g_date_time_format(now,
-+                                       "%Y-%m-%d %H:%M:%S.%%06d%z");
-+            snprintf(buf, 64, nowstr, g_date_time_get_microsecond(now));
-             localfmt = g_strdup_printf("[%s] [ID: %08ld] %s",
--                                       nowstr, syscall(__NR_gettid), fmt);
-+                                       buf, syscall(__NR_gettid), fmt);
-         }
-         fmt = localfmt;
-     }

debian/patches/extra/0004-Revert-x86-acpi-workaround-Windows-not-handling-name.patch

@@ -0,0 +1,45 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Fri, 17 Nov 2023 11:18:06 +0100
+Subject: [PATCH] Revert "x86: acpi: workaround Windows not handling name
+ references in Package properly"
+
+This reverts commit 44d975ef340e2f21f236f9520c53e1b30d2213a4.
+
+As reported in the community forum [0] and reproduced locally this
+breaks VirtIO network adapters in (at least) the German ISO of Windows
+Server 2022. The fix itself was for
+
+> Issue is not fatal but as result acpi-index/"PCI Label ID" property
+> is either not shown in device details page or shows incorrect value.
+
+so revert and tolerate that as a stop-gap, rather than have the
+devices not working at all.
+
+[0]: https://forum.proxmox.com/threads/92094/post-605684
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/i386/acpi-build.c | 8 ++------
+ 1 file changed, 2 insertions(+), 6 deletions(-)
+
+diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
+index 53f804ac16..9b1b9f0412 100644
+--- a/hw/i386/acpi-build.c
++++ b/hw/i386/acpi-build.c
+@@ -347,13 +347,9 @@ Aml *aml_pci_device_dsm(void)
+     {
+         Aml *params = aml_local(0);
+         Aml *pkg = aml_package(2);
+-        aml_append(pkg, aml_int(0));
+-        aml_append(pkg, aml_int(0));
++        aml_append(pkg, aml_name("BSEL"));
++        aml_append(pkg, aml_name("ASUN"));
+         aml_append(method, aml_store(pkg, params));
+-        aml_append(method,
+-            aml_store(aml_name("BSEL"), aml_index(params, aml_int(0))));
+-        aml_append(method,
+-            aml_store(aml_name("ASUN"), aml_index(params, aml_int(1))));
+         aml_append(method,
+             aml_return(aml_call5("PDSM", aml_arg(0), aml_arg(1),
+                                  aml_arg(2), aml_arg(3), params))

debian/patches/extra/0004-chardev-fix-segfault-in-finalize.patch

@@ -1,56 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Maksim Davydov <davydov-max@yandex-team.ru>
-Date: Thu, 25 Aug 2022 19:52:47 +0300
-Subject: [PATCH] chardev: fix segfault in finalize
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-If finalize chardev-msmouse or chardev-wctable is called immediately after
-init it cases QEMU to crash with segfault. This happens because of
-QTAILQ_REMOVE in qemu_input_handler_unregister tries to dereference
-NULL pointer.
-For instance, this error can be reproduced via `qom-list-properties`
-command.
-
-Signed-off-by: Maksim Davydov <davydov-max@yandex-team.ru>
-Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
-Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
-Message-Id: <20220825165247.33704-1-davydov-max@yandex-team.ru>
-(trivial backport from fc0c128531ed55f058bfbad4f1348ebd9a0187f2)
-Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
----
- chardev/msmouse.c  | 4 +++-
- chardev/wctablet.c | 4 +++-
- 2 files changed, 6 insertions(+), 2 deletions(-)
-
-diff --git a/chardev/msmouse.c b/chardev/msmouse.c
-index eb9231dcdb..2cc1b16561 100644
---- a/chardev/msmouse.c
-+++ b/chardev/msmouse.c
-@@ -146,7 +146,9 @@ static void char_msmouse_finalize(Object *obj)
- {
-     MouseChardev *mouse = MOUSE_CHARDEV(obj);
- 
--    qemu_input_handler_unregister(mouse->hs);
-+    if (mouse->hs) {
-+        qemu_input_handler_unregister(mouse->hs);
-+    }
- }
- 
- static QemuInputHandler msmouse_handler = {
-diff --git a/chardev/wctablet.c b/chardev/wctablet.c
-index e8b292c43c..43bdf6b608 100644
---- a/chardev/wctablet.c
-+++ b/chardev/wctablet.c
-@@ -319,7 +319,9 @@ static void wctablet_chr_finalize(Object *obj)
- {
-     TabletChardev *tablet = WCTABLET_CHARDEV(obj);
- 
--    qemu_input_handler_unregister(tablet->hs);
-+    if (tablet->hs) {
-+        qemu_input_handler_unregister(tablet->hs);
-+    }
- }
- 
- static void wctablet_chr_open(Chardev *chr,

debian/patches/extra/0005-block-copy-before-write-use-uint64_t-for-timeout-in-.patch

@@ -0,0 +1,35 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Mon, 29 Apr 2024 15:41:11 +0200
+Subject: [PATCH] block/copy-before-write: use uint64_t for timeout in
+ nanoseconds
+
+rather than the uint32_t for which the maximum is slightly more than 4
+seconds and larger values would overflow. The QAPI interface allows
+specifying the number of seconds, so only values 0 to 4 are safe right
+now, other values lead to a much lower timeout than a user expects.
+
+The block_copy() call where this is used already takes a uint64_t for
+the timeout, so no change required there.
+
+Fixes: 6db7fd1ca9 ("block/copy-before-write: implement cbw-timeout option")
+Reported-by: Friedrich Weber <f.weber@proxmox.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Tested-by: Friedrich Weber <f.weber@proxmox.com>
+---
+ block/copy-before-write.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index 8aba27a71d..026fa9840f 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -43,7 +43,7 @@ typedef struct BDRVCopyBeforeWriteState {
+     BlockCopyState *bcs;
+     BdrvChild *target;
+     OnCbwError on_cbw_error;
+-    uint32_t cbw_timeout_ns;
++    uint64_t cbw_timeout_ns;
+ 
+     /*
+      * @lock: protects access to @access_bitmap, @done_bitmap and

debian/patches/extra/0005-init-daemonize-defuse-PID-file-resolve-error.patch

@@ -1,42 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fiona Ebner <f.ebner@proxmox.com>
-Date: Fri, 28 Oct 2022 10:09:46 +0200
-Subject: [PATCH] init: daemonize: defuse PID file resolve error
-
-When proxmox-file-restore invokes QEMU, the PID file is a (temporary)
-file that's already unlinked, so resolving the absolute path here
-failed.
-
-It should not be a critical error when the PID file unlink handler
-can't be registered, because the path can't be resolved for whatever
-reason. If the file is already gone from QEMU's perspective (i.e.
-errno is ENOENT), silently ignore the error. Otherwise, print a
-warning.
-
-Reported-by: Dominik Csapak <d.csapak@proxmox.com>
-Suggested-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
----
- softmmu/vl.c | 9 +++++----
- 1 file changed, 5 insertions(+), 4 deletions(-)
-
-diff --git a/softmmu/vl.c b/softmmu/vl.c
-index 706bd7cff7..3381c56af7 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -2438,10 +2438,11 @@ static void qemu_maybe_daemonize(const char *pid_file)
- 
-         pid_file_realpath = g_malloc0(PATH_MAX);
-         if (!realpath(pid_file, pid_file_realpath)) {
--            error_report("cannot resolve PID file path: %s: %s",
--                         pid_file, strerror(errno));
--            unlink(pid_file);
--            exit(1);
-+            if (errno != ENOENT) {
-+                warn_report("not removing PID file on exit: cannot resolve PID "
-+                            "file path: %s: %s", pid_file, strerror(errno));
-+            }
-+            return;
-         }
- 
-         qemu_unlink_pidfile_notifier = (struct UnlinkPidfileNotifier) {

debian/patches/extra/0006-block-block-backend-blk_set_enable_write_cache-is-IO.patch

@@ -1,77 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
-Date: Thu, 27 Oct 2022 03:27:26 -0400
-Subject: [PATCH] block/block-backend: blk_set_enable_write_cache is IO_CODE
-
-blk_set_enable_write_cache() is defined as GLOBAL_STATE_CODE
-but can be invoked from iothreads when handling scsi requests.
-This triggers an assertion failure:
-
- 0x00007fd6c3515ce1 in raise () from /lib/x86_64-linux-gnu/libc.so.6
- 0x00007fd6c34ff537 in abort () from /lib/x86_64-linux-gnu/libc.so.6
- 0x00007fd6c34ff40f in ?? () from /lib/x86_64-linux-gnu/libc.so.6
- 0x00007fd6c350e662 in __assert_fail () from /lib/x86_64-linux-gnu/libc.so.6
- 0x000056149e2cea03 in blk_set_enable_write_cache (wce=true, blk=0x5614a01c27f0)
-   at ../src/block/block-backend.c:1949
- 0x000056149e2d0a67 in blk_set_enable_write_cache (blk=0x5614a01c27f0,
-   wce=<optimized out>) at ../src/block/block-backend.c:1951
- 0x000056149dfe9c59 in scsi_disk_apply_mode_select (p=0x7fd6b400c00e "\004",
-   page=<optimized out>, s=<optimized out>) at ../src/hw/scsi/scsi-disk.c:1520
- mode_select_pages (change=true, len=18, p=0x7fd6b400c00e "\004", r=0x7fd6b4001ff0)
-   at ../src/hw/scsi/scsi-disk.c:1570
- scsi_disk_emulate_mode_select (inbuf=<optimized out>, r=0x7fd6b4001ff0) at
-   ../src/hw/scsi/scsi-disk.c:1640
- scsi_disk_emulate_write_data (req=0x7fd6b4001ff0) at ../src/hw/scsi/scsi-disk.c:1934
- 0x000056149e18ff16 in virtio_scsi_handle_cmd_req_submit (req=<optimized out>,
-   req=<optimized out>, s=0x5614a12f16b0) at ../src/hw/scsi/virtio-scsi.c:719
- virtio_scsi_handle_cmd_vq (vq=0x7fd6bab92140, s=0x5614a12f16b0) at
-   ../src/hw/scsi/virtio-scsi.c:761
- virtio_scsi_handle_cmd (vq=<optimized out>, vdev=<optimized out>) at
-   ../src/hw/scsi/virtio-scsi.c:775
- virtio_scsi_handle_cmd (vdev=0x5614a12f16b0, vq=0x7fd6bab92140) at
-   ../src/hw/scsi/virtio-scsi.c:765
- 0x000056149e1a8aa6 in virtio_queue_notify_vq (vq=0x7fd6bab92140) at
-   ../src/hw/virtio/virtio.c:2365
- 0x000056149e3ccea5 in aio_dispatch_handler (ctx=ctx@entry=0x5614a01babe0,
-   node=<optimized out>) at ../src/util/aio-posix.c:369
- 0x000056149e3cd868 in aio_dispatch_ready_handlers (ready_list=0x7fd6c09b2680,
-   ctx=0x5614a01babe0) at ../src/util/aio-posix.c:399
- aio_poll (ctx=0x5614a01babe0, blocking=blocking@entry=true) at
-   ../src/util/aio-posix.c:713
- 0x000056149e2a7796 in iothread_run (opaque=opaque@entry=0x56149ffde500) at
-   ../src/iothread.c:67
- 0x000056149e3d0859 in qemu_thread_start (args=0x7fd6c09b26f0) at
-   ../src/util/qemu-thread-posix.c:504
- 0x00007fd6c36b9ea7 in start_thread () from /lib/x86_64-linux-gnu/libpthread.so.0
- 0x00007fd6c35d9aef in clone () from /lib/x86_64-linux-gnu/libc.so.6
-
-Changing GLOBAL_STATE_CODE in IO_CODE is allowed, since GSC callers are
-allowed to call IO_CODE.
-
-Resolves: #1272
-
-Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
-Message-Id: <20221027072726.2681500-1-eesposit@redhat.com>
-Reviewed-by: Kevin Wolf <kwolf@redhat.com>
-Reviewed-by: Hanna Reitz <hreitz@redhat.com>
-Tested-by: Antoine Damhet <antoine.damhet@shadow.tech>
-Signed-off-by: Kevin Wolf <kwolf@redhat.com>
-(cherry picked from commit be8da05b5ed8fb546731b9edb997f303f272bad8)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/block-backend.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/block/block-backend.c b/block/block-backend.c
-index d4a5df2ac2..1b563e628b 100644
---- a/block/block-backend.c
-+++ b/block/block-backend.c
-@@ -1946,7 +1946,7 @@ bool blk_enable_write_cache(BlockBackend *blk)
- 
- void blk_set_enable_write_cache(BlockBackend *blk, bool wce)
- {
--    GLOBAL_STATE_CODE();
-+    IO_CODE();
-     blk->enable_write_cache = wce;
- }
- 

debian/patches/extra/0006-virtio-gpu-fix-v2-migration.patch

@@ -0,0 +1,98 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= <marcandre.lureau@redhat.com>
+Date: Thu, 16 May 2024 12:40:22 +0400
+Subject: [PATCH] virtio-gpu: fix v2 migration
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Commit dfcf74fa ("virtio-gpu: fix scanout migration post-load") broke
+forward/backward version migration. Versioning of nested VMSD structures
+is not straightforward, as the wire format doesn't have nested
+structures versions. Introduce x-scanout-vmstate-version and a field
+test to save/load appropriately according to the machine version.
+
+Fixes: dfcf74fa ("virtio-gpu: fix scanout migration post-load")
+Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Signed-off-by: Peter Xu <peterx@redhat.com>
+---
+ hw/core/machine.c              |  1 +
+ hw/display/virtio-gpu.c        | 24 ++++++++++++++++--------
+ include/hw/virtio/virtio-gpu.h |  1 +
+ 3 files changed, 18 insertions(+), 8 deletions(-)
+
+diff --git a/hw/core/machine.c b/hw/core/machine.c
+index 37ede0e7d4..d33a37a6f6 100644
+--- a/hw/core/machine.c
++++ b/hw/core/machine.c
+@@ -37,6 +37,7 @@ GlobalProperty hw_compat_8_2[] = {
+     { "migration", "zero-page-detection", "legacy"},
+     { TYPE_VIRTIO_IOMMU_PCI, "granule", "4k" },
+     { TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "64" },
++    { "virtio-gpu-device", "x-scanout-vmstate-version", "1" },
+ };
+ const size_t hw_compat_8_2_len = G_N_ELEMENTS(hw_compat_8_2);
+ 
+diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c
+index ae831b6b3e..85323daf99 100644
+--- a/hw/display/virtio-gpu.c
++++ b/hw/display/virtio-gpu.c
+@@ -1166,10 +1166,17 @@ static void virtio_gpu_cursor_bh(void *opaque)
+     virtio_gpu_handle_cursor(&g->parent_obj.parent_obj, g->cursor_vq);
+ }
+ 
++static bool scanout_vmstate_after_v2(void *opaque, int version)
++{
++    struct VirtIOGPUBase *base = container_of(opaque, VirtIOGPUBase, scanout);
++    struct VirtIOGPU *gpu = container_of(base, VirtIOGPU, parent_obj);
++
++    return gpu->scanout_vmstate_version >= 2;
++}
++
+ static const VMStateDescription vmstate_virtio_gpu_scanout = {
+     .name = "virtio-gpu-one-scanout",
+-    .version_id = 2,
+-    .minimum_version_id = 1,
++    .version_id = 1,
+     .fields = (const VMStateField[]) {
+         VMSTATE_UINT32(resource_id, struct virtio_gpu_scanout),
+         VMSTATE_UINT32(width, struct virtio_gpu_scanout),
+@@ -1181,12 +1188,12 @@ static const VMStateDescription vmstate_virtio_gpu_scanout = {
+         VMSTATE_UINT32(cursor.hot_y, struct virtio_gpu_scanout),
+         VMSTATE_UINT32(cursor.pos.x, struct virtio_gpu_scanout),
+         VMSTATE_UINT32(cursor.pos.y, struct virtio_gpu_scanout),
+-        VMSTATE_UINT32_V(fb.format, struct virtio_gpu_scanout, 2),
+-        VMSTATE_UINT32_V(fb.bytes_pp, struct virtio_gpu_scanout, 2),
+-        VMSTATE_UINT32_V(fb.width, struct virtio_gpu_scanout, 2),
+-        VMSTATE_UINT32_V(fb.height, struct virtio_gpu_scanout, 2),
+-        VMSTATE_UINT32_V(fb.stride, struct virtio_gpu_scanout, 2),
+-        VMSTATE_UINT32_V(fb.offset, struct virtio_gpu_scanout, 2),
++        VMSTATE_UINT32_TEST(fb.format, struct virtio_gpu_scanout, scanout_vmstate_after_v2),
++        VMSTATE_UINT32_TEST(fb.bytes_pp, struct virtio_gpu_scanout, scanout_vmstate_after_v2),
++        VMSTATE_UINT32_TEST(fb.width, struct virtio_gpu_scanout, scanout_vmstate_after_v2),
++        VMSTATE_UINT32_TEST(fb.height, struct virtio_gpu_scanout, scanout_vmstate_after_v2),
++        VMSTATE_UINT32_TEST(fb.stride, struct virtio_gpu_scanout, scanout_vmstate_after_v2),
++        VMSTATE_UINT32_TEST(fb.offset, struct virtio_gpu_scanout, scanout_vmstate_after_v2),
+         VMSTATE_END_OF_LIST()
+     },
+ };
+@@ -1659,6 +1666,7 @@ static Property virtio_gpu_properties[] = {
+     DEFINE_PROP_BIT("blob", VirtIOGPU, parent_obj.conf.flags,
+                     VIRTIO_GPU_FLAG_BLOB_ENABLED, false),
+     DEFINE_PROP_SIZE("hostmem", VirtIOGPU, parent_obj.conf.hostmem, 0),
++    DEFINE_PROP_UINT8("x-scanout-vmstate-version", VirtIOGPU, scanout_vmstate_version, 2),
+     DEFINE_PROP_END_OF_LIST(),
+ };
+ 
+diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h
+index ed44cdad6b..842315d51d 100644
+--- a/include/hw/virtio/virtio-gpu.h
++++ b/include/hw/virtio/virtio-gpu.h
+@@ -177,6 +177,7 @@ typedef struct VGPUDMABuf {
+ struct VirtIOGPU {
+     VirtIOGPUBase parent_obj;
+ 
++    uint8_t scanout_vmstate_version;
+     uint64_t conf_max_hostmem;
+ 
+     VirtQueue *ctrl_vq;

debian/patches/extra/0007-hw-pflash-fix-block-write-start.patch

@@ -0,0 +1,59 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Gerd Hoffmann <kraxel@redhat.com>
+Date: Thu, 16 May 2024 10:46:34 +0200
+Subject: [PATCH] hw/pflash: fix block write start
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Move the pflash_blk_write_start() call.  We need the offset of the
+first data write, not the offset for the setup (number-of-bytes)
+write.  Without this fix u-boot can do block writes to the first
+flash block only.
+
+While being at it drop a leftover FIXME.
+
+Cc: qemu-stable@nongnu.org
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2343
+Fixes: fcc79f2e0955 ("hw/pflash: implement update buffer for block writes")
+Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+(picked up from https://lists.nongnu.org/archive/html/qemu-stable/2024-05/msg00091.html)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/block/pflash_cfi01.c | 8 +++-----
+ 1 file changed, 3 insertions(+), 5 deletions(-)
+
+diff --git a/hw/block/pflash_cfi01.c b/hw/block/pflash_cfi01.c
+index 1bda8424b9..c8f1cf5a87 100644
+--- a/hw/block/pflash_cfi01.c
++++ b/hw/block/pflash_cfi01.c
+@@ -518,10 +518,6 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
+             break;
+         case 0xe8: /* Write to buffer */
+             trace_pflash_write(pfl->name, "write to buffer");
+-            /* FIXME should save @offset, @width for case 1+ */
+-            qemu_log_mask(LOG_UNIMP,
+-                          "%s: Write to buffer emulation is flawed\n",
+-                          __func__);
+             pfl->status |= 0x80; /* Ready! */
+             break;
+         case 0xf0: /* Probe for AMD flash */
+@@ -574,7 +570,6 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
+             }
+             pfl->counter = value;
+             pfl->wcycle++;
+-            pflash_blk_write_start(pfl, offset);
+             break;
+         case 0x60:
+             if (cmd == 0xd0) {
+@@ -605,6 +600,9 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
+         switch (pfl->cmd) {
+         case 0xe8: /* Block write */
+             /* FIXME check @offset, @width */
++            if (pfl->blk_offset == -1 && pfl->counter) {
++                pflash_blk_write_start(pfl, offset);
++            }
+             if (!pfl->ro && (pfl->blk_offset != -1)) {
+                 pflash_data_write(pfl, offset, value, width, be);
+             } else {

debian/patches/extra/0008-target-i386-fix-operand-size-for-DATA16-REX.W-POPCNT.patch

@@ -0,0 +1,51 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Paolo Bonzini <pbonzini@redhat.com>
+Date: Thu, 9 May 2024 12:38:10 +0200
+Subject: [PATCH] target/i386: fix operand size for DATA16 REX.W POPCNT
+
+According to the manual, 32-bit vs 64-bit is governed by REX.W
+and REX ignores the 0x66 prefix.  This can be confirmed with this
+program:
+
+    #include <stdio.h>
+    int main()
+    {
+       int x = 0x12340000;
+       int y;
+       asm("popcntl %1, %0" : "=r" (y) : "r" (x)); printf("%x\n", y);
+       asm("mov $-1, %0; .byte 0x66; popcntl %1, %0" : "+r" (y) : "r" (x)); printf("%x\n", y);
+       asm("mov $-1, %0; .byte 0x66; popcntq %q1, %q0" : "+r" (y) : "r" (x)); printf("%x\n", y);
+    }
+
+which prints 5/ffff0000/5 on real hardware and 5/ffff0000/ffff0000
+on QEMU.
+
+Cc: qemu-stable@nongnu.org
+Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 41c685dc59bb611096f3bb6a663cfa82e4cba97b)
+[FE: keep mo_64_32 helper which still has other users in 9.0.0]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/i386/tcg/translate.c | 7 +------
+ 1 file changed, 1 insertion(+), 6 deletions(-)
+
+diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
+index 76a42c679c..b60f3bd642 100644
+--- a/target/i386/tcg/translate.c
++++ b/target/i386/tcg/translate.c
+@@ -6799,12 +6799,7 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
+         modrm = x86_ldub_code(env, s);
+         reg = ((modrm >> 3) & 7) | REX_R(s);
+ 
+-        if (s->prefix & PREFIX_DATA) {
+-            ot = MO_16;
+-        } else {
+-            ot = mo_64_32(dflag);
+-        }
+-
++        ot = dflag;
+         gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
+         gen_extu(ot, s->T0);
+         tcg_gen_mov_tl(cpu_cc_src, s->T0);

debian/patches/extra/0009-target-i386-rdpkru-wrpkru-are-no-prefix-instructions.patch

@@ -0,0 +1,40 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Paolo Bonzini <pbonzini@redhat.com>
+Date: Thu, 9 May 2024 15:55:47 +0200
+Subject: [PATCH] target/i386: rdpkru/wrpkru are no-prefix instructions
+
+Reject 0x66/0xf3/0xf2 in front of them.
+
+Cc: qemu-stable@nongnu.org
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 40a3ec7b5ffde500789d016660a171057d6b467c)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/i386/tcg/translate.c | 6 ++++--
+ 1 file changed, 4 insertions(+), 2 deletions(-)
+
+diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
+index b60f3bd642..3e949fe964 100644
+--- a/target/i386/tcg/translate.c
++++ b/target/i386/tcg/translate.c
+@@ -6083,7 +6083,8 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
+             gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 1);
+             break;
+         case 0xee: /* rdpkru */
+-            if (prefixes & PREFIX_LOCK) {
++            if (s->prefix & (PREFIX_LOCK | PREFIX_DATA
++                             | PREFIX_REPZ | PREFIX_REPNZ)) {
+                 goto illegal_op;
+             }
+             tcg_gen_trunc_tl_i32(s->tmp2_i32, cpu_regs[R_ECX]);
+@@ -6091,7 +6092,8 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
+             tcg_gen_extr_i64_tl(cpu_regs[R_EAX], cpu_regs[R_EDX], s->tmp1_i64);
+             break;
+         case 0xef: /* wrpkru */
+-            if (prefixes & PREFIX_LOCK) {
++            if (s->prefix & (PREFIX_LOCK | PREFIX_DATA
++                             | PREFIX_REPZ | PREFIX_REPNZ)) {
+                 goto illegal_op;
+             }
+             tcg_gen_concat_tl_i64(s->tmp1_i64, cpu_regs[R_EAX],

debian/patches/extra/0010-target-i386-fix-feature-dependency-for-WAITPKG.patch

@@ -0,0 +1,33 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Paolo Bonzini <pbonzini@redhat.com>
+Date: Wed, 8 May 2024 11:10:54 +0200
+Subject: [PATCH] target/i386: fix feature dependency for WAITPKG
+
+The VMX feature bit depends on general availability of WAITPKG,
+not the other way round.
+
+Fixes: 33cc88261c3 ("target/i386: add support for VMX_SECONDARY_EXEC_ENABLE_USER_WAIT_PAUSE", 2023-08-28)
+Cc: qemu-stable@nongnu.org
+Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit fe01af5d47d4cf7fdf90c54d43f784e5068c8d72)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/i386/cpu.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/target/i386/cpu.c b/target/i386/cpu.c
+index 33760a2ee1..e693f8ca9a 100644
+--- a/target/i386/cpu.c
++++ b/target/i386/cpu.c
+@@ -1550,8 +1550,8 @@ static FeatureDep feature_dependencies[] = {
+         .to = { FEAT_SVM,                   ~0ull },
+     },
+     {
+-        .from = { FEAT_VMX_SECONDARY_CTLS,  VMX_SECONDARY_EXEC_ENABLE_USER_WAIT_PAUSE },
+-        .to = { FEAT_7_0_ECX,               CPUID_7_0_ECX_WAITPKG },
++        .from = { FEAT_7_0_ECX,             CPUID_7_0_ECX_WAITPKG },
++        .to = { FEAT_VMX_SECONDARY_CTLS,    VMX_SECONDARY_EXEC_ENABLE_USER_WAIT_PAUSE },
+     },
+ };
+ 

debian/patches/extra/0011-Revert-virtio-pci-fix-use-of-a-released-vector.patch

@@ -0,0 +1,87 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Thu, 16 May 2024 12:59:52 +0200
+Subject: [PATCH] Revert "virtio-pci: fix use of a released vector"
+
+This reverts commit 2ce6cff94df2650c460f809e5ad263f1d22507c0.
+
+The fix causes some issues:
+https://gitlab.com/qemu-project/qemu/-/issues/2321
+https://gitlab.com/qemu-project/qemu/-/issues/2334
+
+The CVE fixed by commit 2ce6cff94d ("virtio-pci: fix use of a released
+vector") is CVE-2024-4693 [0] and allows a malicious guest that
+controls the boot process in the guest to crash its QEMU process.
+
+The issues sound worse than the CVE, so revert until there is a proper
+fix.
+
+[0]: https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2024-4693
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/virtio/virtio-pci.c | 37 ++-----------------------------------
+ 1 file changed, 2 insertions(+), 35 deletions(-)
+
+diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
+index cb159fd078..cb6940fc0e 100644
+--- a/hw/virtio/virtio-pci.c
++++ b/hw/virtio/virtio-pci.c
+@@ -1424,38 +1424,6 @@ static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy,
+     return offset;
+ }
+ 
+-static void virtio_pci_set_vector(VirtIODevice *vdev,
+-                                  VirtIOPCIProxy *proxy,
+-                                  int queue_no, uint16_t old_vector,
+-                                  uint16_t new_vector)
+-{
+-    bool kvm_irqfd = (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+-        msix_enabled(&proxy->pci_dev) && kvm_msi_via_irqfd_enabled();
+-
+-    if (new_vector == old_vector) {
+-        return;
+-    }
+-
+-    /*
+-     * If the device uses irqfd and the vector changes after DRIVER_OK is
+-     * set, we need to release the old vector and set up the new one.
+-     * Otherwise just need to set the new vector on the device.
+-     */
+-    if (kvm_irqfd && old_vector != VIRTIO_NO_VECTOR) {
+-        kvm_virtio_pci_vector_release_one(proxy, queue_no);
+-    }
+-    /* Set the new vector on the device. */
+-    if (queue_no == VIRTIO_CONFIG_IRQ_IDX) {
+-        vdev->config_vector = new_vector;
+-    } else {
+-        virtio_queue_set_vector(vdev, queue_no, new_vector);
+-    }
+-    /* If the new vector changed need to set it up. */
+-    if (kvm_irqfd && new_vector != VIRTIO_NO_VECTOR) {
+-        kvm_virtio_pci_vector_use_one(proxy, queue_no);
+-    }
+-}
+-
+ int virtio_pci_add_shm_cap(VirtIOPCIProxy *proxy,
+                            uint8_t bar, uint64_t offset, uint64_t length,
+                            uint8_t id)
+@@ -1602,8 +1570,7 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr,
+         } else {
+             val = VIRTIO_NO_VECTOR;
+         }
+-        virtio_pci_set_vector(vdev, proxy, VIRTIO_CONFIG_IRQ_IDX,
+-                              vdev->config_vector, val);
++        vdev->config_vector = val;
+         break;
+     case VIRTIO_PCI_COMMON_STATUS:
+         if (!(val & VIRTIO_CONFIG_S_DRIVER_OK)) {
+@@ -1643,7 +1610,7 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr,
+         } else {
+             val = VIRTIO_NO_VECTOR;
+         }
+-        virtio_pci_set_vector(vdev, proxy, vdev->queue_sel, vector, val);
++        virtio_queue_set_vector(vdev, vdev->queue_sel, val);
+         break;
+     case VIRTIO_PCI_COMMON_Q_ENABLE:
+         if (val == 1) {

debian/patches/extra/0012-hw-core-machine-move-compatibility-flags-for-VirtIO-.patch

@@ -0,0 +1,57 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Thu, 16 May 2024 15:21:07 +0200
+Subject: [PATCH] hw/core/machine: move compatibility flags for VirtIO-net USO
+ to machine 8.1
+
+Migration from an 8.2 or 9.0 binary to an 8.1 binary with machine
+version 8.1 can fail with:
+
+> kvm: Features 0x1c0010130afffa7 unsupported. Allowed features: 0x10179bfffe7
+> kvm: Failed to load virtio-net:virtio
+> kvm: error while loading state for instance 0x0 of device '0000:00:12.0/virtio-net'
+> kvm: load of migration failed: Operation not permitted
+
+The series
+
+53da8b5a99 virtio-net: Add support for USO features
+9da1684954 virtio-net: Add USO flags to vhost support.
+f03e0cf63b tap: Add check for USO features
+2ab0ec3121 tap: Add USO support to tap device.
+
+only landed in QEMU 8.2, so the compatibility flags should be part of
+machine version 8.1.
+
+Moving the flags unfortunately breaks forward migration with machine
+version 8.1 from a binary without this patch to a binary with this
+patch when the feature is enabled by the guest.
+
+Fixes: 53da8b5a99 ("virtio-net: Add support for USO features")
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/core/machine.c | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+diff --git a/hw/core/machine.c b/hw/core/machine.c
+index d33a37a6f6..4273de16a0 100644
+--- a/hw/core/machine.c
++++ b/hw/core/machine.c
+@@ -46,15 +46,15 @@ GlobalProperty hw_compat_8_1[] = {
+     { "ramfb", "x-migrate", "off" },
+     { "vfio-pci-nohotplug", "x-ramfb-migrate", "off" },
+     { "igb", "x-pcie-flr-init", "off" },
++    { TYPE_VIRTIO_NET, "host_uso", "off"},
++    { TYPE_VIRTIO_NET, "guest_uso4", "off"},
++    { TYPE_VIRTIO_NET, "guest_uso6", "off"},
+ };
+ const size_t hw_compat_8_1_len = G_N_ELEMENTS(hw_compat_8_1);
+ 
+ GlobalProperty hw_compat_8_0[] = {
+     { "migration", "multifd-flush-after-each-section", "on"},
+     { TYPE_PCI_DEVICE, "x-pcie-ari-nextfn-1", "on" },
+-    { TYPE_VIRTIO_NET, "host_uso", "off"},
+-    { TYPE_VIRTIO_NET, "guest_uso4", "off"},
+-    { TYPE_VIRTIO_NET, "guest_uso6", "off"},
+ };
+ const size_t hw_compat_8_0_len = G_N_ELEMENTS(hw_compat_8_0);
+ 

debian/patches/pve/0001-PVE-Config-block-file-change-locking-default-to-off.patch

@@ -14,10 +14,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 2 insertions(+), 2 deletions(-)
 
 diff --git a/block/file-posix.c b/block/file-posix.c
-index 48cd096624..3d60b80286 100644
+index 35684f7e21..43bc0bd520 100644
 --- a/block/file-posix.c
 +++ b/block/file-posix.c
-@@ -553,7 +553,7 @@ static QemuOptsList raw_runtime_opts = {
+@@ -563,7 +563,7 @@ static QemuOptsList raw_runtime_opts = {
          {
              .name = "locking",
              .type = QEMU_OPT_STRING,
@@ -26,7 +26,7 @@ index 48cd096624..3d60b80286 100644
          },
          {
              .name = "pr-manager",
-@@ -653,7 +653,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
+@@ -663,7 +663,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
          s->use_lock = false;
          break;
      case ON_OFF_AUTO_AUTO:

debian/patches/pve/0002-PVE-Config-Adjust-network-script-path-to-etc-kvm.patch

@@ -9,10 +9,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 2 insertions(+), 2 deletions(-)
 
 diff --git a/include/net/net.h b/include/net/net.h
-index 523136c7ac..c27859b4f6 100644
+index b1f9b35fcc..096c0d52e4 100644
 --- a/include/net/net.h
 +++ b/include/net/net.h
-@@ -226,8 +226,8 @@ void netdev_add(QemuOpts *opts, Error **errp);
+@@ -317,8 +317,8 @@ void netdev_add(QemuOpts *opts, Error **errp);
  int net_hub_id_for_client(NetClientState *nc, int *id);
  NetClientState *net_hub_port_find(int hub_id);
  

debian/patches/pve/0003-PVE-Config-set-the-CPU-model-to-kvm64-32-instead-of-.patch

@@ -10,10 +10,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 2 insertions(+), 2 deletions(-)
 
 diff --git a/target/i386/cpu.h b/target/i386/cpu.h
-index 82004b65b9..4868db8f94 100644
+index 6b05738079..d82869900a 100644
 --- a/target/i386/cpu.h
 +++ b/target/i386/cpu.h
-@@ -2133,9 +2133,9 @@ uint64_t cpu_get_tsc(CPUX86State *env);
+@@ -2291,9 +2291,9 @@ uint64_t cpu_get_tsc(CPUX86State *env);
  #define CPU_RESOLVING_TYPE TYPE_X86_CPU
  
  #ifdef TARGET_X86_64

debian/patches/pve/0004-PVE-Config-ui-spice-default-to-pve-certificates.patch

@@ -9,10 +9,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 9 insertions(+), 6 deletions(-)
 
 diff --git a/ui/spice-core.c b/ui/spice-core.c
-index c3ac20ad43..37774f1c0a 100644
+index 15be640286..ea20e6153c 100644
 --- a/ui/spice-core.c
 +++ b/ui/spice-core.c
-@@ -689,32 +689,35 @@ static void qemu_spice_init(void)
+@@ -690,32 +690,35 @@ static void qemu_spice_init(void)
  
      if (tls_port) {
          x509_dir = qemu_opt_get(opts, "x509-dir");

debian/patches/pve/0005-PVE-Config-glusterfs-no-default-logfile-if-daemonize.patch

@@ -9,10 +9,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 11 insertions(+), 4 deletions(-)
 
 diff --git a/block/gluster.c b/block/gluster.c
-index b60213ab80..93da76bc31 100644
+index cc74af06dc..3ba9bbfa5e 100644
 --- a/block/gluster.c
 +++ b/block/gluster.c
-@@ -42,7 +42,7 @@
+@@ -43,7 +43,7 @@
  #define GLUSTER_DEBUG_DEFAULT       4
  #define GLUSTER_DEBUG_MAX           9
  #define GLUSTER_OPT_LOGFILE         "logfile"
@@ -21,15 +21,15 @@ index b60213ab80..93da76bc31 100644
  /*
   * Several versions of GlusterFS (3.12? -> 6.0.1) fail when the transfer size
   * is greater or equal to 1024 MiB, so we are limiting the transfer size to 512
-@@ -424,6 +424,7 @@ static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
+@@ -425,6 +425,7 @@ static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
      int old_errno;
      SocketAddressList *server;
-     unsigned long long port;
+     uint64_t port;
 +    const char *logfile;
  
      glfs = glfs_find_preopened(gconf->volume);
      if (glfs) {
-@@ -466,9 +467,15 @@ static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
+@@ -467,9 +468,15 @@ static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
          }
      }
  

debian/patches/pve/0006-PVE-Config-rbd-block-rbd-disable-rbd_cache_writethro.patch

@@ -18,10 +18,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 2 insertions(+)
 
 diff --git a/block/rbd.c b/block/rbd.c
-index f826410f40..64a8d7d48b 100644
+index 84bb2fa5d7..63f60d41be 100644
 --- a/block/rbd.c
 +++ b/block/rbd.c
-@@ -820,6 +820,8 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
+@@ -963,6 +963,8 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
          rados_conf_set(*cluster, "rbd_cache", "false");
      }
  

debian/patches/pve/0007-PVE-Up-glusterfs-allow-partial-reads.patch

@@ -16,10 +16,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 9 insertions(+), 1 deletion(-)
 
 diff --git a/block/gluster.c b/block/gluster.c
-index 93da76bc31..1079b6186b 100644
+index 3ba9bbfa5e..34936eb855 100644
 --- a/block/gluster.c
 +++ b/block/gluster.c
-@@ -57,6 +57,7 @@ typedef struct GlusterAIOCB {
+@@ -58,6 +58,7 @@ typedef struct GlusterAIOCB {
      int ret;
      Coroutine *coroutine;
      AioContext *aio_context;
@@ -27,7 +27,7 @@ index 93da76bc31..1079b6186b 100644
  } GlusterAIOCB;
  
  typedef struct BDRVGlusterState {
-@@ -752,8 +753,10 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret,
+@@ -753,8 +754,10 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret,
          acb->ret = 0; /* Success */
      } else if (ret < 0) {
          acb->ret = -errno; /* Read/Write failed */
@@ -39,7 +39,7 @@ index 93da76bc31..1079b6186b 100644
      }
  
      aio_co_schedule(acb->aio_context, acb->coroutine);
-@@ -1022,6 +1025,7 @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs,
+@@ -1023,6 +1026,7 @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs,
      acb.ret = 0;
      acb.coroutine = qemu_coroutine_self();
      acb.aio_context = bdrv_get_aio_context(bs);
@@ -59,7 +59,7 @@ index 93da76bc31..1079b6186b 100644
          ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
                                  gluster_finish_aiocb, &acb);
      }
-@@ -1269,6 +1275,7 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
+@@ -1268,6 +1274,7 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
      acb.ret = 0;
      acb.coroutine = qemu_coroutine_self();
      acb.aio_context = bdrv_get_aio_context(bs);
@@ -67,7 +67,7 @@ index 93da76bc31..1079b6186b 100644
  
      ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
      if (ret < 0) {
-@@ -1317,6 +1324,7 @@ static coroutine_fn int qemu_gluster_co_pdiscard(BlockDriverState *bs,
+@@ -1316,6 +1323,7 @@ static coroutine_fn int qemu_gluster_co_pdiscard(BlockDriverState *bs,
      acb.ret = 0;
      acb.coroutine = qemu_coroutine_self();
      acb.aio_context = bdrv_get_aio_context(bs);

debian/patches/pve/0007-PVE-Up-qmp-add-get_link_status.patch

@@ -1,88 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Mon, 6 Apr 2020 12:16:37 +0200
-Subject: [PATCH] PVE: [Up] qmp: add get_link_status
-
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- net/net.c        | 27 +++++++++++++++++++++++++++
- qapi/net.json    | 15 +++++++++++++++
- qapi/pragma.json |  1 +
- 3 files changed, 43 insertions(+)
-
-diff --git a/net/net.c b/net/net.c
-index 2db160e063..8329347891 100644
---- a/net/net.c
-+++ b/net/net.c
-@@ -1343,6 +1343,33 @@ void hmp_info_network(Monitor *mon, const QDict *qdict)
-     }
- }
- 
-+int64_t qmp_get_link_status(const char *name, Error **errp)
-+{
-+    NetClientState *ncs[MAX_QUEUE_NUM];
-+    NetClientState *nc;
-+    int queues;
-+    bool ret;
-+
-+    queues = qemu_find_net_clients_except(name, ncs,
-+                                          NET_CLIENT_DRIVER__MAX,
-+                                          MAX_QUEUE_NUM);
-+
-+    if (queues == 0) {
-+        error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
-+                  "Device '%s' not found", name);
-+        return (int64_t) -1;
-+    }
-+
-+    nc = ncs[0];
-+    ret = ncs[0]->link_down;
-+
-+    if (nc->peer->info->type == NET_CLIENT_DRIVER_NIC) {
-+      ret = ncs[0]->peer->link_down;
-+    }
-+
-+    return (int64_t) ret ? 0 : 1;
-+}
-+
- void colo_notify_filters_event(int event, Error **errp)
- {
-     NetClientState *nc;
-diff --git a/qapi/net.json b/qapi/net.json
-index 75ba2cb989..a3c93ab88f 100644
---- a/qapi/net.json
-+++ b/qapi/net.json
-@@ -35,6 +35,21 @@
- ##
- { 'command': 'set_link', 'data': {'name': 'str', 'up': 'bool'} }
- 
-+##
-+# @get_link_status:
-+#
-+# Get the current link state of the nics or nic.
-+#
-+# @name: name of the nic you get the state of
-+#
-+# Return: If link is up 1
-+#         If link is down 0
-+#         If an error occure an empty string.
-+#
-+# Notes: this is an Proxmox VE extension and not offical part of Qemu.
-+##
-+{ 'command': 'get_link_status', 'data': {'name': 'str'} , 'returns': 'int' }
-+
- ##
- # @netdev_add:
- #
-diff --git a/qapi/pragma.json b/qapi/pragma.json
-index 7f810b0e97..a2358e303a 100644
---- a/qapi/pragma.json
-+++ b/qapi/pragma.json
-@@ -26,6 +26,7 @@
-         'system_wakeup' ],
-     # Commands allowed to return a non-dictionary
-     'command-returns-exceptions': [
-+        'get_link_status',
-         'human-monitor-command',
-         'qom-get',
-         'query-tpm-models',

debian/patches/pve/0008-PVE-Up-qemu-img-return-success-on-info-without-snaps.patch

@@ -9,10 +9,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 2 insertions(+), 1 deletion(-)
 
 diff --git a/qemu-img.c b/qemu-img.c
-index 7d4b33b3da..bb36f42dd2 100644
+index 7668f86769..2575e97b43 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -3010,7 +3010,8 @@ static int img_info(int argc, char **argv)
+@@ -3075,7 +3075,8 @@ static int img_info(int argc, char **argv)
      list = collect_image_info_list(image_opts, filename, fmt, chain,
                                     force_share);
      if (!list) {

debian/patches/pve/0009-PVE-Up-qemu-img-dd-add-osize-and-read-from-to-stdin-.patch

@@ -38,10 +38,10 @@ Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
  2 files changed, 133 insertions(+), 73 deletions(-)
 
 diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
-index 1b1dab5b17..d1616c045a 100644
+index c9dd70a892..048788b23d 100644
 --- a/qemu-img-cmds.hx
 +++ b/qemu-img-cmds.hx
-@@ -58,9 +58,9 @@ SRST
+@@ -60,9 +60,9 @@ SRST
  ERST
  
  DEF("dd", img_dd,
@@ -54,10 +54,10 @@ index 1b1dab5b17..d1616c045a 100644
  
  DEF("info", img_info,
 diff --git a/qemu-img.c b/qemu-img.c
-index bb36f42dd2..74afcb79ef 100644
+index 2575e97b43..8ec68b346f 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4826,10 +4826,12 @@ static int img_bitmap(int argc, char **argv)
+@@ -4993,10 +4993,12 @@ static int img_bitmap(int argc, char **argv)
  #define C_IF      04
  #define C_OF      010
  #define C_SKIP    020
@@ -70,7 +70,7 @@ index bb36f42dd2..74afcb79ef 100644
  };
  
  struct DdIo {
-@@ -4905,6 +4907,19 @@ static int img_dd_skip(const char *arg,
+@@ -5072,6 +5074,19 @@ static int img_dd_skip(const char *arg,
      return 0;
  }
  
@@ -90,7 +90,7 @@ index bb36f42dd2..74afcb79ef 100644
  static int img_dd(int argc, char **argv)
  {
      int ret = 0;
-@@ -4945,6 +4960,7 @@ static int img_dd(int argc, char **argv)
+@@ -5112,6 +5127,7 @@ static int img_dd(int argc, char **argv)
          { "if", img_dd_if, C_IF },
          { "of", img_dd_of, C_OF },
          { "skip", img_dd_skip, C_SKIP },
@@ -98,7 +98,7 @@ index bb36f42dd2..74afcb79ef 100644
          { NULL, NULL, 0 }
      };
      const struct option long_options[] = {
-@@ -5020,91 +5036,112 @@ static int img_dd(int argc, char **argv)
+@@ -5187,91 +5203,112 @@ static int img_dd(int argc, char **argv)
          arg = NULL;
      }
  
@@ -275,10 +275,10 @@ index bb36f42dd2..74afcb79ef 100644
      }
  
      if (dd.flags & C_SKIP && (in.offset > INT64_MAX / in.bsz ||
-@@ -5121,20 +5158,43 @@ static int img_dd(int argc, char **argv)
+@@ -5288,20 +5325,43 @@ static int img_dd(int argc, char **argv)
      in.buf = g_new(uint8_t, in.bsz);
  
-     for (out_pos = 0; in_pos < size; block_count++) {
+     for (out_pos = 0; in_pos < size; ) {
 +        int in_ret, out_ret;
          int bytes = (in_pos + in.bsz > size) ? size - in_pos : in.bsz;
 -

debian/patches/pve/0010-PVE-Up-qemu-img-dd-add-isize-parameter.patch

@@ -16,10 +16,10 @@ Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
  1 file changed, 25 insertions(+), 3 deletions(-)
 
 diff --git a/qemu-img.c b/qemu-img.c
-index 74afcb79ef..14594d44b6 100644
+index 8ec68b346f..b98184bba1 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4827,11 +4827,13 @@ static int img_bitmap(int argc, char **argv)
+@@ -4994,11 +4994,13 @@ static int img_bitmap(int argc, char **argv)
  #define C_OF      010
  #define C_SKIP    020
  #define C_OSIZE   040
@@ -33,7 +33,7 @@ index 74afcb79ef..14594d44b6 100644
  };
  
  struct DdIo {
-@@ -4920,6 +4922,19 @@ static int img_dd_osize(const char *arg,
+@@ -5087,6 +5089,19 @@ static int img_dd_osize(const char *arg,
      return 0;
  }
  
@@ -53,13 +53,13 @@ index 74afcb79ef..14594d44b6 100644
  static int img_dd(int argc, char **argv)
  {
      int ret = 0;
-@@ -4934,12 +4949,14 @@ static int img_dd(int argc, char **argv)
+@@ -5101,12 +5116,14 @@ static int img_dd(int argc, char **argv)
      int c, i;
      const char *out_fmt = "raw";
      const char *fmt = NULL;
 -    int64_t size = 0;
 +    int64_t size = 0, readsize = 0;
-     int64_t block_count = 0, out_pos, in_pos;
+     int64_t out_pos, in_pos;
      bool force_share = false;
      struct DdInfo dd = {
          .flags = 0,
@@ -69,7 +69,7 @@ index 74afcb79ef..14594d44b6 100644
      };
      struct DdIo in = {
          .bsz = 512, /* Block size is by default 512 bytes */
-@@ -4961,6 +4978,7 @@ static int img_dd(int argc, char **argv)
+@@ -5128,6 +5145,7 @@ static int img_dd(int argc, char **argv)
          { "of", img_dd_of, C_OF },
          { "skip", img_dd_skip, C_SKIP },
          { "osize", img_dd_osize, C_OSIZE },
@@ -77,20 +77,20 @@ index 74afcb79ef..14594d44b6 100644
          { NULL, NULL, 0 }
      };
      const struct option long_options[] = {
-@@ -5157,9 +5175,10 @@ static int img_dd(int argc, char **argv)
+@@ -5324,9 +5342,10 @@ static int img_dd(int argc, char **argv)
  
      in.buf = g_new(uint8_t, in.bsz);
  
--    for (out_pos = 0; in_pos < size; block_count++) {
+-    for (out_pos = 0; in_pos < size; ) {
 +    readsize = (dd.isize > 0) ? dd.isize : size;
-+    for (out_pos = 0; in_pos < readsize; block_count++) {
++    for (out_pos = 0; in_pos < readsize; ) {
          int in_ret, out_ret;
 -        int bytes = (in_pos + in.bsz > size) ? size - in_pos : in.bsz;
 +        int bytes = (in_pos + in.bsz > readsize) ? readsize - in_pos : in.bsz;
          if (blk1) {
              in_ret = blk_pread(blk1, in_pos, bytes, in.buf, 0);
              if (in_ret == 0) {
-@@ -5168,6 +5187,9 @@ static int img_dd(int argc, char **argv)
+@@ -5335,6 +5354,9 @@ static int img_dd(int argc, char **argv)
          } else {
              in_ret = read(STDIN_FILENO, in.buf, bytes);
              if (in_ret == 0) {

debian/patches/pve/0011-PVE-Up-qemu-img-dd-add-n-skip_create.patch

@@ -5,7 +5,7 @@ Subject: [PATCH] PVE: [Up] qemu-img dd: add -n skip_create
 
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 [FE: fix getopt-string + add documentation]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  docs/tools/qemu-img.rst | 11 ++++++++++-
  qemu-img-cmds.hx        |  4 ++--
@@ -13,10 +13,10 @@ Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
  3 files changed, 26 insertions(+), 12 deletions(-)
 
 diff --git a/docs/tools/qemu-img.rst b/docs/tools/qemu-img.rst
-index 85a6e05b35..699229eef6 100644
+index 3653adb963..d83e8fb3c0 100644
 --- a/docs/tools/qemu-img.rst
 +++ b/docs/tools/qemu-img.rst
-@@ -208,6 +208,10 @@ Parameters to convert subcommand:
+@@ -212,6 +212,10 @@ Parameters to convert subcommand:
  
  Parameters to dd subcommand:
  
@@ -27,7 +27,7 @@ index 85a6e05b35..699229eef6 100644
  .. program:: qemu-img-dd
  
  .. option:: bs=BLOCK_SIZE
-@@ -488,7 +492,7 @@ Command description:
+@@ -492,7 +496,7 @@ Command description:
    it doesn't need to be specified separately in this case.
  
  
@@ -36,7 +36,7 @@ index 85a6e05b35..699229eef6 100644
  
    dd copies from *INPUT* file to *OUTPUT* file converting it from
    *FMT* format to *OUTPUT_FMT* format.
-@@ -499,6 +503,11 @@ Command description:
+@@ -503,6 +507,11 @@ Command description:
  
    The size syntax is similar to :manpage:`dd(1)`'s size syntax.
  
@@ -49,10 +49,10 @@ index 85a6e05b35..699229eef6 100644
  
    Give information about the disk image *FILENAME*. Use it in
 diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
-index d1616c045a..b5b0bb4467 100644
+index 048788b23d..0b29a67a06 100644
 --- a/qemu-img-cmds.hx
 +++ b/qemu-img-cmds.hx
-@@ -58,9 +58,9 @@ SRST
+@@ -60,9 +60,9 @@ SRST
  ERST
  
  DEF("dd", img_dd,
@@ -65,19 +65,19 @@ index d1616c045a..b5b0bb4467 100644
  
  DEF("info", img_info,
 diff --git a/qemu-img.c b/qemu-img.c
-index 14594d44b6..c6b4a5567d 100644
+index b98184bba1..6fc8384f64 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4951,7 +4951,7 @@ static int img_dd(int argc, char **argv)
+@@ -5118,7 +5118,7 @@ static int img_dd(int argc, char **argv)
      const char *fmt = NULL;
      int64_t size = 0, readsize = 0;
-     int64_t block_count = 0, out_pos, in_pos;
+     int64_t out_pos, in_pos;
 -    bool force_share = false;
 +    bool force_share = false, skip_create = false;
      struct DdInfo dd = {
          .flags = 0,
          .count = 0,
-@@ -4989,7 +4989,7 @@ static int img_dd(int argc, char **argv)
+@@ -5156,7 +5156,7 @@ static int img_dd(int argc, char **argv)
          { 0, 0, 0, 0 }
      };
  
@@ -86,7 +86,7 @@ index 14594d44b6..c6b4a5567d 100644
          if (c == EOF) {
              break;
          }
-@@ -5009,6 +5009,9 @@ static int img_dd(int argc, char **argv)
+@@ -5176,6 +5176,9 @@ static int img_dd(int argc, char **argv)
          case 'h':
              help();
              break;
@@ -96,7 +96,7 @@ index 14594d44b6..c6b4a5567d 100644
          case 'U':
              force_share = true;
              break;
-@@ -5139,13 +5142,15 @@ static int img_dd(int argc, char **argv)
+@@ -5306,13 +5309,15 @@ static int img_dd(int argc, char **argv)
                                  size - in.bsz * in.offset, &error_abort);
          }
  

debian/patches/pve/0012-qemu-img-dd-add-l-option-for-loading-a-snapshot.patch

@@ -1,9 +1,9 @@
 From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
 From: Fabian Ebner <f.ebner@proxmox.com>
 Date: Mon, 7 Feb 2022 14:21:01 +0100
-Subject: [PATCH] qemu-img: dd: add -l option for loading a snapshot
+Subject: [PATCH] qemu-img dd: add -l option for loading a snapshot
 
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  docs/tools/qemu-img.rst |  6 +++---
@@ -12,10 +12,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  3 files changed, 36 insertions(+), 7 deletions(-)
 
 diff --git a/docs/tools/qemu-img.rst b/docs/tools/qemu-img.rst
-index 699229eef6..4189ced8bc 100644
+index d83e8fb3c0..61c6b21859 100644
 --- a/docs/tools/qemu-img.rst
 +++ b/docs/tools/qemu-img.rst
-@@ -492,10 +492,10 @@ Command description:
+@@ -496,10 +496,10 @@ Command description:
    it doesn't need to be specified separately in this case.
  
  
@@ -30,10 +30,10 @@ index 699229eef6..4189ced8bc 100644
    The data is by default read and written using blocks of 512 bytes but can be
    modified by specifying *BLOCK_SIZE*. If count=\ *BLOCKS* is specified
 diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
-index b5b0bb4467..36f97e1f19 100644
+index 0b29a67a06..758f397232 100644
 --- a/qemu-img-cmds.hx
 +++ b/qemu-img-cmds.hx
-@@ -58,9 +58,9 @@ SRST
+@@ -60,9 +60,9 @@ SRST
  ERST
  
  DEF("dd", img_dd,
@@ -46,10 +46,10 @@ index b5b0bb4467..36f97e1f19 100644
  
  DEF("info", img_info,
 diff --git a/qemu-img.c b/qemu-img.c
-index c6b4a5567d..041c203fc3 100644
+index 6fc8384f64..a6c88e0860 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4943,6 +4943,7 @@ static int img_dd(int argc, char **argv)
+@@ -5110,6 +5110,7 @@ static int img_dd(int argc, char **argv)
      BlockDriver *drv = NULL, *proto_drv = NULL;
      BlockBackend *blk1 = NULL, *blk2 = NULL;
      QemuOpts *opts = NULL;
@@ -57,15 +57,15 @@ index c6b4a5567d..041c203fc3 100644
      QemuOptsList *create_opts = NULL;
      Error *local_err = NULL;
      bool image_opts = false;
-@@ -4952,6 +4953,7 @@ static int img_dd(int argc, char **argv)
+@@ -5119,6 +5120,7 @@ static int img_dd(int argc, char **argv)
      int64_t size = 0, readsize = 0;
-     int64_t block_count = 0, out_pos, in_pos;
+     int64_t out_pos, in_pos;
      bool force_share = false, skip_create = false;
 +    const char *snapshot_name = NULL;
      struct DdInfo dd = {
          .flags = 0,
          .count = 0,
-@@ -4989,7 +4991,7 @@ static int img_dd(int argc, char **argv)
+@@ -5156,7 +5158,7 @@ static int img_dd(int argc, char **argv)
          { 0, 0, 0, 0 }
      };
  
@@ -74,7 +74,7 @@ index c6b4a5567d..041c203fc3 100644
          if (c == EOF) {
              break;
          }
-@@ -5012,6 +5014,19 @@ static int img_dd(int argc, char **argv)
+@@ -5179,6 +5181,19 @@ static int img_dd(int argc, char **argv)
          case 'n':
              skip_create = true;
              break;
@@ -94,7 +94,7 @@ index c6b4a5567d..041c203fc3 100644
          case 'U':
              force_share = true;
              break;
-@@ -5071,11 +5086,24 @@ static int img_dd(int argc, char **argv)
+@@ -5238,11 +5253,24 @@ static int img_dd(int argc, char **argv)
      if (dd.flags & C_IF) {
          blk1 = img_open(image_opts, in.filename, fmt, 0, false, false,
                          force_share);
@@ -120,7 +120,7 @@ index c6b4a5567d..041c203fc3 100644
      }
  
      if (dd.flags & C_OSIZE) {
-@@ -5230,6 +5258,7 @@ static int img_dd(int argc, char **argv)
+@@ -5397,6 +5425,7 @@ static int img_dd(int argc, char **argv)
  out:
      g_free(arg);
      qemu_opts_del(opts);

debian/patches/pve/0013-PVE-virtio-balloon-improve-query-balloon.patch

@@ -7,17 +7,62 @@ Actually provide memory information via the query-balloon
 command.
 
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: add BalloonInfo to member name exceptions list
+     rebase for 8.0 - moved to hw/core/machine-hmp-cmds.c]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
+ hw/core/machine-hmp-cmds.c | 30 +++++++++++++++++++++++++++++-
  hw/virtio/virtio-balloon.c | 33 +++++++++++++++++++++++++++++++--
- monitor/hmp-cmds.c         | 30 +++++++++++++++++++++++++++++-
  qapi/machine.json          | 22 +++++++++++++++++++++-
- 3 files changed, 81 insertions(+), 4 deletions(-)
+ qapi/pragma.json           |  1 +
+ 4 files changed, 82 insertions(+), 4 deletions(-)
 
+diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c
+index a6ff6a4875..e7f74d1c63 100644
+--- a/hw/core/machine-hmp-cmds.c
++++ b/hw/core/machine-hmp-cmds.c
+@@ -175,7 +175,35 @@ void hmp_info_balloon(Monitor *mon, const QDict *qdict)
+         return;
+     }
+ 
+-    monitor_printf(mon, "balloon: actual=%" PRId64 "\n", info->actual >> 20);
++    monitor_printf(mon, "balloon: actual=%" PRId64, info->actual >> 20);
++    monitor_printf(mon, " max_mem=%" PRId64, info->max_mem >> 20);
++    if (info->has_total_mem) {
++        monitor_printf(mon, " total_mem=%" PRId64, info->total_mem >> 20);
++    }
++    if (info->has_free_mem) {
++        monitor_printf(mon, " free_mem=%" PRId64, info->free_mem >> 20);
++    }
++
++    if (info->has_mem_swapped_in) {
++        monitor_printf(mon, " mem_swapped_in=%" PRId64, info->mem_swapped_in);
++    }
++    if (info->has_mem_swapped_out) {
++        monitor_printf(mon, " mem_swapped_out=%" PRId64, info->mem_swapped_out);
++    }
++    if (info->has_major_page_faults) {
++        monitor_printf(mon, " major_page_faults=%" PRId64,
++                       info->major_page_faults);
++    }
++    if (info->has_minor_page_faults) {
++        monitor_printf(mon, " minor_page_faults=%" PRId64,
++                       info->minor_page_faults);
++    }
++    if (info->has_last_update) {
++        monitor_printf(mon, " last_update=%" PRId64,
++                       info->last_update);
++    }
++
++    monitor_printf(mon, "\n");
+ 
+     qapi_free_BalloonInfo(info);
+ }
 diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
-index 73ac5eb675..bbfe7eca62 100644
+index 609e39a821..8cb6dfcac3 100644
 --- a/hw/virtio/virtio-balloon.c
 +++ b/hw/virtio/virtio-balloon.c
-@@ -806,8 +806,37 @@ static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f,
+@@ -781,8 +781,37 @@ static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f,
  static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
  {
      VirtIOBalloon *dev = opaque;
@@ -57,54 +102,13 @@ index 73ac5eb675..bbfe7eca62 100644
  }
  
  static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
-diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
-index c6cd6f91dd..15572befb1 100644
---- a/monitor/hmp-cmds.c
-+++ b/monitor/hmp-cmds.c
-@@ -715,7 +715,35 @@ void hmp_info_balloon(Monitor *mon, const QDict *qdict)
-         return;
-     }
- 
--    monitor_printf(mon, "balloon: actual=%" PRId64 "\n", info->actual >> 20);
-+    monitor_printf(mon, "balloon: actual=%" PRId64, info->actual >> 20);
-+    monitor_printf(mon, " max_mem=%" PRId64, info->max_mem >> 20);
-+    if (info->has_total_mem) {
-+        monitor_printf(mon, " total_mem=%" PRId64, info->total_mem >> 20);
-+    }
-+    if (info->has_free_mem) {
-+        monitor_printf(mon, " free_mem=%" PRId64, info->free_mem >> 20);
-+    }
-+
-+    if (info->has_mem_swapped_in) {
-+        monitor_printf(mon, " mem_swapped_in=%" PRId64, info->mem_swapped_in);
-+    }
-+    if (info->has_mem_swapped_out) {
-+        monitor_printf(mon, " mem_swapped_out=%" PRId64, info->mem_swapped_out);
-+    }
-+    if (info->has_major_page_faults) {
-+        monitor_printf(mon, " major_page_faults=%" PRId64,
-+                       info->major_page_faults);
-+    }
-+    if (info->has_minor_page_faults) {
-+        monitor_printf(mon, " minor_page_faults=%" PRId64,
-+                       info->minor_page_faults);
-+    }
-+    if (info->has_last_update) {
-+        monitor_printf(mon, " last_update=%" PRId64,
-+                       info->last_update);
-+    }
-+
-+    monitor_printf(mon, "\n");
- 
-     qapi_free_BalloonInfo(info);
- }
 diff --git a/qapi/machine.json b/qapi/machine.json
-index 6afd1936b0..8b4be9b718 100644
+index e8b60641f2..2054cdc70d 100644
 --- a/qapi/machine.json
 +++ b/qapi/machine.json
-@@ -1054,9 +1054,29 @@
- # @actual: the logical size of the VM in bytes
- #          Formula used: logical_vm_size = vm_ram_size - balloon_size
+@@ -1079,9 +1079,29 @@
+ # @actual: the logical size of the VM in bytes Formula used:
+ #     logical_vm_size = vm_ram_size - balloon_size
  #
 +# @last_update: time when stats got updated from guest
 +#
@@ -133,3 +137,15 @@ index 6afd1936b0..8b4be9b718 100644
  
  ##
  # @query-balloon:
+diff --git a/qapi/pragma.json b/qapi/pragma.json
+index 59fbe74b8c..be8fa304c5 100644
+--- a/qapi/pragma.json
++++ b/qapi/pragma.json
+@@ -90,6 +90,7 @@
+     'member-name-exceptions': [     # visible in:
+         'ACPISlotType',             # query-acpi-ospm-status
+         'AcpiTableOptions',         # -acpitable
++        'BalloonInfo',              # query-balloon
+         'BlkdebugEvent',            # blockdev-add, -blockdev
+         'BlkdebugSetStateOptions',  # blockdev-add, -blockdev
+         'BlockDeviceInfo',          # query-block

debian/patches/pve/0014-PVE-qapi-modify-query-machines.patch

@@ -13,13 +13,13 @@ Signed-off-by: Dietmar Maurer <dietmar@proxmox.com>
  2 files changed, 9 insertions(+), 1 deletion(-)
 
 diff --git a/hw/core/machine-qmp-cmds.c b/hw/core/machine-qmp-cmds.c
-index 4f4ab30f8c..76fff60a6b 100644
+index 4b72009cd3..314351cdff 100644
 --- a/hw/core/machine-qmp-cmds.c
 +++ b/hw/core/machine-qmp-cmds.c
-@@ -99,6 +99,12 @@ MachineInfoList *qmp_query_machines(Error **errp)
-         info->hotpluggable_cpus = mc->has_hotpluggable_cpus;
+@@ -90,6 +90,12 @@ MachineInfoList *qmp_query_machines(Error **errp)
          info->numa_mem_supported = mc->numa_mem_supported;
          info->deprecated = !!mc->deprecation_reason;
+         info->acpi = !!object_class_property_find(OBJECT_CLASS(mc), "acpi");
 +
 +        if (strcmp(mc->name, MACHINE_GET_CLASS(current_machine)->name) == 0) {
 +            info->has_is_current = true;
@@ -28,21 +28,21 @@ index 4f4ab30f8c..76fff60a6b 100644
 +
          if (mc->default_cpu_type) {
              info->default_cpu_type = g_strdup(mc->default_cpu_type);
-             info->has_default_cpu_type = true;
+         }
 diff --git a/qapi/machine.json b/qapi/machine.json
-index 8b4be9b718..555458f785 100644
+index 2054cdc70d..a024d5b05d 100644
 --- a/qapi/machine.json
 +++ b/qapi/machine.json
-@@ -138,6 +138,8 @@
+@@ -146,6 +146,8 @@
  #
  # @is-default: whether the machine is default
  #
 +# @is-current: whether this machine is currently used
 +#
  # @cpu-max: maximum number of CPUs supported by the machine type
- #           (since 1.5)
+ #     (since 1.5)
  #
-@@ -159,7 +161,7 @@
+@@ -170,7 +172,7 @@
  ##
  { 'struct': 'MachineInfo',
    'data': { 'name': 'str', '*alias': 'str',
@@ -50,4 +50,4 @@ index 8b4be9b718..555458f785 100644
 +            '*is-default': 'bool', '*is-current': 'bool', 'cpu-max': 'int',
              'hotpluggable-cpus': 'bool',  'numa-mem-supported': 'bool',
              'deprecated': 'bool', '*default-cpu-type': 'str',
-             '*default-ram-id': 'str' } }
+             '*default-ram-id': 'str', 'acpi': 'bool' } }

debian/patches/pve/0015-PVE-qapi-modify-spice-query.patch

@@ -6,16 +6,18 @@ Subject: [PATCH] PVE: qapi: modify spice query
 Provide the last ticket in the SpiceInfo struct optionally.
 
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: adapt to QAPI change]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  qapi/ui.json    | 3 +++
- ui/spice-core.c | 5 +++++
- 2 files changed, 8 insertions(+)
+ ui/spice-core.c | 4 ++++
+ 2 files changed, 7 insertions(+)
 
 diff --git a/qapi/ui.json b/qapi/ui.json
-index cf58ab4283..0be2388941 100644
+index f610bce118..6ea26a9acb 100644
 --- a/qapi/ui.json
 +++ b/qapi/ui.json
-@@ -310,11 +310,14 @@
+@@ -314,11 +314,14 @@
  #
  # @channels: a list of @SpiceChannel for each active spice channel
  #
@@ -31,15 +33,14 @@ index cf58ab4283..0be2388941 100644
    'if': 'CONFIG_SPICE' }
  
 diff --git a/ui/spice-core.c b/ui/spice-core.c
-index 37774f1c0a..367f77f2b4 100644
+index ea20e6153c..55a15fba8b 100644
 --- a/ui/spice-core.c
 +++ b/ui/spice-core.c
-@@ -534,6 +534,11 @@ static SpiceInfo *qmp_query_spice_real(Error **errp)
+@@ -548,6 +548,10 @@ static SpiceInfo *qmp_query_spice_real(Error **errp)
      micro = SPICE_SERVER_VERSION & 0xff;
      info->compiled_version = g_strdup_printf("%d.%d.%d", major, minor, micro);
  
 +    if (auth_passwd) {
-+        info->has_ticket = true;
 +        info->ticket =  g_strdup(auth_passwd);
 +    }
 +

debian/patches/pve/0016-PVE-add-IOChannel-implementation-for-savevm-async.patch

@@ -14,20 +14,21 @@ Additionally, allows tracking the current position from the outside
 (intended to be used for progress tracking).
 
 Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
- migration/channel-savevm-async.c | 182 +++++++++++++++++++++++++++++++
+ migration/channel-savevm-async.c | 184 +++++++++++++++++++++++++++++++
  migration/channel-savevm-async.h |  51 +++++++++
  migration/meson.build            |   1 +
- 3 files changed, 234 insertions(+)
+ 3 files changed, 236 insertions(+)
  create mode 100644 migration/channel-savevm-async.c
  create mode 100644 migration/channel-savevm-async.h
 
 diff --git a/migration/channel-savevm-async.c b/migration/channel-savevm-async.c
 new file mode 100644
-index 0000000000..06d5484778
+index 0000000000..081a192f49
 --- /dev/null
 +++ b/migration/channel-savevm-async.c
-@@ -0,0 +1,182 @@
+@@ -0,0 +1,184 @@
 +/*
 + * QIO Channel implementation to be used by savevm-async QMP calls
 + */
@@ -71,6 +72,7 @@ index 0000000000..06d5484778
 +                               size_t niov,
 +                               int **fds,
 +                               size_t *nfds,
++                               int flags,
 +                               Error **errp)
 +{
 +    QIOChannelSavevmAsync *saioc = QIO_CHANNEL_SAVEVM_ASYNC(ioc);
@@ -173,8 +175,9 @@ index 0000000000..06d5484778
 +
 +static void
 +qio_channel_savevm_async_set_aio_fd_handler(QIOChannel *ioc,
-+                                            AioContext *ctx,
++                                            AioContext *read_ctx,
 +                                            IOHandler *io_read,
++                                            AioContext *write_ctx,
 +                                            IOHandler *io_write,
 +                                            void *opaque)
 +{
@@ -268,14 +271,14 @@ index 0000000000..17ae2cb261
 +
 +#endif /* QIO_CHANNEL_SAVEVM_ASYNC_H */
 diff --git a/migration/meson.build b/migration/meson.build
-index 690487cf1a..8cac83c06c 100644
+index 1eeb915ff6..95d1cf2250 100644
 --- a/migration/meson.build
 +++ b/migration/meson.build
-@@ -13,6 +13,7 @@ softmmu_ss.add(files(
+@@ -13,6 +13,7 @@ system_ss.add(files(
    'block-dirty-bitmap.c',
    'channel.c',
    'channel-block.c',
 +  'channel-savevm-async.c',
-   'colo-failover.c',
-   'colo.c',
+   'dirtyrate.c',
    'exec.c',
+   'fd.c',

debian/patches/pve/0017-PVE-add-savevm-async-for-background-state-snapshots.patch

@@ -21,31 +21,34 @@ still opened by QEMU.
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 Signed-off-by: Dietmar Maurer <dietmar@proxmox.com>
 Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
-[improve aborting]
+[SR: improve aborting
+     register yank before migration_incoming_state_destroy]
 Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 [FE: further improve aborting
-     adapt to removal of QEMUFileOps]
+     adapt to removal of QEMUFileOps
+     improve condition for entering final stage
+     adapt to QAPI and other changes for 8.2]
 Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  hmp-commands-info.hx         |  13 +
- hmp-commands.hx              |  33 +++
+ hmp-commands.hx              |  17 ++
  include/migration/snapshot.h |   2 +
- include/monitor/hmp.h        |   5 +
+ include/monitor/hmp.h        |   3 +
  migration/meson.build        |   1 +
  migration/savevm-async.c     | 531 +++++++++++++++++++++++++++++++++++
- monitor/hmp-cmds.c           |  57 ++++
+ monitor/hmp-cmds.c           |  38 +++
  qapi/migration.json          |  34 +++
- qapi/misc.json               |  32 +++
+ qapi/misc.json               |  18 ++
  qemu-options.hx              |  12 +
- softmmu/vl.c                 |  10 +
- 11 files changed, 730 insertions(+)
+ system/vl.c                  |  10 +
+ 11 files changed, 679 insertions(+)
  create mode 100644 migration/savevm-async.c
 
 diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx
-index 188d9ece3b..97b88eaaad 100644
+index ad1b1306e3..d5ab880492 100644
 --- a/hmp-commands-info.hx
 +++ b/hmp-commands-info.hx
-@@ -538,6 +538,19 @@ SRST
+@@ -525,6 +525,19 @@ SRST
      Show current migration parameters.
  ERST
  
@@ -66,13 +69,13 @@ index 188d9ece3b..97b88eaaad 100644
          .name       = "balloon",
          .args_type  = "",
 diff --git a/hmp-commands.hx b/hmp-commands.hx
-index 182e639d14..bbcc73e942 100644
+index 2e2a3bcf98..7506de251c 100644
 --- a/hmp-commands.hx
 +++ b/hmp-commands.hx
-@@ -1800,3 +1800,36 @@ ERST
-                       "\n\t\t\t\t\t limit on a specified virtual cpu",
-         .cmd        = hmp_cancel_vcpu_dirty_limit,
-     },
+@@ -1862,3 +1862,20 @@ SRST
+   List event channels in the guest
+ ERST
+ #endif
 +
 +    {
 +        .name       = "savevm-start",
@@ -83,22 +86,6 @@ index 182e639d14..bbcc73e942 100644
 +    },
 +
 +    {
-+        .name       = "snapshot-drive",
-+        .args_type  = "device:s,name:s",
-+        .params     = "device name",
-+        .help       = "Create internal snapshot.",
-+        .cmd = hmp_snapshot_drive,
-+    },
-+
-+    {
-+        .name       = "delete-drive-snapshot",
-+        .args_type  = "device:s,name:s",
-+        .params     = "device name",
-+        .help       = "Delete internal snapshot.",
-+        .cmd = hmp_delete_drive_snapshot,
-+    },
-+
-+    {
 +        .name       = "savevm-end",
 +        .args_type  = "",
 +        .params     = "",
@@ -107,21 +94,21 @@ index 182e639d14..bbcc73e942 100644
 +        .coroutine  = true,
 +    },
 diff --git a/include/migration/snapshot.h b/include/migration/snapshot.h
-index e72083b117..c846d37806 100644
+index 9e4dcaaa75..2581730d74 100644
 --- a/include/migration/snapshot.h
 +++ b/include/migration/snapshot.h
-@@ -61,4 +61,6 @@ bool delete_snapshot(const char *name,
-                     bool has_devices, strList *devices,
-                     Error **errp);
+@@ -68,4 +68,6 @@ bool delete_snapshot(const char *name,
+  */
+ void load_snapshot_resume(RunState state);
  
 +int load_snapshot_from_blockdev(const char *filename, Error **errp);
 +
  #endif
 diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h
-index a618eb1e4e..55067beff1 100644
+index 13f9a2dedb..7a7def7530 100644
 --- a/include/monitor/hmp.h
 +++ b/include/monitor/hmp.h
-@@ -26,6 +26,7 @@ void hmp_info_status(Monitor *mon, const QDict *qdict);
+@@ -28,6 +28,7 @@ void hmp_info_status(Monitor *mon, const QDict *qdict);
  void hmp_info_uuid(Monitor *mon, const QDict *qdict);
  void hmp_info_chardev(Monitor *mon, const QDict *qdict);
  void hmp_info_mice(Monitor *mon, const QDict *qdict);
@@ -129,38 +116,38 @@ index a618eb1e4e..55067beff1 100644
  void hmp_info_migrate(Monitor *mon, const QDict *qdict);
  void hmp_info_migrate_capabilities(Monitor *mon, const QDict *qdict);
  void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict);
-@@ -80,6 +81,10 @@ void hmp_netdev_add(Monitor *mon, const QDict *qdict);
- void hmp_netdev_del(Monitor *mon, const QDict *qdict);
- void hmp_getfd(Monitor *mon, const QDict *qdict);
- void hmp_closefd(Monitor *mon, const QDict *qdict);
+@@ -94,6 +95,8 @@ void hmp_closefd(Monitor *mon, const QDict *qdict);
+ void hmp_mouse_move(Monitor *mon, const QDict *qdict);
+ void hmp_mouse_button(Monitor *mon, const QDict *qdict);
+ void hmp_mouse_set(Monitor *mon, const QDict *qdict);
 +void hmp_savevm_start(Monitor *mon, const QDict *qdict);
-+void hmp_snapshot_drive(Monitor *mon, const QDict *qdict);
-+void hmp_delete_drive_snapshot(Monitor *mon, const QDict *qdict);
 +void hmp_savevm_end(Monitor *mon, const QDict *qdict);
  void hmp_sendkey(Monitor *mon, const QDict *qdict);
- void hmp_screendump(Monitor *mon, const QDict *qdict);
+ void coroutine_fn hmp_screendump(Monitor *mon, const QDict *qdict);
  void hmp_chardev_add(Monitor *mon, const QDict *qdict);
 diff --git a/migration/meson.build b/migration/meson.build
-index 8cac83c06c..0842d00cd2 100644
+index 95d1cf2250..800f12a60d 100644
 --- a/migration/meson.build
 +++ b/migration/meson.build
-@@ -24,6 +24,7 @@ softmmu_ss.add(files(
-   'multifd-zlib.c',
+@@ -28,6 +28,7 @@ system_ss.add(files(
+   'options.c',
    'postcopy-ram.c',
    'savevm.c',
 +  'savevm-async.c',
    'socket.c',
    'tls.c',
- ), gnutls)
+   'threadinfo.c',
 diff --git a/migration/savevm-async.c b/migration/savevm-async.c
 new file mode 100644
-index 0000000000..05d394c0e2
+index 0000000000..779e4e2a78
 --- /dev/null
 +++ b/migration/savevm-async.c
 @@ -0,0 +1,531 @@
 +#include "qemu/osdep.h"
 +#include "migration/channel-savevm-async.h"
 +#include "migration/migration.h"
++#include "migration/migration-stats.h"
++#include "migration/options.h"
 +#include "migration/savevm.h"
 +#include "migration/snapshot.h"
 +#include "migration/global_state.h"
@@ -180,6 +167,7 @@ index 0000000000..05d394c0e2
 +#include "qemu/timer.h"
 +#include "qemu/main-loop.h"
 +#include "qemu/rcu.h"
++#include "qemu/yank.h"
 +
 +/* #define DEBUG_SAVEVM_STATE */
 +
@@ -230,24 +218,20 @@ index 0000000000..05d394c0e2
 +        info->bytes = s->bs_pos;
 +        switch (s->state) {
 +        case SAVE_STATE_ERROR:
-+            info->has_status = true;
 +            info->status = g_strdup("failed");
 +            info->has_total_time = true;
 +            info->total_time = s->total_time;
 +            if (s->error) {
-+                info->has_error = true;
 +                info->error = g_strdup(error_get_pretty(s->error));
 +            }
 +            break;
 +        case SAVE_STATE_ACTIVE:
-+            info->has_status = true;
 +            info->status = g_strdup("active");
 +            info->has_total_time = true;
 +            info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME)
 +                - s->total_time;
 +            break;
 +        case SAVE_STATE_COMPLETED:
-+            info->has_status = true;
 +            info->status = g_strdup("completed");
 +            info->has_total_time = true;
 +            info->total_time = s->total_time;
@@ -293,7 +277,7 @@ index 0000000000..05d394c0e2
 +    return ret;
 +}
 +
-+static void save_snapshot_error(const char *fmt, ...)
++static void G_GNUC_PRINTF(1, 2) save_snapshot_error(const char *fmt, ...)
 +{
 +    va_list ap;
 +    char *msg;
@@ -316,7 +300,6 @@ index 0000000000..05d394c0e2
 +static void process_savevm_finalize(void *opaque)
 +{
 +    int ret;
-+    AioContext *iohandler_ctx = iohandler_get_aio_context();
 +    MigrationState *ms = migrate_get_current();
 +
 +    bool aborted = savevm_aborted();
@@ -333,9 +316,7 @@ index 0000000000..05d394c0e2
 +     * so move it back. It can stay in the main context and live out its live
 +     * there, since we're done with it after this method ends anyway.
 +     */
-+    aio_context_acquire(iohandler_ctx);
 +    blk_set_aio_context(snap_state.target, qemu_get_aio_context(), NULL);
-+    aio_context_release(iohandler_ctx);
 +
 +    ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
 +    if (ret < 0) {
@@ -347,7 +328,7 @@ index 0000000000..05d394c0e2
 +        (void)qemu_savevm_state_complete_precopy(snap_state.file, false, false);
 +        ret = qemu_file_get_error(snap_state.file);
 +        if (ret < 0) {
-+                save_snapshot_error("qemu_savevm_state_iterate error %d", ret);
++            save_snapshot_error("qemu_savevm_state_complete_precopy error %d", ret);
 +        }
 +    }
 +
@@ -404,18 +385,32 @@ index 0000000000..05d394c0e2
 +    }
 +
 +    while (snap_state.state == SAVE_STATE_ACTIVE) {
-+        uint64_t pending_size, pend_precopy, pend_compatible, pend_postcopy;
++        uint64_t pending_size, pend_precopy, pend_postcopy;
++        uint64_t threshold = 400 * 1000;
 +
-+        /* pending is expected to be called without iothread lock */
-+        qemu_mutex_unlock_iothread();
-+        qemu_savevm_state_pending(snap_state.file, 0, &pend_precopy, &pend_compatible, &pend_postcopy);
-+        qemu_mutex_lock_iothread();
++        /*
++         * pending_{estimate,exact} are expected to be called without iothread
++         * lock. Similar to what is done in migration.c, call the exact variant
++         * only once pend_precopy in the estimate is below the threshold.
++         */
++        bql_unlock();
++        qemu_savevm_state_pending_estimate(&pend_precopy, &pend_postcopy);
++        if (pend_precopy <= threshold) {
++            qemu_savevm_state_pending_exact(&pend_precopy, &pend_postcopy);
++        }
++        bql_lock();
++        pending_size = pend_precopy + pend_postcopy;
 +
-+        pending_size = pend_precopy + pend_compatible + pend_postcopy;
++        /*
++         * A guest reaching this cutoff is dirtying lots of RAM. It should be
++         * large enough so that the guest can't dirty this much between the
++         * check and the guest actually being stopped, but it should be small
++         * enough to avoid long downtimes for non-hibernation snapshots.
++         */
++        maxlen = blk_getlength(snap_state.target) - 100*1024*1024;
 +
-+        maxlen = blk_getlength(snap_state.target) - 30*1024*1024;
-+
-+        if (pending_size > 400000 && snap_state.bs_pos + pending_size < maxlen) {
++        /* Note that there is no progress for pend_postcopy when iterating */
++        if (pend_precopy > threshold && snap_state.bs_pos + pending_size < maxlen) {
 +            ret = qemu_savevm_state_iterate(snap_state.file, false);
 +            if (ret < 0) {
 +                save_snapshot_error("qemu_savevm_state_iterate error %d", ret);
@@ -424,11 +419,7 @@ index 0000000000..05d394c0e2
 +            DPRINTF("savevm iterate pending size %lu ret %d\n", pending_size, ret);
 +        } else {
 +            qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-+            ret = global_state_store();
-+            if (ret) {
-+                save_snapshot_error("global_state_store error %d", ret);
-+                break;
-+            }
++            global_state_store();
 +
 +            DPRINTF("savevm iterate complete\n");
 +            break;
@@ -447,19 +438,25 @@ index 0000000000..05d394c0e2
 +     * so move there now and after every flush.
 +     */
 +    aio_co_reschedule_self(qemu_get_aio_context());
-+    for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
++    bdrv_graph_co_rdlock();
++    bs = bdrv_first(&it);
++    bdrv_graph_co_rdunlock();
++    while (bs) {
 +        /* target has BDRV_O_NO_FLUSH, no sense calling bdrv_flush on it */
-+        if (bs == blk_bs(snap_state.target)) {
-+            continue;
-+        }
-+
-+        AioContext *bs_ctx = bdrv_get_aio_context(bs);
-+        if (bs_ctx != qemu_get_aio_context()) {
-+            DPRINTF("savevm: async flushing drive %s\n", bs->filename);
-+            aio_co_reschedule_self(bs_ctx);
-+            bdrv_flush(bs);
-+            aio_co_reschedule_self(qemu_get_aio_context());
++        if (bs != blk_bs(snap_state.target)) {
++            AioContext *bs_ctx = bdrv_get_aio_context(bs);
++            if (bs_ctx != qemu_get_aio_context()) {
++                DPRINTF("savevm: async flushing drive %s\n", bs->filename);
++                aio_co_reschedule_self(bs_ctx);
++                bdrv_graph_co_rdlock();
++                bdrv_flush(bs);
++                bdrv_graph_co_rdunlock();
++                aio_co_reschedule_self(qemu_get_aio_context());
++            }
 +        }
++        bdrv_graph_co_rdlock();
++        bs = bdrv_next(&it);
++        bdrv_graph_co_rdunlock();
 +    }
 +
 +    DPRINTF("timing: async flushing took %ld ms\n",
@@ -468,7 +465,7 @@ index 0000000000..05d394c0e2
 +    qemu_bh_schedule(snap_state.finalize_bh);
 +}
 +
-+void qmp_savevm_start(bool has_statefile, const char *statefile, Error **errp)
++void qmp_savevm_start(const char *statefile, Error **errp)
 +{
 +    Error *local_err = NULL;
 +    MigrationState *ms = migrate_get_current();
@@ -482,12 +479,12 @@ index 0000000000..05d394c0e2
 +        return;
 +    }
 +
-+    if (migration_is_running(ms->state)) {
++    if (migration_is_running()) {
 +        error_set(errp, ERROR_CLASS_GENERIC_ERROR, QERR_MIGRATION_ACTIVE);
 +        return;
 +    }
 +
-+    if (migrate_use_block()) {
++    if (migrate_block()) {
 +        error_set(errp, ERROR_CLASS_GENERIC_ERROR,
 +                  "Block migration and snapshots are incompatible");
 +        return;
@@ -505,7 +502,7 @@ index 0000000000..05d394c0e2
 +        snap_state.error = NULL;
 +    }
 +
-+    if (!has_statefile) {
++    if (!statefile) {
 +        vm_stop(RUN_STATE_SAVE_VM);
 +        snap_state.state = SAVE_STATE_COMPLETED;
 +        return;
@@ -539,8 +536,10 @@ index 0000000000..05d394c0e2
 +     * State is cleared in process_savevm_co, but has to be initialized
 +     * here (blocking main thread, from QMP) to avoid race conditions.
 +     */
-+    migrate_init(ms);
-+    memset(&ram_counters, 0, sizeof(ram_counters));
++    if (migrate_init(ms, errp)) {
++        return;
++    }
++    memset(&mig_stats, 0, sizeof(mig_stats));
 +    ms->to_dst_file = snap_state.file;
 +
 +    error_setg(&snap_state.blocker, "block device is in use by savevm");
@@ -549,10 +548,8 @@ index 0000000000..05d394c0e2
 +    snap_state.state = SAVE_STATE_ACTIVE;
 +    snap_state.finalize_bh = qemu_bh_new(process_savevm_finalize, &snap_state);
 +    snap_state.co = qemu_coroutine_create(&process_savevm_co, NULL);
-+    qemu_mutex_unlock_iothread();
 +    qemu_savevm_state_header(snap_state.file);
 +    qemu_savevm_state_setup(snap_state.file);
-+    qemu_mutex_lock_iothread();
 +
 +    /* Async processing from here on out happens in iohandler context, so let
 +     * the target bdrv have its home there.
@@ -623,22 +620,6 @@ index 0000000000..05d394c0e2
 +    DPRINTF("savevm-end: cleanup done\n");
 +}
 +
-+// FIXME: Deprecated
-+void qmp_snapshot_drive(const char *device, const char *name, Error **errp)
-+{
-+    // Compatibility to older qemu-server.
-+    qmp_blockdev_snapshot_internal_sync(device, name, errp);
-+}
-+
-+// FIXME: Deprecated
-+void qmp_delete_drive_snapshot(const char *device, const char *name,
-+                               Error **errp)
-+{
-+    // Compatibility to older qemu-server.
-+    (void)qmp_blockdev_snapshot_delete_internal_sync(device, false, NULL,
-+                                                     true, name, errp);
-+}
-+
 +int load_snapshot_from_blockdev(const char *filename, Error **errp)
 +{
 +    BlockBackend *be;
@@ -673,6 +654,10 @@ index 0000000000..05d394c0e2
 +    dirty_bitmap_mig_before_vm_start();
 +
 +    qemu_fclose(f);
++
++    /* state_destroy assumes a real migration which would have added a yank */
++    yank_register_instance(MIGRATION_YANK_INSTANCE, &error_abort);
++
 +    migration_incoming_state_destroy();
 +    if (ret < 0) {
 +        error_setg_errno(errp, -ret, "Error while loading VM state");
@@ -690,39 +675,28 @@ index 0000000000..05d394c0e2
 +    return ret;
 +}
 diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
-index 15572befb1..1507180990 100644
+index 871898ac46..ef4634e5c1 100644
 --- a/monitor/hmp-cmds.c
 +++ b/monitor/hmp-cmds.c
-@@ -1925,6 +1925,63 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict)
-     hmp_handle_error(mon, err);
- }
+@@ -22,6 +22,7 @@
+ #include "monitor/monitor-internal.h"
+ #include "qapi/error.h"
+ #include "qapi/qapi-commands-control.h"
++#include "qapi/qapi-commands-migration.h"
+ #include "qapi/qapi-commands-misc.h"
+ #include "qapi/qmp/qdict.h"
+ #include "qemu/cutils.h"
+@@ -443,3 +444,40 @@ void hmp_info_mtree(Monitor *mon, const QDict *qdict)
  
+     mtree_info(flatview, dispatch_tree, owner, disabled);
+ }
++
 +void hmp_savevm_start(Monitor *mon, const QDict *qdict)
 +{
 +    Error *errp = NULL;
 +    const char *statefile = qdict_get_try_str(qdict, "statefile");
 +
-+    qmp_savevm_start(statefile != NULL, statefile, &errp);
-+    hmp_handle_error(mon, errp);
-+}
-+
-+void hmp_snapshot_drive(Monitor *mon, const QDict *qdict)
-+{
-+    Error *errp = NULL;
-+    const char *name = qdict_get_str(qdict, "name");
-+    const char *device = qdict_get_str(qdict, "device");
-+
-+    qmp_snapshot_drive(device, name, &errp);
-+    hmp_handle_error(mon, errp);
-+}
-+
-+void hmp_delete_drive_snapshot(Monitor *mon, const QDict *qdict)
-+{
-+    Error *errp = NULL;
-+    const char *name = qdict_get_str(qdict, "name");
-+    const char *device = qdict_get_str(qdict, "device");
-+
-+    qmp_delete_drive_snapshot(device, name, &errp);
++    qmp_savevm_start(statefile, &errp);
 +    hmp_handle_error(mon, errp);
 +}
 +
@@ -739,7 +713,7 @@ index 15572befb1..1507180990 100644
 +    SaveVMInfo *info;
 +    info = qmp_query_savevm(NULL);
 +
-+    if (info->has_status) {
++    if (info->status) {
 +        monitor_printf(mon, "savevm status: %s\n", info->status);
 +        monitor_printf(mon, "total time: %" PRIu64 " milliseconds\n",
 +                       info->total_time);
@@ -749,21 +723,17 @@ index 15572befb1..1507180990 100644
 +    if (info->has_bytes) {
 +        monitor_printf(mon, "Bytes saved: %"PRIu64"\n", info->bytes);
 +    }
-+    if (info->has_error) {
++    if (info->error) {
 +        monitor_printf(mon, "Error: %s\n", info->error);
 +    }
 +}
-+
- void hmp_info_iothreads(Monitor *mon, const QDict *qdict)
- {
-     IOThreadInfoList *info_list = qmp_query_iothreads(NULL);
 diff --git a/qapi/migration.json b/qapi/migration.json
-index 81185d4311..3129f71fa8 100644
+index 8c65b90328..ed20d066cd 100644
 --- a/qapi/migration.json
 +++ b/qapi/migration.json
-@@ -261,6 +261,40 @@
-            '*compression': 'CompressionStats',
-            '*socket-address': ['SocketAddress'] } }
+@@ -297,6 +297,40 @@
+            '*dirty-limit-throttle-time-per-round': 'uint64',
+            '*dirty-limit-ring-full-time': 'uint64'} }
  
 +##
 +# @SaveVMInfo:
@@ -803,10 +773,10 @@ index 81185d4311..3129f71fa8 100644
  # @query-migrate:
  #
 diff --git a/qapi/misc.json b/qapi/misc.json
-index 27ef5a2b20..b3ce75dcae 100644
+index ec30e5c570..7147199a12 100644
 --- a/qapi/misc.json
 +++ b/qapi/misc.json
-@@ -435,6 +435,38 @@
+@@ -454,6 +454,24 @@
  ##
  { 'command': 'query-fdsets', 'returns': ['FdsetInfo'] }
  
@@ -815,26 +785,12 @@ index 27ef5a2b20..b3ce75dcae 100644
 +#
 +# Prepare for snapshot and halt VM. Save VM state to statefile.
 +#
++# @statefile: target file that state should be written to.
++#
 +##
 +{ 'command': 'savevm-start', 'data': { '*statefile': 'str' } }
 +
 +##
-+# @snapshot-drive:
-+#
-+# Create an internal drive snapshot.
-+#
-+##
-+{ 'command': 'snapshot-drive', 'data': { 'device': 'str', 'name': 'str' } }
-+
-+##
-+# @delete-drive-snapshot:
-+#
-+# Delete a drive snapshot.
-+#
-+##
-+{ 'command': 'delete-drive-snapshot', 'data': { 'device': 'str', 'name': 'str' } }
-+
-+##
 +# @savevm-end:
 +#
 +# Resume VM after a snapshot.
@@ -846,10 +802,10 @@ index 27ef5a2b20..b3ce75dcae 100644
  # @CommandLineParameterType:
  #
 diff --git a/qemu-options.hx b/qemu-options.hx
-index 31c04f7eea..c2ca6e91b5 100644
+index 8ce85d4559..511ab9415e 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
-@@ -4341,6 +4341,18 @@ SRST
+@@ -4610,6 +4610,18 @@ SRST
      Start right away with a saved state (``loadvm`` in monitor)
  ERST
  
@@ -868,11 +824,11 @@ index 31c04f7eea..c2ca6e91b5 100644
  #ifndef _WIN32
  DEF("daemonize", 0, QEMU_OPTION_daemonize, \
      "-daemonize      daemonize QEMU after initializing\n", QEMU_ARCH_ALL)
-diff --git a/softmmu/vl.c b/softmmu/vl.c
-index 706bd7cff7..b8637c4262 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -165,6 +165,7 @@ static const char *accelerators;
+diff --git a/system/vl.c b/system/vl.c
+index c644222982..2738ab7c91 100644
+--- a/system/vl.c
++++ b/system/vl.c
+@@ -163,6 +163,7 @@ static const char *accelerators;
  static bool have_custom_ram_size;
  static const char *ram_memdev_id;
  static QDict *machine_opts_dict;
@@ -880,10 +836,10 @@ index 706bd7cff7..b8637c4262 100644
  static QTAILQ_HEAD(, ObjectOption) object_opts = QTAILQ_HEAD_INITIALIZER(object_opts);
  static QTAILQ_HEAD(, DeviceOption) device_opts = QTAILQ_HEAD_INITIALIZER(device_opts);
  static int display_remote;
-@@ -2584,6 +2585,12 @@ void qmp_x_exit_preconfig(Error **errp)
- 
-     if (loadvm) {
+@@ -2712,6 +2713,12 @@ void qmp_x_exit_preconfig(Error **errp)
+         RunState state = autostart ? RUN_STATE_RUNNING : runstate_get();
          load_snapshot(loadvm, NULL, false, NULL, &error_fatal);
+         load_snapshot_resume(state);
 +    } else if (loadstate) {
 +        Error *local_err = NULL;
 +        if (load_snapshot_from_blockdev(loadstate, &local_err) < 0) {
@@ -893,7 +849,7 @@ index 706bd7cff7..b8637c4262 100644
      }
      if (replay_mode != REPLAY_MODE_NONE) {
          replay_vmstate_init();
-@@ -3133,6 +3140,9 @@ void qemu_init(int argc, char **argv, char **envp)
+@@ -3259,6 +3266,9 @@ void qemu_init(int argc, char **argv)
              case QEMU_OPTION_loadvm:
                  loadvm = optarg;
                  break;

debian/patches/pve/0018-PVE-add-optional-buffer-size-to-QEMUFile.patch

@@ -13,18 +13,18 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 [FE: adapt to removal of QEMUFileOps]
 Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
- migration/qemu-file.c    | 49 +++++++++++++++++++++++++++-------------
+ migration/qemu-file.c    | 50 +++++++++++++++++++++++++++-------------
  migration/qemu-file.h    |  2 ++
  migration/savevm-async.c |  5 ++--
- 3 files changed, 38 insertions(+), 18 deletions(-)
+ 3 files changed, 39 insertions(+), 18 deletions(-)
 
 diff --git a/migration/qemu-file.c b/migration/qemu-file.c
-index 4f400c2e52..21e8998867 100644
+index a10882d47f..19c1de0472 100644
 --- a/migration/qemu-file.c
 +++ b/migration/qemu-file.c
-@@ -31,8 +31,8 @@
- #include "trace.h"
- #include "qapi/error.h"
+@@ -35,8 +35,8 @@
+ #include "rdma.h"
+ #include "io/channel-file.h"
  
 -#define IO_BUF_SIZE 32768
 -#define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
@@ -32,8 +32,8 @@ index 4f400c2e52..21e8998867 100644
 +#define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 256)
  
  struct QEMUFile {
-     const QEMUFileHooks *hooks;
-@@ -55,7 +55,8 @@ struct QEMUFile {
+     QIOChannel *ioc;
+@@ -44,7 +44,8 @@ struct QEMUFile {
  
      int buf_index;
      int buf_size; /* 0 when writing */
@@ -43,8 +43,8 @@ index 4f400c2e52..21e8998867 100644
  
      DECLARE_BITMAP(may_free, MAX_IOV_SIZE);
      struct iovec iov[MAX_IOV_SIZE];
-@@ -106,7 +107,9 @@ bool qemu_file_mode_is_not_valid(const char *mode)
-     return false;
+@@ -101,7 +102,9 @@ int qemu_file_shutdown(QEMUFile *f)
+     return 0;
  }
  
 -static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
@@ -54,7 +54,7 @@ index 4f400c2e52..21e8998867 100644
  {
      QEMUFile *f;
  
-@@ -115,6 +118,8 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
+@@ -110,6 +113,8 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
      object_ref(ioc);
      f->ioc = ioc;
      f->is_writable = is_writable;
@@ -63,7 +63,7 @@ index 4f400c2e52..21e8998867 100644
  
      return f;
  }
-@@ -125,17 +130,27 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
+@@ -120,17 +125,27 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
   */
  QEMUFile *qemu_file_get_return_path(QEMUFile *f)
  {
@@ -93,8 +93,8 @@ index 4f400c2e52..21e8998867 100644
 +    return qemu_file_new_impl(ioc, false, buffer_size);
  }
  
- void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks)
-@@ -393,7 +408,7 @@ static ssize_t qemu_fill_buffer(QEMUFile *f)
+ /*
+@@ -328,7 +343,7 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
      do {
          len = qio_channel_read(f->ioc,
                                 (char *)f->buf + pending,
@@ -103,16 +103,17 @@ index 4f400c2e52..21e8998867 100644
                                 &local_error);
          if (len == QIO_CHANNEL_ERR_BLOCK) {
              if (qemu_in_coroutine()) {
-@@ -443,6 +458,8 @@ int qemu_fclose(QEMUFile *f)
+@@ -368,6 +383,9 @@ int qemu_fclose(QEMUFile *f)
+         ret = ret2;
      }
      g_clear_pointer(&f->ioc, object_unref);
- 
++
 +    free(f->buf);
 +
-     /* If any error was spotted before closing, we should report it
-      * instead of the close() return value.
-      */
-@@ -497,7 +514,7 @@ static void add_buf_to_iovec(QEMUFile *f, size_t len)
+     error_free(f->last_error_obj);
+     g_free(f);
+     trace_qemu_file_fclose();
+@@ -416,7 +434,7 @@ static void add_buf_to_iovec(QEMUFile *f, size_t len)
  {
      if (!add_to_iovec(f, f->buf + f->buf_index, len, false)) {
          f->buf_index += len;
@@ -121,7 +122,7 @@ index 4f400c2e52..21e8998867 100644
              qemu_fflush(f);
          }
      }
-@@ -523,7 +540,7 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
+@@ -441,7 +459,7 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
      }
  
      while (size > 0) {
@@ -130,7 +131,7 @@ index 4f400c2e52..21e8998867 100644
          if (l > size) {
              l = size;
          }
-@@ -570,8 +587,8 @@ size_t qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t size, size_t offset)
+@@ -587,8 +605,8 @@ size_t coroutine_mixed_fn qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t si
      size_t index;
  
      assert(!qemu_file_is_writable(f));
@@ -141,7 +142,7 @@ index 4f400c2e52..21e8998867 100644
  
      /* The 1st byte to read from */
      index = f->buf_index + offset;
-@@ -621,7 +638,7 @@ size_t qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size)
+@@ -638,7 +656,7 @@ size_t coroutine_mixed_fn qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size
          size_t res;
          uint8_t *src;
  
@@ -150,16 +151,16 @@ index 4f400c2e52..21e8998867 100644
          if (res == 0) {
              return done;
          }
-@@ -655,7 +672,7 @@ size_t qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size)
+@@ -672,7 +690,7 @@ size_t coroutine_mixed_fn qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size
   */
- size_t qemu_get_buffer_in_place(QEMUFile *f, uint8_t **buf, size_t size)
+ size_t coroutine_mixed_fn qemu_get_buffer_in_place(QEMUFile *f, uint8_t **buf, size_t size)
  {
 -    if (size < IO_BUF_SIZE) {
 +    if (size < f->buf_allocated_size) {
          size_t res;
          uint8_t *src = NULL;
  
-@@ -680,7 +697,7 @@ int qemu_peek_byte(QEMUFile *f, int offset)
+@@ -697,7 +715,7 @@ int coroutine_mixed_fn qemu_peek_byte(QEMUFile *f, int offset)
      int index = f->buf_index + offset;
  
      assert(!qemu_file_is_writable(f));
@@ -168,7 +169,7 @@ index 4f400c2e52..21e8998867 100644
  
      if (index >= f->buf_size) {
          qemu_fill_buffer(f);
-@@ -832,7 +849,7 @@ static int qemu_compress_data(z_stream *stream, uint8_t *dest, size_t dest_len,
+@@ -811,7 +829,7 @@ static int qemu_compress_data(z_stream *stream, uint8_t *dest, size_t dest_len,
  ssize_t qemu_put_compression_data(QEMUFile *f, z_stream *stream,
                                    const uint8_t *p, size_t size)
  {
@@ -178,24 +179,24 @@ index 4f400c2e52..21e8998867 100644
      if (blen < compressBound(size)) {
          return -1;
 diff --git a/migration/qemu-file.h b/migration/qemu-file.h
-index fa13d04d78..914f1a63a8 100644
+index 32fd4a34fd..36a0cd8cc8 100644
 --- a/migration/qemu-file.h
 +++ b/migration/qemu-file.h
-@@ -63,7 +63,9 @@ typedef struct QEMUFileHooks {
- } QEMUFileHooks;
+@@ -30,7 +30,9 @@
+ #include "io/channel.h"
  
  QEMUFile *qemu_file_new_input(QIOChannel *ioc);
 +QEMUFile *qemu_file_new_input_sized(QIOChannel *ioc, size_t buffer_size);
  QEMUFile *qemu_file_new_output(QIOChannel *ioc);
 +QEMUFile *qemu_file_new_output_sized(QIOChannel *ioc, size_t buffer_size);
- void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks);
  int qemu_fclose(QEMUFile *f);
  
+ /*
 diff --git a/migration/savevm-async.c b/migration/savevm-async.c
-index b3692739a0..e65a5e3482 100644
+index 779e4e2a78..bf36fc06d2 100644
 --- a/migration/savevm-async.c
 +++ b/migration/savevm-async.c
-@@ -367,7 +367,7 @@ void qmp_savevm_start(bool has_statefile, const char *statefile, Error **errp)
+@@ -379,7 +379,7 @@ void qmp_savevm_start(const char *statefile, Error **errp)
  
      QIOChannel *ioc = QIO_CHANNEL(qio_channel_savevm_async_new(snap_state.target,
                                                                 &snap_state.bs_pos));
@@ -204,7 +205,7 @@ index b3692739a0..e65a5e3482 100644
  
      if (!snap_state.file) {
          error_set(errp, ERROR_CLASS_GENERIC_ERROR, "failed to open '%s'", statefile);
-@@ -500,7 +500,8 @@ int load_snapshot_from_blockdev(const char *filename, Error **errp)
+@@ -496,7 +496,8 @@ int load_snapshot_from_blockdev(const char *filename, Error **errp)
      blk_op_block_all(be, blocker);
  
      /* restore the VM state */

debian/patches/pve/0019-PVE-block-add-the-zeroinit-block-driver-filter.patch

@@ -4,32 +4,33 @@ Date: Mon, 6 Apr 2020 12:16:47 +0200
 Subject: [PATCH] PVE: block: add the zeroinit block driver filter
 
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-[adapt to changed function signatures]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+[FE: adapt to changed function signatures
+     adhere to block graph lock requirements]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  block/meson.build |   1 +
- block/zeroinit.c  | 196 ++++++++++++++++++++++++++++++++++++++++++++++
- 2 files changed, 197 insertions(+)
+ block/zeroinit.c  | 214 ++++++++++++++++++++++++++++++++++++++++++++++
+ 2 files changed, 215 insertions(+)
  create mode 100644 block/zeroinit.c
 
 diff --git a/block/meson.build b/block/meson.build
-index 60bc305597..ad40c10b6a 100644
+index e1f03fd773..b530e117b5 100644
 --- a/block/meson.build
 +++ b/block/meson.build
-@@ -43,6 +43,7 @@ block_ss.add(files(
-   'vmdk.c',
-   'vpc.c',
+@@ -39,6 +39,7 @@ block_ss.add(files(
+   'throttle.c',
+   'throttle-groups.c',
    'write-threshold.c',
 +  'zeroinit.c',
  ), zstd, zlib, gnutls)
  
- softmmu_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
+ system_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
 diff --git a/block/zeroinit.c b/block/zeroinit.c
 new file mode 100644
-index 0000000000..20ee611f22
+index 0000000000..696558d8d6
 --- /dev/null
 +++ b/block/zeroinit.c
-@@ -0,0 +1,196 @@
+@@ -0,0 +1,214 @@
 +/*
 + * Filter to fake a zero-initialized block device.
 + *
@@ -43,6 +44,8 @@ index 0000000000..20ee611f22
 +#include "qemu/osdep.h"
 +#include "qapi/error.h"
 +#include "block/block_int.h"
++#include "block/block-io.h"
++#include "block/graph-lock.h"
 +#include "qapi/qmp/qdict.h"
 +#include "qapi/qmp/qstring.h"
 +#include "qemu/cutils.h"
@@ -93,6 +96,7 @@ index 0000000000..20ee611f22
 +                          Error **errp)
 +{
 +    BDRVZeroinitState *s = bs->opaque;
++    BdrvChild *file = NULL;
 +    QemuOpts *opts;
 +    Error *local_err = NULL;
 +    int ret;
@@ -108,8 +112,13 @@ index 0000000000..20ee611f22
 +    }
 +
 +    /* Open the raw file */
-+    bs->file = bdrv_open_child(qemu_opt_get(opts, "x-next"), options, "next",
-+                               bs, &child_of_bds, BDRV_CHILD_FILTERED, false, &local_err);
++    file = bdrv_open_child(qemu_opt_get(opts, "x-next"), options, "next", bs,
++                           &child_of_bds,
++                           BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, false,
++                           &local_err);
++    bdrv_graph_wrlock();
++    bs->file = file;
++    bdrv_graph_wrunlock();
 +    if (local_err) {
 +        ret = -EINVAL;
 +        error_propagate(errp, local_err);
@@ -122,7 +131,9 @@ index 0000000000..20ee611f22
 +    ret = 0;
 +fail:
 +    if (ret < 0) {
++        bdrv_graph_wrlock();
 +        bdrv_unref_child(bs, bs->file);
++        bdrv_graph_wrunlock();
 +    }
 +    qemu_opts_del(opts);
 +    return ret;
@@ -134,19 +145,22 @@ index 0000000000..20ee611f22
 +    (void)s;
 +}
 +
-+static int64_t zeroinit_getlength(BlockDriverState *bs)
++static coroutine_fn int64_t GRAPH_RDLOCK
++zeroinit_co_getlength(BlockDriverState *bs)
 +{
-+    return bdrv_getlength(bs->file->bs);
++    return bdrv_co_getlength(bs->file->bs);
 +}
 +
-+static int coroutine_fn zeroinit_co_preadv(BlockDriverState *bs,
-+    int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags)
++static int coroutine_fn GRAPH_RDLOCK
++zeroinit_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
++                   QEMUIOVector *qiov, BdrvRequestFlags flags)
 +{
 +    return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
 +}
 +
-+static int coroutine_fn zeroinit_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
-+                                                 int64_t bytes, BdrvRequestFlags flags)
++static int coroutine_fn GRAPH_RDLOCK
++zeroinit_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes,
++                          BdrvRequestFlags flags)
 +{
 +    BDRVZeroinitState *s = bs->opaque;
 +    if (offset >= s->extents)
@@ -154,8 +168,9 @@ index 0000000000..20ee611f22
 +    return bdrv_pwrite_zeroes(bs->file, offset, bytes, flags);
 +}
 +
-+static int coroutine_fn zeroinit_co_pwritev(BlockDriverState *bs,
-+    int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags)
++static int coroutine_fn GRAPH_RDLOCK
++zeroinit_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
++                    QEMUIOVector *qiov, BdrvRequestFlags flags)
 +{
 +    BDRVZeroinitState *s = bs->opaque;
 +    int64_t extents = offset + bytes;
@@ -164,33 +179,37 @@ index 0000000000..20ee611f22
 +    return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
 +}
 +
-+static coroutine_fn int zeroinit_co_flush(BlockDriverState *bs)
++static coroutine_fn int GRAPH_RDLOCK
++zeroinit_co_flush(BlockDriverState *bs)
 +{
 +    return bdrv_co_flush(bs->file->bs);
 +}
 +
-+static int zeroinit_has_zero_init(BlockDriverState *bs)
++static int GRAPH_RDLOCK
++zeroinit_has_zero_init(BlockDriverState *bs)
 +{
 +    BDRVZeroinitState *s = bs->opaque;
 +    return s->has_zero_init;
 +}
 +
-+static int coroutine_fn zeroinit_co_pdiscard(BlockDriverState *bs,
-+                                             int64_t offset, int64_t bytes)
++static int coroutine_fn GRAPH_RDLOCK
++zeroinit_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)
 +{
 +    return bdrv_co_pdiscard(bs->file, offset, bytes);
 +}
 +
-+static int zeroinit_co_truncate(BlockDriverState *bs, int64_t offset,
-+                                _Bool exact, PreallocMode prealloc,
-+                                BdrvRequestFlags req_flags, Error **errp)
++static int GRAPH_RDLOCK
++zeroinit_co_truncate(BlockDriverState *bs, int64_t offset, _Bool exact,
++                     PreallocMode prealloc, BdrvRequestFlags req_flags,
++                     Error **errp)
 +{
 +    return bdrv_co_truncate(bs->file, offset, exact, prealloc, req_flags, errp);
 +}
 +
-+static int zeroinit_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
++static coroutine_fn int GRAPH_RDLOCK
++zeroinit_co_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 +{
-+    return bdrv_get_info(bs->file->bs, bdi);
++    return bdrv_co_get_info(bs->file->bs, bdi);
 +}
 +
 +static BlockDriver bdrv_zeroinit = {
@@ -201,7 +220,7 @@ index 0000000000..20ee611f22
 +    .bdrv_parse_filename              = zeroinit_parse_filename,
 +    .bdrv_file_open                   = zeroinit_open,
 +    .bdrv_close                       = zeroinit_close,
-+    .bdrv_getlength                   = zeroinit_getlength,
++    .bdrv_co_getlength                = zeroinit_co_getlength,
 +    .bdrv_child_perm                  = bdrv_default_perms,
 +    .bdrv_co_flush_to_disk            = zeroinit_co_flush,
 +
@@ -217,7 +236,7 @@ index 0000000000..20ee611f22
 +    .bdrv_co_pdiscard                 = zeroinit_co_pdiscard,
 +
 +    .bdrv_co_truncate                 = zeroinit_co_truncate,
-+    .bdrv_get_info                    = zeroinit_get_info,
++    .bdrv_co_get_info                 = zeroinit_co_get_info,
 +};
 +
 +static void bdrv_zeroinit_init(void)

debian/patches/pve/0020-PVE-Add-dummy-id-command-line-parameter.patch

@@ -10,14 +10,14 @@ Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  qemu-options.hx | 3 +++
- softmmu/vl.c    | 8 ++++++++
+ system/vl.c     | 8 ++++++++
  2 files changed, 11 insertions(+)
 
 diff --git a/qemu-options.hx b/qemu-options.hx
-index c2ca6e91b5..ab4734ef32 100644
+index 511ab9415e..92e301d545 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
-@@ -1118,6 +1118,9 @@ backend describes how QEMU handles the data.
+@@ -1237,6 +1237,9 @@ legacy PC, they are not recommended for modern configurations.
  
  ERST
  
@@ -27,11 +27,11 @@ index c2ca6e91b5..ab4734ef32 100644
  DEF("fda", HAS_ARG, QEMU_OPTION_fda,
      "-fda/-fdb file  use 'file' as floppy disk 0/1 image\n", QEMU_ARCH_ALL)
  DEF("fdb", HAS_ARG, QEMU_OPTION_fdb, "", QEMU_ARCH_ALL)
-diff --git a/softmmu/vl.c b/softmmu/vl.c
-index b8637c4262..39f149924e 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -2620,6 +2620,7 @@ void qemu_init(int argc, char **argv, char **envp)
+diff --git a/system/vl.c b/system/vl.c
+index 2738ab7c91..20ebf2c920 100644
+--- a/system/vl.c
++++ b/system/vl.c
+@@ -2748,6 +2748,7 @@ void qemu_init(int argc, char **argv)
      MachineClass *machine_class;
      bool userconfig = true;
      FILE *vmstate_dump_file = NULL;
@@ -39,7 +39,7 @@ index b8637c4262..39f149924e 100644
  
      qemu_add_opts(&qemu_drive_opts);
      qemu_add_drive_opts(&qemu_legacy_drive_opts);
-@@ -3245,6 +3246,13 @@ void qemu_init(int argc, char **argv, char **envp)
+@@ -3371,6 +3372,13 @@ void qemu_init(int argc, char **argv)
                  machine_parse_property_opt(qemu_find_opts("smp-opts"),
                                             "smp", optarg);
                  break;
@@ -50,6 +50,6 @@ index b8637c4262..39f149924e 100644
 +                    exit(1);
 +                }
 +                break;
+ #ifdef CONFIG_VNC
              case QEMU_OPTION_vnc:
                  vnc_parse(optarg);
-                 break;

debian/patches/pve/0021-PVE-Config-Revert-target-i386-disable-LINT0-after-re.patch

@@ -11,10 +11,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 9 insertions(+)
 
 diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c
-index 2a20982066..7968ad5a93 100644
+index d8fc1e2815..789694b8b3 100644
 --- a/hw/intc/apic_common.c
 +++ b/hw/intc/apic_common.c
-@@ -278,6 +278,15 @@ static void apic_reset_common(DeviceState *dev)
+@@ -263,6 +263,15 @@ static void apic_reset_common(DeviceState *dev)
      info->vapic_base_update(s);
  
      apic_init_reset(dev);

debian/patches/pve/0022-PVE-Up-Config-file-posix-make-locking-optiono-on-cre.patch

@@ -9,14 +9,14 @@ Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  block/file-posix.c   | 59 ++++++++++++++++++++++++++++++--------------
- qapi/block-core.json |  3 ++-
- 2 files changed, 42 insertions(+), 20 deletions(-)
+ qapi/block-core.json |  7 +++++-
+ 2 files changed, 46 insertions(+), 20 deletions(-)
 
 diff --git a/block/file-posix.c b/block/file-posix.c
-index 3d60b80286..49ee1db5f9 100644
+index 43bc0bd520..60e98c87f1 100644
 --- a/block/file-posix.c
 +++ b/block/file-posix.c
-@@ -2475,6 +2475,7 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
+@@ -2876,6 +2876,7 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
      int fd;
      uint64_t perm, shared;
      int result = 0;
@@ -24,7 +24,7 @@ index 3d60b80286..49ee1db5f9 100644
  
      /* Validate options and set default values */
      assert(options->driver == BLOCKDEV_DRIVER_FILE);
-@@ -2515,19 +2516,22 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
+@@ -2916,19 +2917,22 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
      perm = BLK_PERM_WRITE | BLK_PERM_RESIZE;
      shared = BLK_PERM_ALL & ~BLK_PERM_RESIZE;
  
@@ -59,7 +59,7 @@ index 3d60b80286..49ee1db5f9 100644
      }
  
      /* Clear the file by truncating it to 0 */
-@@ -2581,13 +2585,15 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
+@@ -2982,13 +2986,15 @@ raw_co_create(BlockdevCreateOptions *options, Error **errp)
      }
  
  out_unlock:
@@ -82,7 +82,7 @@ index 3d60b80286..49ee1db5f9 100644
      }
  
  out_close:
-@@ -2612,6 +2618,7 @@ static int coroutine_fn raw_co_create_opts(BlockDriver *drv,
+@@ -3012,6 +3018,7 @@ raw_co_create_opts(BlockDriver *drv, const char *filename,
      PreallocMode prealloc;
      char *buf = NULL;
      Error *local_err = NULL;
@@ -90,7 +90,7 @@ index 3d60b80286..49ee1db5f9 100644
  
      /* Skip file: protocol prefix */
      strstart(filename, "file:", &filename);
-@@ -2634,6 +2641,18 @@ static int coroutine_fn raw_co_create_opts(BlockDriver *drv,
+@@ -3034,6 +3041,18 @@ raw_co_create_opts(BlockDriver *drv, const char *filename,
          return -EINVAL;
      }
  
@@ -109,7 +109,7 @@ index 3d60b80286..49ee1db5f9 100644
      options = (BlockdevCreateOptions) {
          .driver     = BLOCKDEV_DRIVER_FILE,
          .u.file     = {
-@@ -2645,6 +2664,8 @@ static int coroutine_fn raw_co_create_opts(BlockDriver *drv,
+@@ -3045,6 +3064,8 @@ raw_co_create_opts(BlockDriver *drv, const char *filename,
              .nocow              = nocow,
              .has_extent_size_hint = has_extent_size_hint,
              .extent_size_hint   = extent_size_hint,
@@ -119,10 +119,21 @@ index 3d60b80286..49ee1db5f9 100644
      };
      return raw_co_create(&options, errp);
 diff --git a/qapi/block-core.json b/qapi/block-core.json
-index e1857e7094..ddac91e8f6 100644
+index 45ab548dfe..f7c2b63c5d 100644
 --- a/qapi/block-core.json
 +++ b/qapi/block-core.json
-@@ -4537,7 +4537,8 @@
+@@ -4956,6 +4956,10 @@
+ # @extent-size-hint: Extent size hint to add to the image file; 0 for
+ #     not adding an extent size hint (default: 1 MB, since 5.1)
+ #
++# @locking: whether to enable file locking.  If set to 'auto', only
++#     enable when Open File Descriptor (OFD) locking API is available
++#     (default: auto).
++#
+ # Since: 2.12
+ ##
+ { 'struct': 'BlockdevCreateOptionsFile',
+@@ -4963,7 +4967,8 @@
              'size':                 'size',
              '*preallocation':       'PreallocMode',
              '*nocow':               'bool',

debian/patches/pve/0023-PVE-monitor-disable-oob-capability.patch

@@ -18,10 +18,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 2 deletions(-)
 
 diff --git a/monitor/qmp.c b/monitor/qmp.c
-index 6b8cfcf6d8..3ec67e32d3 100644
+index 589c9524f8..2505dd658a 100644
 --- a/monitor/qmp.c
 +++ b/monitor/qmp.c
-@@ -519,8 +519,7 @@ void monitor_init_qmp(Chardev *chr, bool pretty, Error **errp)
+@@ -536,8 +536,7 @@ void monitor_init_qmp(Chardev *chr, bool pretty, Error **errp)
      qemu_chr_fe_set_echo(&mon->common.chr, true);
  
      /* Note: we run QMP monitor in I/O thread when @chr supports that */

debian/patches/pve/0024-PVE-Compat-4.0-used-balloon-qemu-4-0-config-size-fal.patch

@@ -26,10 +26,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 2 insertions(+), 1 deletion(-)
 
 diff --git a/hw/core/machine.c b/hw/core/machine.c
-index a673302cce..fa424440bd 100644
+index 4273de16a0..83f1fc0293 100644
 --- a/hw/core/machine.c
 +++ b/hw/core/machine.c
-@@ -127,7 +127,8 @@ GlobalProperty hw_compat_4_0[] = {
+@@ -162,7 +162,8 @@ GlobalProperty hw_compat_4_0[] = {
      { "virtio-vga",     "edid", "false" },
      { "virtio-gpu-device", "edid", "false" },
      { "virtio-device", "use-started", "false" },

debian/patches/pve/0025-PVE-Allow-version-code-in-machine-type.patch

@@ -11,78 +11,79 @@ and only if 'is-current').
 
 Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: adapt to QAPI changes]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
- hw/core/machine-qmp-cmds.c |  6 ++++++
+ hw/core/machine-qmp-cmds.c |  5 +++++
  include/hw/boards.h        |  2 ++
  qapi/machine.json          |  4 +++-
- softmmu/vl.c               | 25 +++++++++++++++++++++++++
- 4 files changed, 36 insertions(+), 1 deletion(-)
+ system/vl.c                | 25 +++++++++++++++++++++++++
+ 4 files changed, 35 insertions(+), 1 deletion(-)
 
 diff --git a/hw/core/machine-qmp-cmds.c b/hw/core/machine-qmp-cmds.c
-index 76fff60a6b..ec9201fb9a 100644
+index 314351cdff..628a3537c5 100644
 --- a/hw/core/machine-qmp-cmds.c
 +++ b/hw/core/machine-qmp-cmds.c
-@@ -103,6 +103,12 @@ MachineInfoList *qmp_query_machines(Error **errp)
+@@ -94,6 +94,11 @@ MachineInfoList *qmp_query_machines(Error **errp)
          if (strcmp(mc->name, MACHINE_GET_CLASS(current_machine)->name) == 0) {
              info->has_is_current = true;
              info->is_current = true;
 +
 +            // PVE version string only exists for current machine
 +            if (mc->pve_version) {
-+                info->has_pve_version = true;
 +                info->pve_version = g_strdup(mc->pve_version);
 +            }
          }
  
          if (mc->default_cpu_type) {
 diff --git a/include/hw/boards.h b/include/hw/boards.h
-index 7b416c9787..8ae15c51aa 100644
+index 8b8f6d5c00..dd6d0a1447 100644
 --- a/include/hw/boards.h
 +++ b/include/hw/boards.h
-@@ -230,6 +230,8 @@ struct MachineClass {
+@@ -246,6 +246,8 @@ struct MachineClass {
      const char *desc;
      const char *deprecation_reason;
  
 +    const char *pve_version;
 +
      void (*init)(MachineState *state);
-     void (*reset)(MachineState *state);
+     void (*reset)(MachineState *state, ShutdownCause reason);
      void (*wakeup)(MachineState *state);
 diff --git a/qapi/machine.json b/qapi/machine.json
-index 555458f785..d868e4d31d 100644
+index a024d5b05d..1d69bffaa0 100644
 --- a/qapi/machine.json
 +++ b/qapi/machine.json
-@@ -157,6 +157,8 @@
+@@ -168,6 +168,8 @@
  #
- # @default-ram-id: the default ID of initial RAM memory backend (since 5.2)
+ # @acpi: machine type supports ACPI (since 8.0)
  #
 +# @pve-version: custom PVE version suffix specified as 'machine+pveN'
 +#
  # Since: 1.2
  ##
  { 'struct': 'MachineInfo',
-@@ -164,7 +166,7 @@
+@@ -175,7 +177,7 @@
              '*is-default': 'bool', '*is-current': 'bool', 'cpu-max': 'int',
              'hotpluggable-cpus': 'bool',  'numa-mem-supported': 'bool',
              'deprecated': 'bool', '*default-cpu-type': 'str',
--            '*default-ram-id': 'str' } }
-+            '*default-ram-id': 'str', '*pve-version': 'str' } }
+-            '*default-ram-id': 'str', 'acpi': 'bool' } }
++            '*default-ram-id': 'str', 'acpi': 'bool', '*pve-version': 'str' } }
  
  ##
  # @query-machines:
-diff --git a/softmmu/vl.c b/softmmu/vl.c
-index 39f149924e..0d233d55f3 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -1580,6 +1580,7 @@ static const QEMUOption *lookup_opt(int argc, char **argv,
+diff --git a/system/vl.c b/system/vl.c
+index 20ebf2c920..4d39e32097 100644
+--- a/system/vl.c
++++ b/system/vl.c
+@@ -1659,6 +1659,7 @@ static const QEMUOption *lookup_opt(int argc, char **argv,
  static MachineClass *select_machine(QDict *qdict, Error **errp)
  {
-     const char *optarg = qdict_get_try_str(qdict, "type");
+     const char *machine_type = qdict_get_try_str(qdict, "type");
 +    const char *pvever = qdict_get_try_str(qdict, "pvever");
      GSList *machines = object_class_get_list(TYPE_MACHINE, false);
      MachineClass *machine_class;
      Error *local_err = NULL;
-@@ -1597,6 +1598,11 @@ static MachineClass *select_machine(QDict *qdict, Error **errp)
+@@ -1676,6 +1677,11 @@ static MachineClass *select_machine(QDict *qdict, Error **errp)
          }
      }
  
@@ -94,7 +95,7 @@ index 39f149924e..0d233d55f3 100644
      g_slist_free(machines);
      if (local_err) {
          error_append_hint(&local_err, "Use -machine help to list supported machines\n");
-@@ -3187,12 +3193,31 @@ void qemu_init(int argc, char **argv, char **envp)
+@@ -3313,12 +3319,31 @@ void qemu_init(int argc, char **argv)
              case QEMU_OPTION_machine:
                  {
                      bool help;

debian/patches/pve/0026-block-backup-move-bcs-bitmap-initialization-to-job-c.patch

@@ -25,7 +25,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 4 insertions(+), 4 deletions(-)
 
 diff --git a/block/backup.c b/block/backup.c
-index b2b649e305..b6fa9e8a69 100644
+index ec29d6b810..270957c0cd 100644
 --- a/block/backup.c
 +++ b/block/backup.c
 @@ -237,8 +237,8 @@ static void backup_init_bcs_bitmap(BackupBlockJob *job)
@@ -48,9 +48,9 @@ index b2b649e305..b6fa9e8a69 100644
      if (s->sync_mode == MIRROR_SYNC_MODE_TOP) {
          int64_t offset = 0;
          int64_t count;
-@@ -492,6 +490,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
-     block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
+@@ -501,6 +499,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
                         &error_abort);
+     bdrv_graph_wrunlock();
  
 +    backup_init_bcs_bitmap(job);
 +

debian/patches/pve/0027-PVE-Backup-add-vma-backup-format-code.patch

@@ -3,40 +3,46 @@ From: Dietmar Maurer <dietmar@proxmox.com>
 Date: Mon, 6 Apr 2020 12:16:57 +0200
 Subject: [PATCH] PVE-Backup: add vma backup format code
 
+Notes about partial restoring: skipping a certain drive is done via a
+map line of the form skip=drive-scsi0. Since in PVE, most archives are
+compressed and piped to vma for restore, it's not easily possible to
+skip reads.
+
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-[FE: create: register all streams before entering coroutines]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+[FE: improvements during create
+     allow partial restore]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  block/meson.build |   2 +
  meson.build       |   5 +
- vma-reader.c      | 859 ++++++++++++++++++++++++++++++++++++++++++++++
- vma-writer.c      | 791 ++++++++++++++++++++++++++++++++++++++++++
- vma.c             | 849 +++++++++++++++++++++++++++++++++++++++++++++
+ vma-reader.c      | 870 ++++++++++++++++++++++++++++++++++++++++++++
+ vma-writer.c      | 818 +++++++++++++++++++++++++++++++++++++++++
+ vma.c             | 901 ++++++++++++++++++++++++++++++++++++++++++++++
  vma.h             | 150 ++++++++
- 6 files changed, 2656 insertions(+)
+ 6 files changed, 2746 insertions(+)
  create mode 100644 vma-reader.c
  create mode 100644 vma-writer.c
  create mode 100644 vma.c
  create mode 100644 vma.h
 
 diff --git a/block/meson.build b/block/meson.build
-index ad40c10b6a..3a0b84bc11 100644
+index b530e117b5..b245daa98e 100644
 --- a/block/meson.build
 +++ b/block/meson.build
-@@ -46,6 +46,8 @@ block_ss.add(files(
+@@ -42,6 +42,8 @@ block_ss.add(files(
    'zeroinit.c',
  ), zstd, zlib, gnutls)
  
 +block_ss.add(files('../vma-writer.c'), libuuid)
 +
- softmmu_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
+ system_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
+ system_ss.add(files('block-ram-registrar.c'))
  
- if get_option('qcow1').allowed()
 diff --git a/meson.build b/meson.build
-index d5230eadd6..ffff66c0cc 100644
+index 91a0aa64c6..620cc594b2 100644
 --- a/meson.build
 +++ b/meson.build
-@@ -1462,6 +1462,8 @@ keyutils = dependency('libkeyutils', required: false,
+@@ -1922,6 +1922,8 @@ endif
  
  has_gettid = cc.has_function('gettid')
  
@@ -45,7 +51,7 @@ index d5230eadd6..ffff66c0cc 100644
  # libselinux
  selinux = dependency('libselinux',
                       required: get_option('selinux'),
-@@ -3607,6 +3609,9 @@ if have_tools
+@@ -4023,6 +4025,9 @@ if have_tools
                 dependencies: [blockdev, qemuutil, gnutls, selinux],
                 install: true)
  
@@ -53,14 +59,14 @@ index d5230eadd6..ffff66c0cc 100644
 +                   dependencies: [authz, block, crypto, io, qom], install: true)
 +
    subdir('storage-daemon')
-   subdir('contrib/rdmacm-mux')
-   subdir('contrib/elf2dmp')
+ 
+   foreach exe: [ 'qemu-img', 'qemu-io', 'qemu-nbd', 'qemu-storage-daemon']
 diff --git a/vma-reader.c b/vma-reader.c
 new file mode 100644
-index 0000000000..e65f1e8415
+index 0000000000..d0b6721812
 --- /dev/null
 +++ b/vma-reader.c
-@@ -0,0 +1,859 @@
+@@ -0,0 +1,870 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -82,6 +88,7 @@ index 0000000000..e65f1e8415
 +#include "qemu/ratelimit.h"
 +#include "vma.h"
 +#include "block/block.h"
++#include "block/graph-lock.h"
 +#include "sysemu/block-backend.h"
 +
 +static unsigned char zero_vma_block[VMA_BLOCK_SIZE];
@@ -91,6 +98,7 @@ index 0000000000..e65f1e8415
 +    bool write_zeroes;
 +    unsigned long *bitmap;
 +    int bitmap_size;
++    bool skip;
 +}  VmaRestoreState;
 +
 +struct VmaReader {
@@ -488,13 +496,14 @@ index 0000000000..e65f1e8415
 +}
 +
 +static void allocate_rstate(VmaReader *vmar,  guint8 dev_id,
-+                            BlockBackend *target, bool write_zeroes)
++                            BlockBackend *target, bool write_zeroes, bool skip)
 +{
 +    assert(vmar);
 +    assert(dev_id);
 +
 +    vmar->rstate[dev_id].target = target;
 +    vmar->rstate[dev_id].write_zeroes = write_zeroes;
++    vmar->rstate[dev_id].skip = skip;
 +
 +    int64_t size = vmar->devinfo[dev_id].size;
 +
@@ -509,28 +518,30 @@ index 0000000000..e65f1e8415
 +}
 +
 +int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id, BlockBackend *target,
-+                           bool write_zeroes, Error **errp)
++                           bool write_zeroes, bool skip, Error **errp)
 +{
 +    assert(vmar);
-+    assert(target != NULL);
++    assert(target != NULL || skip);
 +    assert(dev_id);
-+    assert(vmar->rstate[dev_id].target == NULL);
++    assert(vmar->rstate[dev_id].target == NULL && !vmar->rstate[dev_id].skip);
 +
-+    int64_t size = blk_getlength(target);
-+    int64_t size_diff = size - vmar->devinfo[dev_id].size;
++    if (target != NULL) {
++        int64_t size = blk_getlength(target);
++        int64_t size_diff = size - vmar->devinfo[dev_id].size;
 +
-+    /* storage types can have different size restrictions, so it
-+     * is not always possible to create an image with exact size.
-+     * So we tolerate a size difference up to 4MB.
-+     */
-+    if ((size_diff < 0) || (size_diff > 4*1024*1024)) {
-+        error_setg(errp, "vma_reader_register_bs for stream %s failed - "
-+                   "unexpected size %zd != %zd", vmar->devinfo[dev_id].devname,
-+                   size, vmar->devinfo[dev_id].size);
-+        return -1;
++        /* storage types can have different size restrictions, so it
++         * is not always possible to create an image with exact size.
++         * So we tolerate a size difference up to 4MB.
++         */
++        if ((size_diff < 0) || (size_diff > 4*1024*1024)) {
++            error_setg(errp, "vma_reader_register_bs for stream %s failed - "
++                       "unexpected size %zd != %zd", vmar->devinfo[dev_id].devname,
++                       size, vmar->devinfo[dev_id].size);
++            return -1;
++        }
 +    }
 +
-+    allocate_rstate(vmar, dev_id, target, write_zeroes);
++    allocate_rstate(vmar, dev_id, target, write_zeroes, skip);
 +
 +    return 0;
 +}
@@ -590,8 +601,10 @@ index 0000000000..e65f1e8415
 +    } else {
 +        int res = blk_pwrite(target, sector_num * BDRV_SECTOR_SIZE, nb_sectors * BDRV_SECTOR_SIZE, buf, 0);
 +        if (res < 0) {
++            bdrv_graph_rdlock_main_loop();
 +            error_setg(errp, "blk_pwrite to %s failed (%d)",
 +                       bdrv_get_device_name(blk_bs(target)), res);
++            bdrv_graph_rdunlock_main_loop();
 +            return -1;
 +        }
 +    }
@@ -623,19 +636,23 @@ index 0000000000..e65f1e8415
 +        VmaRestoreState *rstate = &vmar->rstate[dev_id];
 +        BlockBackend *target = NULL;
 +
++        bool skip = rstate->skip;
++
 +        if (dev_id != vmar->vmstate_stream) {
 +            target = rstate->target;
-+            if (!verify && !target) {
++            if (!verify && !target && !skip) {
 +                error_setg(errp, "got wrong dev id %d", dev_id);
 +                return -1;
 +            }
 +
-+            if (vma_reader_get_bitmap(rstate, cluster_num)) {
-+                error_setg(errp, "found duplicated cluster %zd for stream %s",
-+                          cluster_num, vmar->devinfo[dev_id].devname);
-+                return -1;
++            if (!skip) {
++                if (vma_reader_get_bitmap(rstate, cluster_num)) {
++                    error_setg(errp, "found duplicated cluster %zd for stream %s",
++                              cluster_num, vmar->devinfo[dev_id].devname);
++                    return -1;
++                }
++                vma_reader_set_bitmap(rstate, cluster_num, 1);
 +            }
-+            vma_reader_set_bitmap(rstate, cluster_num, 1);
 +
 +            max_sector = vmar->devinfo[dev_id].size/BDRV_SECTOR_SIZE;
 +        } else {
@@ -681,7 +698,7 @@ index 0000000000..e65f1e8415
 +                return -1;
 +            }
 +
-+            if (!verify) {
++            if (!verify && !skip) {
 +                int nb_sectors = end_sector - sector_num;
 +                if (restore_write_data(vmar, dev_id, target, vmstate_fd,
 +                                       buf + start, sector_num, nb_sectors,
@@ -717,7 +734,7 @@ index 0000000000..e65f1e8415
 +                        return -1;
 +                    }
 +
-+                    if (!verify) {
++                    if (!verify && !skip) {
 +                        int nb_sectors = end_sector - sector_num;
 +                        if (restore_write_data(vmar, dev_id, target, vmstate_fd,
 +                                               buf + start, sector_num,
@@ -742,7 +759,7 @@ index 0000000000..e65f1e8415
 +                            vmar->partial_zero_cluster_data += zero_size;
 +                        }
 +
-+                        if (rstate->write_zeroes && !verify) {
++                        if (rstate->write_zeroes && !verify && !skip) {
 +                            if (restore_write_data(vmar, dev_id, target, vmstate_fd,
 +                                                   zero_vma_block, sector_num,
 +                                                   nb_sectors, errp) < 0) {
@@ -913,7 +930,7 @@ index 0000000000..e65f1e8415
 +
 +    for (dev_id = 1; dev_id < 255; dev_id++) {
 +        if (vma_reader_get_device_info(vmar, dev_id)) {
-+            allocate_rstate(vmar, dev_id, NULL, false);
++            allocate_rstate(vmar, dev_id, NULL, false, false);
 +        }
 +    }
 +
@@ -922,10 +939,10 @@ index 0000000000..e65f1e8415
 +
 diff --git a/vma-writer.c b/vma-writer.c
 new file mode 100644
-index 0000000000..df4b20793d
+index 0000000000..126b296647
 --- /dev/null
 +++ b/vma-writer.c
-@@ -0,0 +1,791 @@
+@@ -0,0 +1,818 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -941,6 +958,8 @@ index 0000000000..df4b20793d
 +
 +#include "qemu/osdep.h"
 +#include <glib.h>
++#include <linux/magic.h>
++#include <sys/vfs.h>
 +#include <uuid/uuid.h>
 +
 +#include "vma.h"
@@ -949,6 +968,7 @@ index 0000000000..df4b20793d
 +#include "qemu/main-loop.h"
 +#include "qemu/coroutine.h"
 +#include "qemu/cutils.h"
++#include "qemu/error-report.h"
 +#include "qemu/memalign.h"
 +
 +#define DEBUG_VMA 0
@@ -1132,10 +1152,10 @@ index 0000000000..df4b20793d
 +{
 +    assert(qemu_in_coroutine());
 +    AioContext *ctx = qemu_get_current_aio_context();
-+    aio_set_fd_handler(ctx, fd, false, NULL, (IOHandler *)qemu_coroutine_enter,
-+                       NULL, NULL, qemu_coroutine_self());
++    aio_set_fd_handler(ctx, fd, NULL, (IOHandler *)qemu_coroutine_enter, NULL,
++                       NULL, qemu_coroutine_self());
 +    qemu_coroutine_yield();
-+    aio_set_fd_handler(ctx, fd, false, NULL, NULL, NULL, NULL, NULL);
++    aio_set_fd_handler(ctx, fd, NULL, NULL, NULL, NULL, NULL);
 +}
 +
 +static ssize_t coroutine_fn
@@ -1184,6 +1204,23 @@ index 0000000000..df4b20793d
 +    return (done == bytes) ? bytes : -1;
 +}
 +
++static bool is_path_tmpfs(const char *path) {
++    struct statfs fs;
++    int ret;
++
++    do {
++        ret = statfs(path, &fs);
++    } while (ret != 0 && errno == EINTR);
++
++    if (ret != 0) {
++        warn_report("statfs call for %s failed, assuming not tmpfs - %s\n",
++                    path, strerror(errno));
++        return false;
++    }
++
++    return fs.f_type == TMPFS_MAGIC;
++}
++
 +VmaWriter *vma_writer_create(const char *filename, uuid_t uuid, Error **errp)
 +{
 +    const char *p;
@@ -1233,12 +1270,19 @@ index 0000000000..df4b20793d
 +            }
 +            /* try to use O_NONBLOCK */
 +            fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_NONBLOCK);
-+        } else  {
-+            oflags = O_NONBLOCK|O_DIRECT|O_WRONLY|O_EXCL;
++        } else {
++            gchar *dirname = g_path_get_dirname(filename);
++            oflags = O_NONBLOCK|O_WRONLY|O_EXCL;
++            if (!is_path_tmpfs(dirname)) {
++                oflags |= O_DIRECT;
++            }
++            g_free(dirname);
 +            vmaw->fd = qemu_create(filename, oflags, 0644, errp);
 +        }
 +
 +        if (vmaw->fd < 0) {
++            error_free(*errp);
++            *errp = NULL;
 +            error_setg(errp, "can't open file %s - %s\n", filename,
 +                       g_strerror(errno));
 +            goto err;
@@ -1719,10 +1763,10 @@ index 0000000000..df4b20793d
 +}
 diff --git a/vma.c b/vma.c
 new file mode 100644
-index 0000000000..e8dffb43e0
+index 0000000000..bb715e9061
 --- /dev/null
 +++ b/vma.c
-@@ -0,0 +1,849 @@
+@@ -0,0 +1,901 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -1756,7 +1800,7 @@ index 0000000000..e8dffb43e0
 +        "vma list <filename>\n"
 +        "vma config <filename> [-c config]\n"
 +        "vma create <filename> [-c config] pathname ...\n"
-+        "vma extract <filename> [-r <fifo>] <targetdir>\n"
++        "vma extract <filename> [-d <drive-list>] [-r <fifo>] <targetdir>\n"
 +        "vma verify <filename> [-v]\n"
 +        ;
 +
@@ -1863,6 +1907,7 @@ index 0000000000..e8dffb43e0
 +    char *throttling_group;
 +    char *cache;
 +    bool write_zero;
++    bool skip;
 +} RestoreMap;
 +
 +static bool try_parse_option(char **line, const char *optname, char **out, const char *inbuf) {
@@ -1900,9 +1945,10 @@ index 0000000000..e8dffb43e0
 +    const char *filename;
 +    const char *dirname;
 +    const char *readmap = NULL;
++    gchar **drive_list = NULL;
 +
 +    for (;;) {
-+        c = getopt(argc, argv, "hvr:");
++        c = getopt(argc, argv, "hvd:r:");
 +        if (c == -1) {
 +            break;
 +        }
@@ -1911,6 +1957,9 @@ index 0000000000..e8dffb43e0
 +        case 'h':
 +            help();
 +            break;
++        case 'd':
++            drive_list = g_strsplit(optarg, ",", 254);
++            break;
 +        case 'r':
 +            readmap = optarg;
 +            break;
@@ -1970,74 +2019,89 @@ index 0000000000..e8dffb43e0
 +            char *bps = NULL;
 +            char *group = NULL;
 +            char *cache = NULL;
++            char *devname = NULL;
++            bool skip = false;
++            uint64_t bps_value = 0;
++            const char *path = NULL;
++            bool write_zero = true;
++
 +            if (!line || line[0] == '\0' || !strcmp(line, "done\n")) {
 +                break;
 +            }
 +            int len = strlen(line);
 +            if (line[len - 1] == '\n') {
 +                line[len - 1] = '\0';
-+                if (len == 1) {
++                len = len - 1;
++                if (len == 0) {
 +                    break;
 +                }
 +            }
 +
-+            while (1) {
-+                if (!try_parse_option(&line, "format", &format, inbuf) &&
-+                    !try_parse_option(&line, "throttling.bps", &bps, inbuf) &&
-+                    !try_parse_option(&line, "throttling.group", &group, inbuf) &&
-+                    !try_parse_option(&line, "cache", &cache, inbuf))
-+                {
-+                    break;
++            if (strncmp(line, "skip", 4) == 0) {
++                if (len < 6 || line[4] != '=') {
++                    g_error("read map failed - option 'skip' has no value ('%s')",
++                            inbuf);
++                } else {
++                    devname = line + 5;
++                    skip = true;
 +                }
-+            }
-+
-+            uint64_t bps_value = 0;
-+            if (bps) {
-+                bps_value = verify_u64(bps);
-+                g_free(bps);
-+            }
-+
-+            const char *path;
-+            bool write_zero;
-+            if (line[0] == '0' && line[1] == ':') {
-+                path = line + 2;
-+                write_zero = false;
-+            } else if (line[0] == '1' && line[1] == ':') {
-+                path = line + 2;
-+                write_zero = true;
 +            } else {
-+                g_error("read map failed - parse error ('%s')", inbuf);
++                while (1) {
++                    if (!try_parse_option(&line, "format", &format, inbuf) &&
++                        !try_parse_option(&line, "throttling.bps", &bps, inbuf) &&
++                        !try_parse_option(&line, "throttling.group", &group, inbuf) &&
++                        !try_parse_option(&line, "cache", &cache, inbuf))
++                    {
++                        break;
++                    }
++                }
++
++                if (bps) {
++                    bps_value = verify_u64(bps);
++                    g_free(bps);
++                }
++
++                if (line[0] == '0' && line[1] == ':') {
++                    path = line + 2;
++                    write_zero = false;
++                } else if (line[0] == '1' && line[1] == ':') {
++                    path = line + 2;
++                    write_zero = true;
++                } else {
++                    g_error("read map failed - parse error ('%s')", inbuf);
++                }
++
++                path = extract_devname(path, &devname, -1);
 +            }
 +
-+            char *devname = NULL;
-+            path = extract_devname(path, &devname, -1);
 +            if (!devname) {
 +                g_error("read map failed - no dev name specified ('%s')",
 +                        inbuf);
 +            }
 +
-+            RestoreMap *map = g_new0(RestoreMap, 1);
-+            map->devname = g_strdup(devname);
-+            map->path = g_strdup(path);
-+            map->format = format;
-+            map->throttling_bps = bps_value;
-+            map->throttling_group = group;
-+            map->cache = cache;
-+            map->write_zero = write_zero;
++            RestoreMap *restore_map = g_new0(RestoreMap, 1);
++            restore_map->devname = g_strdup(devname);
++            restore_map->path = g_strdup(path);
++            restore_map->format = format;
++            restore_map->throttling_bps = bps_value;
++            restore_map->throttling_group = group;
++            restore_map->cache = cache;
++            restore_map->write_zero = write_zero;
++            restore_map->skip = skip;
 +
-+            g_hash_table_insert(devmap, map->devname, map);
++            g_hash_table_insert(devmap, restore_map->devname, restore_map);
 +
 +        };
 +    }
 +
 +    int i;
 +    int vmstate_fd = -1;
-+    guint8 vmstate_stream = 0;
++    bool drive_rename_bitmap[255];
++    memset(drive_rename_bitmap, 0, sizeof(drive_rename_bitmap));
 +
 +    for (i = 1; i < 255; i++) {
 +        VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i);
 +        if (di && (strcmp(di->devname, "vmstate") == 0)) {
-+            vmstate_stream = i;
 +            char *statefn = g_strdup_printf("%s/vmstate.bin", dirname);
 +            vmstate_fd = open(statefn, O_WRONLY|O_CREAT|O_EXCL, 0644);
 +            if (vmstate_fd < 0) {
@@ -2053,10 +2117,25 @@ index 0000000000..e8dffb43e0
 +            const char *cache = NULL;
 +            int flags = BDRV_O_RDWR;
 +            bool write_zero = true;
++            bool skip = false;
 +
 +            BlockBackend *blk = NULL;
 +
-+            if (readmap) {
++            if (drive_list) {
++                skip = true;
++                int j;
++                for (j = 0; drive_list[j]; j++) {
++                    if (strcmp(drive_list[j], di->devname) == 0) {
++                        skip = false;
++                        drive_rename_bitmap[i] = true;
++                        break;
++                    }
++                }
++            } else {
++                drive_rename_bitmap[i] = true;
++            }
++
++            if (!skip && readmap) {
 +                RestoreMap *map;
 +                map = (RestoreMap *)g_hash_table_lookup(devmap, di->devname);
 +                if (map == NULL) {
@@ -2068,7 +2147,8 @@ index 0000000000..e8dffb43e0
 +                throttling_group = map->throttling_group;
 +                cache = map->cache;
 +                write_zero = map->write_zero;
-+            } else {
++                skip = map->skip;
++            } else if (!skip) {
 +                devfn = g_strdup_printf("%s/tmp-disk-%s.raw",
 +                                        dirname, di->devname);
 +                printf("DEVINFO %s %zd\n", devfn, di->size);
@@ -2086,57 +2166,60 @@ index 0000000000..e8dffb43e0
 +                write_zero = false;
 +            }
 +
-+	    size_t devlen = strlen(devfn);
-+	    QDict *options = NULL;
-+            bool writethrough;
-+            if (format) {
-+                /* explicit format from commandline */
-+                options = qdict_new();
-+                qdict_put_str(options, "driver", format);
-+            } else if ((devlen > 4 && strcmp(devfn+devlen-4, ".raw") == 0) ||
-+	               strncmp(devfn, "/dev/", 5) == 0)
-+	    {
-+                /* This part is now deprecated for PVE as well (just as qemu
-+                 * deprecated not specifying an explicit raw format, too.
-+                 */
-+		/* explicit raw format */
-+		options = qdict_new();
-+		qdict_put_str(options, "driver", "raw");
-+	    }
-+            if (cache && bdrv_parse_cache_mode(cache, &flags, &writethrough)) {
-+                g_error("invalid cache option: %s\n", cache);
-+            }
-+
-+	    if (errp || !(blk = blk_new_open(devfn, NULL, options, flags, &errp))) {
-+                g_error("can't open file %s - %s", devfn,
-+                        error_get_pretty(errp));
-+            }
-+
-+            if (cache) {
-+                blk_set_enable_write_cache(blk, !writethrough);
-+            }
-+
-+            if (throttling_group) {
-+                blk_io_limits_enable(blk, throttling_group);
-+            }
-+
-+            if (throttling_bps) {
-+                if (!throttling_group) {
-+                    blk_io_limits_enable(blk, devfn);
++            if (!skip) {
++                size_t devlen = strlen(devfn);
++                QDict *options = NULL;
++                bool writethrough;
++                if (format) {
++                    /* explicit format from commandline */
++                    options = qdict_new();
++                    qdict_put_str(options, "driver", format);
++                } else if ((devlen > 4 && strcmp(devfn+devlen-4, ".raw") == 0) ||
++                    strncmp(devfn, "/dev/", 5) == 0)
++                {
++                    /* This part is now deprecated for PVE as well (just as qemu
++                     * deprecated not specifying an explicit raw format, too.
++                     */
++                    /* explicit raw format */
++                    options = qdict_new();
++                    qdict_put_str(options, "driver", "raw");
 +                }
 +
-+                ThrottleConfig cfg;
-+                throttle_config_init(&cfg);
-+                cfg.buckets[THROTTLE_BPS_WRITE].avg = throttling_bps;
-+                Error *err = NULL;
-+                if (!throttle_is_valid(&cfg, &err)) {
-+                    error_report_err(err);
-+                    g_error("failed to apply throttling");
++                if (cache && bdrv_parse_cache_mode(cache, &flags, &writethrough)) {
++                    g_error("invalid cache option: %s\n", cache);
++                }
++
++                if (errp || !(blk = blk_new_open(devfn, NULL, options, flags, &errp))) {
++                    g_error("can't open file %s - %s", devfn,
++                            error_get_pretty(errp));
++                }
++
++                if (cache) {
++                    blk_set_enable_write_cache(blk, !writethrough);
++                }
++
++                if (throttling_group) {
++                    blk_io_limits_enable(blk, throttling_group);
++                }
++
++                if (throttling_bps) {
++                    if (!throttling_group) {
++                        blk_io_limits_enable(blk, devfn);
++                    }
++
++                    ThrottleConfig cfg;
++                    throttle_config_init(&cfg);
++                    cfg.buckets[THROTTLE_BPS_WRITE].avg = throttling_bps;
++                    Error *err = NULL;
++                    if (!throttle_is_valid(&cfg, &err)) {
++                        error_report_err(err);
++                        g_error("failed to apply throttling");
++                    }
++                    blk_set_io_limits(blk, &cfg);
 +                }
-+                blk_set_io_limits(blk, &cfg);
 +            }
 +
-+            if (vma_reader_register_bs(vmar, i, blk, write_zero, &errp) < 0) {
++            if (vma_reader_register_bs(vmar, i, blk, write_zero, skip, &errp) < 0) {
 +                g_error("%s", error_get_pretty(errp));
 +            }
 +
@@ -2146,6 +2229,10 @@ index 0000000000..e8dffb43e0
 +        }
 +    }
 +
++    if (drive_list) {
++        g_strfreev(drive_list);
++    }
++
 +    if (vma_reader_restore(vmar, vmstate_fd, verbose, &errp) < 0) {
 +        g_error("restore failed - %s", error_get_pretty(errp));
 +    }
@@ -2153,7 +2240,7 @@ index 0000000000..e8dffb43e0
 +    if (!readmap) {
 +        for (i = 1; i < 255; i++) {
 +            VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i);
-+            if (di && (i != vmstate_stream)) {
++            if (di && drive_rename_bitmap[i]) {
 +                char *tmpfn = g_strdup_printf("%s/tmp-disk-%s.raw",
 +                                              dirname, di->devname);
 +                char *fn = g_strdup_printf("%s/disk-%s.raw",
@@ -2252,7 +2339,7 @@ index 0000000000..e8dffb43e0
 +    struct iovec iov;
 +    QEMUIOVector qiov;
 +
-+    int64_t start, end;
++    int64_t start, end, readlen;
 +    int ret = 0;
 +
 +    unsigned char *buf = blk_blockalign(job->target, VMA_CLUSTER_SIZE);
@@ -2266,16 +2353,24 @@ index 0000000000..e8dffb43e0
 +        iov.iov_len = VMA_CLUSTER_SIZE;
 +        qemu_iovec_init_external(&qiov, &iov, 1);
 +
++        if (start + 1 == end) {
++            memset(buf, 0, VMA_CLUSTER_SIZE);
++            readlen = job->len - start * VMA_CLUSTER_SIZE;
++            assert(readlen > 0 && readlen <= VMA_CLUSTER_SIZE);
++        } else {
++            readlen = VMA_CLUSTER_SIZE;
++        }
++
 +        ret = blk_co_preadv(job->target, start * VMA_CLUSTER_SIZE,
-+                            VMA_CLUSTER_SIZE, &qiov, 0);
++                            readlen, &qiov, 0);
 +        if (ret < 0) {
-+            vma_writer_set_error(job->vmaw, "read error", -1);
++            vma_writer_set_error(job->vmaw, "read error");
 +            goto out;
 +        }
 +
 +        size_t zb = 0;
 +        if (vma_writer_write(job->vmaw, job->dev_id, start, buf, &zb) < 0) {
-+            vma_writer_set_error(job->vmaw, "backup_dump_cb vma_writer_write failed", -1);
++            vma_writer_set_error(job->vmaw, "backup_dump_cb vma_writer_write failed");
 +            goto out;
 +        }
 +    }
@@ -2293,7 +2388,7 @@ index 0000000000..e8dffb43e0
 +
 +static int create_archive(int argc, char **argv)
 +{
-+    int i, c;
++    int c;
 +    int verbose = 0;
 +    const char *archivename;
 +    GList *backup_coroutines = NULL;
@@ -2451,6 +2546,7 @@ index 0000000000..e8dffb43e0
 +    vma_writer_get_status(vmaw, &vmastat);
 +
 +    if (verbose) {
++        int i;
 +        for (i = 0; i < 256; i++) {
 +            VmaStreamInfo *si = &vmastat.stream_info[i];
 +            if (si->size) {
@@ -2574,7 +2670,7 @@ index 0000000000..e8dffb43e0
 +}
 diff --git a/vma.h b/vma.h
 new file mode 100644
-index 0000000000..c895c97f6d
+index 0000000000..86d2873aa5
 --- /dev/null
 +++ b/vma.h
 @@ -0,0 +1,150 @@
@@ -2712,7 +2808,7 @@ index 0000000000..c895c97f6d
 +int coroutine_fn vma_writer_flush_output(VmaWriter *vmaw);
 +
 +int vma_writer_get_status(VmaWriter *vmaw, VmaStatus *status);
-+void vma_writer_set_error(VmaWriter *vmaw, const char *fmt, ...);
++void vma_writer_set_error(VmaWriter *vmaw, const char *fmt, ...) G_GNUC_PRINTF(2, 3);
 +
 +
 +VmaReader *vma_reader_create(const char *filename, Error **errp);
@@ -2722,7 +2818,7 @@ index 0000000000..c895c97f6d
 +VmaDeviceInfo *vma_reader_get_device_info(VmaReader *vmar, guint8 dev_id);
 +int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id,
 +                           BlockBackend *target, bool write_zeroes,
-+                           Error **errp);
++                           bool skip, Error **errp);
 +int vma_reader_restore(VmaReader *vmar, int vmstate_fd, bool verbose,
 +                       Error **errp);
 +int vma_reader_verify(VmaReader *vmar, bool verbose, Error **errp);

debian/patches/pve/0028-PVE-Backup-add-backup-dump-block-driver.patch

@@ -9,21 +9,23 @@ Subject: [PATCH] PVE-Backup: add backup-dump block driver
 - job.c: make job_should_pause non-static
 
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: adapt to coroutine changes]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
- block/backup-dump.c              | 167 +++++++++++++++++++++++++++++++
+ block/backup-dump.c              | 172 +++++++++++++++++++++++++++++++
  block/backup.c                   |  30 ++----
  block/meson.build                |   1 +
  include/block/block_int-common.h |  35 +++++++
  job.c                            |   3 +-
- 5 files changed, 213 insertions(+), 23 deletions(-)
+ 5 files changed, 218 insertions(+), 23 deletions(-)
  create mode 100644 block/backup-dump.c
 
 diff --git a/block/backup-dump.c b/block/backup-dump.c
 new file mode 100644
-index 0000000000..04718a94e2
+index 0000000000..e46abf1070
 --- /dev/null
 +++ b/block/backup-dump.c
-@@ -0,0 +1,167 @@
+@@ -0,0 +1,172 @@
 +/*
 + * BlockDriver to send backup data stream to a callback function
 + *
@@ -35,6 +37,8 @@ index 0000000000..04718a94e2
 + */
 +
 +#include "qemu/osdep.h"
++
++#include "qapi/qmp/qdict.h"
 +#include "qom/object_interfaces.h"
 +#include "block/block_int.h"
 +
@@ -45,7 +49,8 @@ index 0000000000..04718a94e2
 +    void           *dump_cb_data;
 +} BDRVBackupDumpState;
 +
-+static int qemu_backup_dump_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
++static coroutine_fn int qemu_backup_dump_co_get_info(BlockDriverState *bs,
++                                                     BlockDriverInfo *bdi)
 +{
 +    BDRVBackupDumpState *s = bs->opaque;
 +
@@ -86,7 +91,7 @@ index 0000000000..04718a94e2
 +    /* Nothing to do. */
 +}
 +
-+static int64_t qemu_backup_dump_getlength(BlockDriverState *bs)
++static coroutine_fn int64_t qemu_backup_dump_co_getlength(BlockDriverState *bs)
 +{
 +    BDRVBackupDumpState *s = bs->opaque;
 +
@@ -146,8 +151,8 @@ index 0000000000..04718a94e2
 +
 +    .bdrv_close                   = qemu_backup_dump_close,
 +    .bdrv_has_zero_init           = bdrv_has_zero_init_1,
-+    .bdrv_getlength               = qemu_backup_dump_getlength,
-+    .bdrv_get_info                = qemu_backup_dump_get_info,
++    .bdrv_co_getlength            = qemu_backup_dump_co_getlength,
++    .bdrv_co_get_info             = qemu_backup_dump_co_get_info,
 +
 +    .bdrv_co_writev               = qemu_backup_dump_co_writev,
 +
@@ -166,7 +171,7 @@ index 0000000000..04718a94e2
 +block_init(bdrv_backup_dump_init);
 +
 +
-+BlockDriverState *bdrv_backup_dump_create(
++BlockDriverState *coroutine_fn bdrv_co_backup_dump_create(
 +    int dump_cb_block_size,
 +    uint64_t byte_size,
 +    BackupDumpFunc *dump_cb,
@@ -174,9 +179,11 @@ index 0000000000..04718a94e2
 +    Error **errp)
 +{
 +    BDRVBackupDumpState *state;
-+    BlockDriverState *bs = bdrv_new_open_driver(
-+        &bdrv_backup_dump_drive, NULL, BDRV_O_RDWR, errp);
 +
++    QDict *options = qdict_new();
++    qdict_put_str(options, "driver", "backup-dump-drive");
++
++    BlockDriverState *bs = bdrv_co_open(NULL, NULL, options, BDRV_O_RDWR, errp);
 +    if (!bs) {
 +        return NULL;
 +    }
@@ -192,7 +199,7 @@ index 0000000000..04718a94e2
 +    return bs;
 +}
 diff --git a/block/backup.c b/block/backup.c
-index b6fa9e8a69..789f8b7799 100644
+index 270957c0cd..16d611c4ca 100644
 --- a/block/backup.c
 +++ b/block/backup.c
 @@ -29,28 +29,6 @@
@@ -224,7 +231,7 @@ index b6fa9e8a69..789f8b7799 100644
  static const BlockJobDriver backup_job_driver;
  
  static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
-@@ -454,6 +432,14 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+@@ -461,6 +439,14 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
      }
  
      cluster_size = block_copy_cluster_size(bcs);
@@ -240,7 +247,7 @@ index b6fa9e8a69..789f8b7799 100644
      if (perf->max_chunk && perf->max_chunk < cluster_size) {
          error_setg(errp, "Required max-chunk (%" PRIi64 ") is less than backup "
 diff --git a/block/meson.build b/block/meson.build
-index 3a0b84bc11..7f22e7f177 100644
+index b245daa98e..e99914eaa4 100644
 --- a/block/meson.build
 +++ b/block/meson.build
 @@ -4,6 +4,7 @@ block_ss.add(files(
@@ -248,28 +255,28 @@ index 3a0b84bc11..7f22e7f177 100644
    'amend.c',
    'backup.c',
 +  'backup-dump.c',
-   'copy-before-write.c',
    'blkdebug.c',
    'blklogwrites.c',
+   'blkverify.c',
 diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
-index 8947abab76..f272d0d8dc 100644
+index 761276127e..b3e6697613 100644
 --- a/include/block/block_int-common.h
 +++ b/include/block/block_int-common.h
 @@ -26,6 +26,7 @@
  
- #include "block/accounting.h"
- #include "block/block.h"
+ #include "block/aio.h"
+ #include "block/block-common.h"
 +#include "block/block-copy.h"
- #include "block/aio-wait.h"
- #include "qemu/queue.h"
- #include "qemu/coroutine.h"
-@@ -64,6 +65,40 @@
+ #include "block/block-global-state.h"
+ #include "block/snapshot.h"
+ #include "qemu/iov.h"
+@@ -60,6 +61,40 @@
  
  #define BLOCK_PROBE_BUF_SIZE        512
  
 +typedef int BackupDumpFunc(void *opaque, uint64_t offset, uint64_t bytes, const void *buf);
 +
-+BlockDriverState *bdrv_backup_dump_create(
++BlockDriverState *coroutine_fn bdrv_co_backup_dump_create(
 +    int dump_cb_block_size,
 +    uint64_t byte_size,
 +    BackupDumpFunc *dump_cb,
@@ -305,16 +312,16 @@ index 8947abab76..f272d0d8dc 100644
      BDRV_TRACKED_READ,
      BDRV_TRACKED_WRITE,
 diff --git a/job.c b/job.c
-index 075c6f3a20..e5699ad200 100644
+index 660ce22c56..baf54c8d60 100644
 --- a/job.c
 +++ b/job.c
-@@ -276,7 +276,8 @@ static bool job_started(Job *job)
-     return job->co;
+@@ -331,7 +331,8 @@ static bool job_started_locked(Job *job)
  }
  
--static bool job_should_pause(Job *job)
-+bool job_should_pause(Job *job);
-+bool job_should_pause(Job *job)
+ /* Called with job_mutex held. */
+-static bool job_should_pause_locked(Job *job)
++bool job_should_pause_locked(Job *job);
++bool job_should_pause_locked(Job *job)
  {
      return job->pause_count > 0;
  }

debian/patches/pve/0029-PVE-Add-sequential-job-transaction-support.patch

@@ -7,14 +7,14 @@ Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  include/qemu/job.h | 12 ++++++++++++
- job.c              | 31 +++++++++++++++++++++++++++++++
- 2 files changed, 43 insertions(+)
+ job.c              | 34 ++++++++++++++++++++++++++++++++++
+ 2 files changed, 46 insertions(+)
 
 diff --git a/include/qemu/job.h b/include/qemu/job.h
-index c105b31076..5096679571 100644
+index 2b873f2576..528cd6acb9 100644
 --- a/include/qemu/job.h
 +++ b/include/qemu/job.h
-@@ -316,6 +316,18 @@ typedef enum JobCreateFlags {
+@@ -362,6 +362,18 @@ void job_unlock(void);
   */
  JobTxn *job_txn_new(void);
  
@@ -34,10 +34,10 @@ index c105b31076..5096679571 100644
   * Release a reference that was previously acquired with job_txn_add_job or
   * job_txn_new. If it's the last reference to the object, it will be freed.
 diff --git a/job.c b/job.c
-index e5699ad200..34c9758349 100644
+index baf54c8d60..3ac5e5cde2 100644
 --- a/job.c
 +++ b/job.c
-@@ -72,6 +72,8 @@ struct JobTxn {
+@@ -94,6 +94,8 @@ struct JobTxn {
  
      /* Reference count */
      int refcnt;
@@ -45,8 +45,8 @@ index e5699ad200..34c9758349 100644
 +    bool sequential;
  };
  
- /* Right now, this mutex is only needed to synchronize accesses to job->busy
-@@ -102,6 +104,25 @@ JobTxn *job_txn_new(void)
+ void job_lock(void)
+@@ -119,6 +121,25 @@ JobTxn *job_txn_new(void)
      return txn;
  }
  
@@ -69,20 +69,23 @@ index e5699ad200..34c9758349 100644
 +    job_start(first);
 +}
 +
- static void job_txn_ref(JobTxn *txn)
+ /* Called with job_mutex held. */
+ static void job_txn_ref_locked(JobTxn *txn)
  {
-     txn->refcnt++;
-@@ -897,6 +918,9 @@ static void job_completed_txn_success(Job *job)
+@@ -1042,6 +1063,12 @@ static void job_completed_txn_success_locked(Job *job)
       */
      QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
-         if (!job_is_completed(other_job)) {
+         if (!job_is_completed_locked(other_job)) {
 +            if (txn->sequential) {
++                job_unlock();
++                /* Needs to be called without holding the job lock */
 +                job_start(other_job);
++                job_lock();
 +            }
              return;
          }
          assert(other_job->ret == 0);
-@@ -1093,6 +1117,13 @@ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
+@@ -1253,6 +1280,13 @@ int job_finish_sync_locked(Job *job,
          return -EBUSY;
      }
  
@@ -90,9 +93,9 @@ index e5699ad200..34c9758349 100644
 +     * of cancelling, these have not begun work so job_enter won't do anything,
 +     * let's ensure they are marked as ABORTING if required */
 +    if (job->status == JOB_STATUS_CREATED && job->txn->sequential) {
-+        job_update_rc(job);
++        job_update_rc_locked(job);
 +    }
 +
-     AIO_WAIT_WHILE(job->aio_context,
-                    (job_enter(job), !job_is_completed(job)));
- 
+     job_unlock();
+     AIO_WAIT_WHILE_UNLOCKED(job->aio_context,
+                             (job_enter(job), !job_is_completed(job)));

debian/patches/pve/0031-PVE-Backup-Add-dirty-bitmap-tracking-for-incremental.patch

@@ -1,452 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Mon, 29 Jun 2020 11:06:03 +0200
-Subject: [PATCH] PVE-Backup: Add dirty-bitmap tracking for incremental backups
-
-Uses QEMU's existing MIRROR_SYNC_MODE_BITMAP and a dirty-bitmap on top
-of all backed-up drives. This will only execute the data-write callback
-for any changed chunks, the PBS rust code will reuse chunks from the
-previous index for everything it doesn't receive if reuse_index is true.
-
-On error or cancellation, remove all dirty bitmaps to ensure
-consistency.
-
-Add PBS/incremental specific information to query backup info QMP and
-HMP commands.
-
-Only supported for PBS backups.
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Dietmar Maurer <dietmar@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/monitor/block-hmp-cmds.c |   1 +
- monitor/hmp-cmds.c             |  45 ++++++++++----
- proxmox-backup-client.c        |   3 +-
- proxmox-backup-client.h        |   1 +
- pve-backup.c                   | 103 ++++++++++++++++++++++++++++++---
- qapi/block-core.json           |  12 +++-
- 6 files changed, 142 insertions(+), 23 deletions(-)
-
-diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
-index 89ca64444d..45da74d7a0 100644
---- a/block/monitor/block-hmp-cmds.c
-+++ b/block/monitor/block-hmp-cmds.c
-@@ -1042,6 +1042,7 @@ void hmp_backup(Monitor *mon, const QDict *qdict)
-         false, NULL, // PBS fingerprint
-         false, NULL, // PBS backup-id
-         false, 0, // PBS backup-time
-+        false, false, // PBS incremental
-         true, dir ? BACKUP_FORMAT_DIR : BACKUP_FORMAT_VMA,
-         false, NULL, false, NULL, !!devlist,
-         devlist, qdict_haskey(qdict, "speed"), speed, &error);
-diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
-index 1168773da7..4c1671e289 100644
---- a/monitor/hmp-cmds.c
-+++ b/monitor/hmp-cmds.c
-@@ -223,19 +223,42 @@ void hmp_info_backup(Monitor *mon, const QDict *qdict)
-             monitor_printf(mon, "End time: %s", ctime(&info->end_time));
-         }
- 
--        int per = (info->has_total && info->total &&
--            info->has_transferred && info->transferred) ?
--            (info->transferred * 100)/info->total : 0;
--        int zero_per = (info->has_total && info->total &&
--                        info->has_zero_bytes && info->zero_bytes) ?
--            (info->zero_bytes * 100)/info->total : 0;
-         monitor_printf(mon, "Backup file: %s\n", info->backup_file);
-         monitor_printf(mon, "Backup uuid: %s\n", info->uuid);
--        monitor_printf(mon, "Total size: %zd\n", info->total);
--        monitor_printf(mon, "Transferred bytes: %zd (%d%%)\n",
--                       info->transferred, per);
--        monitor_printf(mon, "Zero bytes: %zd (%d%%)\n",
--                       info->zero_bytes, zero_per);
-+
-+        if (!(info->has_total && info->total))  {
-+            // this should not happen normally
-+            monitor_printf(mon, "Total size: %d\n", 0);
-+        } else {
-+            bool incremental = false;
-+            size_t total_or_dirty = info->total;
-+            if (info->has_transferred) {
-+                if (info->has_dirty && info->dirty) {
-+                     if (info->dirty < info->total) {
-+                        total_or_dirty = info->dirty;
-+                        incremental = true;
-+                    }
-+                }
-+            }
-+
-+            int per = (info->transferred * 100)/total_or_dirty;
-+
-+            monitor_printf(mon, "Backup mode: %s\n", incremental ? "incremental" : "full");
-+
-+            int zero_per = (info->has_zero_bytes && info->zero_bytes) ?
-+                (info->zero_bytes * 100)/info->total : 0;
-+            monitor_printf(mon, "Total size: %zd\n", info->total);
-+            monitor_printf(mon, "Transferred bytes: %zd (%d%%)\n",
-+                           info->transferred, per);
-+            monitor_printf(mon, "Zero bytes: %zd (%d%%)\n",
-+                           info->zero_bytes, zero_per);
-+
-+            if (info->has_reused) {
-+                int reused_per = (info->reused * 100)/total_or_dirty;
-+                monitor_printf(mon, "Reused bytes: %zd (%d%%)\n",
-+                               info->reused, reused_per);
-+            }
-+        }
-     }
- 
-     qapi_free_BackupStatus(info);
-diff --git a/proxmox-backup-client.c b/proxmox-backup-client.c
-index a8f6653a81..4ce7bc0b5e 100644
---- a/proxmox-backup-client.c
-+++ b/proxmox-backup-client.c
-@@ -89,6 +89,7 @@ proxmox_backup_co_register_image(
-     ProxmoxBackupHandle *pbs,
-     const char *device_name,
-     uint64_t size,
-+    bool incremental,
-     Error **errp)
- {
-     Coroutine *co = qemu_coroutine_self();
-@@ -98,7 +99,7 @@ proxmox_backup_co_register_image(
-     int pbs_res = -1;
- 
-     proxmox_backup_register_image_async(
--        pbs, device_name, size ,proxmox_backup_schedule_wake, &waker, &pbs_res, &pbs_err);
-+        pbs, device_name, size, incremental, proxmox_backup_schedule_wake, &waker, &pbs_res, &pbs_err);
-     qemu_coroutine_yield();
-     if (pbs_res < 0) {
-         if (errp) error_setg(errp, "backup register image failed: %s", pbs_err ? pbs_err : "unknown error");
-diff --git a/proxmox-backup-client.h b/proxmox-backup-client.h
-index 1dda8b7d8f..8cbf645b2c 100644
---- a/proxmox-backup-client.h
-+++ b/proxmox-backup-client.h
-@@ -32,6 +32,7 @@ proxmox_backup_co_register_image(
-     ProxmoxBackupHandle *pbs,
-     const char *device_name,
-     uint64_t size,
-+    bool incremental,
-     Error **errp);
- 
- 
-diff --git a/pve-backup.c b/pve-backup.c
-index 88f5ee133f..1c49cd178d 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -28,6 +28,8 @@
-  *
-  */
- 
-+const char *PBS_BITMAP_NAME = "pbs-incremental-dirty-bitmap";
-+
- static struct PVEBackupState {
-     struct {
-         // Everithing accessed from qmp_backup_query command is protected using lock
-@@ -39,7 +41,9 @@ static struct PVEBackupState {
-         uuid_t uuid;
-         char uuid_str[37];
-         size_t total;
-+        size_t dirty;
-         size_t transferred;
-+        size_t reused;
-         size_t zero_bytes;
-     } stat;
-     int64_t speed;
-@@ -66,6 +70,7 @@ typedef struct PVEBackupDevInfo {
-     uint8_t dev_id;
-     bool completed;
-     char targetfile[PATH_MAX];
-+    BdrvDirtyBitmap *bitmap;
-     BlockDriverState *target;
- } PVEBackupDevInfo;
- 
-@@ -105,11 +110,12 @@ static bool pvebackup_error_or_canceled(void)
-     return error_or_canceled;
- }
- 
--static void pvebackup_add_transfered_bytes(size_t transferred, size_t zero_bytes)
-+static void pvebackup_add_transfered_bytes(size_t transferred, size_t zero_bytes, size_t reused)
- {
-     qemu_mutex_lock(&backup_state.stat.lock);
-     backup_state.stat.zero_bytes += zero_bytes;
-     backup_state.stat.transferred += transferred;
-+    backup_state.stat.reused += reused;
-     qemu_mutex_unlock(&backup_state.stat.lock);
- }
- 
-@@ -148,7 +154,8 @@ pvebackup_co_dump_pbs_cb(
-         pvebackup_propagate_error(local_err);
-         return pbs_res;
-     } else {
--        pvebackup_add_transfered_bytes(size, !buf ? size : 0);
-+        size_t reused = (pbs_res == 0) ? size : 0;
-+        pvebackup_add_transfered_bytes(size, !buf ? size : 0, reused);
-     }
- 
-     return size;
-@@ -208,11 +215,11 @@ pvebackup_co_dump_vma_cb(
-         } else {
-             if (remaining >= VMA_CLUSTER_SIZE) {
-                 assert(ret == VMA_CLUSTER_SIZE);
--                pvebackup_add_transfered_bytes(VMA_CLUSTER_SIZE, zero_bytes);
-+                pvebackup_add_transfered_bytes(VMA_CLUSTER_SIZE, zero_bytes, 0);
-                 remaining -= VMA_CLUSTER_SIZE;
-             } else {
-                 assert(ret == remaining);
--                pvebackup_add_transfered_bytes(remaining, zero_bytes);
-+                pvebackup_add_transfered_bytes(remaining, zero_bytes, 0);
-                 remaining = 0;
-             }
-         }
-@@ -248,6 +255,18 @@ static void coroutine_fn pvebackup_co_cleanup(void *unused)
-             if (local_err != NULL) {
-                 pvebackup_propagate_error(local_err);
-             }
-+        } else {
-+            // on error or cancel we cannot ensure synchronization of dirty
-+            // bitmaps with backup server, so remove all and do full backup next
-+            GList *l = backup_state.di_list;
-+            while (l) {
-+                PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-+                l = g_list_next(l);
-+
-+                if (di->bitmap) {
-+                    bdrv_release_dirty_bitmap(di->bitmap);
-+                }
-+            }
-         }
- 
-         proxmox_backup_disconnect(backup_state.pbs);
-@@ -303,6 +322,12 @@ static void pvebackup_complete_cb(void *opaque, int ret)
-     // remove self from job queue
-     backup_state.di_list = g_list_remove(backup_state.di_list, di);
- 
-+    if (di->bitmap && ret < 0) {
-+        // on error or cancel we cannot ensure synchronization of dirty
-+        // bitmaps with backup server, so remove all and do full backup next
-+        bdrv_release_dirty_bitmap(di->bitmap);
-+    }
-+
-     g_free(di);
- 
-     qemu_mutex_unlock(&backup_state.backup_mutex);
-@@ -472,12 +497,18 @@ static bool create_backup_jobs(void) {
- 
-         assert(di->target != NULL);
- 
-+        MirrorSyncMode sync_mode = MIRROR_SYNC_MODE_FULL;
-+        BitmapSyncMode bitmap_mode = BITMAP_SYNC_MODE_NEVER;
-+        if (di->bitmap) {
-+            sync_mode = MIRROR_SYNC_MODE_BITMAP;
-+            bitmap_mode = BITMAP_SYNC_MODE_ON_SUCCESS;
-+        }
-         AioContext *aio_context = bdrv_get_aio_context(di->bs);
-         aio_context_acquire(aio_context);
- 
-         BlockJob *job = backup_job_create(
--            NULL, di->bs, di->target, backup_state.speed, MIRROR_SYNC_MODE_FULL, NULL,
--            BITMAP_SYNC_MODE_NEVER, false, NULL, &perf, BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
-+            NULL, di->bs, di->target, backup_state.speed, sync_mode, di->bitmap,
-+            bitmap_mode, false, NULL, &perf, BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
-             JOB_DEFAULT, pvebackup_complete_cb, di, NULL, &local_err);
- 
-         aio_context_release(aio_context);
-@@ -528,6 +559,8 @@ typedef struct QmpBackupTask {
-     const char *fingerprint;
-     bool has_fingerprint;
-     int64_t backup_time;
-+    bool has_use_dirty_bitmap;
-+    bool use_dirty_bitmap;
-     bool has_format;
-     BackupFormat format;
-     bool has_config_file;
-@@ -619,6 +652,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     }
- 
-     size_t total = 0;
-+    size_t dirty = 0;
- 
-     l = di_list;
-     while (l) {
-@@ -656,6 +690,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-         int dump_cb_block_size = PROXMOX_BACKUP_DEFAULT_CHUNK_SIZE; // Hardcoded (4M)
-         firewall_name = "fw.conf";
- 
-+        bool use_dirty_bitmap = task->has_use_dirty_bitmap && task->use_dirty_bitmap;
-+
-         char *pbs_err = NULL;
-         pbs = proxmox_backup_new(
-             task->backup_file,
-@@ -675,7 +711,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             goto err;
-         }
- 
--        if (proxmox_backup_co_connect(pbs, task->errp) < 0)
-+        int connect_result = proxmox_backup_co_connect(pbs, task->errp);
-+        if (connect_result < 0)
-             goto err;
- 
-         /* register all devices */
-@@ -686,9 +723,40 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
- 
-             const char *devname = bdrv_get_device_name(di->bs);
- 
--            int dev_id = proxmox_backup_co_register_image(pbs, devname, di->size, task->errp);
--            if (dev_id < 0)
-+            BdrvDirtyBitmap *bitmap = bdrv_find_dirty_bitmap(di->bs, PBS_BITMAP_NAME);
-+            bool expect_only_dirty = false;
-+
-+            if (use_dirty_bitmap) {
-+                if (bitmap == NULL) {
-+                    bitmap = bdrv_create_dirty_bitmap(di->bs, dump_cb_block_size, PBS_BITMAP_NAME, task->errp);
-+                    if (!bitmap) {
-+                        goto err;
-+                    }
-+                } else {
-+                    expect_only_dirty = proxmox_backup_check_incremental(pbs, devname, di->size) != 0;
-+                }
-+
-+                if (expect_only_dirty) {
-+                    dirty += bdrv_get_dirty_count(bitmap);
-+                } else {
-+                    /* mark entire bitmap as dirty to make full backup */
-+                    bdrv_set_dirty_bitmap(bitmap, 0, di->size);
-+                    dirty += di->size;
-+                }
-+                di->bitmap = bitmap;
-+            } else {
-+                dirty += di->size;
-+
-+                /* after a full backup the old dirty bitmap is invalid anyway */
-+                if (bitmap != NULL) {
-+                    bdrv_release_dirty_bitmap(bitmap);
-+                }
-+            }
-+
-+            int dev_id = proxmox_backup_co_register_image(pbs, devname, di->size, expect_only_dirty, task->errp);
-+            if (dev_id < 0) {
-                 goto err;
-+            }
- 
-             if (!(di->target = bdrv_backup_dump_create(dump_cb_block_size, di->size, pvebackup_co_dump_pbs_cb, di, task->errp))) {
-                 goto err;
-@@ -697,6 +765,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             di->dev_id = dev_id;
-         }
-     } else if (format == BACKUP_FORMAT_VMA) {
-+        dirty = total;
-+
-         vmaw = vma_writer_create(task->backup_file, uuid, &local_err);
-         if (!vmaw) {
-             if (local_err) {
-@@ -724,6 +794,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             }
-         }
-     } else if (format == BACKUP_FORMAT_DIR) {
-+        dirty = total;
-+
-         if (mkdir(task->backup_file, 0640) != 0) {
-             error_setg_errno(task->errp, errno, "can't create directory '%s'\n",
-                              task->backup_file);
-@@ -796,8 +868,10 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     char *uuid_str = g_strdup(backup_state.stat.uuid_str);
- 
-     backup_state.stat.total = total;
-+    backup_state.stat.dirty = dirty;
-     backup_state.stat.transferred = 0;
-     backup_state.stat.zero_bytes = 0;
-+    backup_state.stat.reused = format == BACKUP_FORMAT_PBS && dirty >= total ? 0 : total - dirty;
- 
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
-@@ -821,6 +895,10 @@ err:
-         PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-         l = g_list_next(l);
- 
-+        if (di->bitmap) {
-+            bdrv_release_dirty_bitmap(di->bitmap);
-+        }
-+
-         if (di->target) {
-             bdrv_unref(di->target);
-         }
-@@ -862,6 +940,7 @@ UuidInfo *qmp_backup(
-     bool has_fingerprint, const char *fingerprint,
-     bool has_backup_id, const char *backup_id,
-     bool has_backup_time, int64_t backup_time,
-+    bool has_use_dirty_bitmap, bool use_dirty_bitmap,
-     bool has_format, BackupFormat format,
-     bool has_config_file, const char *config_file,
-     bool has_firewall_file, const char *firewall_file,
-@@ -880,6 +959,8 @@ UuidInfo *qmp_backup(
-         .backup_id = backup_id,
-         .has_backup_time = has_backup_time,
-         .backup_time = backup_time,
-+        .has_use_dirty_bitmap = has_use_dirty_bitmap,
-+        .use_dirty_bitmap = use_dirty_bitmap,
-         .has_format = has_format,
-         .format = format,
-         .has_config_file = has_config_file,
-@@ -948,10 +1029,14 @@ BackupStatus *qmp_query_backup(Error **errp)
- 
-     info->has_total = true;
-     info->total = backup_state.stat.total;
-+    info->has_dirty = true;
-+    info->dirty = backup_state.stat.dirty;
-     info->has_zero_bytes = true;
-     info->zero_bytes = backup_state.stat.zero_bytes;
-     info->has_transferred = true;
-     info->transferred = backup_state.stat.transferred;
-+    info->has_reused = true;
-+    info->reused = backup_state.stat.reused;
- 
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 90ad07b7ee..3ad9eb5d1a 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -753,8 +753,13 @@
- #
- # @total: total amount of bytes involved in the backup process
- #
-+# @dirty: with incremental mode (PBS) this is the amount of bytes involved
-+#         in the backup process which are marked dirty.
-+#
- # @transferred: amount of bytes already backed up.
- #
-+# @reused: amount of bytes reused due to deduplication.
-+#
- # @zero-bytes: amount of 'zero' bytes detected.
- #
- # @start-time: time (epoch) when backup job started.
-@@ -767,8 +772,8 @@
- #
- ##
- { 'struct': 'BackupStatus',
--  'data': {'*status': 'str', '*errmsg': 'str', '*total': 'int',
--           '*transferred': 'int', '*zero-bytes': 'int',
-+  'data': {'*status': 'str', '*errmsg': 'str', '*total': 'int', '*dirty': 'int',
-+           '*transferred': 'int', '*zero-bytes': 'int', '*reused': 'int',
-            '*start-time': 'int', '*end-time': 'int',
-            '*backup-file': 'str', '*uuid': 'str' } }
- 
-@@ -811,6 +816,8 @@
- #
- # @backup-time: backup timestamp (Unix epoch, required for format 'pbs')
- #
-+# @use-dirty-bitmap: use dirty bitmap to detect incremental changes since last job (optional for format 'pbs')
-+#
- # Returns: the uuid of the backup job
- #
- ##
-@@ -821,6 +828,7 @@
-                                     '*fingerprint': 'str',
-                                     '*backup-id': 'str',
-                                     '*backup-time': 'int',
-+                                    '*use-dirty-bitmap': 'bool',
-                                     '*format': 'BackupFormat',
-                                     '*config-file': 'str',
-                                     '*firewall-file': 'str',

debian/patches/pve/0031-PVE-Backup-pbs-restore-new-command-to-restore-from-p.patch

@@ -5,17 +5,19 @@ Subject: [PATCH] PVE-Backup: pbs-restore - new command to restore from proxmox
  backup server
 
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[WB: add namespace support]
+Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
 ---
  meson.build   |   4 +
- pbs-restore.c | 223 ++++++++++++++++++++++++++++++++++++++++++++++++++
- 2 files changed, 227 insertions(+)
+ pbs-restore.c | 236 ++++++++++++++++++++++++++++++++++++++++++++++++++
+ 2 files changed, 240 insertions(+)
  create mode 100644 pbs-restore.c
 
 diff --git a/meson.build b/meson.build
-index 0bc2fb5b10..f48d2e0457 100644
+index d16b97cf3c..6de51c34cb 100644
 --- a/meson.build
 +++ b/meson.build
-@@ -3613,6 +3613,10 @@ if have_tools
+@@ -4029,6 +4029,10 @@ if have_tools
    vma = executable('vma', files('vma.c', 'vma-reader.c') + genh,
                     dependencies: [authz, block, crypto, io, qom], install: true)
  
@@ -24,14 +26,14 @@ index 0bc2fb5b10..f48d2e0457 100644
 +                    libproxmox_backup_qemu], install: true)
 +
    subdir('storage-daemon')
-   subdir('contrib/rdmacm-mux')
-   subdir('contrib/elf2dmp')
+ 
+   foreach exe: [ 'qemu-img', 'qemu-io', 'qemu-nbd', 'qemu-storage-daemon']
 diff --git a/pbs-restore.c b/pbs-restore.c
 new file mode 100644
-index 0000000000..2f834cf42e
+index 0000000000..f03d9bab8d
 --- /dev/null
 +++ b/pbs-restore.c
-@@ -0,0 +1,223 @@
+@@ -0,0 +1,236 @@
 +/*
 + * Qemu image restore helper for Proxmox Backup
 + *
@@ -63,7 +65,7 @@ index 0000000000..2f834cf42e
 +static void help(void)
 +{
 +    const char *help_msg =
-+        "usage: pbs-restore [--repository <repo>] snapshot archive-name target [command options]\n"
++        "usage: pbs-restore [--repository <repo>] [--ns namespace] snapshot archive-name target [command options]\n"
 +        ;
 +
 +    printf("%s", help_msg);
@@ -111,6 +113,7 @@ index 0000000000..2f834cf42e
 +    Error *main_loop_err = NULL;
 +    const char *format = "raw";
 +    const char *repository = NULL;
++    const char *backup_ns = NULL;
 +    const char *keyfile = NULL;
 +    int verbose = false;
 +    bool skip_zero = false;
@@ -124,6 +127,7 @@ index 0000000000..2f834cf42e
 +            {"verbose", no_argument, 0, 'v'},
 +            {"format", required_argument, 0, 'f'},
 +            {"repository", required_argument, 0, 'r'},
++            {"ns", required_argument, 0, 'n'},
 +            {"keyfile", required_argument, 0, 'k'},
 +            {0, 0, 0, 0}
 +        };
@@ -144,6 +148,9 @@ index 0000000000..2f834cf42e
 +            case 'r':
 +                repository = g_strdup(argv[optind - 1]);
 +                break;
++            case 'n':
++                backup_ns = g_strdup(argv[optind - 1]);
++                break;
 +            case 'k':
 +                keyfile = g_strdup(argv[optind - 1]);
 +                break;
@@ -194,8 +201,16 @@ index 0000000000..2f834cf42e
 +        fprintf(stderr, "connecting to repository '%s'\n", repository);
 +    }
 +    char *pbs_error = NULL;
-+    ProxmoxRestoreHandle *conn = proxmox_restore_new(
-+        repository, snapshot, password, keyfile, key_password, fingerprint, &pbs_error);
++    ProxmoxRestoreHandle *conn = proxmox_restore_new_ns(
++        repository,
++        snapshot,
++        backup_ns,
++        password,
++        keyfile,
++        key_password,
++        fingerprint,
++        &pbs_error
++    );
 +    if (conn == NULL) {
 +        fprintf(stderr, "restore failed: %s\n", pbs_error);
 +        return -1;

debian/patches/pve/0032-PVE-Add-PBS-block-driver-to-map-backup-archives-into.patch

@@ -7,38 +7,40 @@ Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 [error cleanups, file_open implementation]
 Signed-off-by: Dietmar Maurer <dietmar@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[WB: add namespace support]
+Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
 [FE: adapt to changed function signatures
-     make pbs_co_preadv return values consistent with QEMU]
+     make pbs_co_preadv return values consistent with QEMU
+     getlength is now a coroutine function]
 Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
- block/meson.build    |   3 +
- block/pbs.c          | 276 +++++++++++++++++++++++++++++++++++++++++++
- configure            |   9 ++
+ block/meson.build    |   2 +
+ block/pbs.c          | 307 +++++++++++++++++++++++++++++++++++++++++++
  meson.build          |   2 +-
- qapi/block-core.json |  13 ++
- 5 files changed, 302 insertions(+), 1 deletion(-)
+ qapi/block-core.json |  29 ++++
+ qapi/pragma.json     |   1 +
+ 5 files changed, 340 insertions(+), 1 deletion(-)
  create mode 100644 block/pbs.c
 
 diff --git a/block/meson.build b/block/meson.build
-index 2783b77e9c..a26a69434e 100644
+index 6bba803f94..1945e04eeb 100644
 --- a/block/meson.build
 +++ b/block/meson.build
-@@ -53,6 +53,9 @@ block_ss.add(files(
+@@ -49,6 +49,8 @@ block_ss.add(files(
    '../pve-backup.c',
  ), libproxmox_backup_qemu)
  
-+block_ss.add(when: 'CONFIG_PBS_BDRV', if_true: files('pbs.c'))
-+block_ss.add(when: 'CONFIG_PBS_BDRV', if_true: libproxmox_backup_qemu)
++block_ss.add(files('pbs.c'), libproxmox_backup_qemu)
 +
  
- softmmu_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
- 
+ system_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
+ system_ss.add(files('block-ram-registrar.c'))
 diff --git a/block/pbs.c b/block/pbs.c
 new file mode 100644
-index 0000000000..9d1f1f39d4
+index 0000000000..dd72356bd3
 --- /dev/null
 +++ b/block/pbs.c
-@@ -0,0 +1,276 @@
+@@ -0,0 +1,307 @@
 +/*
 + * Proxmox Backup Server read-only block driver
 + */
@@ -51,10 +53,12 @@ index 0000000000..9d1f1f39d4
 +#include "qemu/option.h"
 +#include "qemu/cutils.h"
 +#include "block/block_int.h"
++#include "block/block-io.h"
 +
 +#include <proxmox-backup-qemu.h>
 +
 +#define PBS_OPT_REPOSITORY "repository"
++#define PBS_OPT_NAMESPACE "namespace"
 +#define PBS_OPT_SNAPSHOT "snapshot"
 +#define PBS_OPT_ARCHIVE "archive"
 +#define PBS_OPT_KEYFILE "keyfile"
@@ -68,6 +72,7 @@ index 0000000000..9d1f1f39d4
 +    int64_t length;
 +
 +    char *repository;
++    char *namespace;
 +    char *snapshot;
 +    char *archive;
 +} BDRVPBSState;
@@ -82,6 +87,11 @@ index 0000000000..9d1f1f39d4
 +            .help = "The server address and repository to connect to.",
 +        },
 +        {
++            .name = PBS_OPT_NAMESPACE,
++            .type = QEMU_OPT_STRING,
++            .help = "Optional: The snapshot's namespace.",
++        },
++        {
 +            .name = PBS_OPT_SNAPSHOT,
 +            .type = QEMU_OPT_STRING,
 +            .help = "The snapshot to read.",
@@ -117,7 +127,7 @@ index 0000000000..9d1f1f39d4
 +
 +
 +// filename format:
-+// pbs:repository=<repo>,snapshot=<snap>,password=<pw>,key_password=<kpw>,fingerprint=<fp>,archive=<archive>
++// pbs:repository=<repo>,namespace=<ns>,snapshot=<snap>,password=<pw>,key_password=<kpw>,fingerprint=<fp>,archive=<archive>
 +static void pbs_parse_filename(const char *filename, QDict *options,
 +                                     Error **errp)
 +{
@@ -153,6 +163,7 @@ index 0000000000..9d1f1f39d4
 +    s->archive = g_strdup(qemu_opt_get(opts, PBS_OPT_ARCHIVE));
 +    const char *keyfile = qemu_opt_get(opts, PBS_OPT_KEYFILE);
 +    const char *password = qemu_opt_get(opts, PBS_OPT_PASSWORD);
++    const char *namespace = qemu_opt_get(opts, PBS_OPT_NAMESPACE);
 +    const char *fingerprint = qemu_opt_get(opts, PBS_OPT_FINGERPRINT);
 +    const char *key_password = qemu_opt_get(opts, PBS_OPT_ENCRYPTION_PASSWORD);
 +
@@ -165,9 +176,12 @@ index 0000000000..9d1f1f39d4
 +    if (!key_password) {
 +        key_password = getenv("PBS_ENCRYPTION_PASSWORD");
 +    }
++    if (namespace) {
++        s->namespace = g_strdup(namespace);
++    }
 +
 +    /* connect to PBS server in read mode */
-+    s->conn = proxmox_restore_new(s->repository, s->snapshot, password,
++    s->conn = proxmox_restore_new_ns(s->repository, s->snapshot, s->namespace, password,
 +        keyfile, key_password, fingerprint, &pbs_error);
 +
 +    /* invalidates qemu_opt_get char pointers from above */
@@ -212,12 +226,14 @@ index 0000000000..9d1f1f39d4
 +static void pbs_close(BlockDriverState *bs) {
 +    BDRVPBSState *s = bs->opaque;
 +    g_free(s->repository);
++    g_free(s->namespace);
 +    g_free(s->snapshot);
 +    g_free(s->archive);
 +    proxmox_restore_disconnect(s->conn);
 +}
 +
-+static int64_t pbs_getlength(BlockDriverState *bs)
++static coroutine_fn int64_t GRAPH_RDLOCK
++pbs_co_getlength(BlockDriverState *bs)
 +{
 +    BDRVPBSState *s = bs->opaque;
 +    return s->length;
@@ -234,14 +250,23 @@ index 0000000000..9d1f1f39d4
 +    aio_co_schedule(rcb->ctx, rcb->co);
 +}
 +
-+static coroutine_fn int pbs_co_preadv(BlockDriverState *bs,
-+                                      int64_t offset, int64_t bytes,
-+                                      QEMUIOVector *qiov, BdrvRequestFlags flags)
++static coroutine_fn int GRAPH_RDLOCK
++pbs_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
++              QEMUIOVector *qiov, BdrvRequestFlags flags)
 +{
 +    BDRVPBSState *s = bs->opaque;
 +    int ret;
 +    char *pbs_error = NULL;
-+    uint8_t *buf = malloc(bytes);
++    uint8_t *buf;
++    bool inline_buf = true;
++
++    /* for single-buffer IO vectors we can fast-path the write directly to it */
++    if (qiov->niov == 1 && qiov->iov->iov_len >= bytes) {
++        buf = qiov->iov->iov_base;
++    } else {
++        inline_buf = false;
++        buf = g_malloc(bytes);
++    }
 +
 +    if (offset < 0 || bytes < 0) {
 +        fprintf(stderr, "unexpected negative 'offset' or 'bytes' value!\n");
@@ -264,26 +289,34 @@ index 0000000000..9d1f1f39d4
 +        return -EIO;
 +    }
 +
-+    qemu_iovec_from_buf(qiov, 0, buf, bytes);
-+    free(buf);
++    if (!inline_buf) {
++        qemu_iovec_from_buf(qiov, 0, buf, bytes);
++        g_free(buf);
++    }
 +
 +    return 0;
 +}
 +
-+static coroutine_fn int pbs_co_pwritev(BlockDriverState *bs,
-+                                       int64_t offset, int64_t bytes,
-+                                       QEMUIOVector *qiov, BdrvRequestFlags flags)
++static coroutine_fn int GRAPH_RDLOCK
++pbs_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
++               QEMUIOVector *qiov, BdrvRequestFlags flags)
 +{
 +    fprintf(stderr, "pbs-bdrv: cannot write to backup file, make sure "
 +           "any attached disk devices are set to read-only!\n");
 +    return -EPERM;
 +}
 +
-+static void pbs_refresh_filename(BlockDriverState *bs)
++static void GRAPH_RDLOCK
++pbs_refresh_filename(BlockDriverState *bs)
 +{
 +    BDRVPBSState *s = bs->opaque;
-+    snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s/%s(%s)",
-+             s->repository, s->snapshot, s->archive);
++    if (s->namespace) {
++        snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s/%s:%s(%s)",
++                 s->repository, s->namespace, s->snapshot, s->archive);
++    } else {
++        snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s/%s(%s)",
++                 s->repository, s->snapshot, s->archive);
++    }
 +}
 +
 +static const char *const pbs_strong_runtime_opts[] = {
@@ -300,7 +333,7 @@ index 0000000000..9d1f1f39d4
 +    .bdrv_file_open         = pbs_file_open,
 +    .bdrv_open              = pbs_open,
 +    .bdrv_close             = pbs_close,
-+    .bdrv_getlength         = pbs_getlength,
++    .bdrv_co_getlength      = pbs_co_getlength,
 +
 +    .bdrv_co_preadv         = pbs_co_preadv,
 +    .bdrv_co_pwritev        = pbs_co_pwritev,
@@ -315,52 +348,11 @@ index 0000000000..9d1f1f39d4
 +}
 +
 +block_init(bdrv_pbs_init);
-diff --git a/configure b/configure
-index 72ab03f11a..7203c270ec 100755
---- a/configure
-+++ b/configure
-@@ -309,6 +309,7 @@ linux_user=""
- bsd_user=""
- pie=""
- coroutine=""
-+pbs_bdrv="yes"
- plugins="$default_feature"
- meson=""
- meson_args=""
-@@ -902,6 +903,10 @@ for opt do
-   --enable-uuid|--disable-uuid)
-       echo "$0: $opt is obsolete, UUID support is always built" >&2
-   ;;
-+  --disable-pbs-bdrv) pbs_bdrv="no"
-+  ;;
-+  --enable-pbs-bdrv) pbs_bdrv="yes"
-+  ;;
-   --with-git=*) git="$optarg"
-   ;;
-   --with-git-submodules=*)
-@@ -1087,6 +1092,7 @@ cat << EOF
-   debug-info      debugging information
-   safe-stack      SafeStack Stack Smash Protection. Depends on
-                   clang/llvm >= 3.7 and requires coroutine backend ucontext.
-+  pbs-bdrv        Proxmox backup server read-only block driver support
- 
- NOTE: The object files are built at the place where configure is launched
- EOF
-@@ -2463,6 +2469,9 @@ echo "TARGET_DIRS=$target_list" >> $config_host_mak
- if test "$modules" = "yes"; then
-   echo "CONFIG_MODULES=y" >> $config_host_mak
- fi
-+if test "$pbs_bdrv" = "yes" ; then
-+  echo "CONFIG_PBS_BDRV=y" >> $config_host_mak
-+fi
- 
- # XXX: suppress that
- if [ "$bsd" = "yes" ] ; then
 diff --git a/meson.build b/meson.build
-index f48d2e0457..be4785e2f6 100644
+index 6de51c34cb..3bc039f60f 100644
 --- a/meson.build
 +++ b/meson.build
-@@ -3986,7 +3986,7 @@ summary_info += {'bzip2 support':     libbzip2}
+@@ -4477,7 +4477,7 @@ summary_info += {'bzip2 support':     libbzip2}
  summary_info += {'lzfse support':     liblzfse}
  summary_info += {'zstd support':      zstd}
  summary_info += {'NUMA host support': numa}
@@ -370,18 +362,18 @@ index f48d2e0457..be4785e2f6 100644
  summary_info += {'libdaxctl support': libdaxctl}
  summary_info += {'libudev':           libudev}
 diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 4120052690..96bc696aaa 100644
+index e49c7b5bc9..fc32ff9957 100644
 --- a/qapi/block-core.json
 +++ b/qapi/block-core.json
-@@ -3099,6 +3099,7 @@
-             'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
-             'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+@@ -3457,6 +3457,7 @@
+             'parallels', 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum',
+             'raw', 'rbd',
              { 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
 +            'pbs',
-             'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
- 
- ##
-@@ -3171,6 +3172,17 @@
+             'ssh', 'throttle', 'vdi', 'vhdx',
+             { 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
+@@ -3543,6 +3544,33 @@
  { 'struct': 'BlockdevOptionsNull',
    'data': { '*size': 'int', '*latency-ns': 'uint64', '*read-zeroes': 'bool' } }
  
@@ -390,20 +382,48 @@ index 4120052690..96bc696aaa 100644
 +#
 +# Driver specific block device options for the PBS backend.
 +#
++# @repository: Proxmox Backup Server repository.
++#
++# @snapshot: backup snapshots ID.
++#
++# @archive: archive name.
++#
++# @keyfile: keyfile to use for encryption.
++#
++# @password: password to use for connection.
++#
++# @fingerprint: backup server fingerprint.
++#
++# @key_password: password to unlock key.
++#
++# @namespace: namespace where backup snapshot lives.
++#
 +##
 +{ 'struct': 'BlockdevOptionsPbs',
 +  'data': { 'repository': 'str', 'snapshot': 'str', 'archive': 'str',
 +            '*keyfile': 'str', '*password': 'str', '*fingerprint': 'str',
-+            '*key_password': 'str' } }
++            '*key_password': 'str', '*namespace': 'str' } }
 +
  ##
  # @BlockdevOptionsNVMe:
  #
-@@ -4455,6 +4467,7 @@
+@@ -4977,6 +5005,7 @@
        'nfs':        'BlockdevOptionsNfs',
        'null-aio':   'BlockdevOptionsNull',
        'null-co':    'BlockdevOptionsNull',
 +      'pbs':        'BlockdevOptionsPbs',
        'nvme':       'BlockdevOptionsNVMe',
-       'parallels':  'BlockdevOptionsGenericFormat',
-       'preallocate':'BlockdevOptionsPreallocate',
+       'nvme-io_uring': { 'type': 'BlockdevOptionsNvmeIoUring',
+                          'if': 'CONFIG_BLKIO' },
+diff --git a/qapi/pragma.json b/qapi/pragma.json
+index be8fa304c5..7ff46bd128 100644
+--- a/qapi/pragma.json
++++ b/qapi/pragma.json
+@@ -100,6 +100,7 @@
+         'BlockInfo',                # query-block
+         'BlockdevAioOptions',       # blockdev-add, -blockdev
+         'BlockdevDriver',           # blockdev-add, query-blockstats, ...
++        'BlockdevOptionsPbs',       # for PBS backwards compat
+         'BlockdevVmdkAdapterType',  # blockdev-create (to match VMDK spec)
+         'BlockdevVmdkSubformat',    # blockdev-create (to match VMDK spec)
+         'ColoCompareProperties',    # object_add, -object

debian/patches/pve/0032-PVE-various-PBS-fixes.patch

@@ -1,219 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Dietmar Maurer <dietmar@proxmox.com>
-Date: Thu, 9 Jul 2020 12:53:08 +0200
-Subject: [PATCH] PVE: various PBS fixes
-
-pbs: fix crypt and compress parameters
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
-
-PVE: handle PBS write callback with big blocks correctly
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-
-PVE: add zero block handling to PBS dump callback
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/monitor/block-hmp-cmds.c |  4 ++-
- pve-backup.c                   | 57 +++++++++++++++++++++++++++-------
- qapi/block-core.json           |  6 ++++
- 3 files changed, 54 insertions(+), 13 deletions(-)
-
-diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
-index 45da74d7a0..ea7b665aa2 100644
---- a/block/monitor/block-hmp-cmds.c
-+++ b/block/monitor/block-hmp-cmds.c
-@@ -1042,7 +1042,9 @@ void hmp_backup(Monitor *mon, const QDict *qdict)
-         false, NULL, // PBS fingerprint
-         false, NULL, // PBS backup-id
-         false, 0, // PBS backup-time
--        false, false, // PBS incremental
-+        false, false, // PBS use-dirty-bitmap
-+        false, false, // PBS compress
-+        false, false, // PBS encrypt
-         true, dir ? BACKUP_FORMAT_DIR : BACKUP_FORMAT_VMA,
-         false, NULL, false, NULL, !!devlist,
-         devlist, qdict_haskey(qdict, "speed"), speed, &error);
-diff --git a/pve-backup.c b/pve-backup.c
-index 1c49cd178d..c15abefdda 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -8,6 +8,7 @@
- #include "block/blockjob.h"
- #include "qapi/qapi-commands-block.h"
- #include "qapi/qmp/qerror.h"
-+#include "qemu/cutils.h"
- 
- /* PVE backup state and related function */
- 
-@@ -67,6 +68,7 @@ opts_init(pvebackup_init);
- typedef struct PVEBackupDevInfo {
-     BlockDriverState *bs;
-     size_t size;
-+    uint64_t block_size;
-     uint8_t dev_id;
-     bool completed;
-     char targetfile[PATH_MAX];
-@@ -135,10 +137,13 @@ pvebackup_co_dump_pbs_cb(
-     PVEBackupDevInfo *di = opaque;
- 
-     assert(backup_state.pbs);
-+    assert(buf);
- 
-     Error *local_err = NULL;
-     int pbs_res = -1;
- 
-+    bool is_zero_block = size == di->block_size && buffer_is_zero(buf, size);
-+
-     qemu_co_mutex_lock(&backup_state.dump_callback_mutex);
- 
-     // avoid deadlock if job is cancelled
-@@ -147,17 +152,29 @@ pvebackup_co_dump_pbs_cb(
-         return -1;
-     }
- 
--    pbs_res = proxmox_backup_co_write_data(backup_state.pbs, di->dev_id, buf, start, size, &local_err);
--    qemu_co_mutex_unlock(&backup_state.dump_callback_mutex);
-+    uint64_t transferred = 0;
-+    uint64_t reused = 0;
-+    while (transferred < size) {
-+        uint64_t left = size - transferred;
-+        uint64_t to_transfer = left < di->block_size ? left : di->block_size;
- 
--    if (pbs_res < 0) {
--        pvebackup_propagate_error(local_err);
--        return pbs_res;
--    } else {
--        size_t reused = (pbs_res == 0) ? size : 0;
--        pvebackup_add_transfered_bytes(size, !buf ? size : 0, reused);
-+        pbs_res = proxmox_backup_co_write_data(backup_state.pbs, di->dev_id,
-+            is_zero_block ? NULL : buf + transferred, start + transferred,
-+            to_transfer, &local_err);
-+        transferred += to_transfer;
-+
-+        if (pbs_res < 0) {
-+            pvebackup_propagate_error(local_err);
-+            qemu_co_mutex_unlock(&backup_state.dump_callback_mutex);
-+            return pbs_res;
-+        }
-+
-+        reused += pbs_res == 0 ? to_transfer : 0;
-     }
- 
-+    qemu_co_mutex_unlock(&backup_state.dump_callback_mutex);
-+    pvebackup_add_transfered_bytes(size, is_zero_block ? size : 0, reused);
-+
-     return size;
- }
- 
-@@ -178,6 +195,7 @@ pvebackup_co_dump_vma_cb(
-     int ret = -1;
- 
-     assert(backup_state.vmaw);
-+    assert(buf);
- 
-     uint64_t remaining = size;
- 
-@@ -204,9 +222,7 @@ pvebackup_co_dump_vma_cb(
-         qemu_co_mutex_unlock(&backup_state.dump_callback_mutex);
- 
-         ++cluster_num;
--        if (buf) {
--            buf += VMA_CLUSTER_SIZE;
--        }
-+        buf += VMA_CLUSTER_SIZE;
-         if (ret < 0) {
-             Error *local_err = NULL;
-             vma_writer_error_propagate(backup_state.vmaw, &local_err);
-@@ -569,6 +585,10 @@ typedef struct QmpBackupTask {
-     const char *firewall_file;
-     bool has_devlist;
-     const char *devlist;
-+    bool has_compress;
-+    bool compress;
-+    bool has_encrypt;
-+    bool encrypt;
-     bool has_speed;
-     int64_t speed;
-     Error **errp;
-@@ -692,6 +712,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
- 
-         bool use_dirty_bitmap = task->has_use_dirty_bitmap && task->use_dirty_bitmap;
- 
-+
-         char *pbs_err = NULL;
-         pbs = proxmox_backup_new(
-             task->backup_file,
-@@ -701,8 +722,10 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             task->has_password ? task->password : NULL,
-             task->has_keyfile ? task->keyfile : NULL,
-             task->has_key_password ? task->key_password : NULL,
-+            task->has_compress ? task->compress : true,
-+            task->has_encrypt ? task->encrypt : task->has_keyfile,
-             task->has_fingerprint ? task->fingerprint : NULL,
--            &pbs_err);
-+             &pbs_err);
- 
-         if (!pbs) {
-             error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-@@ -721,6 +744,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-             l = g_list_next(l);
- 
-+            di->block_size = dump_cb_block_size;
-+
-             const char *devname = bdrv_get_device_name(di->bs);
- 
-             BdrvDirtyBitmap *bitmap = bdrv_find_dirty_bitmap(di->bs, PBS_BITMAP_NAME);
-@@ -941,6 +966,8 @@ UuidInfo *qmp_backup(
-     bool has_backup_id, const char *backup_id,
-     bool has_backup_time, int64_t backup_time,
-     bool has_use_dirty_bitmap, bool use_dirty_bitmap,
-+    bool has_compress, bool compress,
-+    bool has_encrypt, bool encrypt,
-     bool has_format, BackupFormat format,
-     bool has_config_file, const char *config_file,
-     bool has_firewall_file, const char *firewall_file,
-@@ -951,6 +978,8 @@ UuidInfo *qmp_backup(
-         .backup_file = backup_file,
-         .has_password = has_password,
-         .password = password,
-+        .has_keyfile = has_keyfile,
-+        .keyfile = keyfile,
-         .has_key_password = has_key_password,
-         .key_password = key_password,
-         .has_fingerprint = has_fingerprint,
-@@ -961,6 +990,10 @@ UuidInfo *qmp_backup(
-         .backup_time = backup_time,
-         .has_use_dirty_bitmap = has_use_dirty_bitmap,
-         .use_dirty_bitmap = use_dirty_bitmap,
-+        .has_compress = has_compress,
-+        .compress = compress,
-+        .has_encrypt = has_encrypt,
-+        .encrypt = encrypt,
-         .has_format = has_format,
-         .format = format,
-         .has_config_file = has_config_file,
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 3ad9eb5d1a..4120052690 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -818,6 +818,10 @@
- #
- # @use-dirty-bitmap: use dirty bitmap to detect incremental changes since last job (optional for format 'pbs')
- #
-+# @compress: use compression (optional for format 'pbs', defaults to true)
-+#
-+# @encrypt: use encryption ((optional for format 'pbs', defaults to true if there is a keyfile)
-+#
- # Returns: the uuid of the backup job
- #
- ##
-@@ -829,6 +833,8 @@
-                                     '*backup-id': 'str',
-                                     '*backup-time': 'int',
-                                     '*use-dirty-bitmap': 'bool',
-+                                    '*compress': 'bool',
-+                                    '*encrypt': 'bool',
-                                     '*format': 'BackupFormat',
-                                     '*config-file': 'str',
-                                     '*firewall-file': 'str',

debian/patches/pve/0033-PVE-redirect-stderr-to-journal-when-daemonized.patch

@@ -9,15 +9,15 @@ fitting.
 Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
- meson.build | 2 ++
+ meson.build | 3 ++-
  os-posix.c  | 7 +++++--
- 2 files changed, 7 insertions(+), 2 deletions(-)
+ 2 files changed, 7 insertions(+), 3 deletions(-)
 
 diff --git a/meson.build b/meson.build
-index be4785e2f6..3fc7c8d435 100644
+index 3bc039f60f..067e8956a7 100644
 --- a/meson.build
 +++ b/meson.build
-@@ -1463,6 +1463,7 @@ keyutils = dependency('libkeyutils', required: false,
+@@ -1923,6 +1923,7 @@ endif
  has_gettid = cc.has_function('gettid')
  
  libuuid = cc.find_library('uuid', required: true)
@@ -25,28 +25,29 @@ index be4785e2f6..3fc7c8d435 100644
  libproxmox_backup_qemu = cc.find_library('proxmox_backup_qemu', required: true)
  
  # libselinux
-@@ -3105,6 +3106,7 @@ if have_block
-   # os-posix.c contains POSIX-specific functions used by qemu-storage-daemon,
-   # os-win32.c does not
-   blockdev_ss.add(when: 'CONFIG_POSIX', if_true: files('os-posix.c'))
-+  blockdev_ss.add(when: 'CONFIG_POSIX', if_true: libsystemd)
-   softmmu_ss.add(when: 'CONFIG_WIN32', if_true: [files('os-win32.c')])
+@@ -3530,7 +3531,7 @@ if have_block
+   if host_os == 'windows'
+     system_ss.add(files('os-win32.c'))
+   else
+-    blockdev_ss.add(files('os-posix.c'))
++    blockdev_ss.add(files('os-posix.c'), libsystemd)
+   endif
  endif
  
 diff --git a/os-posix.c b/os-posix.c
-index 321fc4bd13..b1870d2690 100644
+index a4284e2c07..197a2120fd 100644
 --- a/os-posix.c
 +++ b/os-posix.c
-@@ -28,6 +28,8 @@
+@@ -29,6 +29,8 @@
  #include <pwd.h>
  #include <grp.h>
  #include <libgen.h>
 +#include <systemd/sd-journal.h>
 +#include <syslog.h>
  
- /* Needed early for CONFIG_BSD etc. */
- #include "net/slirp.h"
-@@ -281,9 +283,10 @@ void os_setup_post(void)
+ #include "qemu/error-report.h"
+ #include "qemu/log.h"
+@@ -302,9 +304,10 @@ void os_setup_post(void)
  
          dup2(fd, 0);
          dup2(fd, 1);

debian/patches/pve/0034-PVE-Migrate-dirty-bitmap-state-via-savevm.patch

@@ -13,21 +13,23 @@ safe migration is possible and makes sense.
 
 Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+[FE: split up state_pending for 8.0]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  include/migration/misc.h |   3 ++
  migration/meson.build    |   2 +
  migration/migration.c    |   1 +
- migration/pbs-state.c    | 106 +++++++++++++++++++++++++++++++++++++++
+ migration/pbs-state.c    | 104 +++++++++++++++++++++++++++++++++++++++
  pve-backup.c             |   1 +
  qapi/block-core.json     |   6 +++
- 6 files changed, 119 insertions(+)
+ 6 files changed, 117 insertions(+)
  create mode 100644 migration/pbs-state.c
 
 diff --git a/include/migration/misc.h b/include/migration/misc.h
-index 465906710d..4f0aeceb6f 100644
+index c9e200f4eb..12c99ebc69 100644
 --- a/include/migration/misc.h
 +++ b/include/migration/misc.h
-@@ -75,4 +75,7 @@ bool migration_in_bg_snapshot(void);
+@@ -117,4 +117,7 @@ bool migration_in_bg_snapshot(void);
  /* migration/block-dirty-bitmap.c */
  void dirty_bitmap_mig_init(void);
  
@@ -36,38 +38,37 @@ index 465906710d..4f0aeceb6f 100644
 +
  #endif
 diff --git a/migration/meson.build b/migration/meson.build
-index 0842d00cd2..d012f4d8d3 100644
+index 800f12a60d..35a4306183 100644
 --- a/migration/meson.build
 +++ b/migration/meson.build
-@@ -6,8 +6,10 @@ migration_files = files(
+@@ -7,7 +7,9 @@ migration_files = files(
    'vmstate.c',
    'qemu-file.c',
    'yank_functions.c',
 +  'pbs-state.c',
  )
- softmmu_ss.add(migration_files)
-+softmmu_ss.add(libproxmox_backup_qemu)
++system_ss.add(libproxmox_backup_qemu)
  
- softmmu_ss.add(files(
+ system_ss.add(files(
    'block-dirty-bitmap.c',
 diff --git a/migration/migration.c b/migration/migration.c
-index bb8bbddfe4..8109e468eb 100644
+index 86bf76e925..b8d7e471a4 100644
 --- a/migration/migration.c
 +++ b/migration/migration.c
-@@ -229,6 +229,7 @@ void migration_object_init(void)
+@@ -239,6 +239,7 @@ void migration_object_init(void)
      blk_mig_init();
      ram_mig_init();
      dirty_bitmap_mig_init();
 +    pbs_state_mig_init();
  }
  
- void migration_cancel(const Error *error)
+ typedef struct {
 diff --git a/migration/pbs-state.c b/migration/pbs-state.c
 new file mode 100644
-index 0000000000..29f2b3860d
+index 0000000000..887e998b9e
 --- /dev/null
 +++ b/migration/pbs-state.c
-@@ -0,0 +1,106 @@
+@@ -0,0 +1,104 @@
 +/*
 + * PBS (dirty-bitmap) state migration
 + */
@@ -86,11 +87,8 @@ index 0000000000..29f2b3860d
 +/* state is accessed via this static variable directly, 'opaque' is NULL */
 +static PBSState pbs_state;
 +
-+static void pbs_state_save_pending(QEMUFile *f, void *opaque,
-+                                      uint64_t max_size,
-+                                      uint64_t *res_precopy_only,
-+                                      uint64_t *res_compatible,
-+                                      uint64_t *res_postcopy_only)
++static void pbs_state_pending(void *opaque, uint64_t *must_precopy,
++                              uint64_t *can_postcopy)
 +{
 +    /* we send everything in save_setup, so nothing is ever pending */
 +}
@@ -160,7 +158,8 @@ index 0000000000..29f2b3860d
 +static SaveVMHandlers savevm_pbs_state_handlers = {
 +    .save_setup = pbs_state_save_setup,
 +    .has_postcopy = pbs_state_has_postcopy,
-+    .save_live_pending = pbs_state_save_pending,
++    .state_pending_exact = pbs_state_pending,
++    .state_pending_estimate = pbs_state_pending,
 +    .is_active_iterate = pbs_state_is_active_iterate,
 +    .load_state = pbs_state_load,
 +    .is_active = pbs_state_is_active,
@@ -175,22 +174,22 @@ index 0000000000..29f2b3860d
 +                         NULL);
 +}
 diff --git a/pve-backup.c b/pve-backup.c
-index 6f05796fad..5fa3cc1352 100644
+index 9c13a92623..9d480a8eec 100644
 --- a/pve-backup.c
 +++ b/pve-backup.c
-@@ -1132,6 +1132,7 @@ ProxmoxSupportStatus *qmp_query_proxmox_support(Error **errp)
+@@ -1091,6 +1091,7 @@ ProxmoxSupportStatus *qmp_query_proxmox_support(Error **errp)
      ret->pbs_library_version = g_strdup(proxmox_backup_qemu_version());
      ret->pbs_dirty_bitmap = true;
      ret->pbs_dirty_bitmap_savevm = true;
 +    ret->pbs_dirty_bitmap_migration = true;
      ret->query_bitmap_info = true;
-     return ret;
- }
+     ret->pbs_masterkey = true;
+     ret->backup_max_workers = true;
 diff --git a/qapi/block-core.json b/qapi/block-core.json
-index cb17d00fe0..bd978ea562 100644
+index fc32ff9957..f516d8e95a 100644
 --- a/qapi/block-core.json
 +++ b/qapi/block-core.json
-@@ -879,6 +879,11 @@
+@@ -1004,6 +1004,11 @@
  # @pbs-dirty-bitmap-savevm: True if 'dirty-bitmaps' migration capability can
  #                           safely be set for savevm-async.
  #
@@ -199,14 +198,14 @@ index cb17d00fe0..bd978ea562 100644
 +#                              migration cap if this is false/unset may lead
 +#                              to crashes on migration!
 +#
- # @pbs-library-version: Running version of libproxmox-backup-qemu0 library.
+ # @pbs-masterkey: True if the QMP backup call supports the 'master_keyfile'
+ #                 parameter.
  #
- ##
-@@ -886,6 +891,7 @@
+@@ -1017,6 +1022,7 @@
    'data': { 'pbs-dirty-bitmap': 'bool',
              'query-bitmap-info': 'bool',
              'pbs-dirty-bitmap-savevm': 'bool',
 +            'pbs-dirty-bitmap-migration': 'bool',
-             'pbs-library-version': 'str' } }
- 
- ##
+             'pbs-masterkey': 'bool',
+             'pbs-library-version': 'str',
+             'backup-max-workers': 'bool' } }

debian/patches/pve/0034-PVE-add-query_proxmox_support-QMP-command.patch

@@ -1,74 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 8 Jul 2020 11:57:53 +0200
-Subject: [PATCH] PVE: add query_proxmox_support QMP command
-
-Generic interface for future use, currently used for PBS dirty-bitmap
-backup support.
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-[PVE: query-proxmox-support: include library version]
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
----
- pve-backup.c         |  9 +++++++++
- qapi/block-core.json | 29 +++++++++++++++++++++++++++++
- 2 files changed, 38 insertions(+)
-
-diff --git a/pve-backup.c b/pve-backup.c
-index c15abefdda..4684789813 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -1075,3 +1075,12 @@ BackupStatus *qmp_query_backup(Error **errp)
- 
-     return info;
- }
-+
-+ProxmoxSupportStatus *qmp_query_proxmox_support(Error **errp)
-+{
-+    ProxmoxSupportStatus *ret = g_malloc0(sizeof(*ret));
-+    ret->pbs_library_version = g_strdup(proxmox_backup_qemu_version());
-+    ret->pbs_dirty_bitmap = true;
-+    ret->pbs_dirty_bitmap_savevm = true;
-+    return ret;
-+}
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 96bc696aaa..0b453c61d4 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -863,6 +863,35 @@
- ##
- { 'command': 'backup-cancel' }
- 
-+##
-+# @ProxmoxSupportStatus:
-+#
-+# Contains info about supported features added by Proxmox.
-+#
-+# @pbs-dirty-bitmap: True if dirty-bitmap-incremental backups to PBS are
-+#                    supported.
-+#
-+# @pbs-dirty-bitmap-savevm: True if 'dirty-bitmaps' migration capability can
-+#                           safely be set for savevm-async.
-+#
-+# @pbs-library-version: Running version of libproxmox-backup-qemu0 library.
-+#
-+##
-+{ 'struct': 'ProxmoxSupportStatus',
-+  'data': { 'pbs-dirty-bitmap': 'bool',
-+            'pbs-dirty-bitmap-savevm': 'bool',
-+            'pbs-library-version': 'str' } }
-+
-+##
-+# @query-proxmox-support:
-+#
-+# Returns information about supported features added by Proxmox.
-+#
-+# Returns: @ProxmoxSupportStatus
-+#
-+##
-+{ 'command': 'query-proxmox-support', 'returns': 'ProxmoxSupportStatus' }
-+
- ##
- # @BlockDeviceTimedStats:
- #

debian/patches/pve/0035-PVE-add-query-pbs-bitmap-info-QMP-call.patch

@@ -1,441 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 19 Aug 2020 17:02:00 +0200
-Subject: [PATCH] PVE: add query-pbs-bitmap-info QMP call
-
-Returns advanced information about dirty bitmaps used (or not used) for
-the latest PBS backup.
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- monitor/hmp-cmds.c   |  28 ++++++-----
- pve-backup.c         | 117 ++++++++++++++++++++++++++++++++-----------
- qapi/block-core.json |  56 +++++++++++++++++++++
- 3 files changed, 159 insertions(+), 42 deletions(-)
-
-diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
-index 4c1671e289..c1152f55a7 100644
---- a/monitor/hmp-cmds.c
-+++ b/monitor/hmp-cmds.c
-@@ -200,6 +200,7 @@ void hmp_info_mice(Monitor *mon, const QDict *qdict)
- void hmp_info_backup(Monitor *mon, const QDict *qdict)
- {
-     BackupStatus *info;
-+    PBSBitmapInfoList *bitmap_info;
- 
-     info = qmp_query_backup(NULL);
- 
-@@ -230,26 +231,29 @@ void hmp_info_backup(Monitor *mon, const QDict *qdict)
-             // this should not happen normally
-             monitor_printf(mon, "Total size: %d\n", 0);
-         } else {
--            bool incremental = false;
-             size_t total_or_dirty = info->total;
--            if (info->has_transferred) {
--                if (info->has_dirty && info->dirty) {
--                     if (info->dirty < info->total) {
--                        total_or_dirty = info->dirty;
--                        incremental = true;
--                    }
--                }
-+            bitmap_info = qmp_query_pbs_bitmap_info(NULL);
-+
-+            while (bitmap_info) {
-+                monitor_printf(mon, "Drive %s:\n",
-+                        bitmap_info->value->drive);
-+                monitor_printf(mon, "  bitmap action: %s\n",
-+                        PBSBitmapAction_str(bitmap_info->value->action));
-+                monitor_printf(mon, "  size: %zd\n",
-+                        bitmap_info->value->size);
-+                monitor_printf(mon, "  dirty: %zd\n",
-+                        bitmap_info->value->dirty);
-+                bitmap_info = bitmap_info->next;
-             }
- 
--            int per = (info->transferred * 100)/total_or_dirty;
--
--            monitor_printf(mon, "Backup mode: %s\n", incremental ? "incremental" : "full");
-+            qapi_free_PBSBitmapInfoList(bitmap_info);
- 
-             int zero_per = (info->has_zero_bytes && info->zero_bytes) ?
-                 (info->zero_bytes * 100)/info->total : 0;
-             monitor_printf(mon, "Total size: %zd\n", info->total);
-+            int trans_per = (info->transferred * 100)/total_or_dirty;
-             monitor_printf(mon, "Transferred bytes: %zd (%d%%)\n",
--                           info->transferred, per);
-+                           info->transferred, trans_per);
-             monitor_printf(mon, "Zero bytes: %zd (%d%%)\n",
-                            info->zero_bytes, zero_per);
- 
-diff --git a/pve-backup.c b/pve-backup.c
-index 4684789813..f90abaa50a 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -46,6 +46,7 @@ static struct PVEBackupState {
-         size_t transferred;
-         size_t reused;
-         size_t zero_bytes;
-+        GList *bitmap_list;
-     } stat;
-     int64_t speed;
-     VmaWriter *vmaw;
-@@ -672,7 +673,6 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     }
- 
-     size_t total = 0;
--    size_t dirty = 0;
- 
-     l = di_list;
-     while (l) {
-@@ -693,18 +693,33 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
- 
-     uuid_generate(uuid);
- 
-+    qemu_mutex_lock(&backup_state.stat.lock);
-+    backup_state.stat.reused = 0;
-+
-+    /* clear previous backup's bitmap_list */
-+    if (backup_state.stat.bitmap_list) {
-+        GList *bl = backup_state.stat.bitmap_list;
-+        while (bl) {
-+            g_free(((PBSBitmapInfo *)bl->data)->drive);
-+            g_free(bl->data);
-+            bl = g_list_next(bl);
-+        }
-+        g_list_free(backup_state.stat.bitmap_list);
-+        backup_state.stat.bitmap_list = NULL;
-+    }
-+
-     if (format == BACKUP_FORMAT_PBS) {
-         if (!task->has_password) {
-             error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'password'");
--            goto err;
-+            goto err_mutex;
-         }
-         if (!task->has_backup_id) {
-             error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'backup-id'");
--            goto err;
-+            goto err_mutex;
-         }
-         if (!task->has_backup_time) {
-             error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'backup-time'");
--            goto err;
-+            goto err_mutex;
-         }
- 
-         int dump_cb_block_size = PROXMOX_BACKUP_DEFAULT_CHUNK_SIZE; // Hardcoded (4M)
-@@ -731,12 +746,12 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-                       "proxmox_backup_new failed: %s", pbs_err);
-             proxmox_backup_free_error(pbs_err);
--            goto err;
-+            goto err_mutex;
-         }
- 
-         int connect_result = proxmox_backup_co_connect(pbs, task->errp);
-         if (connect_result < 0)
--            goto err;
-+            goto err_mutex;
- 
-         /* register all devices */
-         l = di_list;
-@@ -747,6 +762,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             di->block_size = dump_cb_block_size;
- 
-             const char *devname = bdrv_get_device_name(di->bs);
-+            PBSBitmapAction action = PBS_BITMAP_ACTION_NOT_USED;
-+            size_t dirty = di->size;
- 
-             BdrvDirtyBitmap *bitmap = bdrv_find_dirty_bitmap(di->bs, PBS_BITMAP_NAME);
-             bool expect_only_dirty = false;
-@@ -755,49 +772,59 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-                 if (bitmap == NULL) {
-                     bitmap = bdrv_create_dirty_bitmap(di->bs, dump_cb_block_size, PBS_BITMAP_NAME, task->errp);
-                     if (!bitmap) {
--                        goto err;
-+                        goto err_mutex;
-                     }
-+                    action = PBS_BITMAP_ACTION_NEW;
-                 } else {
-                     expect_only_dirty = proxmox_backup_check_incremental(pbs, devname, di->size) != 0;
-                 }
- 
-                 if (expect_only_dirty) {
--                    dirty += bdrv_get_dirty_count(bitmap);
-+                    /* track clean chunks as reused */
-+                    dirty = MIN(bdrv_get_dirty_count(bitmap), di->size);
-+                    backup_state.stat.reused += di->size - dirty;
-+                    action = PBS_BITMAP_ACTION_USED;
-                 } else {
-                     /* mark entire bitmap as dirty to make full backup */
-                     bdrv_set_dirty_bitmap(bitmap, 0, di->size);
--                    dirty += di->size;
-+                    if (action != PBS_BITMAP_ACTION_NEW) {
-+                        action = PBS_BITMAP_ACTION_INVALID;
-+                    }
-                 }
-                 di->bitmap = bitmap;
-             } else {
--                dirty += di->size;
--
-                 /* after a full backup the old dirty bitmap is invalid anyway */
-                 if (bitmap != NULL) {
-                     bdrv_release_dirty_bitmap(bitmap);
-+                    action = PBS_BITMAP_ACTION_NOT_USED_REMOVED;
-                 }
-             }
- 
-             int dev_id = proxmox_backup_co_register_image(pbs, devname, di->size, expect_only_dirty, task->errp);
-             if (dev_id < 0) {
--                goto err;
-+                goto err_mutex;
-             }
- 
-             if (!(di->target = bdrv_backup_dump_create(dump_cb_block_size, di->size, pvebackup_co_dump_pbs_cb, di, task->errp))) {
--                goto err;
-+                goto err_mutex;
-             }
- 
-             di->dev_id = dev_id;
-+
-+            PBSBitmapInfo *info = g_malloc(sizeof(*info));
-+            info->drive = g_strdup(devname);
-+            info->action = action;
-+            info->size = di->size;
-+            info->dirty = dirty;
-+            backup_state.stat.bitmap_list = g_list_append(backup_state.stat.bitmap_list, info);
-         }
-     } else if (format == BACKUP_FORMAT_VMA) {
--        dirty = total;
--
-         vmaw = vma_writer_create(task->backup_file, uuid, &local_err);
-         if (!vmaw) {
-             if (local_err) {
-                 error_propagate(task->errp, local_err);
-             }
--            goto err;
-+            goto err_mutex;
-         }
- 
-         /* register all devices for vma writer */
-@@ -807,7 +834,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             l = g_list_next(l);
- 
-             if (!(di->target = bdrv_backup_dump_create(VMA_CLUSTER_SIZE, di->size, pvebackup_co_dump_vma_cb, di, task->errp))) {
--                goto err;
-+                goto err_mutex;
-             }
- 
-             const char *devname = bdrv_get_device_name(di->bs);
-@@ -815,16 +842,14 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             if (di->dev_id <= 0) {
-                 error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-                           "register_stream failed");
--                goto err;
-+                goto err_mutex;
-             }
-         }
-     } else if (format == BACKUP_FORMAT_DIR) {
--        dirty = total;
--
-         if (mkdir(task->backup_file, 0640) != 0) {
-             error_setg_errno(task->errp, errno, "can't create directory '%s'\n",
-                              task->backup_file);
--            goto err;
-+            goto err_mutex;
-         }
-         backup_dir = task->backup_file;
- 
-@@ -841,18 +866,18 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-                             di->size, flags, false, &local_err);
-             if (local_err) {
-                 error_propagate(task->errp, local_err);
--                goto err;
-+                goto err_mutex;
-             }
- 
-             di->target = bdrv_open(di->targetfile, NULL, NULL, flags, &local_err);
-             if (!di->target) {
-                 error_propagate(task->errp, local_err);
--                goto err;
-+                goto err_mutex;
-             }
-         }
-     } else {
-         error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "unknown backup format");
--        goto err;
-+        goto err_mutex;
-     }
- 
- 
-@@ -860,7 +885,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     if (task->has_config_file) {
-         if (pvebackup_co_add_config(task->config_file, config_name, format, backup_dir,
-                                     vmaw, pbs, task->errp) != 0) {
--            goto err;
-+            goto err_mutex;
-         }
-     }
- 
-@@ -868,12 +893,11 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     if (task->has_firewall_file) {
-         if (pvebackup_co_add_config(task->firewall_file, firewall_name, format, backup_dir,
-                                     vmaw, pbs, task->errp) != 0) {
--            goto err;
-+            goto err_mutex;
-         }
-     }
-     /* initialize global backup_state now */
--
--    qemu_mutex_lock(&backup_state.stat.lock);
-+    /* note: 'reused' and 'bitmap_list' are initialized earlier */
- 
-     if (backup_state.stat.error) {
-         error_free(backup_state.stat.error);
-@@ -893,10 +917,9 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     char *uuid_str = g_strdup(backup_state.stat.uuid_str);
- 
-     backup_state.stat.total = total;
--    backup_state.stat.dirty = dirty;
-+    backup_state.stat.dirty = total - backup_state.stat.reused;
-     backup_state.stat.transferred = 0;
-     backup_state.stat.zero_bytes = 0;
--    backup_state.stat.reused = format == BACKUP_FORMAT_PBS && dirty >= total ? 0 : total - dirty;
- 
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
-@@ -913,6 +936,9 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     task->result = uuid_info;
-     return;
- 
-+err_mutex:
-+    qemu_mutex_unlock(&backup_state.stat.lock);
-+
- err:
- 
-     l = di_list;
-@@ -1076,11 +1102,42 @@ BackupStatus *qmp_query_backup(Error **errp)
-     return info;
- }
- 
-+PBSBitmapInfoList *qmp_query_pbs_bitmap_info(Error **errp)
-+{
-+    PBSBitmapInfoList *head = NULL, **p_next = &head;
-+
-+    qemu_mutex_lock(&backup_state.stat.lock);
-+
-+    GList *l = backup_state.stat.bitmap_list;
-+    while (l) {
-+        PBSBitmapInfo *info = (PBSBitmapInfo *)l->data;
-+        l = g_list_next(l);
-+
-+        /* clone bitmap info to avoid auto free after QMP marshalling */
-+        PBSBitmapInfo *info_ret = g_malloc0(sizeof(*info_ret));
-+        info_ret->drive = g_strdup(info->drive);
-+        info_ret->action = info->action;
-+        info_ret->size = info->size;
-+        info_ret->dirty = info->dirty;
-+
-+        PBSBitmapInfoList *info_list = g_malloc0(sizeof(*info_list));
-+        info_list->value = info_ret;
-+
-+        *p_next = info_list;
-+        p_next = &info_list->next;
-+    }
-+
-+    qemu_mutex_unlock(&backup_state.stat.lock);
-+
-+    return head;
-+}
-+
- ProxmoxSupportStatus *qmp_query_proxmox_support(Error **errp)
- {
-     ProxmoxSupportStatus *ret = g_malloc0(sizeof(*ret));
-     ret->pbs_library_version = g_strdup(proxmox_backup_qemu_version());
-     ret->pbs_dirty_bitmap = true;
-     ret->pbs_dirty_bitmap_savevm = true;
-+    ret->query_bitmap_info = true;
-     return ret;
- }
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 0b453c61d4..16e184dd28 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -871,6 +871,8 @@
- # @pbs-dirty-bitmap: True if dirty-bitmap-incremental backups to PBS are
- #                    supported.
- #
-+# @query-bitmap-info: True if the 'query-pbs-bitmap-info' QMP call is supported.
-+#
- # @pbs-dirty-bitmap-savevm: True if 'dirty-bitmaps' migration capability can
- #                           safely be set for savevm-async.
- #
-@@ -879,6 +881,7 @@
- ##
- { 'struct': 'ProxmoxSupportStatus',
-   'data': { 'pbs-dirty-bitmap': 'bool',
-+            'query-bitmap-info': 'bool',
-             'pbs-dirty-bitmap-savevm': 'bool',
-             'pbs-library-version': 'str' } }
- 
-@@ -892,6 +895,59 @@
- ##
- { 'command': 'query-proxmox-support', 'returns': 'ProxmoxSupportStatus' }
- 
-+##
-+# @PBSBitmapAction:
-+#
-+# An action taken on a dirty-bitmap when a backup job was started.
-+#
-+# @not-used: Bitmap mode was not enabled.
-+#
-+# @not-used-removed: Bitmap mode was not enabled, but a bitmap from a
-+#                    previous backup still existed and was removed.
-+#
-+# @new: A new bitmap was attached to the drive for this backup.
-+#
-+# @used: An existing bitmap will be used to only backup changed data.
-+#
-+# @invalid: A bitmap existed, but had to be cleared since it's associated
-+#           base snapshot did not match the base given for the current job or
-+#           the crypt mode has changed.
-+#
-+##
-+{ 'enum': 'PBSBitmapAction',
-+  'data': ['not-used', 'not-used-removed', 'new', 'used', 'invalid'] }
-+
-+##
-+# @PBSBitmapInfo:
-+#
-+# Contains information about dirty bitmaps used for each drive in a PBS backup.
-+#
-+# @drive: The underlying drive.
-+#
-+# @action: The action that was taken when the backup started.
-+#
-+# @size: The total size of the drive.
-+#
-+# @dirty: How much of the drive is considered dirty and will be backed up,
-+#         or 'size' if everything will be.
-+#
-+##
-+{ 'struct': 'PBSBitmapInfo',
-+  'data': { 'drive': 'str', 'action': 'PBSBitmapAction', 'size': 'int',
-+            'dirty': 'int' } }
-+
-+##
-+# @query-pbs-bitmap-info:
-+#
-+# Returns information about dirty bitmaps used on the most recently started
-+# backup. Returns nothing when the last backup was not using PBS or if no
-+# backup occured in this session.
-+#
-+# Returns: @PBSBitmapInfo
-+#
-+##
-+{ 'command': 'query-pbs-bitmap-info', 'returns': ['PBSBitmapInfo'] }
-+
- ##
- # @BlockDeviceTimedStats:
- #

debian/patches/pve/0035-migration-block-dirty-bitmap-migrate-other-bitmaps-e.patch

@@ -19,10 +19,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/migration/block-dirty-bitmap.c b/migration/block-dirty-bitmap.c
-index 9aba7d9c22..f4ecf9c9f9 100644
+index 2708abf3d7..fb17c01308 100644
 --- a/migration/block-dirty-bitmap.c
 +++ b/migration/block-dirty-bitmap.c
-@@ -538,7 +538,7 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
+@@ -540,7 +540,7 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
  
          if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, &local_err)) {
              error_report_err(local_err);

debian/patches/pve/0036-PVE-fall-back-to-open-iscsi-initiatorname.patch

@@ -21,10 +21,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 30 insertions(+)
 
 diff --git a/block/iscsi.c b/block/iscsi.c
-index d707d0b354..da6ed52323 100644
+index 2ff14b7472..46f275fbf7 100644
 --- a/block/iscsi.c
 +++ b/block/iscsi.c
-@@ -1386,12 +1386,42 @@ static char *get_initiator_name(QemuOpts *opts)
+@@ -1392,12 +1392,42 @@ static char *get_initiator_name(QemuOpts *opts)
      const char *name;
      char *iscsi_name;
      UuidInfo *uuid_info;

debian/patches/pve/0037-PVE-block-stream-increase-chunk-size.patch

@@ -11,10 +11,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/block/stream.c b/block/stream.c
-index 694709bd25..e09bd5c4ef 100644
+index 7031eef12b..d2da83ae7c 100644
 --- a/block/stream.c
 +++ b/block/stream.c
-@@ -28,7 +28,7 @@ enum {
+@@ -27,7 +27,7 @@ enum {
       * large enough to process multiple clusters in a single call, so
       * that populating contiguous regions of the image is efficient.
       */

debian/patches/pve/0038-PVE-Backup-Use-a-transaction-to-synchronize-job-stat.patch

@@ -1,295 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Thu, 20 Aug 2020 14:25:00 +0200
-Subject: [PATCH] PVE-Backup: Use a transaction to synchronize job states
-
-By using a JobTxn, we can sync dirty bitmaps only when *all* jobs were
-successful - meaning we don't need to remove them when the backup fails,
-since QEMU's BITMAP_SYNC_MODE_ON_SUCCESS will now handle that for us.
-
-To keep the rate-limiting and IO impact from before, we use a sequential
-transaction, so drives will still be backed up one after the other.
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-[add new force parameter to job_cancel_sync calls]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- pve-backup.c | 167 +++++++++++++++------------------------------------
- 1 file changed, 49 insertions(+), 118 deletions(-)
-
-diff --git a/pve-backup.c b/pve-backup.c
-index f90abaa50a..63c686463f 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -52,6 +52,7 @@ static struct PVEBackupState {
-     VmaWriter *vmaw;
-     ProxmoxBackupHandle *pbs;
-     GList *di_list;
-+    JobTxn *txn;
-     QemuMutex backup_mutex;
-     CoMutex dump_callback_mutex;
- } backup_state;
-@@ -71,32 +72,12 @@ typedef struct PVEBackupDevInfo {
-     size_t size;
-     uint64_t block_size;
-     uint8_t dev_id;
--    bool completed;
-     char targetfile[PATH_MAX];
-     BdrvDirtyBitmap *bitmap;
-     BlockDriverState *target;
-+    BlockJob *job;
- } PVEBackupDevInfo;
- 
--static void pvebackup_run_next_job(void);
--
--static BlockJob *
--lookup_active_block_job(PVEBackupDevInfo *di)
--{
--    if (!di->completed && di->bs) {
--        for (BlockJob *job = block_job_next(NULL); job; job = block_job_next(job)) {
--            if (job->job.driver->job_type != JOB_TYPE_BACKUP) {
--                continue;
--            }
--
--            BackupBlockJob *bjob = container_of(job, BackupBlockJob, common);
--            if (bjob && bjob->source_bs == di->bs) {
--                return job;
--            }
--        }
--    }
--    return NULL;
--}
--
- static void pvebackup_propagate_error(Error *err)
- {
-     qemu_mutex_lock(&backup_state.stat.lock);
-@@ -272,18 +253,6 @@ static void coroutine_fn pvebackup_co_cleanup(void *unused)
-             if (local_err != NULL) {
-                 pvebackup_propagate_error(local_err);
-             }
--        } else {
--            // on error or cancel we cannot ensure synchronization of dirty
--            // bitmaps with backup server, so remove all and do full backup next
--            GList *l = backup_state.di_list;
--            while (l) {
--                PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
--                l = g_list_next(l);
--
--                if (di->bitmap) {
--                    bdrv_release_dirty_bitmap(di->bitmap);
--                }
--            }
-         }
- 
-         proxmox_backup_disconnect(backup_state.pbs);
-@@ -322,8 +291,6 @@ static void pvebackup_complete_cb(void *opaque, int ret)
- 
-     qemu_mutex_lock(&backup_state.backup_mutex);
- 
--    di->completed = true;
--
-     if (ret < 0) {
-         Error *local_err = NULL;
-         error_setg(&local_err, "job failed with err %d - %s", ret, strerror(-ret));
-@@ -336,20 +303,17 @@ static void pvebackup_complete_cb(void *opaque, int ret)
- 
-     block_on_coroutine_fn(pvebackup_complete_stream, di);
- 
--    // remove self from job queue
-+    // remove self from job list
-     backup_state.di_list = g_list_remove(backup_state.di_list, di);
- 
--    if (di->bitmap && ret < 0) {
--        // on error or cancel we cannot ensure synchronization of dirty
--        // bitmaps with backup server, so remove all and do full backup next
--        bdrv_release_dirty_bitmap(di->bitmap);
--    }
--
-     g_free(di);
- 
--    qemu_mutex_unlock(&backup_state.backup_mutex);
-+    /* call cleanup if we're the last job */
-+    if (!g_list_first(backup_state.di_list)) {
-+        block_on_coroutine_fn(pvebackup_co_cleanup, NULL);
-+    }
- 
--    pvebackup_run_next_job();
-+    qemu_mutex_unlock(&backup_state.backup_mutex);
- }
- 
- static void pvebackup_cancel(void)
-@@ -371,36 +335,28 @@ static void pvebackup_cancel(void)
-         proxmox_backup_abort(backup_state.pbs, "backup canceled");
-     }
- 
--    qemu_mutex_unlock(&backup_state.backup_mutex);
--
--    for(;;) {
--
--        BlockJob *next_job = NULL;
--
--        qemu_mutex_lock(&backup_state.backup_mutex);
--
--        GList *l = backup_state.di_list;
--        while (l) {
--            PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
--            l = g_list_next(l);
-+    /* it's enough to cancel one job in the transaction, the rest will follow
-+     * automatically */
-+    GList *bdi = g_list_first(backup_state.di_list);
-+    BlockJob *cancel_job = bdi && bdi->data ?
-+        ((PVEBackupDevInfo *)bdi->data)->job :
-+        NULL;
- 
--            BlockJob *job = lookup_active_block_job(di);
--            if (job != NULL) {
--                next_job = job;
--                break;
--            }
--        }
-+    /* ref the job before releasing the mutex, just to be safe */
-+    if (cancel_job) {
-+        job_ref(&cancel_job->job);
-+    }
- 
--        qemu_mutex_unlock(&backup_state.backup_mutex);
-+    /* job_cancel_sync may enter the job, so we need to release the
-+     * backup_mutex to avoid deadlock */
-+    qemu_mutex_unlock(&backup_state.backup_mutex);
- 
--        if (next_job) {
--            AioContext *aio_context = next_job->job.aio_context;
--            aio_context_acquire(aio_context);
--            job_cancel_sync(&next_job->job, true);
--            aio_context_release(aio_context);
--        } else {
--            break;
--        }
-+    if (cancel_job) {
-+        AioContext *aio_context = cancel_job->job.aio_context;
-+        aio_context_acquire(aio_context);
-+        job_cancel_sync(&cancel_job->job, true);
-+        job_unref(&cancel_job->job);
-+        aio_context_release(aio_context);
-     }
- }
- 
-@@ -459,51 +415,19 @@ static int coroutine_fn pvebackup_co_add_config(
-     goto out;
- }
- 
--bool job_should_pause(Job *job);
--
--static void pvebackup_run_next_job(void)
--{
--    assert(!qemu_in_coroutine());
--
--    qemu_mutex_lock(&backup_state.backup_mutex);
--
--    GList *l = backup_state.di_list;
--    while (l) {
--        PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
--        l = g_list_next(l);
--
--        BlockJob *job = lookup_active_block_job(di);
--
--        if (job) {
--            qemu_mutex_unlock(&backup_state.backup_mutex);
--
--            AioContext *aio_context = job->job.aio_context;
--            aio_context_acquire(aio_context);
--
--            if (job_should_pause(&job->job)) {
--                bool error_or_canceled = pvebackup_error_or_canceled();
--                if (error_or_canceled) {
--                    job_cancel_sync(&job->job, true);
--                } else {
--                    job_resume(&job->job);
--                }
--            }
--            aio_context_release(aio_context);
--            return;
--        }
--    }
--
--    block_on_coroutine_fn(pvebackup_co_cleanup, NULL); // no more jobs, run cleanup
--
--    qemu_mutex_unlock(&backup_state.backup_mutex);
--}
--
- static bool create_backup_jobs(void) {
- 
-     assert(!qemu_in_coroutine());
- 
-     Error *local_err = NULL;
- 
-+    /* create job transaction to synchronize bitmap commit and cancel all
-+     * jobs in case one errors */
-+    if (backup_state.txn) {
-+        job_txn_unref(backup_state.txn);
-+    }
-+    backup_state.txn = job_txn_new_seq();
-+
-     BackupPerf perf = { .max_workers = 16 };
- 
-     /* create and start all jobs (paused state) */
-@@ -526,7 +450,7 @@ static bool create_backup_jobs(void) {
-         BlockJob *job = backup_job_create(
-             NULL, di->bs, di->target, backup_state.speed, sync_mode, di->bitmap,
-             bitmap_mode, false, NULL, &perf, BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
--            JOB_DEFAULT, pvebackup_complete_cb, di, NULL, &local_err);
-+            JOB_DEFAULT, pvebackup_complete_cb, di, backup_state.txn, &local_err);
- 
-         aio_context_release(aio_context);
- 
-@@ -538,7 +462,8 @@ static bool create_backup_jobs(void) {
-             pvebackup_propagate_error(create_job_err);
-             break;
-         }
--        job_start(&job->job);
-+
-+        di->job = job;
- 
-         bdrv_unref(di->target);
-         di->target = NULL;
-@@ -556,6 +481,10 @@ static bool create_backup_jobs(void) {
-                 bdrv_unref(di->target);
-                 di->target = NULL;
-             }
-+
-+            if (di->job) {
-+                job_unref(&di->job->job);
-+            }
-         }
-     }
- 
-@@ -946,10 +875,6 @@ err:
-         PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-         l = g_list_next(l);
- 
--        if (di->bitmap) {
--            bdrv_release_dirty_bitmap(di->bitmap);
--        }
--
-         if (di->target) {
-             bdrv_unref(di->target);
-         }
-@@ -1038,9 +963,15 @@ UuidInfo *qmp_backup(
-     block_on_coroutine_fn(pvebackup_co_prepare, &task);
- 
-     if (*errp == NULL) {
--        create_backup_jobs();
-+        bool errors = create_backup_jobs();
-         qemu_mutex_unlock(&backup_state.backup_mutex);
--        pvebackup_run_next_job();
-+
-+        if (!errors) {
-+            /* start the first job in the transaction
-+             * note: this might directly enter the job, so we need to do this
-+             * after unlocking the backup_mutex */
-+            job_txn_start_seq(backup_state.txn);
-+        }
-     } else {
-         qemu_mutex_unlock(&backup_state.backup_mutex);
-     }

debian/patches/pve/0038-block-add-alloc-track-driver.patch

@@ -19,26 +19,33 @@ well.
 This only worked if the target supports backing images, so up until now
 only for qcow2, with alloc-track any driver for the target can be used.
 
-If 'auto-remove' is set, alloc-track will automatically detach itself
-once the backing image is removed. It will be replaced by 'file'.
+Replacing the node cannot be done in the
+track_co_change_backing_file() callback, because replacing a node
+cannot happen in a coroutine and requires the block graph lock
+exclusively. Could either become a special option for the stream job,
+or maybe the upcoming blockdev-replace QMP command can be used in the
+future.
 
 Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 [FE: adapt to changed function signatures
-     make error return value consistent with QEMU]
+     make error return value consistent with QEMU
+     avoid premature break during read
+     adhere to block graph lock requirements]
 Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
- block/alloc-track.c | 350 ++++++++++++++++++++++++++++++++++++++++++++
+ block/alloc-track.c | 366 ++++++++++++++++++++++++++++++++++++++++++++
  block/meson.build   |   1 +
- 2 files changed, 351 insertions(+)
+ block/stream.c      |  34 ++++
+ 3 files changed, 401 insertions(+)
  create mode 100644 block/alloc-track.c
 
 diff --git a/block/alloc-track.c b/block/alloc-track.c
 new file mode 100644
-index 0000000000..43d40d11af
+index 0000000000..b9f8ea9137
 --- /dev/null
 +++ b/block/alloc-track.c
-@@ -0,0 +1,350 @@
+@@ -0,0 +1,366 @@
 +/*
 + * Node to allow backing images to be applied to any node. Assumes a blank
 + * image to begin with, only new writes are tracked as allocated, thus this
@@ -54,9 +61,12 @@ index 0000000000..43d40d11af
 +#include "qemu/osdep.h"
 +#include "qapi/error.h"
 +#include "block/block_int.h"
++#include "block/dirty-bitmap.h"
++#include "block/graph-lock.h"
 +#include "qapi/qmp/qdict.h"
 +#include "qapi/qmp/qstring.h"
 +#include "qemu/cutils.h"
++#include "qemu/error-report.h"
 +#include "qemu/option.h"
 +#include "qemu/module.h"
 +#include "sysemu/block-backend.h"
@@ -65,12 +75,12 @@ index 0000000000..43d40d11af
 +
 +typedef enum DropState {
 +    DropNone,
-+    DropRequested,
 +    DropInProgress,
 +} DropState;
 +
 +typedef struct {
 +    BdrvDirtyBitmap *bitmap;
++    uint64_t granularity;
 +    DropState drop_state;
 +    bool auto_remove;
 +} BDRVAllocTrackState;
@@ -89,26 +99,29 @@ index 0000000000..43d40d11af
 +    },
 +};
 +
-+static void track_refresh_limits(BlockDriverState *bs, Error **errp)
++static void GRAPH_RDLOCK
++track_refresh_limits(BlockDriverState *bs, Error **errp)
 +{
-+    BlockDriverInfo bdi;
++    BDRVAllocTrackState *s = bs->opaque;
 +
 +    if (!bs->file) {
 +        return;
 +    }
 +
-+    /* always use alignment from underlying write device so RMW cycle for
-+     * bdrv_pwritev reads data from our backing via track_co_preadv (no partial
-+     * cluster allocation in 'file') */
-+    bdrv_get_info(bs->file->bs, &bdi);
++    /*
++     * Always use alignment from underlying write device so RMW cycle for
++     * bdrv_pwritev reads data from our backing via track_co_preadv. Also use at
++     * least the bitmap granularity.
++     */
 +    bs->bl.request_alignment = MAX(bs->file->bs->bl.request_alignment,
-+                                   MAX(bdi.cluster_size, BDRV_SECTOR_SIZE));
++                                   s->granularity);
 +}
 +
 +static int track_open(BlockDriverState *bs, QDict *options, int flags,
 +                      Error **errp)
 +{
 +    BDRVAllocTrackState *s = bs->opaque;
++    BdrvChild *file = NULL;
 +    QemuOpts *opts;
 +    Error *local_err = NULL;
 +    int ret = 0;
@@ -124,18 +137,45 @@ index 0000000000..43d40d11af
 +    s->auto_remove = qemu_opt_get_bool(opts, TRACK_OPT_AUTO_REMOVE, false);
 +
 +    /* open the target (write) node, backing will be attached by block layer */
-+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
-+                               BDRV_CHILD_DATA | BDRV_CHILD_METADATA, false,
-+                               &local_err);
++    file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
++                           BDRV_CHILD_DATA | BDRV_CHILD_METADATA, false,
++                           &local_err);
++    bdrv_graph_wrlock();
++    bs->file = file;
++    bdrv_graph_wrunlock();
 +    if (local_err) {
 +        ret = -EINVAL;
 +        error_propagate(errp, local_err);
 +        goto fail;
 +    }
 +
++    bdrv_graph_rdlock_main_loop();
++    BlockDriverInfo bdi = {0};
++    ret = bdrv_get_info(bs->file->bs, &bdi);
++    if (ret < 0) {
++        /*
++         * Not a hard failure. Worst that can happen is partial cluster
++         * allocation in the write target. However, the driver here returns its
++         * allocation status based on the dirty bitmap, so any other data that
++         * maps to such a cluster will still be copied later by a stream job (or
++         * during writes to that cluster).
++         */
++        warn_report("alloc-track: unable to query cluster size for write target: %s",
++                    strerror(ret));
++    }
++    ret = 0;
++    /*
++     * Always consider alignment from underlying write device so RMW cycle for
++     * bdrv_pwritev reads data from our backing via track_co_preadv. Also try to
++     * avoid partial cluster allocation in the write target by considering the
++     * cluster size.
++     */
++    s->granularity = MAX(bs->file->bs->bl.request_alignment,
++                         MAX(bdi.cluster_size, BDRV_SECTOR_SIZE));
 +    track_refresh_limits(bs, errp);
-+    uint64_t gran = bs->bl.request_alignment;
-+    s->bitmap = bdrv_create_dirty_bitmap(bs->file->bs, gran, NULL, &local_err);
++    s->bitmap = bdrv_create_dirty_bitmap(bs->file->bs, s->granularity, NULL,
++                                         &local_err);
++    bdrv_graph_rdunlock_main_loop();
 +    if (local_err) {
 +        ret = -EIO;
 +        error_propagate(errp, local_err);
@@ -146,7 +186,9 @@ index 0000000000..43d40d11af
 +
 +fail:
 +    if (ret < 0) {
++        bdrv_graph_wrlock();
 +        bdrv_unref_child(bs, bs->file);
++        bdrv_graph_wrunlock();
 +        if (s->bitmap) {
 +            bdrv_release_dirty_bitmap(s->bitmap);
 +        }
@@ -163,13 +205,15 @@ index 0000000000..43d40d11af
 +    }
 +}
 +
-+static int64_t track_getlength(BlockDriverState *bs)
++static coroutine_fn int64_t GRAPH_RDLOCK
++track_co_getlength(BlockDriverState *bs)
 +{
-+    return bdrv_getlength(bs->file->bs);
++    return bdrv_co_getlength(bs->file->bs);
 +}
 +
-+static int coroutine_fn track_co_preadv(BlockDriverState *bs,
-+    int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags)
++static int coroutine_fn GRAPH_RDLOCK
++track_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
++                QEMUIOVector *qiov, BdrvRequestFlags flags)
 +{
 +    BDRVAllocTrackState *s = bs->opaque;
 +    QEMUIOVector local_qiov;
@@ -215,7 +259,8 @@ index 0000000000..43d40d11af
 +            ret = bdrv_co_preadv(bs->backing, local_offset, local_bytes,
 +                                 &local_qiov, flags);
 +        } else {
-+            ret = qemu_iovec_memset(&local_qiov, cur_offset, 0, local_bytes);
++            qemu_iovec_memset(&local_qiov, cur_offset, 0, local_bytes);
++            ret = 0;
 +        }
 +
 +        if (ret != 0) {
@@ -226,36 +271,39 @@ index 0000000000..43d40d11af
 +    return ret;
 +}
 +
-+static int coroutine_fn track_co_pwritev(BlockDriverState *bs,
-+    int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags)
++static int coroutine_fn GRAPH_RDLOCK
++track_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
++                 QEMUIOVector *qiov, BdrvRequestFlags flags)
 +{
 +    return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
 +}
 +
-+static int coroutine_fn track_co_pwrite_zeroes(BlockDriverState *bs,
-+    int64_t offset, int64_t bytes, BdrvRequestFlags flags)
++static int coroutine_fn GRAPH_RDLOCK
++track_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes,
++                       BdrvRequestFlags flags)
 +{
 +    return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
 +}
 +
-+static int coroutine_fn track_co_pdiscard(BlockDriverState *bs,
-+    int64_t offset, int64_t bytes)
++static int coroutine_fn GRAPH_RDLOCK
++track_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)
 +{
 +    return bdrv_co_pdiscard(bs->file, offset, bytes);
 +}
 +
-+static coroutine_fn int track_co_flush(BlockDriverState *bs)
++static coroutine_fn int GRAPH_RDLOCK
++track_co_flush(BlockDriverState *bs)
 +{
 +    return bdrv_co_flush(bs->file->bs);
 +}
 +
-+static int coroutine_fn track_co_block_status(BlockDriverState *bs,
-+                                              bool want_zero,
-+                                              int64_t offset,
-+                                              int64_t bytes,
-+                                              int64_t *pnum,
-+                                              int64_t *map,
-+                                              BlockDriverState **file)
++static int coroutine_fn GRAPH_RDLOCK
++track_co_block_status(BlockDriverState *bs, bool want_zero,
++                                            int64_t offset,
++                                            int64_t bytes,
++                                            int64_t *pnum,
++                                            int64_t *map,
++                                            BlockDriverState **file)
 +{
 +    BDRVAllocTrackState *s = bs->opaque;
 +
@@ -281,10 +329,10 @@ index 0000000000..43d40d11af
 +    return 0;
 +}
 +
-+static void track_child_perm(BlockDriverState *bs, BdrvChild *c,
-+                             BdrvChildRole role, BlockReopenQueue *reopen_queue,
-+                             uint64_t perm, uint64_t shared,
-+                             uint64_t *nperm, uint64_t *nshared)
++static void GRAPH_RDLOCK
++track_child_perm(BlockDriverState *bs, BdrvChild *c, BdrvChildRole role,
++                 BlockReopenQueue *reopen_queue, uint64_t perm, uint64_t shared,
++                 uint64_t *nperm, uint64_t *nshared)
 +{
 +    BDRVAllocTrackState *s = bs->opaque;
 +
@@ -307,53 +355,28 @@ index 0000000000..43d40d11af
 +    }
 +}
 +
-+static void track_drop(void *opaque)
++static int coroutine_fn GRAPH_RDLOCK
++track_co_change_backing_file(BlockDriverState *bs, const char *backing_file,
++                             const char *backing_fmt)
 +{
-+    BlockDriverState *bs = (BlockDriverState*)opaque;
-+    BlockDriverState *file = bs->file->bs;
-+    BDRVAllocTrackState *s = bs->opaque;
-+
-+    assert(file);
-+
-+    /* we rely on the fact that we're not used anywhere else, so let's wait
-+     * until we're only used once - in the drive connected to the guest (and one
-+     * ref is held by bdrv_ref in track_change_backing_file) */
-+    if (bs->refcnt > 2) {
-+        aio_bh_schedule_oneshot(qemu_get_aio_context(), track_drop, opaque);
-+        return;
-+    }
-+    AioContext *aio_context = bdrv_get_aio_context(bs);
-+    aio_context_acquire(aio_context);
-+
-+    bdrv_drained_begin(bs);
-+
-+    /* now that we're drained, we can safely set 'DropInProgress' */
-+    s->drop_state = DropInProgress;
-+    bdrv_child_refresh_perms(bs, bs->file, &error_abort);
-+
-+    bdrv_replace_node(bs, file, &error_abort);
-+    bdrv_set_backing_hd(bs, NULL, &error_abort);
-+    bdrv_drained_end(bs);
-+    bdrv_unref(bs);
-+    aio_context_release(aio_context);
-+}
-+
-+static int track_change_backing_file(BlockDriverState *bs,
-+                                     const char *backing_file,
-+                                     const char *backing_fmt)
-+{
-+    BDRVAllocTrackState *s = bs->opaque;
-+    if (s->auto_remove && s->drop_state == DropNone &&
-+        backing_file == NULL && backing_fmt == NULL)
-+    {
-+        /* backing file has been disconnected, there's no longer any use for
-+         * this node, so let's remove ourselves from the block graph - we need
-+         * to schedule this for later however, since when this function is
-+         * called, the blockjob modifying us is probably not done yet and has a
-+         * blocker on 'bs' */
-+        s->drop_state = DropRequested;
-+        bdrv_ref(bs);
-+        aio_bh_schedule_oneshot(qemu_get_aio_context(), track_drop, (void*)bs);
++    /*
++     * Note that the actual backing file graph change is already done in the
++     * stream job itself with bdrv_set_backing_hd_drained(), so no need to
++     * actually do anything here. But still needs to be implemented, to make
++     * our caller (i.e. bdrv_co_change_backing_file() do the right thing).
++     *
++     * FIXME
++     * We'd like to auto-remove ourselves from the block graph, but it cannot
++     * be done from a coroutine. Currently done in the stream job, where it
++     * kinda fits better, but in the long-term, a special parameter would be
++     * nice (or done via qemu-server via upcoming blockdev-replace QMP command).
++     */
++    if (backing_file == NULL) {
++        BDRVAllocTrackState *s = bs->opaque;
++        bdrv_drained_begin(bs);
++        s->drop_state = DropInProgress;
++        bdrv_child_refresh_perms(bs, bs->file, &error_abort);
++        bdrv_drained_end(bs);
 +    }
 +
 +    return 0;
@@ -365,7 +388,7 @@ index 0000000000..43d40d11af
 +
 +    .bdrv_file_open                   = track_open,
 +    .bdrv_close                       = track_close,
-+    .bdrv_getlength                   = track_getlength,
++    .bdrv_co_getlength                = track_co_getlength,
 +    .bdrv_child_perm                  = track_child_perm,
 +    .bdrv_refresh_limits              = track_refresh_limits,
 +
@@ -380,7 +403,7 @@ index 0000000000..43d40d11af
 +    .supports_backing                 = true,
 +
 +    .bdrv_co_block_status             = track_co_block_status,
-+    .bdrv_change_backing_file         = track_change_backing_file,
++    .bdrv_co_change_backing_file      = track_co_change_backing_file,
 +};
 +
 +static void bdrv_alloc_track_init(void)
@@ -390,7 +413,7 @@ index 0000000000..43d40d11af
 +
 +block_init(bdrv_alloc_track_init);
 diff --git a/block/meson.build b/block/meson.build
-index a26a69434e..74e5f49758 100644
+index 1945e04eeb..2873f3a25a 100644
 --- a/block/meson.build
 +++ b/block/meson.build
 @@ -2,6 +2,7 @@ block_ss.add(genh)
@@ -401,3 +424,48 @@ index a26a69434e..74e5f49758 100644
    'amend.c',
    'backup.c',
    'backup-dump.c',
+diff --git a/block/stream.c b/block/stream.c
+index d2da83ae7c..f941cba14e 100644
+--- a/block/stream.c
++++ b/block/stream.c
+@@ -120,6 +120,40 @@ static int stream_prepare(Job *job)
+             ret = -EPERM;
+             goto out;
+         }
++
++        /*
++         * This cannot be done in the co_change_backing_file callback, because
++         * bdrv_replace_node() cannot be done in a coroutine. The latter also
++         * requires the graph lock exclusively. Only required for the
++         * alloc-track driver.
++         *
++         * The long-term plan is to either have an explicit parameter for the
++         * stream job or use the upcoming blockdev-replace QMP command.
++         */
++        if (base_id == NULL && strcmp(unfiltered_bs->drv->format_name, "alloc-track") == 0) {
++            BlockDriverState *file_bs;
++
++            bdrv_graph_rdlock_main_loop();
++            file_bs = unfiltered_bs->file->bs;
++            bdrv_graph_rdunlock_main_loop();
++
++            bdrv_ref(unfiltered_bs); // unrefed by bdrv_replace_node()
++            bdrv_drained_begin(file_bs);
++            bdrv_graph_wrlock();
++
++            bdrv_replace_node(unfiltered_bs, file_bs, &local_err);
++
++            bdrv_graph_wrunlock();
++            bdrv_drained_end(file_bs);
++            bdrv_unref(unfiltered_bs);
++
++            if (local_err) {
++                error_prepend(&local_err, "failed to replace alloc-track node: ");
++                error_report_err(local_err);
++                ret = -EPERM;
++                goto out;
++            }
++        }
+     }
+ 
+ out:

debian/patches/pve/0039-PVE-Backup-Don-t-block-on-finishing-and-cleanup-crea.patch

@@ -1,503 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Mon, 28 Sep 2020 13:40:51 +0200
-Subject: [PATCH] PVE-Backup: Don't block on finishing and cleanup
- create_backup_jobs
-
-proxmox_backup_co_finish is already async, but previously we would wait
-for the coroutine using block_on_coroutine_fn(). Avoid this by
-scheduling pvebackup_co_complete_stream (and thus pvebackup_co_cleanup)
-as a real coroutine when calling from pvebackup_complete_cb. This is ok,
-since complete_stream uses the backup_mutex internally to synchronize,
-and other streams can happily continue writing in the meantime anyway.
-
-To accomodate, backup_mutex is converted to a CoMutex. This means
-converting every user to a coroutine. This is not just useful here, but
-will come in handy once this series[0] is merged, and QMP calls can be
-yield-able coroutines too. Then we can also finally get rid of
-block_on_coroutine_fn.
-
-Cases of aio_context_acquire/release from within what is now a coroutine
-are changed to aio_co_reschedule_self, which works since a running
-coroutine always holds the aio lock for the context it is running in.
-
-job_cancel_sync is called from a BH since it can't be run from a
-coroutine (uses AIO_WAIT_WHILE internally).
-
-Same thing for create_backup_jobs, which is converted to a BH too.
-
-To communicate the finishing state, a new property is introduced to
-query-backup: 'finishing'. A new state is explicitly not used, since
-that would break compatibility with older qemu-server versions.
-
-Also fix create_backup_jobs:
-
-No more weird bool returns, just the standard "errp" format used
-everywhere else too. With this, if backup_job_create fails, the error
-message is actually returned over QMP and can be shown to the user.
-
-To facilitate correct cleanup on such an error, we call
-create_backup_jobs as a bottom half directly from pvebackup_co_prepare.
-This additionally allows us to actually hold the backup_mutex during
-operation.
-
-Also add a job_cancel_sync before job_unref, since a job must be in
-STATUS_NULL to be deleted by unref, which could trigger an assert
-before.
-
-[0] https://lists.gnu.org/archive/html/qemu-devel/2020-09/msg03515.html
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-[add new force parameter to job_cancel_sync calls]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- pve-backup.c         | 217 ++++++++++++++++++++++++++++---------------
- qapi/block-core.json |   5 +-
- 2 files changed, 144 insertions(+), 78 deletions(-)
-
-diff --git a/pve-backup.c b/pve-backup.c
-index 63c686463f..6f05796fad 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -33,7 +33,9 @@ const char *PBS_BITMAP_NAME = "pbs-incremental-dirty-bitmap";
- 
- static struct PVEBackupState {
-     struct {
--        // Everithing accessed from qmp_backup_query command is protected using lock
-+        // Everything accessed from qmp_backup_query command is protected using
-+        // this lock. Do NOT hold this lock for long times, as it is sometimes
-+        // acquired from coroutines, and thus any wait time may block the guest.
-         QemuMutex lock;
-         Error *error;
-         time_t start_time;
-@@ -47,20 +49,22 @@ static struct PVEBackupState {
-         size_t reused;
-         size_t zero_bytes;
-         GList *bitmap_list;
-+        bool finishing;
-+        bool starting;
-     } stat;
-     int64_t speed;
-     VmaWriter *vmaw;
-     ProxmoxBackupHandle *pbs;
-     GList *di_list;
-     JobTxn *txn;
--    QemuMutex backup_mutex;
-+    CoMutex backup_mutex;
-     CoMutex dump_callback_mutex;
- } backup_state;
- 
- static void pvebackup_init(void)
- {
-     qemu_mutex_init(&backup_state.stat.lock);
--    qemu_mutex_init(&backup_state.backup_mutex);
-+    qemu_co_mutex_init(&backup_state.backup_mutex);
-     qemu_co_mutex_init(&backup_state.dump_callback_mutex);
- }
- 
-@@ -72,6 +76,7 @@ typedef struct PVEBackupDevInfo {
-     size_t size;
-     uint64_t block_size;
-     uint8_t dev_id;
-+    int completed_ret; // INT_MAX if not completed
-     char targetfile[PATH_MAX];
-     BdrvDirtyBitmap *bitmap;
-     BlockDriverState *target;
-@@ -227,12 +232,12 @@ pvebackup_co_dump_vma_cb(
- }
- 
- // assumes the caller holds backup_mutex
--static void coroutine_fn pvebackup_co_cleanup(void *unused)
-+static void coroutine_fn pvebackup_co_cleanup(void)
- {
-     assert(qemu_in_coroutine());
- 
-     qemu_mutex_lock(&backup_state.stat.lock);
--    backup_state.stat.end_time = time(NULL);
-+    backup_state.stat.finishing = true;
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
-     if (backup_state.vmaw) {
-@@ -261,35 +266,29 @@ static void coroutine_fn pvebackup_co_cleanup(void *unused)
- 
-     g_list_free(backup_state.di_list);
-     backup_state.di_list = NULL;
-+
-+    qemu_mutex_lock(&backup_state.stat.lock);
-+    backup_state.stat.end_time = time(NULL);
-+    backup_state.stat.finishing = false;
-+    qemu_mutex_unlock(&backup_state.stat.lock);
- }
- 
--// assumes the caller holds backup_mutex
--static void coroutine_fn pvebackup_complete_stream(void *opaque)
-+static void coroutine_fn pvebackup_co_complete_stream(void *opaque)
- {
-     PVEBackupDevInfo *di = opaque;
-+    int ret = di->completed_ret;
- 
--    bool error_or_canceled = pvebackup_error_or_canceled();
--
--    if (backup_state.vmaw) {
--        vma_writer_close_stream(backup_state.vmaw, di->dev_id);
-+    qemu_mutex_lock(&backup_state.stat.lock);
-+    bool starting = backup_state.stat.starting;
-+    qemu_mutex_unlock(&backup_state.stat.lock);
-+    if (starting) {
-+        /* in 'starting' state, no tasks have been run yet, meaning we can (and
-+         * must) skip all cleanup, as we don't know what has and hasn't been
-+         * initialized yet. */
-+        return;
-     }
- 
--    if (backup_state.pbs && !error_or_canceled) {
--        Error *local_err = NULL;
--        proxmox_backup_co_close_image(backup_state.pbs, di->dev_id, &local_err);
--        if (local_err != NULL) {
--            pvebackup_propagate_error(local_err);
--        }
--    }
--}
--
--static void pvebackup_complete_cb(void *opaque, int ret)
--{
--    assert(!qemu_in_coroutine());
--
--    PVEBackupDevInfo *di = opaque;
--
--    qemu_mutex_lock(&backup_state.backup_mutex);
-+    qemu_co_mutex_lock(&backup_state.backup_mutex);
- 
-     if (ret < 0) {
-         Error *local_err = NULL;
-@@ -301,7 +300,19 @@ static void pvebackup_complete_cb(void *opaque, int ret)
- 
-     assert(di->target == NULL);
- 
--    block_on_coroutine_fn(pvebackup_complete_stream, di);
-+    bool error_or_canceled = pvebackup_error_or_canceled();
-+
-+    if (backup_state.vmaw) {
-+        vma_writer_close_stream(backup_state.vmaw, di->dev_id);
-+    }
-+
-+    if (backup_state.pbs && !error_or_canceled) {
-+        Error *local_err = NULL;
-+        proxmox_backup_co_close_image(backup_state.pbs, di->dev_id, &local_err);
-+        if (local_err != NULL) {
-+            pvebackup_propagate_error(local_err);
-+        }
-+    }
- 
-     // remove self from job list
-     backup_state.di_list = g_list_remove(backup_state.di_list, di);
-@@ -310,21 +321,49 @@ static void pvebackup_complete_cb(void *opaque, int ret)
- 
-     /* call cleanup if we're the last job */
-     if (!g_list_first(backup_state.di_list)) {
--        block_on_coroutine_fn(pvebackup_co_cleanup, NULL);
-+        pvebackup_co_cleanup();
-     }
- 
--    qemu_mutex_unlock(&backup_state.backup_mutex);
-+    qemu_co_mutex_unlock(&backup_state.backup_mutex);
- }
- 
--static void pvebackup_cancel(void)
-+static void pvebackup_complete_cb(void *opaque, int ret)
- {
--    assert(!qemu_in_coroutine());
-+    PVEBackupDevInfo *di = opaque;
-+    di->completed_ret = ret;
-+
-+    /*
-+     * Schedule stream cleanup in async coroutine. close_image and finish might
-+     * take a while, so we can't block on them here. This way it also doesn't
-+     * matter if we're already running in a coroutine or not.
-+     * Note: di is a pointer to an entry in the global backup_state struct, so
-+     * it stays valid.
-+     */
-+    Coroutine *co = qemu_coroutine_create(pvebackup_co_complete_stream, di);
-+    aio_co_enter(qemu_get_aio_context(), co);
-+}
-+
-+/*
-+ * job_cancel(_sync) does not like to be called from coroutines, so defer to
-+ * main loop processing via a bottom half.
-+ */
-+static void job_cancel_bh(void *opaque) {
-+    CoCtxData *data = (CoCtxData*)opaque;
-+    Job *job = (Job*)data->data;
-+    AioContext *job_ctx = job->aio_context;
-+    aio_context_acquire(job_ctx);
-+    job_cancel_sync(job, true);
-+    aio_context_release(job_ctx);
-+    aio_co_enter(data->ctx, data->co);
-+}
- 
-+static void coroutine_fn pvebackup_co_cancel(void *opaque)
-+{
-     Error *cancel_err = NULL;
-     error_setg(&cancel_err, "backup canceled");
-     pvebackup_propagate_error(cancel_err);
- 
--    qemu_mutex_lock(&backup_state.backup_mutex);
-+    qemu_co_mutex_lock(&backup_state.backup_mutex);
- 
-     if (backup_state.vmaw) {
-         /* make sure vma writer does not block anymore */
-@@ -342,27 +381,22 @@ static void pvebackup_cancel(void)
-         ((PVEBackupDevInfo *)bdi->data)->job :
-         NULL;
- 
--    /* ref the job before releasing the mutex, just to be safe */
-     if (cancel_job) {
--        job_ref(&cancel_job->job);
-+        CoCtxData data = {
-+            .ctx = qemu_get_current_aio_context(),
-+            .co = qemu_coroutine_self(),
-+            .data = &cancel_job->job,
-+        };
-+        aio_bh_schedule_oneshot(data.ctx, job_cancel_bh, &data);
-+        qemu_coroutine_yield();
-     }
- 
--    /* job_cancel_sync may enter the job, so we need to release the
--     * backup_mutex to avoid deadlock */
--    qemu_mutex_unlock(&backup_state.backup_mutex);
--
--    if (cancel_job) {
--        AioContext *aio_context = cancel_job->job.aio_context;
--        aio_context_acquire(aio_context);
--        job_cancel_sync(&cancel_job->job, true);
--        job_unref(&cancel_job->job);
--        aio_context_release(aio_context);
--    }
-+    qemu_co_mutex_unlock(&backup_state.backup_mutex);
- }
- 
- void qmp_backup_cancel(Error **errp)
- {
--    pvebackup_cancel();
-+    block_on_coroutine_fn(pvebackup_co_cancel, NULL);
- }
- 
- // assumes the caller holds backup_mutex
-@@ -415,10 +449,18 @@ static int coroutine_fn pvebackup_co_add_config(
-     goto out;
- }
- 
--static bool create_backup_jobs(void) {
-+/*
-+ * backup_job_create can *not* be run from a coroutine (and requires an
-+ * acquired AioContext), so this can't either.
-+ * The caller is responsible that backup_mutex is held nonetheless.
-+ */
-+static void create_backup_jobs_bh(void *opaque) {
- 
-     assert(!qemu_in_coroutine());
- 
-+    CoCtxData *data = (CoCtxData*)opaque;
-+    Error **errp = (Error**)data->data;
-+
-     Error *local_err = NULL;
- 
-     /* create job transaction to synchronize bitmap commit and cancel all
-@@ -454,24 +496,19 @@ static bool create_backup_jobs(void) {
- 
-         aio_context_release(aio_context);
- 
--        if (!job || local_err != NULL) {
--            Error *create_job_err = NULL;
--            error_setg(&create_job_err, "backup_job_create failed: %s",
--                       local_err ? error_get_pretty(local_err) : "null");
-+        di->job = job;
- 
--            pvebackup_propagate_error(create_job_err);
-+        if (!job || local_err) {
-+            error_setg(errp, "backup_job_create failed: %s",
-+                       local_err ? error_get_pretty(local_err) : "null");
-             break;
-         }
- 
--        di->job = job;
--
-         bdrv_unref(di->target);
-         di->target = NULL;
-     }
- 
--    bool errors = pvebackup_error_or_canceled();
--
--    if (errors) {
-+    if (*errp) {
-         l = backup_state.di_list;
-         while (l) {
-             PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-@@ -483,12 +520,17 @@ static bool create_backup_jobs(void) {
-             }
- 
-             if (di->job) {
-+                AioContext *ctx = di->job->job.aio_context;
-+                aio_context_acquire(ctx);
-+                job_cancel_sync(&di->job->job, true);
-                 job_unref(&di->job->job);
-+                aio_context_release(ctx);
-             }
-         }
-     }
- 
--    return errors;
-+    /* return */
-+    aio_co_enter(data->ctx, data->co);
- }
- 
- typedef struct QmpBackupTask {
-@@ -525,11 +567,12 @@ typedef struct QmpBackupTask {
-     UuidInfo *result;
- } QmpBackupTask;
- 
--// assumes the caller holds backup_mutex
- static void coroutine_fn pvebackup_co_prepare(void *opaque)
- {
-     assert(qemu_in_coroutine());
- 
-+    qemu_co_mutex_lock(&backup_state.backup_mutex);
-+
-     QmpBackupTask *task = opaque;
- 
-     task->result = NULL; // just to be sure
-@@ -550,8 +593,9 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     const char *firewall_name = "qemu-server.fw";
- 
-     if (backup_state.di_list) {
--         error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-+        error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-                   "previous backup not finished");
-+        qemu_co_mutex_unlock(&backup_state.backup_mutex);
-         return;
-     }
- 
-@@ -618,6 +662,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-         }
-         di->size = size;
-         total += size;
-+
-+        di->completed_ret = INT_MAX;
-     }
- 
-     uuid_generate(uuid);
-@@ -849,6 +895,8 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     backup_state.stat.dirty = total - backup_state.stat.reused;
-     backup_state.stat.transferred = 0;
-     backup_state.stat.zero_bytes = 0;
-+    backup_state.stat.finishing = false;
-+    backup_state.stat.starting = true;
- 
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
-@@ -863,6 +911,33 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     uuid_info->UUID = uuid_str;
- 
-     task->result = uuid_info;
-+
-+    /* Run create_backup_jobs_bh outside of coroutine (in BH) but keep
-+    * backup_mutex locked. This is fine, a CoMutex can be held across yield
-+    * points, and we'll release it as soon as the BH reschedules us.
-+    */
-+    CoCtxData waker = {
-+        .co = qemu_coroutine_self(),
-+        .ctx = qemu_get_current_aio_context(),
-+        .data = &local_err,
-+    };
-+    aio_bh_schedule_oneshot(waker.ctx, create_backup_jobs_bh, &waker);
-+    qemu_coroutine_yield();
-+
-+    if (local_err) {
-+        error_propagate(task->errp, local_err);
-+        goto err;
-+    }
-+
-+    qemu_co_mutex_unlock(&backup_state.backup_mutex);
-+
-+    qemu_mutex_lock(&backup_state.stat.lock);
-+    backup_state.stat.starting = false;
-+    qemu_mutex_unlock(&backup_state.stat.lock);
-+
-+    /* start the first job in the transaction */
-+    job_txn_start_seq(backup_state.txn);
-+
-     return;
- 
- err_mutex:
-@@ -885,6 +960,7 @@ err:
-         g_free(di);
-     }
-     g_list_free(di_list);
-+    backup_state.di_list = NULL;
- 
-     if (devs) {
-         g_strfreev(devs);
-@@ -905,6 +981,8 @@ err:
-     }
- 
-     task->result = NULL;
-+
-+    qemu_co_mutex_unlock(&backup_state.backup_mutex);
-     return;
- }
- 
-@@ -958,24 +1036,8 @@ UuidInfo *qmp_backup(
-         .errp = errp,
-     };
- 
--    qemu_mutex_lock(&backup_state.backup_mutex);
--
-     block_on_coroutine_fn(pvebackup_co_prepare, &task);
- 
--    if (*errp == NULL) {
--        bool errors = create_backup_jobs();
--        qemu_mutex_unlock(&backup_state.backup_mutex);
--
--        if (!errors) {
--            /* start the first job in the transaction
--             * note: this might directly enter the job, so we need to do this
--             * after unlocking the backup_mutex */
--            job_txn_start_seq(backup_state.txn);
--        }
--    } else {
--        qemu_mutex_unlock(&backup_state.backup_mutex);
--    }
--
-     return task.result;
- }
- 
-@@ -1027,6 +1089,7 @@ BackupStatus *qmp_query_backup(Error **errp)
-     info->transferred = backup_state.stat.transferred;
-     info->has_reused = true;
-     info->reused = backup_state.stat.reused;
-+    info->finishing = backup_state.stat.finishing;
- 
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 16e184dd28..cb17d00fe0 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -770,12 +770,15 @@
- #
- # @uuid: uuid for this backup job
- #
-+# @finishing: if status='active' and finishing=true, then the backup process is
-+#             waiting for the target to finish.
-+#
- ##
- { 'struct': 'BackupStatus',
-   'data': {'*status': 'str', '*errmsg': 'str', '*total': 'int', '*dirty': 'int',
-            '*transferred': 'int', '*zero-bytes': 'int', '*reused': 'int',
-            '*start-time': 'int', '*end-time': 'int',
--           '*backup-file': 'str', '*uuid': 'str' } }
-+           '*backup-file': 'str', '*uuid': 'str', 'finishing': 'bool' } }
- 
- ##
- # @BackupFormat:

debian/patches/pve/0039-Revert-block-rbd-workaround-for-ceph-issue-53784.patch

@@ -7,15 +7,16 @@ This reverts commit fc176116cdea816ceb8dd969080b2b95f58edbc0 in
 preparation to revert 0347a8fd4c3faaedf119be04c197804be40a384b.
 
 Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  block/rbd.c | 42 ++----------------------------------------
  1 file changed, 2 insertions(+), 40 deletions(-)
 
 diff --git a/block/rbd.c b/block/rbd.c
-index 64a8d7d48b..9fc6dcb957 100644
+index 63f60d41be..367db42dce 100644
 --- a/block/rbd.c
 +++ b/block/rbd.c
-@@ -1348,7 +1348,6 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
+@@ -1515,7 +1515,6 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
      int status, r;
      RBDDiffIterateReq req = { .offs = offset };
      uint64_t features, flags;
@@ -23,7 +24,7 @@ index 64a8d7d48b..9fc6dcb957 100644
  
      assert(offset + bytes <= s->image_size);
  
-@@ -1376,43 +1375,7 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
+@@ -1543,43 +1542,7 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
          return status;
      }
  
@@ -68,7 +69,7 @@ index 64a8d7d48b..9fc6dcb957 100644
                            qemu_rbd_diff_iterate_cb, &req);
      if (r < 0 && r != QEMU_RBD_EXIT_DIFF_ITERATE2) {
          return status;
-@@ -1431,8 +1394,7 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
+@@ -1598,8 +1561,7 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
          status = BDRV_BLOCK_ZERO | BDRV_BLOCK_OFFSET_VALID;
      }
  

debian/patches/pve/0040-Revert-block-rbd-fix-handling-of-holes-in-.bdrv_co_b.patch

@@ -8,15 +8,16 @@ This reverts commit 9e302f64bb407a9bb097b626da97228c2654cfee in
 preparation to revert 0347a8fd4c3faaedf119be04c197804be40a384b.
 
 Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  block/rbd.c | 10 +++++-----
  1 file changed, 5 insertions(+), 5 deletions(-)
 
 diff --git a/block/rbd.c b/block/rbd.c
-index 9fc6dcb957..98f4ba2620 100644
+index 367db42dce..347b121626 100644
 --- a/block/rbd.c
 +++ b/block/rbd.c
-@@ -1307,11 +1307,11 @@ static int qemu_rbd_diff_iterate_cb(uint64_t offs, size_t len,
+@@ -1474,11 +1474,11 @@ static int qemu_rbd_diff_iterate_cb(uint64_t offs, size_t len,
      RBDDiffIterateReq *req = opaque;
  
      assert(req->offs + req->bytes <= offs);

debian/patches/pve/0041-Revert-block-rbd-implement-bdrv_co_block_status.patch

@@ -18,15 +18,16 @@ Upstream bug report:
 https://gitlab.com/qemu-project/qemu/-/issues/1026
 
 Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
  block/rbd.c | 112 ----------------------------------------------------
  1 file changed, 112 deletions(-)
 
 diff --git a/block/rbd.c b/block/rbd.c
-index 98f4ba2620..efcbbe5949 100644
+index 347b121626..e61b359b97 100644
 --- a/block/rbd.c
 +++ b/block/rbd.c
-@@ -97,12 +97,6 @@ typedef struct RBDTask {
+@@ -108,12 +108,6 @@ typedef struct RBDTask {
      int64_t ret;
  } RBDTask;
  
@@ -39,7 +40,7 @@ index 98f4ba2620..efcbbe5949 100644
  static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
                              BlockdevOptionsRbd *opts, bool cache,
                              const char *keypairs, const char *secretid,
-@@ -1293,111 +1287,6 @@ static ImageInfoSpecific *qemu_rbd_get_specific_info(BlockDriverState *bs,
+@@ -1460,111 +1454,6 @@ static ImageInfoSpecific *qemu_rbd_get_specific_info(BlockDriverState *bs,
      return spec_info;
  }
  
@@ -148,10 +149,10 @@ index 98f4ba2620..efcbbe5949 100644
 -    return status;
 -}
 -
- static int64_t qemu_rbd_getlength(BlockDriverState *bs)
+ static int64_t coroutine_fn qemu_rbd_co_getlength(BlockDriverState *bs)
  {
      BDRVRBDState *s = bs->opaque;
-@@ -1633,7 +1522,6 @@ static BlockDriver bdrv_rbd = {
+@@ -1800,7 +1689,6 @@ static BlockDriver bdrv_rbd = {
  #ifdef LIBRBD_SUPPORTS_WRITE_ZEROES
      .bdrv_co_pwrite_zeroes  = qemu_rbd_co_pwrite_zeroes,
  #endif

debian/patches/pve/0042-alloc-track-error-out-when-auto-remove-is-not-set.patch

@@ -0,0 +1,43 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Tue, 26 Mar 2024 14:57:51 +0100
+Subject: [PATCH] alloc-track: error out when auto-remove is not set
+
+Since replacing the node now happens in the stream job, where the
+option cannot be read from (it's internal to the driver), it will
+always be treated as on.
+
+qemu-server will always set it, make sure to have other users notice
+the change (should they even exist). The option can be fully dropped
+in the future while adding a version guard in qemu-server.
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ block/alloc-track.c | 7 +++++--
+ 1 file changed, 5 insertions(+), 2 deletions(-)
+
+diff --git a/block/alloc-track.c b/block/alloc-track.c
+index b9f8ea9137..f3ed2935c4 100644
+--- a/block/alloc-track.c
++++ b/block/alloc-track.c
+@@ -34,7 +34,6 @@ typedef struct {
+     BdrvDirtyBitmap *bitmap;
+     uint64_t granularity;
+     DropState drop_state;
+-    bool auto_remove;
+ } BDRVAllocTrackState;
+ 
+ static QemuOptsList runtime_opts = {
+@@ -86,7 +85,11 @@ static int track_open(BlockDriverState *bs, QDict *options, int flags,
+         goto fail;
+     }
+ 
+-    s->auto_remove = qemu_opt_get_bool(opts, TRACK_OPT_AUTO_REMOVE, false);
++    if (!qemu_opt_get_bool(opts, TRACK_OPT_AUTO_REMOVE, false)) {
++        error_setg(errp, "alloc-track: requires auto-remove option to be set to on");
++        ret = -EINVAL;
++        goto fail;
++    }
+ 
+     /* open the target (write) node, backing will be attached by block layer */
+     file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,

debian/patches/pve/0043-PVE-Use-coroutine-QMP-for-backup-cancel_backup.patch

@@ -1,598 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Tue, 26 Jan 2021 15:45:30 +0100
-Subject: [PATCH] PVE: Use coroutine QMP for backup/cancel_backup
-
-Finally turn backup QMP calls into coroutines, now that it's possible.
-This has the benefit that calls are asynchronous to the main loop, i.e.
-long running operations like connecting to a PBS server will no longer
-hang the VM.
-
-Additionally, it allows us to get rid of block_on_coroutine_fn, which
-was always a hacky workaround.
-
-While we're already spring cleaning, also remove the QmpBackupTask
-struct, since we can now put the 'prepare' function directly into
-qmp_backup and thus no longer need those giant walls of text.
-
-(Note that for our patches to work with 5.2.0 this change is actually
-required, otherwise monitor_get_fd() fails as we're not in a QMP
-coroutine, but one we start ourselves - we could of course set the
-monitor for that coroutine ourselves, but let's just fix it the right
-way instead)
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/monitor/block-hmp-cmds.c |   4 +-
- hmp-commands.hx                |   2 +
- proxmox-backup-client.c        |  31 -----
- pve-backup.c                   | 232 ++++++++++-----------------------
- qapi/block-core.json           |   4 +-
- 5 files changed, 77 insertions(+), 196 deletions(-)
-
-diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
-index ea7b665aa2..ef45552e3b 100644
---- a/block/monitor/block-hmp-cmds.c
-+++ b/block/monitor/block-hmp-cmds.c
-@@ -1016,7 +1016,7 @@ void hmp_info_snapshots(Monitor *mon, const QDict *qdict)
-     g_free(global_snapshots);
- }
- 
--void hmp_backup_cancel(Monitor *mon, const QDict *qdict)
-+void coroutine_fn hmp_backup_cancel(Monitor *mon, const QDict *qdict)
- {
-     Error *error = NULL;
- 
-@@ -1025,7 +1025,7 @@ void hmp_backup_cancel(Monitor *mon, const QDict *qdict)
-     hmp_handle_error(mon, error);
- }
- 
--void hmp_backup(Monitor *mon, const QDict *qdict)
-+void coroutine_fn hmp_backup(Monitor *mon, const QDict *qdict)
- {
-     Error *error = NULL;
- 
-diff --git a/hmp-commands.hx b/hmp-commands.hx
-index 97f24942b3..7a2be816da 100644
---- a/hmp-commands.hx
-+++ b/hmp-commands.hx
-@@ -111,6 +111,7 @@ ERST
- 		    "\n\t\t\t Use -d to dump data into a directory instead"
- 		    "\n\t\t\t of using VMA format.",
-         .cmd = hmp_backup,
-+        .coroutine  = true,
-     },
- 
- SRST
-@@ -124,6 +125,7 @@ ERST
-         .params     = "",
-         .help       = "cancel the current VM backup",
-         .cmd        = hmp_backup_cancel,
-+        .coroutine  = true,
-     },
- 
- SRST
-diff --git a/proxmox-backup-client.c b/proxmox-backup-client.c
-index 4ce7bc0b5e..0923037dec 100644
---- a/proxmox-backup-client.c
-+++ b/proxmox-backup-client.c
-@@ -5,37 +5,6 @@
- 
- /* Proxmox Backup Server client bindings using coroutines */
- 
--typedef struct BlockOnCoroutineWrapper {
--    AioContext *ctx;
--    CoroutineEntry *entry;
--    void *entry_arg;
--    bool finished;
--} BlockOnCoroutineWrapper;
--
--static void coroutine_fn block_on_coroutine_wrapper(void *opaque)
--{
--    BlockOnCoroutineWrapper *wrapper = opaque;
--    wrapper->entry(wrapper->entry_arg);
--    wrapper->finished = true;
--    aio_wait_kick();
--}
--
--void block_on_coroutine_fn(CoroutineEntry *entry, void *entry_arg)
--{
--    assert(!qemu_in_coroutine());
--
--    AioContext *ctx = qemu_get_current_aio_context();
--    BlockOnCoroutineWrapper wrapper = {
--        .finished = false,
--        .entry = entry,
--        .entry_arg = entry_arg,
--        .ctx = ctx,
--    };
--    Coroutine *wrapper_co = qemu_coroutine_create(block_on_coroutine_wrapper, &wrapper);
--    aio_co_enter(ctx, wrapper_co);
--    AIO_WAIT_WHILE(ctx, !wrapper.finished);
--}
--
- // This is called from another thread, so we use aio_co_schedule()
- static void proxmox_backup_schedule_wake(void *data) {
-     CoCtxData *waker = (CoCtxData *)data;
-diff --git a/pve-backup.c b/pve-backup.c
-index 5fa3cc1352..323014744c 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -357,7 +357,7 @@ static void job_cancel_bh(void *opaque) {
-     aio_co_enter(data->ctx, data->co);
- }
- 
--static void coroutine_fn pvebackup_co_cancel(void *opaque)
-+void coroutine_fn qmp_backup_cancel(Error **errp)
- {
-     Error *cancel_err = NULL;
-     error_setg(&cancel_err, "backup canceled");
-@@ -394,11 +394,6 @@ static void coroutine_fn pvebackup_co_cancel(void *opaque)
-     qemu_co_mutex_unlock(&backup_state.backup_mutex);
- }
- 
--void qmp_backup_cancel(Error **errp)
--{
--    block_on_coroutine_fn(pvebackup_co_cancel, NULL);
--}
--
- // assumes the caller holds backup_mutex
- static int coroutine_fn pvebackup_co_add_config(
-     const char *file,
-@@ -533,50 +528,27 @@ static void create_backup_jobs_bh(void *opaque) {
-     aio_co_enter(data->ctx, data->co);
- }
- 
--typedef struct QmpBackupTask {
--    const char *backup_file;
--    bool has_password;
--    const char *password;
--    bool has_keyfile;
--    const char *keyfile;
--    bool has_key_password;
--    const char *key_password;
--    bool has_backup_id;
--    const char *backup_id;
--    bool has_backup_time;
--    const char *fingerprint;
--    bool has_fingerprint;
--    int64_t backup_time;
--    bool has_use_dirty_bitmap;
--    bool use_dirty_bitmap;
--    bool has_format;
--    BackupFormat format;
--    bool has_config_file;
--    const char *config_file;
--    bool has_firewall_file;
--    const char *firewall_file;
--    bool has_devlist;
--    const char *devlist;
--    bool has_compress;
--    bool compress;
--    bool has_encrypt;
--    bool encrypt;
--    bool has_speed;
--    int64_t speed;
--    Error **errp;
--    UuidInfo *result;
--} QmpBackupTask;
--
--static void coroutine_fn pvebackup_co_prepare(void *opaque)
-+UuidInfo coroutine_fn *qmp_backup(
-+    const char *backup_file,
-+    bool has_password, const char *password,
-+    bool has_keyfile, const char *keyfile,
-+    bool has_key_password, const char *key_password,
-+    bool has_fingerprint, const char *fingerprint,
-+    bool has_backup_id, const char *backup_id,
-+    bool has_backup_time, int64_t backup_time,
-+    bool has_use_dirty_bitmap, bool use_dirty_bitmap,
-+    bool has_compress, bool compress,
-+    bool has_encrypt, bool encrypt,
-+    bool has_format, BackupFormat format,
-+    bool has_config_file, const char *config_file,
-+    bool has_firewall_file, const char *firewall_file,
-+    bool has_devlist, const char *devlist,
-+    bool has_speed, int64_t speed, Error **errp)
- {
-     assert(qemu_in_coroutine());
- 
-     qemu_co_mutex_lock(&backup_state.backup_mutex);
- 
--    QmpBackupTask *task = opaque;
--
--    task->result = NULL; // just to be sure
--
-     BlockBackend *blk;
-     BlockDriverState *bs = NULL;
-     const char *backup_dir = NULL;
-@@ -593,17 +565,17 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     const char *firewall_name = "qemu-server.fw";
- 
-     if (backup_state.di_list) {
--        error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-+        error_set(errp, ERROR_CLASS_GENERIC_ERROR,
-                   "previous backup not finished");
-         qemu_co_mutex_unlock(&backup_state.backup_mutex);
--        return;
-+        return NULL;
-     }
- 
-     /* Todo: try to auto-detect format based on file name */
--    BackupFormat format = task->has_format ? task->format : BACKUP_FORMAT_VMA;
-+    format = has_format ? format : BACKUP_FORMAT_VMA;
- 
--    if (task->has_devlist) {
--        devs = g_strsplit_set(task->devlist, ",;:", -1);
-+    if (has_devlist) {
-+        devs = g_strsplit_set(devlist, ",;:", -1);
- 
-         gchar **d = devs;
-         while (d && *d) {
-@@ -611,14 +583,14 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             if (blk) {
-                 bs = blk_bs(blk);
-                 if (!bdrv_is_inserted(bs)) {
--                    error_setg(task->errp, QERR_DEVICE_HAS_NO_MEDIUM, *d);
-+                    error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, *d);
-                     goto err;
-                 }
-                 PVEBackupDevInfo *di = g_new0(PVEBackupDevInfo, 1);
-                 di->bs = bs;
-                 di_list = g_list_append(di_list, di);
-             } else {
--                error_set(task->errp, ERROR_CLASS_DEVICE_NOT_FOUND,
-+                error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
-                           "Device '%s' not found", *d);
-                 goto err;
-             }
-@@ -641,7 +613,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     }
- 
-     if (!di_list) {
--        error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "empty device list");
-+        error_set(errp, ERROR_CLASS_GENERIC_ERROR, "empty device list");
-         goto err;
-     }
- 
-@@ -651,13 +623,13 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     while (l) {
-         PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-         l = g_list_next(l);
--        if (bdrv_op_is_blocked(di->bs, BLOCK_OP_TYPE_BACKUP_SOURCE, task->errp)) {
-+        if (bdrv_op_is_blocked(di->bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
-             goto err;
-         }
- 
-         ssize_t size = bdrv_getlength(di->bs);
-         if (size < 0) {
--            error_setg_errno(task->errp, -di->size, "bdrv_getlength failed");
-+            error_setg_errno(errp, -di->size, "bdrv_getlength failed");
-             goto err;
-         }
-         di->size = size;
-@@ -684,47 +656,44 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     }
- 
-     if (format == BACKUP_FORMAT_PBS) {
--        if (!task->has_password) {
--            error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'password'");
-+        if (!has_password) {
-+            error_set(errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'password'");
-             goto err_mutex;
-         }
--        if (!task->has_backup_id) {
--            error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'backup-id'");
-+        if (!has_backup_id) {
-+            error_set(errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'backup-id'");
-             goto err_mutex;
-         }
--        if (!task->has_backup_time) {
--            error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'backup-time'");
-+        if (!has_backup_time) {
-+            error_set(errp, ERROR_CLASS_GENERIC_ERROR, "missing parameter 'backup-time'");
-             goto err_mutex;
-         }
- 
-         int dump_cb_block_size = PROXMOX_BACKUP_DEFAULT_CHUNK_SIZE; // Hardcoded (4M)
-         firewall_name = "fw.conf";
- 
--        bool use_dirty_bitmap = task->has_use_dirty_bitmap && task->use_dirty_bitmap;
--
--
-         char *pbs_err = NULL;
-         pbs = proxmox_backup_new(
--            task->backup_file,
--            task->backup_id,
--            task->backup_time,
-+            backup_file,
-+            backup_id,
-+            backup_time,
-             dump_cb_block_size,
--            task->has_password ? task->password : NULL,
--            task->has_keyfile ? task->keyfile : NULL,
--            task->has_key_password ? task->key_password : NULL,
--            task->has_compress ? task->compress : true,
--            task->has_encrypt ? task->encrypt : task->has_keyfile,
--            task->has_fingerprint ? task->fingerprint : NULL,
-+            has_password ? password : NULL,
-+            has_keyfile ? keyfile : NULL,
-+            has_key_password ? key_password : NULL,
-+            has_compress ? compress : true,
-+            has_encrypt ? encrypt : has_keyfile,
-+            has_fingerprint ? fingerprint : NULL,
-              &pbs_err);
- 
-         if (!pbs) {
--            error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-+            error_set(errp, ERROR_CLASS_GENERIC_ERROR,
-                       "proxmox_backup_new failed: %s", pbs_err);
-             proxmox_backup_free_error(pbs_err);
-             goto err_mutex;
-         }
- 
--        int connect_result = proxmox_backup_co_connect(pbs, task->errp);
-+        int connect_result = proxmox_backup_co_connect(pbs, errp);
-         if (connect_result < 0)
-             goto err_mutex;
- 
-@@ -743,9 +712,9 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             BdrvDirtyBitmap *bitmap = bdrv_find_dirty_bitmap(di->bs, PBS_BITMAP_NAME);
-             bool expect_only_dirty = false;
- 
--            if (use_dirty_bitmap) {
-+            if (has_use_dirty_bitmap && use_dirty_bitmap) {
-                 if (bitmap == NULL) {
--                    bitmap = bdrv_create_dirty_bitmap(di->bs, dump_cb_block_size, PBS_BITMAP_NAME, task->errp);
-+                    bitmap = bdrv_create_dirty_bitmap(di->bs, dump_cb_block_size, PBS_BITMAP_NAME, errp);
-                     if (!bitmap) {
-                         goto err_mutex;
-                     }
-@@ -775,12 +744,12 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-                 }
-             }
- 
--            int dev_id = proxmox_backup_co_register_image(pbs, devname, di->size, expect_only_dirty, task->errp);
-+            int dev_id = proxmox_backup_co_register_image(pbs, devname, di->size, expect_only_dirty, errp);
-             if (dev_id < 0) {
-                 goto err_mutex;
-             }
- 
--            if (!(di->target = bdrv_backup_dump_create(dump_cb_block_size, di->size, pvebackup_co_dump_pbs_cb, di, task->errp))) {
-+            if (!(di->target = bdrv_backup_dump_create(dump_cb_block_size, di->size, pvebackup_co_dump_pbs_cb, di, errp))) {
-                 goto err_mutex;
-             }
- 
-@@ -794,10 +763,10 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             backup_state.stat.bitmap_list = g_list_append(backup_state.stat.bitmap_list, info);
-         }
-     } else if (format == BACKUP_FORMAT_VMA) {
--        vmaw = vma_writer_create(task->backup_file, uuid, &local_err);
-+        vmaw = vma_writer_create(backup_file, uuid, &local_err);
-         if (!vmaw) {
-             if (local_err) {
--                error_propagate(task->errp, local_err);
-+                error_propagate(errp, local_err);
-             }
-             goto err_mutex;
-         }
-@@ -808,25 +777,25 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-             l = g_list_next(l);
- 
--            if (!(di->target = bdrv_backup_dump_create(VMA_CLUSTER_SIZE, di->size, pvebackup_co_dump_vma_cb, di, task->errp))) {
-+            if (!(di->target = bdrv_backup_dump_create(VMA_CLUSTER_SIZE, di->size, pvebackup_co_dump_vma_cb, di, errp))) {
-                 goto err_mutex;
-             }
- 
-             const char *devname = bdrv_get_device_name(di->bs);
-             di->dev_id = vma_writer_register_stream(vmaw, devname, di->size);
-             if (di->dev_id <= 0) {
--                error_set(task->errp, ERROR_CLASS_GENERIC_ERROR,
-+                error_set(errp, ERROR_CLASS_GENERIC_ERROR,
-                           "register_stream failed");
-                 goto err_mutex;
-             }
-         }
-     } else if (format == BACKUP_FORMAT_DIR) {
--        if (mkdir(task->backup_file, 0640) != 0) {
--            error_setg_errno(task->errp, errno, "can't create directory '%s'\n",
--                             task->backup_file);
-+        if (mkdir(backup_file, 0640) != 0) {
-+            error_setg_errno(errp, errno, "can't create directory '%s'\n",
-+                             backup_file);
-             goto err_mutex;
-         }
--        backup_dir = task->backup_file;
-+        backup_dir = backup_file;
- 
-         l = di_list;
-         while (l) {
-@@ -840,34 +809,34 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-             bdrv_img_create(di->targetfile, "raw", NULL, NULL, NULL,
-                             di->size, flags, false, &local_err);
-             if (local_err) {
--                error_propagate(task->errp, local_err);
-+                error_propagate(errp, local_err);
-                 goto err_mutex;
-             }
- 
-             di->target = bdrv_open(di->targetfile, NULL, NULL, flags, &local_err);
-             if (!di->target) {
--                error_propagate(task->errp, local_err);
-+                error_propagate(errp, local_err);
-                 goto err_mutex;
-             }
-         }
-     } else {
--        error_set(task->errp, ERROR_CLASS_GENERIC_ERROR, "unknown backup format");
-+        error_set(errp, ERROR_CLASS_GENERIC_ERROR, "unknown backup format");
-         goto err_mutex;
-     }
- 
- 
-     /* add configuration file to archive */
--    if (task->has_config_file) {
--        if (pvebackup_co_add_config(task->config_file, config_name, format, backup_dir,
--                                    vmaw, pbs, task->errp) != 0) {
-+    if (has_config_file) {
-+        if (pvebackup_co_add_config(config_file, config_name, format, backup_dir,
-+                                    vmaw, pbs, errp) != 0) {
-             goto err_mutex;
-         }
-     }
- 
-     /* add firewall file to archive */
--    if (task->has_firewall_file) {
--        if (pvebackup_co_add_config(task->firewall_file, firewall_name, format, backup_dir,
--                                    vmaw, pbs, task->errp) != 0) {
-+    if (has_firewall_file) {
-+        if (pvebackup_co_add_config(firewall_file, firewall_name, format, backup_dir,
-+                                    vmaw, pbs, errp) != 0) {
-             goto err_mutex;
-         }
-     }
-@@ -885,7 +854,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     if (backup_state.stat.backup_file) {
-         g_free(backup_state.stat.backup_file);
-     }
--    backup_state.stat.backup_file = g_strdup(task->backup_file);
-+    backup_state.stat.backup_file = g_strdup(backup_file);
- 
-     uuid_copy(backup_state.stat.uuid, uuid);
-     uuid_unparse_lower(uuid, backup_state.stat.uuid_str);
-@@ -900,7 +869,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
- 
-     qemu_mutex_unlock(&backup_state.stat.lock);
- 
--    backup_state.speed = (task->has_speed && task->speed > 0) ? task->speed : 0;
-+    backup_state.speed = (has_speed && speed > 0) ? speed : 0;
- 
-     backup_state.vmaw = vmaw;
-     backup_state.pbs = pbs;
-@@ -910,8 +879,6 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     uuid_info = g_malloc0(sizeof(*uuid_info));
-     uuid_info->UUID = uuid_str;
- 
--    task->result = uuid_info;
--
-     /* Run create_backup_jobs_bh outside of coroutine (in BH) but keep
-     * backup_mutex locked. This is fine, a CoMutex can be held across yield
-     * points, and we'll release it as soon as the BH reschedules us.
-@@ -925,7 +892,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     qemu_coroutine_yield();
- 
-     if (local_err) {
--        error_propagate(task->errp, local_err);
-+        error_propagate(errp, local_err);
-         goto err;
-     }
- 
-@@ -938,7 +905,7 @@ static void coroutine_fn pvebackup_co_prepare(void *opaque)
-     /* start the first job in the transaction */
-     job_txn_start_seq(backup_state.txn);
- 
--    return;
-+    return uuid_info;
- 
- err_mutex:
-     qemu_mutex_unlock(&backup_state.stat.lock);
-@@ -969,7 +936,7 @@ err:
-     if (vmaw) {
-         Error *err = NULL;
-         vma_writer_close(vmaw, &err);
--        unlink(task->backup_file);
-+        unlink(backup_file);
-     }
- 
-     if (pbs) {
-@@ -980,65 +947,8 @@ err:
-         rmdir(backup_dir);
-     }
- 
--    task->result = NULL;
--
-     qemu_co_mutex_unlock(&backup_state.backup_mutex);
--    return;
--}
--
--UuidInfo *qmp_backup(
--    const char *backup_file,
--    bool has_password, const char *password,
--    bool has_keyfile, const char *keyfile,
--    bool has_key_password, const char *key_password,
--    bool has_fingerprint, const char *fingerprint,
--    bool has_backup_id, const char *backup_id,
--    bool has_backup_time, int64_t backup_time,
--    bool has_use_dirty_bitmap, bool use_dirty_bitmap,
--    bool has_compress, bool compress,
--    bool has_encrypt, bool encrypt,
--    bool has_format, BackupFormat format,
--    bool has_config_file, const char *config_file,
--    bool has_firewall_file, const char *firewall_file,
--    bool has_devlist, const char *devlist,
--    bool has_speed, int64_t speed, Error **errp)
--{
--    QmpBackupTask task = {
--        .backup_file = backup_file,
--        .has_password = has_password,
--        .password = password,
--        .has_keyfile = has_keyfile,
--        .keyfile = keyfile,
--        .has_key_password = has_key_password,
--        .key_password = key_password,
--        .has_fingerprint = has_fingerprint,
--        .fingerprint = fingerprint,
--        .has_backup_id = has_backup_id,
--        .backup_id = backup_id,
--        .has_backup_time = has_backup_time,
--        .backup_time = backup_time,
--        .has_use_dirty_bitmap = has_use_dirty_bitmap,
--        .use_dirty_bitmap = use_dirty_bitmap,
--        .has_compress = has_compress,
--        .compress = compress,
--        .has_encrypt = has_encrypt,
--        .encrypt = encrypt,
--        .has_format = has_format,
--        .format = format,
--        .has_config_file = has_config_file,
--        .config_file = config_file,
--        .has_firewall_file = has_firewall_file,
--        .firewall_file = firewall_file,
--        .has_devlist = has_devlist,
--        .devlist = devlist,
--        .has_speed = has_speed,
--        .speed = speed,
--        .errp = errp,
--    };
--
--    block_on_coroutine_fn(pvebackup_co_prepare, &task);
--
--    return task.result;
-+    return NULL;
- }
- 
- BackupStatus *qmp_query_backup(Error **errp)
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index bd978ea562..ca1966f54b 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -842,7 +842,7 @@
-                                     '*config-file': 'str',
-                                     '*firewall-file': 'str',
-                                     '*devlist': 'str', '*speed': 'int' },
--  'returns': 'UuidInfo' }
-+  'returns': 'UuidInfo', 'coroutine': true }
- 
- ##
- # @query-backup:
-@@ -864,7 +864,7 @@
- # Notes: This command succeeds even if there is no backup process running.
- #
- ##
--{ 'command': 'backup-cancel' }
-+{ 'command': 'backup-cancel', 'coroutine': true }
- 
- ##
- # @ProxmoxSupportStatus:

debian/patches/pve/0043-alloc-track-avoid-seemingly-superfluous-child-permis.patch

@@ -0,0 +1,84 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Wed, 27 Mar 2024 11:15:39 +0100
+Subject: [PATCH] alloc-track: avoid seemingly superfluous child permission
+ update
+
+Doesn't seem necessary nowadays (maybe after commit "alloc-track: fix
+deadlock during drop" where the dropping is not rescheduled and delayed
+anymore or some upstream change). Should there really be some issue,
+instead of having a drop state, this could also be just based off the
+fact whether there is still a backing child.
+
+Dumping the cumulative (shared) permissions for the BDS with a debug
+print yields the same values after this patch and with QEMU 8.1,
+namely 3 and 5.
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ block/alloc-track.c | 26 --------------------------
+ 1 file changed, 26 deletions(-)
+
+diff --git a/block/alloc-track.c b/block/alloc-track.c
+index f3ed2935c4..29138dcc49 100644
+--- a/block/alloc-track.c
++++ b/block/alloc-track.c
+@@ -25,15 +25,9 @@
+ 
+ #define TRACK_OPT_AUTO_REMOVE "auto-remove"
+ 
+-typedef enum DropState {
+-    DropNone,
+-    DropInProgress,
+-} DropState;
+-
+ typedef struct {
+     BdrvDirtyBitmap *bitmap;
+     uint64_t granularity;
+-    DropState drop_state;
+ } BDRVAllocTrackState;
+ 
+ static QemuOptsList runtime_opts = {
+@@ -137,8 +131,6 @@ static int track_open(BlockDriverState *bs, QDict *options, int flags,
+         goto fail;
+     }
+ 
+-    s->drop_state = DropNone;
+-
+ fail:
+     if (ret < 0) {
+         bdrv_graph_wrlock();
+@@ -289,18 +281,8 @@ track_child_perm(BlockDriverState *bs, BdrvChild *c, BdrvChildRole role,
+                  BlockReopenQueue *reopen_queue, uint64_t perm, uint64_t shared,
+                  uint64_t *nperm, uint64_t *nshared)
+ {
+-    BDRVAllocTrackState *s = bs->opaque;
+-
+     *nshared = BLK_PERM_ALL;
+ 
+-    /* in case we're currently dropping ourselves, claim to not use any
+-     * permissions at all - which is fine, since from this point on we will
+-     * never issue a read or write anymore */
+-    if (s->drop_state == DropInProgress) {
+-        *nperm = 0;
+-        return;
+-    }
+-
+     if (role & BDRV_CHILD_DATA) {
+         *nperm = perm & DEFAULT_PERM_PASSTHROUGH;
+     } else {
+@@ -326,14 +308,6 @@ track_co_change_backing_file(BlockDriverState *bs, const char *backing_file,
+      * kinda fits better, but in the long-term, a special parameter would be
+      * nice (or done via qemu-server via upcoming blockdev-replace QMP command).
+      */
+-    if (backing_file == NULL) {
+-        BDRVAllocTrackState *s = bs->opaque;
+-        bdrv_drained_begin(bs);
+-        s->drop_state = DropInProgress;
+-        bdrv_child_refresh_perms(bs, bs->file, &error_abort);
+-        bdrv_drained_end(bs);
+-    }
+-
+     return 0;
+ }
+ 

debian/patches/pve/0044-PBS-add-master-key-support.patch

@@ -1,98 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 10 Feb 2021 11:07:06 +0100
-Subject: [PATCH] PBS: add master key support
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-this requires a new enough libproxmox-backup-qemu0, and allows querying
-from the PVE side to avoid QMP calls with unsupported parameters.
-
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/monitor/block-hmp-cmds.c | 1 +
- pve-backup.c                   | 3 +++
- qapi/block-core.json           | 7 +++++++
- 3 files changed, 11 insertions(+)
-
-diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
-index ef45552e3b..4c799f00d9 100644
---- a/block/monitor/block-hmp-cmds.c
-+++ b/block/monitor/block-hmp-cmds.c
-@@ -1039,6 +1039,7 @@ void coroutine_fn hmp_backup(Monitor *mon, const QDict *qdict)
-         false, NULL, // PBS password
-         false, NULL, // PBS keyfile
-         false, NULL, // PBS key_password
-+        false, NULL, // PBS master_keyfile
-         false, NULL, // PBS fingerprint
-         false, NULL, // PBS backup-id
-         false, 0, // PBS backup-time
-diff --git a/pve-backup.c b/pve-backup.c
-index 323014744c..9f6c04a512 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -533,6 +533,7 @@ UuidInfo coroutine_fn *qmp_backup(
-     bool has_password, const char *password,
-     bool has_keyfile, const char *keyfile,
-     bool has_key_password, const char *key_password,
-+    bool has_master_keyfile, const char *master_keyfile,
-     bool has_fingerprint, const char *fingerprint,
-     bool has_backup_id, const char *backup_id,
-     bool has_backup_time, int64_t backup_time,
-@@ -681,6 +682,7 @@ UuidInfo coroutine_fn *qmp_backup(
-             has_password ? password : NULL,
-             has_keyfile ? keyfile : NULL,
-             has_key_password ? key_password : NULL,
-+            has_master_keyfile ? master_keyfile : NULL,
-             has_compress ? compress : true,
-             has_encrypt ? encrypt : has_keyfile,
-             has_fingerprint ? fingerprint : NULL,
-@@ -1044,5 +1046,6 @@ ProxmoxSupportStatus *qmp_query_proxmox_support(Error **errp)
-     ret->pbs_dirty_bitmap_savevm = true;
-     ret->pbs_dirty_bitmap_migration = true;
-     ret->query_bitmap_info = true;
-+    ret->pbs_masterkey = true;
-     return ret;
- }
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index ca1966f54b..fc8a125451 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -813,6 +813,8 @@
- #
- # @key-password: password for keyfile (optional for format 'pbs')
- #
-+# @master-keyfile: PEM-formatted master public keyfile (optional for format 'pbs')
-+#
- # @fingerprint: server cert fingerprint (optional for format 'pbs')
- #
- # @backup-id: backup ID (required for format 'pbs')
-@@ -832,6 +834,7 @@
-                                     '*password': 'str',
-                                     '*keyfile': 'str',
-                                     '*key-password': 'str',
-+                                    '*master-keyfile': 'str',
-                                     '*fingerprint': 'str',
-                                     '*backup-id': 'str',
-                                     '*backup-time': 'int',
-@@ -884,6 +887,9 @@
- #                              migration cap if this is false/unset may lead
- #                              to crashes on migration!
- #
-+# @pbs-masterkey: True if the QMP backup call supports the 'master_keyfile'
-+#                 parameter.
-+#
- # @pbs-library-version: Running version of libproxmox-backup-qemu0 library.
- #
- ##
-@@ -892,6 +898,7 @@
-             'query-bitmap-info': 'bool',
-             'pbs-dirty-bitmap-savevm': 'bool',
-             'pbs-dirty-bitmap-migration': 'bool',
-+            'pbs-masterkey': 'bool',
-             'pbs-library-version': 'str' } }
- 
- ##

debian/patches/pve/0044-block-copy-before-write-fix-permission.patch

@@ -0,0 +1,55 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Date: Thu, 11 Apr 2024 11:29:22 +0200
+Subject: [PATCH] block/copy-before-write: fix permission
+
+In case when source node does not have any parents, the condition still
+works as required: backup job do create the parent by
+
+  block_job_create -> block_job_add_bdrv -> bdrv_root_attach_child
+
+Still, in this case checking @perm variable doesn't work, as backup job
+creates the root blk with empty permissions (as it rely on CBW filter
+to require correct permissions and don't want to create extra
+conflicts).
+
+So, we should not check @perm.
+
+The hack may be dropped entirely when transactional insertion of
+filter (when we don't try to recalculate permissions in intermediate
+state, when filter does conflict with original parent of the source
+node) merged (old big series
+"[PATCH v5 00/45] Transactional block-graph modifying API"[1] and it's
+current in-flight part is "[PATCH v8 0/7] blockdev-replace"[2])
+
+[1] https://patchew.org/QEMU/20220330212902.590099-1-vsementsov@openvz.org/
+[2] https://patchew.org/QEMU/20231017184444.932733-1-vsementsov@yandex-team.ru/
+
+Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/copy-before-write.c | 10 +++++++---
+ 1 file changed, 7 insertions(+), 3 deletions(-)
+
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index 026fa9840f..5a9456d426 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -364,9 +364,13 @@ cbw_child_perm(BlockDriverState *bs, BdrvChild *c, BdrvChildRole role,
+                            perm, shared, nperm, nshared);
+ 
+         if (!QLIST_EMPTY(&bs->parents)) {
+-            if (perm & BLK_PERM_WRITE) {
+-                *nperm = *nperm | BLK_PERM_CONSISTENT_READ;
+-            }
++            /*
++             * Note, that source child may be shared with backup job. Backup job
++             * does create own blk parent on copy-before-write node, so this
++             * works even if source node does not have any parents before backup
++             * start
++             */
++            *nperm = *nperm | BLK_PERM_CONSISTENT_READ;
+             *nshared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
+         }
+     }

debian/patches/pve/0045-PVE-block-pbs-fast-path-reads-without-allocation-if-.patch

@@ -1,53 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 9 Dec 2020 11:46:57 +0100
-Subject: [PATCH] PVE: block/pbs: fast-path reads without allocation if
- possible
-
-...and switch over to g_malloc/g_free while at it to align with other
-QEMU code.
-
-Tracing shows the fast-path is taken almost all the time, though not
-100% so the slow one is still necessary.
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/pbs.c | 17 ++++++++++++++---
- 1 file changed, 14 insertions(+), 3 deletions(-)
-
-diff --git a/block/pbs.c b/block/pbs.c
-index 0b05ea9080..c5eb4d5bad 100644
---- a/block/pbs.c
-+++ b/block/pbs.c
-@@ -200,7 +200,16 @@ static coroutine_fn int pbs_co_preadv(BlockDriverState *bs,
-     BDRVPBSState *s = bs->opaque;
-     int ret;
-     char *pbs_error = NULL;
--    uint8_t *buf = malloc(bytes);
-+    uint8_t *buf;
-+    bool inline_buf = true;
-+
-+    /* for single-buffer IO vectors we can fast-path the write directly to it */
-+    if (qiov->niov == 1 && qiov->iov->iov_len >= bytes) {
-+        buf = qiov->iov->iov_base;
-+    } else {
-+        inline_buf = false;
-+        buf = g_malloc(bytes);
-+    }
- 
-     if (offset < 0 || bytes < 0) {
-         fprintf(stderr, "unexpected negative 'offset' or 'bytes' value!\n");
-@@ -223,8 +232,10 @@ static coroutine_fn int pbs_co_preadv(BlockDriverState *bs,
-         return -EIO;
-     }
- 
--    qemu_iovec_from_buf(qiov, 0, buf, bytes);
--    free(buf);
-+    if (!inline_buf) {
-+        qemu_iovec_from_buf(qiov, 0, buf, bytes);
-+        g_free(buf);
-+    }
- 
-     return 0;
- }

debian/patches/pve/0045-block-copy-before-write-support-unligned-snapshot-di.patch

@@ -0,0 +1,48 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Date: Thu, 11 Apr 2024 11:29:23 +0200
+Subject: [PATCH] block/copy-before-write: support unligned snapshot-discard
+
+First thing that crashes on unligned access here is
+bdrv_reset_dirty_bitmap(). Correct way is to align-down the
+snapshot-discard request.
+
+Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/copy-before-write.c | 16 +++++++++++++---
+ 1 file changed, 13 insertions(+), 3 deletions(-)
+
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index 5a9456d426..c0e70669a2 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -325,14 +325,24 @@ static int coroutine_fn GRAPH_RDLOCK
+ cbw_co_pdiscard_snapshot(BlockDriverState *bs, int64_t offset, int64_t bytes)
+ {
+     BDRVCopyBeforeWriteState *s = bs->opaque;
++    uint32_t cluster_size = block_copy_cluster_size(s->bcs);
++    int64_t aligned_offset = QEMU_ALIGN_UP(offset, cluster_size);
++    int64_t aligned_end = QEMU_ALIGN_DOWN(offset + bytes, cluster_size);
++    int64_t aligned_bytes;
++
++    if (aligned_end <= aligned_offset) {
++        return 0;
++    }
++    aligned_bytes = aligned_end - aligned_offset;
+ 
+     WITH_QEMU_LOCK_GUARD(&s->lock) {
+-        bdrv_reset_dirty_bitmap(s->access_bitmap, offset, bytes);
++        bdrv_reset_dirty_bitmap(s->access_bitmap, aligned_offset,
++                                aligned_bytes);
+     }
+ 
+-    block_copy_reset(s->bcs, offset, bytes);
++    block_copy_reset(s->bcs, aligned_offset, aligned_bytes);
+ 
+-    return bdrv_co_pdiscard(s->target, offset, bytes);
++    return bdrv_co_pdiscard(s->target, aligned_offset, aligned_bytes);
+ }
+ 
+ static void GRAPH_RDLOCK cbw_refresh_filename(BlockDriverState *bs)

debian/patches/pve/0046-block-copy-before-write-create-block_copy-bitmap-in-.patch

@@ -0,0 +1,373 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Date: Thu, 11 Apr 2024 11:29:24 +0200
+Subject: [PATCH] block/copy-before-write: create block_copy bitmap in filter
+ node
+
+Currently block_copy creates copy_bitmap in source node. But that is in
+bad relation with .independent_close=true of copy-before-write filter:
+source node may be detached and removed before .bdrv_close() handler
+called, which should call block_copy_state_free(), which in turn should
+remove copy_bitmap.
+
+That's all not ideal: it would be better if internal bitmap of
+block-copy object is not attached to any node. But that is not possible
+now.
+
+The simplest solution is just create copy_bitmap in filter node, where
+anyway two other bitmaps are created.
+
+Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/block-copy.c         |   3 +-
+ block/copy-before-write.c  |   2 +-
+ include/block/block-copy.h |   1 +
+ tests/qemu-iotests/257.out | 112 ++++++++++++++++++-------------------
+ 4 files changed, 60 insertions(+), 58 deletions(-)
+
+diff --git a/block/block-copy.c b/block/block-copy.c
+index 9ee3dd7ef5..8fca2c3698 100644
+--- a/block/block-copy.c
++++ b/block/block-copy.c
+@@ -351,6 +351,7 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
+ }
+ 
+ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
++                                     BlockDriverState *copy_bitmap_bs,
+                                      const BdrvDirtyBitmap *bitmap,
+                                      Error **errp)
+ {
+@@ -367,7 +368,7 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+         return NULL;
+     }
+ 
+-    copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL,
++    copy_bitmap = bdrv_create_dirty_bitmap(copy_bitmap_bs, cluster_size, NULL,
+                                            errp);
+     if (!copy_bitmap) {
+         return NULL;
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index c0e70669a2..94db31512d 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -468,7 +468,7 @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
+             ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) &
+              bs->file->bs->supported_zero_flags);
+ 
+-    s->bcs = block_copy_state_new(bs->file, s->target, bitmap, errp);
++    s->bcs = block_copy_state_new(bs->file, s->target, bs, bitmap, errp);
+     if (!s->bcs) {
+         error_prepend(errp, "Cannot create block-copy-state: ");
+         return -EINVAL;
+diff --git a/include/block/block-copy.h b/include/block/block-copy.h
+index 0700953ab8..8b41643bfa 100644
+--- a/include/block/block-copy.h
++++ b/include/block/block-copy.h
+@@ -25,6 +25,7 @@ typedef struct BlockCopyState BlockCopyState;
+ typedef struct BlockCopyCallState BlockCopyCallState;
+ 
+ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
++                                     BlockDriverState *copy_bitmap_bs,
+                                      const BdrvDirtyBitmap *bitmap,
+                                      Error **errp);
+ 
+diff --git a/tests/qemu-iotests/257.out b/tests/qemu-iotests/257.out
+index aa76131ca9..c33dd7f3a9 100644
+--- a/tests/qemu-iotests/257.out
++++ b/tests/qemu-iotests/257.out
+@@ -120,16 +120,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -596,16 +596,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -865,16 +865,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -1341,16 +1341,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -1610,16 +1610,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -2086,16 +2086,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -2355,16 +2355,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -2831,16 +2831,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -3100,16 +3100,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -3576,16 +3576,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -3845,16 +3845,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -4321,16 +4321,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -4590,16 +4590,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,
+@@ -5066,16 +5066,16 @@ write -P0x67 0x3fe0000 0x20000
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      }
+-    ],
+-    "drive0": [
++      },
+       {
+         "busy": false,
+         "count": 0,
+         "granularity": 65536,
+         "persistent": false,
+         "recording": false
+-      },
++      }
++    ],
++    "drive0": [
+       {
+         "busy": false,
+         "count": 458752,

debian/patches/pve/0047-block-io-accept-NULL-qiov-in-bdrv_pad_request.patch

@@ -1,33 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Tue, 2 Mar 2021 16:11:54 +0100
-Subject: [PATCH] block/io: accept NULL qiov in bdrv_pad_request
-
-Some operations, e.g. block-stream, perform reads while discarding the
-results (only copy-on-read matters). In this case they will pass NULL as
-the target QEMUIOVector, which will however trip bdrv_pad_request, since
-it wants to extend its passed vector.
-
-Simply check for NULL and do nothing, there's no reason to pad the
-target if it will be discarded anyway.
-
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/io.c | 4 ++++
- 1 file changed, 4 insertions(+)
-
-diff --git a/block/io.c b/block/io.c
-index 0a8cbefe86..531b3b7a2d 100644
---- a/block/io.c
-+++ b/block/io.c
-@@ -1734,6 +1734,10 @@ static int bdrv_pad_request(BlockDriverState *bs,
- {
-     int ret;
- 
-+    if (!qiov) {
-+        return 0;
-+    }
-+
-     bdrv_check_qiov_request(*offset, *bytes, *qiov, *qiov_offset, &error_abort);
- 
-     if (!bdrv_init_padding(bs, *offset, *bytes, pad)) {

debian/patches/pve/0047-qapi-blockdev-backup-add-discard-source-parameter.patch

@@ -0,0 +1,277 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Date: Thu, 11 Apr 2024 11:29:25 +0200
+Subject: [PATCH] qapi: blockdev-backup: add discard-source parameter
+
+Add a parameter that enables discard-after-copy. That is mostly useful
+in "push backup with fleecing" scheme, when source is snapshot-access
+format driver node, based on copy-before-write filter snapshot-access
+API:
+
+[guest]      [snapshot-access] ~~ blockdev-backup ~~> [backup target]
+   |            |
+   | root       | file
+   v            v
+[copy-before-write]
+   |             |
+   | file        | target
+   v             v
+[active disk]   [temp.img]
+
+In this case discard-after-copy does two things:
+
+ - discard data in temp.img to save disk space
+ - avoid further copy-before-write operation in discarded area
+
+Note that we have to declare WRITE permission on source in
+copy-before-write filter, for discard to work. Still we can't take it
+unconditionally, as it will break normal backup from RO source. So, we
+have to add a parameter and pass it thorough bdrv_open flags.
+
+Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/backup.c                         |  5 +++--
+ block/block-copy.c                     |  9 +++++++++
+ block/copy-before-write.c              | 15 +++++++++++++--
+ block/copy-before-write.h              |  1 +
+ block/replication.c                    |  4 ++--
+ blockdev.c                             |  2 +-
+ include/block/block-common.h           |  2 ++
+ include/block/block-copy.h             |  1 +
+ include/block/block_int-global-state.h |  2 +-
+ qapi/block-core.json                   |  4 ++++
+ 10 files changed, 37 insertions(+), 8 deletions(-)
+
+diff --git a/block/backup.c b/block/backup.c
+index 16d611c4ca..1963e47ab9 100644
+--- a/block/backup.c
++++ b/block/backup.c
+@@ -332,7 +332,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+                   BlockDriverState *target, int64_t speed,
+                   MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
+                   BitmapSyncMode bitmap_mode,
+-                  bool compress,
++                  bool compress, bool discard_source,
+                   const char *filter_node_name,
+                   BackupPerf *perf,
+                   BlockdevOnError on_source_error,
+@@ -433,7 +433,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+         goto error;
+     }
+ 
+-    cbw = bdrv_cbw_append(bs, target, filter_node_name, &bcs, errp);
++    cbw = bdrv_cbw_append(bs, target, filter_node_name, discard_source,
++                          &bcs, errp);
+     if (!cbw) {
+         goto error;
+     }
+diff --git a/block/block-copy.c b/block/block-copy.c
+index 8fca2c3698..7e3b378528 100644
+--- a/block/block-copy.c
++++ b/block/block-copy.c
+@@ -137,6 +137,7 @@ typedef struct BlockCopyState {
+     CoMutex lock;
+     int64_t in_flight_bytes;
+     BlockCopyMethod method;
++    bool discard_source;
+     BlockReqList reqs;
+     QLIST_HEAD(, BlockCopyCallState) calls;
+     /*
+@@ -353,6 +354,7 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
+ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                      BlockDriverState *copy_bitmap_bs,
+                                      const BdrvDirtyBitmap *bitmap,
++                                     bool discard_source,
+                                      Error **errp)
+ {
+     ERRP_GUARD();
+@@ -418,6 +420,7 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                     cluster_size),
+     };
+ 
++    s->discard_source = discard_source;
+     block_copy_set_copy_opts(s, false, false);
+ 
+     ratelimit_init(&s->rate_limit);
+@@ -589,6 +592,12 @@ static coroutine_fn int block_copy_task_entry(AioTask *task)
+     co_put_to_shres(s->mem, t->req.bytes);
+     block_copy_task_end(t, ret);
+ 
++    if (s->discard_source && ret == 0) {
++        int64_t nbytes =
++            MIN(t->req.offset + t->req.bytes, s->len) - t->req.offset;
++        bdrv_co_pdiscard(s->source, t->req.offset, nbytes);
++    }
++
+     return ret;
+ }
+ 
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index 94db31512d..853e01a1eb 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -44,6 +44,7 @@ typedef struct BDRVCopyBeforeWriteState {
+     BdrvChild *target;
+     OnCbwError on_cbw_error;
+     uint64_t cbw_timeout_ns;
++    bool discard_source;
+ 
+     /*
+      * @lock: protects access to @access_bitmap, @done_bitmap and
+@@ -357,6 +358,8 @@ cbw_child_perm(BlockDriverState *bs, BdrvChild *c, BdrvChildRole role,
+                uint64_t perm, uint64_t shared,
+                uint64_t *nperm, uint64_t *nshared)
+ {
++    BDRVCopyBeforeWriteState *s = bs->opaque;
++
+     if (!(role & BDRV_CHILD_FILTERED)) {
+         /*
+          * Target child
+@@ -381,6 +384,10 @@ cbw_child_perm(BlockDriverState *bs, BdrvChild *c, BdrvChildRole role,
+              * start
+              */
+             *nperm = *nperm | BLK_PERM_CONSISTENT_READ;
++            if (s->discard_source) {
++                *nperm = *nperm | BLK_PERM_WRITE;
++            }
++
+             *nshared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
+         }
+     }
+@@ -468,7 +475,9 @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
+             ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) &
+              bs->file->bs->supported_zero_flags);
+ 
+-    s->bcs = block_copy_state_new(bs->file, s->target, bs, bitmap, errp);
++    s->discard_source = flags & BDRV_O_CBW_DISCARD_SOURCE;
++    s->bcs = block_copy_state_new(bs->file, s->target, bs, bitmap,
++                                  flags & BDRV_O_CBW_DISCARD_SOURCE, errp);
+     if (!s->bcs) {
+         error_prepend(errp, "Cannot create block-copy-state: ");
+         return -EINVAL;
+@@ -535,12 +544,14 @@ static BlockDriver bdrv_cbw_filter = {
+ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+                                   BlockDriverState *target,
+                                   const char *filter_node_name,
++                                  bool discard_source,
+                                   BlockCopyState **bcs,
+                                   Error **errp)
+ {
+     BDRVCopyBeforeWriteState *state;
+     BlockDriverState *top;
+     QDict *opts;
++    int flags = BDRV_O_RDWR | (discard_source ? BDRV_O_CBW_DISCARD_SOURCE : 0);
+ 
+     assert(source->total_sectors == target->total_sectors);
+     GLOBAL_STATE_CODE();
+@@ -553,7 +564,7 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+     qdict_put_str(opts, "file", bdrv_get_node_name(source));
+     qdict_put_str(opts, "target", bdrv_get_node_name(target));
+ 
+-    top = bdrv_insert_node(source, opts, BDRV_O_RDWR, errp);
++    top = bdrv_insert_node(source, opts, flags, errp);
+     if (!top) {
+         return NULL;
+     }
+diff --git a/block/copy-before-write.h b/block/copy-before-write.h
+index 6e72bb25e9..01af0cd3c4 100644
+--- a/block/copy-before-write.h
++++ b/block/copy-before-write.h
+@@ -39,6 +39,7 @@
+ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+                                   BlockDriverState *target,
+                                   const char *filter_node_name,
++                                  bool discard_source,
+                                   BlockCopyState **bcs,
+                                   Error **errp);
+ void bdrv_cbw_drop(BlockDriverState *bs);
+diff --git a/block/replication.c b/block/replication.c
+index ca6bd0a720..0415a5e8b7 100644
+--- a/block/replication.c
++++ b/block/replication.c
+@@ -582,8 +582,8 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode,
+ 
+         s->backup_job = backup_job_create(
+                                 NULL, s->secondary_disk->bs, s->hidden_disk->bs,
+-                                0, MIRROR_SYNC_MODE_NONE, NULL, 0, false, NULL,
+-                                &perf,
++                                0, MIRROR_SYNC_MODE_NONE, NULL, 0, false, false,
++                                NULL, &perf,
+                                 BLOCKDEV_ON_ERROR_REPORT,
+                                 BLOCKDEV_ON_ERROR_REPORT, JOB_INTERNAL,
+                                 backup_job_completed, bs, NULL, &local_err);
+diff --git a/blockdev.c b/blockdev.c
+index 5e5dbc1da9..1054a69279 100644
+--- a/blockdev.c
++++ b/blockdev.c
+@@ -2727,7 +2727,7 @@ static BlockJob *do_backup_common(BackupCommon *backup,
+ 
+     job = backup_job_create(backup->job_id, bs, target_bs, backup->speed,
+                             backup->sync, bmap, backup->bitmap_mode,
+-                            backup->compress,
++                            backup->compress, backup->discard_source,
+                             backup->filter_node_name,
+                             &perf,
+                             backup->on_source_error,
+diff --git a/include/block/block-common.h b/include/block/block-common.h
+index a846023a09..338fe5ff7a 100644
+--- a/include/block/block-common.h
++++ b/include/block/block-common.h
+@@ -243,6 +243,8 @@ typedef enum {
+                                       read-write fails */
+ #define BDRV_O_IO_URING    0x40000 /* use io_uring instead of the thread pool */
+ 
++#define BDRV_O_CBW_DISCARD_SOURCE 0x80000 /* for copy-before-write filter */
++
+ #define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_NO_FLUSH)
+ 
+ 
+diff --git a/include/block/block-copy.h b/include/block/block-copy.h
+index 8b41643bfa..bdc703bacd 100644
+--- a/include/block/block-copy.h
++++ b/include/block/block-copy.h
+@@ -27,6 +27,7 @@ typedef struct BlockCopyCallState BlockCopyCallState;
+ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                      BlockDriverState *copy_bitmap_bs,
+                                      const BdrvDirtyBitmap *bitmap,
++                                     bool discard_source,
+                                      Error **errp);
+ 
+ /* Function should be called prior any actual copy request */
+diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h
+index cc1387ae02..f0c642b194 100644
+--- a/include/block/block_int-global-state.h
++++ b/include/block/block_int-global-state.h
+@@ -195,7 +195,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+                             MirrorSyncMode sync_mode,
+                             BdrvDirtyBitmap *sync_bitmap,
+                             BitmapSyncMode bitmap_mode,
+-                            bool compress,
++                            bool compress, bool discard_source,
+                             const char *filter_node_name,
+                             BackupPerf *perf,
+                             BlockdevOnError on_source_error,
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index f516d8e95a..d796d49abb 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -1849,6 +1849,9 @@
+ #     node specified by @drive.  If this option is not given, a node
+ #     name is autogenerated.  (Since: 4.2)
+ #
++# @discard-source: Discard blocks on source which are already copied
++#     to the target.  (Since 9.0)
++#
+ # @x-perf: Performance options.  (Since 6.0)
+ #
+ # Features:
+@@ -1870,6 +1873,7 @@
+             '*on-target-error': 'BlockdevOnError',
+             '*auto-finalize': 'bool', '*auto-dismiss': 'bool',
+             '*filter-node-name': 'str',
++            '*discard-source': 'bool',
+             '*x-perf': { 'type': 'BackupPerf',
+                          'features': [ 'unstable' ] } } }
+ 

debian/patches/pve/0048-copy-before-write-allow-specifying-minimum-cluster-s.patch

@@ -0,0 +1,133 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Thu, 11 Apr 2024 11:29:26 +0200
+Subject: [PATCH] copy-before-write: allow specifying minimum cluster size
+
+Useful to make discard-source work in the context of backup fleecing
+when the fleecing image has a larger granularity than the backup
+target.
+
+Copy-before-write operations will use at least this granularity and in
+particular, discard requests to the source node will too. If the
+granularity is too small, they will just be aligned down in
+cbw_co_pdiscard_snapshot() and thus effectively ignored.
+
+The QAPI uses uint32 so the value will be non-negative, but still fit
+into a uint64_t.
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/block-copy.c         | 17 +++++++++++++----
+ block/copy-before-write.c  |  3 ++-
+ include/block/block-copy.h |  1 +
+ qapi/block-core.json       |  8 +++++++-
+ 4 files changed, 23 insertions(+), 6 deletions(-)
+
+diff --git a/block/block-copy.c b/block/block-copy.c
+index 7e3b378528..adb1cbb440 100644
+--- a/block/block-copy.c
++++ b/block/block-copy.c
+@@ -310,6 +310,7 @@ void block_copy_set_copy_opts(BlockCopyState *s, bool use_copy_range,
+ }
+ 
+ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
++                                                 int64_t min_cluster_size,
+                                                  Error **errp)
+ {
+     int ret;
+@@ -335,7 +336,7 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
+                     "used. If the actual block size of the target exceeds "
+                     "this default, the backup may be unusable",
+                     BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
+-        return BLOCK_COPY_CLUSTER_SIZE_DEFAULT;
++        return MAX(min_cluster_size, BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
+     } else if (ret < 0 && !target_does_cow) {
+         error_setg_errno(errp, -ret,
+             "Couldn't determine the cluster size of the target image, "
+@@ -345,16 +346,18 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
+         return ret;
+     } else if (ret < 0 && target_does_cow) {
+         /* Not fatal; just trudge on ahead. */
+-        return BLOCK_COPY_CLUSTER_SIZE_DEFAULT;
++        return MAX(min_cluster_size, BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
+     }
+ 
+-    return MAX(BLOCK_COPY_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
++    return MAX(min_cluster_size,
++               MAX(BLOCK_COPY_CLUSTER_SIZE_DEFAULT, bdi.cluster_size));
+ }
+ 
+ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                      BlockDriverState *copy_bitmap_bs,
+                                      const BdrvDirtyBitmap *bitmap,
+                                      bool discard_source,
++                                     int64_t min_cluster_size,
+                                      Error **errp)
+ {
+     ERRP_GUARD();
+@@ -365,7 +368,13 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+ 
+     GLOBAL_STATE_CODE();
+ 
+-    cluster_size = block_copy_calculate_cluster_size(target->bs, errp);
++    if (min_cluster_size && !is_power_of_2(min_cluster_size)) {
++        error_setg(errp, "min-cluster-size needs to be a power of 2");
++        return NULL;
++    }
++
++    cluster_size = block_copy_calculate_cluster_size(target->bs,
++                                                     min_cluster_size, errp);
+     if (cluster_size < 0) {
+         return NULL;
+     }
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index 853e01a1eb..47b3cdd09f 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -477,7 +477,8 @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
+ 
+     s->discard_source = flags & BDRV_O_CBW_DISCARD_SOURCE;
+     s->bcs = block_copy_state_new(bs->file, s->target, bs, bitmap,
+-                                  flags & BDRV_O_CBW_DISCARD_SOURCE, errp);
++                                  flags & BDRV_O_CBW_DISCARD_SOURCE,
++                                  opts->min_cluster_size, errp);
+     if (!s->bcs) {
+         error_prepend(errp, "Cannot create block-copy-state: ");
+         return -EINVAL;
+diff --git a/include/block/block-copy.h b/include/block/block-copy.h
+index bdc703bacd..77857c6c68 100644
+--- a/include/block/block-copy.h
++++ b/include/block/block-copy.h
+@@ -28,6 +28,7 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                      BlockDriverState *copy_bitmap_bs,
+                                      const BdrvDirtyBitmap *bitmap,
+                                      bool discard_source,
++                                     int64_t min_cluster_size,
+                                      Error **errp);
+ 
+ /* Function should be called prior any actual copy request */
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index d796d49abb..edbf6e78b9 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -4930,12 +4930,18 @@
+ #     @on-cbw-error parameter will decide how this failure is handled.
+ #     Default 0.  (Since 7.1)
+ #
++# @min-cluster-size: Minimum size of blocks used by copy-before-write
++#     operations.  Has to be a power of 2.  No effect if smaller than
++#     the maximum of the target's cluster size and 64 KiB.  Default 0.
++#     (Since 8.1)
++#
+ # Since: 6.2
+ ##
+ { 'struct': 'BlockdevOptionsCbw',
+   'base': 'BlockdevOptionsGenericFormat',
+   'data': { 'target': 'BlockdevRef', '*bitmap': 'BlockDirtyBitmap',
+-            '*on-cbw-error': 'OnCbwError', '*cbw-timeout': 'uint32' } }
++            '*on-cbw-error': 'OnCbwError', '*cbw-timeout': 'uint32',
++            '*min-cluster-size': 'uint32' } }
+ 
+ ##
+ # @BlockdevOptions:

debian/patches/pve/0049-PVE-whitelist-invalid-QAPI-names-for-backwards-compa.patch

@@ -1,33 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 26 May 2021 15:26:30 +0200
-Subject: [PATCH] PVE: whitelist 'invalid' QAPI names for backwards compat
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- qapi/pragma.json | 5 ++++-
- 1 file changed, 4 insertions(+), 1 deletion(-)
-
-diff --git a/qapi/pragma.json b/qapi/pragma.json
-index a2358e303a..9ff5c84ffd 100644
---- a/qapi/pragma.json
-+++ b/qapi/pragma.json
-@@ -15,6 +15,7 @@
-         'device_add',
-         'device_del',
-         'expire_password',
-+        'get_link_status',
-         'migrate_cancel',
-         'netdev_add',
-         'netdev_del',
-@@ -64,6 +65,8 @@
-         'SysEmuTarget',             # query-cpu-fast, query-target
-         'UuidInfo',                 # query-uuid
-         'VncClientInfo',            # query-vnc, query-vnc-servers, ...
--        'X86CPURegister32'          # qom-get of x86 CPU properties
-+        'X86CPURegister32',         # qom-get of x86 CPU properties
-                                     # feature-words, filtered-features
-+        'BlockdevOptionsPbs',       # for PBS backwards compat
-+        'BalloonInfo'
-     ] } }

debian/patches/pve/0049-backup-add-minimum-cluster-size-to-performance-optio.patch

@@ -0,0 +1,106 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Thu, 11 Apr 2024 11:29:27 +0200
+Subject: [PATCH] backup: add minimum cluster size to performance options
+
+Useful to make discard-source work in the context of backup fleecing
+when the fleecing image has a larger granularity than the backup
+target.
+
+Backup/block-copy will use at least this granularity for copy operations
+and in particular, discard requests to the backup source will too. If
+the granularity is too small, they will just be aligned down in
+cbw_co_pdiscard_snapshot() and thus effectively ignored.
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/backup.c            | 2 +-
+ block/copy-before-write.c | 2 ++
+ block/copy-before-write.h | 1 +
+ blockdev.c                | 3 +++
+ qapi/block-core.json      | 9 +++++++--
+ 5 files changed, 14 insertions(+), 3 deletions(-)
+
+diff --git a/block/backup.c b/block/backup.c
+index 1963e47ab9..fe69723ada 100644
+--- a/block/backup.c
++++ b/block/backup.c
+@@ -434,7 +434,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+     }
+ 
+     cbw = bdrv_cbw_append(bs, target, filter_node_name, discard_source,
+-                          &bcs, errp);
++                          perf->min_cluster_size, &bcs, errp);
+     if (!cbw) {
+         goto error;
+     }
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index 47b3cdd09f..bba58326d7 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -546,6 +546,7 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+                                   BlockDriverState *target,
+                                   const char *filter_node_name,
+                                   bool discard_source,
++                                  int64_t min_cluster_size,
+                                   BlockCopyState **bcs,
+                                   Error **errp)
+ {
+@@ -564,6 +565,7 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+     }
+     qdict_put_str(opts, "file", bdrv_get_node_name(source));
+     qdict_put_str(opts, "target", bdrv_get_node_name(target));
++    qdict_put_int(opts, "min-cluster-size", min_cluster_size);
+ 
+     top = bdrv_insert_node(source, opts, flags, errp);
+     if (!top) {
+diff --git a/block/copy-before-write.h b/block/copy-before-write.h
+index 01af0cd3c4..dc6cafe7fa 100644
+--- a/block/copy-before-write.h
++++ b/block/copy-before-write.h
+@@ -40,6 +40,7 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+                                   BlockDriverState *target,
+                                   const char *filter_node_name,
+                                   bool discard_source,
++                                  int64_t min_cluster_size,
+                                   BlockCopyState **bcs,
+                                   Error **errp);
+ void bdrv_cbw_drop(BlockDriverState *bs);
+diff --git a/blockdev.c b/blockdev.c
+index 1054a69279..cbe224387b 100644
+--- a/blockdev.c
++++ b/blockdev.c
+@@ -2654,6 +2654,9 @@ static BlockJob *do_backup_common(BackupCommon *backup,
+         if (backup->x_perf->has_max_chunk) {
+             perf.max_chunk = backup->x_perf->max_chunk;
+         }
++        if (backup->x_perf->has_min_cluster_size) {
++            perf.min_cluster_size = backup->x_perf->min_cluster_size;
++        }
+     }
+ 
+     if ((backup->sync == MIRROR_SYNC_MODE_BITMAP) ||
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index edbf6e78b9..6e7ee87633 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -1790,11 +1790,16 @@
+ #     it should not be less than job cluster size which is calculated
+ #     as maximum of target image cluster size and 64k.  Default 0.
+ #
++# @min-cluster-size: Minimum size of blocks used by copy-before-write
++#     and background copy operations.  Has to be a power of 2.  No
++#     effect if smaller than the maximum of the target's cluster size
++#     and 64 KiB.  Default 0. (Since 8.1)
++#
+ # Since: 6.0
+ ##
+ { 'struct': 'BackupPerf',
+-  'data': { '*use-copy-range': 'bool',
+-            '*max-workers': 'int', '*max-chunk': 'int64' } }
++  'data': { '*use-copy-range': 'bool', '*max-workers': 'int',
++            '*max-chunk': 'int64', '*min-cluster-size': 'uint32' } }
+ 
+ ##
+ # @BackupCommon:

debian/patches/pve/0050-PVE-backup-add-fleecing-option.patch

@@ -0,0 +1,345 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Thu, 11 Apr 2024 11:29:28 +0200
+Subject: [PATCH] PVE backup: add fleecing option
+
+When a fleecing option is given, it is expected that each device has
+a corresponding "-fleecing" block device already attached, except for
+EFI disk and TPM state, where fleecing is never used.
+
+The following graph was adapted from [0] which also contains more
+details about fleecing.
+
+[guest]
+   |
+   | root
+   v                 file
+[copy-before-write]<------[snapshot-access]
+   |           |
+   | file      | target
+   v           v
+[source] [fleecing]
+
+For fleecing, a copy-before-write filter is inserted on top of the
+source node, as well as a snapshot-access node pointing to the filter
+node which allows to read the consistent state of the image at the
+time it was inserted. New guest writes are passed through the
+copy-before-write filter which will first copy over old data to the
+fleecing image in case that old data is still needed by the
+snapshot-access node.
+
+The backup process will sequentially read from the snapshot access,
+which has a bitmap and knows whether to read from the original image
+or the fleecing image to get the "snapshot" state, i.e. data from the
+source image at the time when the copy-before-write filter was
+inserted. After reading, the copied sections are discarded from the
+fleecing image to reduce space usage.
+
+All of this can be restricted by an initial dirty bitmap to parts of
+the source image that are required for an incremental backup.
+
+For discard to work, it is necessary that the fleecing image does not
+have a larger cluster size than the backup job granularity. Since
+querying that size does not always work, e.g. for RBD with krbd, the
+cluster size will not be reported, a minimum of 4 MiB is used. A job
+with PBS target already has at least this granularity, so it's just
+relevant for other targets. I.e. edge cases where this minimum is not
+enough should be very rare in practice. If ever necessary in the
+future, can still add a passed-in value for the backup QMP command to
+override.
+
+Additionally, the cbw-timeout and on-cbw-error=break-snapshot options
+are set when installing the copy-before-write filter and
+snapshot-access. When an error or timeout occurs, the problematic (and
+each further) snapshot operation will fail and thus cancel the backup
+instead of breaking the guest write.
+
+Note that job_id cannot be inferred from the snapshot-access bs because
+it has no parent, so just pass the one from the original bs.
+
+[0]: https://www.mail-archive.com/qemu-devel@nongnu.org/msg876056.html
+
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ block/monitor/block-hmp-cmds.c |   1 +
+ pve-backup.c                   | 143 ++++++++++++++++++++++++++++++++-
+ qapi/block-core.json           |  10 ++-
+ 3 files changed, 150 insertions(+), 4 deletions(-)
+
+diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
+index 5000c084c5..70b3de4c7e 100644
+--- a/block/monitor/block-hmp-cmds.c
++++ b/block/monitor/block-hmp-cmds.c
+@@ -1043,6 +1043,7 @@ void coroutine_fn hmp_backup(Monitor *mon, const QDict *qdict)
+         NULL, NULL,
+         devlist, qdict_haskey(qdict, "speed"), speed,
+         false, 0, // BackupPerf max-workers
++        false, false, // fleecing
+         &error);
+ 
+     hmp_handle_error(mon, error);
+diff --git a/pve-backup.c b/pve-backup.c
+index 9d480a8eec..7cc1dd3724 100644
+--- a/pve-backup.c
++++ b/pve-backup.c
+@@ -7,9 +7,11 @@
+ #include "sysemu/blockdev.h"
+ #include "block/block_int-global-state.h"
+ #include "block/blockjob.h"
++#include "block/copy-before-write.h"
+ #include "block/dirty-bitmap.h"
+ #include "block/graph-lock.h"
+ #include "qapi/qapi-commands-block.h"
++#include "qapi/qmp/qdict.h"
+ #include "qapi/qmp/qerror.h"
+ #include "qemu/cutils.h"
+ 
+@@ -81,8 +83,15 @@ static void pvebackup_init(void)
+ // initialize PVEBackupState at startup
+ opts_init(pvebackup_init);
+ 
++typedef struct PVEBackupFleecingInfo {
++    BlockDriverState *bs;
++    BlockDriverState *cbw;
++    BlockDriverState *snapshot_access;
++} PVEBackupFleecingInfo;
++
+ typedef struct PVEBackupDevInfo {
+     BlockDriverState *bs;
++    PVEBackupFleecingInfo fleecing;
+     size_t size;
+     uint64_t block_size;
+     uint8_t dev_id;
+@@ -355,6 +364,25 @@ static void pvebackup_complete_cb(void *opaque, int ret)
+     PVEBackupDevInfo *di = opaque;
+     di->completed_ret = ret;
+ 
++    /*
++     * Handle block-graph specific cleanup (for fleecing) outside of the coroutine, because the work
++     * won't be done as a coroutine anyways:
++     * - For snapshot_access, allows doing bdrv_unref() directly. Doing it via bdrv_co_unref() would
++     *   just spawn a BH calling bdrv_unref().
++     * - For cbw, draining would need to spawn a BH.
++     *
++     * Note that the AioContext lock is already acquired by our caller, i.e.
++     * job_finalize_single_locked()
++     */
++    if (di->fleecing.snapshot_access) {
++        bdrv_unref(di->fleecing.snapshot_access);
++        di->fleecing.snapshot_access = NULL;
++    }
++    if (di->fleecing.cbw) {
++        bdrv_cbw_drop(di->fleecing.cbw);
++        di->fleecing.cbw = NULL;
++    }
++
+     /*
+      * Needs to happen outside of coroutine, because it takes the graph write lock.
+      */
+@@ -522,9 +550,82 @@ static void create_backup_jobs_bh(void *opaque) {
+         }
+         bdrv_drained_begin(di->bs);
+ 
++        BackupPerf perf = (BackupPerf){ .max_workers = backup_state.perf.max_workers };
++
++        BlockDriverState *source_bs = di->bs;
++        bool discard_source = false;
++        bdrv_graph_co_rdlock();
++        const char *job_id = bdrv_get_device_name(di->bs);
++        bdrv_graph_co_rdunlock();
++        if (di->fleecing.bs) {
++            QDict *cbw_opts = qdict_new();
++            qdict_put_str(cbw_opts, "driver", "copy-before-write");
++            qdict_put_str(cbw_opts, "file", bdrv_get_node_name(di->bs));
++            qdict_put_str(cbw_opts, "target", bdrv_get_node_name(di->fleecing.bs));
++
++            if (di->bitmap) {
++                /*
++                 * Only guest writes to parts relevant for the backup need to be intercepted with
++                 * old data being copied to the fleecing image.
++                 */
++                qdict_put_str(cbw_opts, "bitmap.node", bdrv_get_node_name(di->bs));
++                qdict_put_str(cbw_opts, "bitmap.name", bdrv_dirty_bitmap_name(di->bitmap));
++            }
++            /*
++             * Fleecing storage is supposed to be fast and it's better to break backup than guest
++             * writes. Certain guest drivers like VirtIO-win have 60 seconds timeout by default, so
++             * abort a bit before that.
++             */
++            qdict_put_str(cbw_opts, "on-cbw-error", "break-snapshot");
++            qdict_put_int(cbw_opts, "cbw-timeout", 45);
++
++            di->fleecing.cbw = bdrv_insert_node(di->bs, cbw_opts, BDRV_O_RDWR, &local_err);
++
++            if (!di->fleecing.cbw) {
++                error_setg(errp, "appending cbw node for fleecing failed: %s",
++                           local_err ? error_get_pretty(local_err) : "unknown error");
++                break;
++            }
++
++            QDict *snapshot_access_opts = qdict_new();
++            qdict_put_str(snapshot_access_opts, "driver", "snapshot-access");
++            qdict_put_str(snapshot_access_opts, "file", bdrv_get_node_name(di->fleecing.cbw));
++
++            /*
++             * Holding the AioContext lock here would cause a deadlock, because bdrv_open_driver()
++             * will aquire it a second time. But it's allowed to be held exactly once when polling
++             * and that happens when the bdrv_refresh_total_sectors() call is made there.
++             */
++            di->fleecing.snapshot_access =
++                bdrv_open(NULL, NULL, snapshot_access_opts, BDRV_O_RDWR | BDRV_O_UNMAP, &local_err);
++            if (!di->fleecing.snapshot_access) {
++                error_setg(errp, "setting up snapshot access for fleecing failed: %s",
++                           local_err ? error_get_pretty(local_err) : "unknown error");
++                break;
++            }
++            source_bs = di->fleecing.snapshot_access;
++            discard_source = true;
++
++            /*
++             * bdrv_get_info() just retuns 0 (= doesn't matter) for RBD when using krbd. But discard
++             * on the fleecing image won't work if the backup job's granularity is less than the RBD
++             * object size (default 4 MiB), so it does matter. Always use at least 4 MiB. With a PBS
++             * target, the backup job granularity would already be at least this much.
++             */
++            perf.min_cluster_size = 4 * 1024 * 1024;
++            /*
++             * For discard to work, cluster size for the backup job must be at least the same as for
++             * the fleecing image.
++             */
++            BlockDriverInfo bdi;
++            if (bdrv_get_info(di->fleecing.bs, &bdi) >= 0) {
++                perf.min_cluster_size = MAX(perf.min_cluster_size, bdi.cluster_size);
++            }
++        }
++
+         BlockJob *job = backup_job_create(
+-            NULL, di->bs, di->target, backup_state.speed, sync_mode, di->bitmap,
+-            bitmap_mode, false, NULL, &backup_state.perf, BLOCKDEV_ON_ERROR_REPORT,
++            job_id, source_bs, di->target, backup_state.speed, sync_mode, di->bitmap,
++            bitmap_mode, false, discard_source, NULL, &perf, BLOCKDEV_ON_ERROR_REPORT,
+             BLOCKDEV_ON_ERROR_REPORT, JOB_DEFAULT, pvebackup_complete_cb, di, backup_state.txn,
+             &local_err);
+ 
+@@ -580,6 +681,14 @@ static void create_backup_jobs_bh(void *opaque) {
+     aio_co_enter(data->ctx, data->co);
+ }
+ 
++/*
++ * EFI disk and TPM state are small and it's just not worth setting up fleecing for them.
++ */
++static bool device_uses_fleecing(const char *device_id)
++{
++    return strncmp(device_id, "drive-efidisk", 13) && strncmp(device_id, "drive-tpmstate", 14);
++}
++
+ /*
+  * Returns a list of device infos, which needs to be freed by the caller. In
+  * case of an error, errp will be set, but the returned value might still be a
+@@ -587,6 +696,7 @@ static void create_backup_jobs_bh(void *opaque) {
+  */
+ static GList coroutine_fn GRAPH_RDLOCK *get_device_info(
+     const char *devlist,
++    bool fleecing,
+     Error **errp)
+ {
+     gchar **devs = NULL;
+@@ -610,6 +720,31 @@ static GList coroutine_fn GRAPH_RDLOCK *get_device_info(
+             }
+             PVEBackupDevInfo *di = g_new0(PVEBackupDevInfo, 1);
+             di->bs = bs;
++
++            if (fleecing && device_uses_fleecing(*d)) {
++                g_autofree gchar *fleecing_devid = g_strconcat(*d, "-fleecing", NULL);
++                BlockBackend *fleecing_blk = blk_by_name(fleecing_devid);
++                if (!fleecing_blk) {
++                    error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
++                              "Device '%s' not found", fleecing_devid);
++                    goto err;
++                }
++                BlockDriverState *fleecing_bs = blk_bs(fleecing_blk);
++                if (!bdrv_co_is_inserted(fleecing_bs)) {
++                    error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, fleecing_devid);
++                    goto err;
++                }
++                /*
++                 * Fleecing image needs to be the same size to act as a cbw target.
++                 */
++                if (bs->total_sectors != fleecing_bs->total_sectors) {
++                    error_setg(errp, "Size mismatch for '%s' - sector count %ld != %ld",
++                               fleecing_devid, fleecing_bs->total_sectors, bs->total_sectors);
++                    goto err;
++                }
++                di->fleecing.bs = fleecing_bs;
++            }
++
+             di_list = g_list_append(di_list, di);
+             d++;
+         }
+@@ -659,6 +794,7 @@ UuidInfo coroutine_fn *qmp_backup(
+     const char *devlist,
+     bool has_speed, int64_t speed,
+     bool has_max_workers, int64_t max_workers,
++    bool has_fleecing, bool fleecing,
+     Error **errp)
+ {
+     assert(qemu_in_coroutine());
+@@ -687,7 +823,7 @@ UuidInfo coroutine_fn *qmp_backup(
+     format = has_format ? format : BACKUP_FORMAT_VMA;
+ 
+     bdrv_graph_co_rdlock();
+-    di_list = get_device_info(devlist, &local_err);
++    di_list = get_device_info(devlist, has_fleecing && fleecing, &local_err);
+     bdrv_graph_co_rdunlock();
+     if (local_err) {
+         error_propagate(errp, local_err);
+@@ -1095,5 +1231,6 @@ ProxmoxSupportStatus *qmp_query_proxmox_support(Error **errp)
+     ret->query_bitmap_info = true;
+     ret->pbs_masterkey = true;
+     ret->backup_max_workers = true;
++    ret->backup_fleecing = true;
+     return ret;
+ }
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index 6e7ee87633..dc5f75cd39 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -948,6 +948,10 @@
+ #
+ # @max-workers: see @BackupPerf for details. Default 16.
+ #
++# @fleecing: perform a backup with fleecing. For each device in @devlist, a
++#            corresponing '-fleecing' device with the same size already needs to
++#            be present.
++#
+ # Returns: the uuid of the backup job
+ #
+ ##
+@@ -968,7 +972,8 @@
+                                     '*firewall-file': 'str',
+                                     '*devlist': 'str',
+                                     '*speed': 'int',
+-                                    '*max-workers': 'int' },
++                                    '*max-workers': 'int',
++                                    '*fleecing': 'bool' },
+   'returns': 'UuidInfo', 'coroutine': true }
+ 
+ ##
+@@ -1014,6 +1019,8 @@
+ #
+ # @pbs-library-version: Running version of libproxmox-backup-qemu0 library.
+ #
++# @backup-fleecing: Whether backup fleecing is supported or not.
++#
+ # @backup-max-workers: Whether the 'max-workers' @BackupPerf setting is
+ #     supported or not.
+ #
+@@ -1025,6 +1032,7 @@
+             'pbs-dirty-bitmap-migration': 'bool',
+             'pbs-masterkey': 'bool',
+             'pbs-library-version': 'str',
++            'backup-fleecing': 'bool',
+             'backup-max-workers': 'bool' } }
+ 
+ ##

debian/patches/pve/0050-PVE-savevm-async-register-yank-before-migration_inco.patch

@@ -1,35 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 26 May 2021 17:36:55 +0200
-Subject: [PATCH] PVE: savevm-async: register yank before
- migration_incoming_state_destroy
-
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- migration/savevm-async.c | 5 +++++
- 1 file changed, 5 insertions(+)
-
-diff --git a/migration/savevm-async.c b/migration/savevm-async.c
-index e65a5e3482..2ed2536816 100644
---- a/migration/savevm-async.c
-+++ b/migration/savevm-async.c
-@@ -20,6 +20,7 @@
- #include "qemu/timer.h"
- #include "qemu/main-loop.h"
- #include "qemu/rcu.h"
-+#include "qemu/yank.h"
- 
- /* #define DEBUG_SAVEVM_STATE */
- 
-@@ -514,6 +515,10 @@ int load_snapshot_from_blockdev(const char *filename, Error **errp)
-     dirty_bitmap_mig_before_vm_start();
- 
-     qemu_fclose(f);
-+
-+    /* state_destroy assumes a real migration which would have added a yank */
-+    yank_register_instance(MIGRATION_YANK_INSTANCE, &error_abort);
-+
-     migration_incoming_state_destroy();
-     if (ret < 0) {
-         error_setg_errno(errp, -ret, "Error while loading VM state");

debian/patches/pve/0051-PVE-backup-improve-error-when-copy-before-write-fail.patch

@@ -0,0 +1,117 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Mon, 29 Apr 2024 14:43:58 +0200
+Subject: [PATCH] PVE backup: improve error when copy-before-write fails for
+ fleecing
+
+With fleecing, failure for copy-before-write does not fail the guest
+write, but only sets the snapshot error that is associated to the
+copy-before-write filter, making further requests to the snapshot
+access fail with EACCES, which then also fails the job. But that error
+code is not the root cause of why the backup failed, so bubble up the
+original snapshot error instead.
+
+Reported-by: Friedrich Weber <f.weber@proxmox.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Tested-by: Friedrich Weber <f.weber@proxmox.com>
+---
+ block/copy-before-write.c | 18 ++++++++++++------
+ block/copy-before-write.h |  1 +
+ pve-backup.c              |  9 +++++++++
+ 3 files changed, 22 insertions(+), 6 deletions(-)
+
+diff --git a/block/copy-before-write.c b/block/copy-before-write.c
+index bba58326d7..50cc4c7aae 100644
+--- a/block/copy-before-write.c
++++ b/block/copy-before-write.c
+@@ -27,6 +27,7 @@
+ #include "qapi/qmp/qjson.h"
+ 
+ #include "sysemu/block-backend.h"
++#include "qemu/atomic.h"
+ #include "qemu/cutils.h"
+ #include "qapi/error.h"
+ #include "block/block_int.h"
+@@ -74,7 +75,8 @@ typedef struct BDRVCopyBeforeWriteState {
+      * @snapshot_error is normally zero. But on first copy-before-write failure
+      * when @on_cbw_error == ON_CBW_ERROR_BREAK_SNAPSHOT, @snapshot_error takes
+      * value of this error (<0). After that all in-flight and further
+-     * snapshot-API requests will fail with that error.
++     * snapshot-API requests will fail with that error. To be accessed with
++     * atomics.
+      */
+     int snapshot_error;
+ } BDRVCopyBeforeWriteState;
+@@ -114,7 +116,7 @@ static coroutine_fn int cbw_do_copy_before_write(BlockDriverState *bs,
+         return 0;
+     }
+ 
+-    if (s->snapshot_error) {
++    if (qatomic_read(&s->snapshot_error)) {
+         return 0;
+     }
+ 
+@@ -138,9 +140,7 @@ static coroutine_fn int cbw_do_copy_before_write(BlockDriverState *bs,
+     WITH_QEMU_LOCK_GUARD(&s->lock) {
+         if (ret < 0) {
+             assert(s->on_cbw_error == ON_CBW_ERROR_BREAK_SNAPSHOT);
+-            if (!s->snapshot_error) {
+-                s->snapshot_error = ret;
+-            }
++            qatomic_cmpxchg(&s->snapshot_error, 0, ret);
+         } else {
+             bdrv_set_dirty_bitmap(s->done_bitmap, off, end - off);
+         }
+@@ -214,7 +214,7 @@ cbw_snapshot_read_lock(BlockDriverState *bs, int64_t offset, int64_t bytes,
+ 
+     QEMU_LOCK_GUARD(&s->lock);
+ 
+-    if (s->snapshot_error) {
++    if (qatomic_read(&s->snapshot_error)) {
+         g_free(req);
+         return NULL;
+     }
+@@ -585,6 +585,12 @@ void bdrv_cbw_drop(BlockDriverState *bs)
+     bdrv_unref(bs);
+ }
+ 
++int bdrv_cbw_snapshot_error(BlockDriverState *bs)
++{
++    BDRVCopyBeforeWriteState *s = bs->opaque;
++    return qatomic_read(&s->snapshot_error);
++}
++
+ static void cbw_init(void)
+ {
+     bdrv_register(&bdrv_cbw_filter);
+diff --git a/block/copy-before-write.h b/block/copy-before-write.h
+index dc6cafe7fa..a27d2d7d9f 100644
+--- a/block/copy-before-write.h
++++ b/block/copy-before-write.h
+@@ -44,5 +44,6 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
+                                   BlockCopyState **bcs,
+                                   Error **errp);
+ void bdrv_cbw_drop(BlockDriverState *bs);
++int bdrv_cbw_snapshot_error(BlockDriverState *bs);
+ 
+ #endif /* COPY_BEFORE_WRITE_H */
+diff --git a/pve-backup.c b/pve-backup.c
+index 7cc1dd3724..07709aa350 100644
+--- a/pve-backup.c
++++ b/pve-backup.c
+@@ -379,6 +379,15 @@ static void pvebackup_complete_cb(void *opaque, int ret)
+         di->fleecing.snapshot_access = NULL;
+     }
+     if (di->fleecing.cbw) {
++        /*
++         * With fleecing, failure for cbw does not fail the guest write, but only sets the snapshot
++         * error, making further requests to the snapshot fail with EACCES, which then also fail the
++         * job. But that code is not the root cause and just confusing, so update it.
++         */
++        int snapshot_error = bdrv_cbw_snapshot_error(di->fleecing.cbw);
++        if (di->completed_ret == -EACCES && snapshot_error) {
++            di->completed_ret = snapshot_error;
++        }
+         bdrv_cbw_drop(di->fleecing.cbw);
+         di->fleecing.cbw = NULL;
+     }

debian/patches/pve/0052-vma-allow-partial-restore.patch

@@ -1,407 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fabian Ebner <f.ebner@proxmox.com>
-Date: Thu, 21 Apr 2022 13:26:48 +0200
-Subject: [PATCH] vma: allow partial restore
-
-Introduce a new map line for skipping a certain drive, of the form
-skip=drive-scsi0
-
-Since in PVE, most archives are compressed and piped to vma for
-restore, it's not easily possible to skip reads.
-
-For the reader, a new skip flag for VmaRestoreState is added and the
-target is allowed to be NULL if skip is specified when registering. If
-the skip flag is set, no writes will be made as well as no check for
-duplicate clusters. Therefore, the flag is not set for verify.
-
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
-Acked-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- vma-reader.c |  64 ++++++++++++---------
- vma.c        | 157 +++++++++++++++++++++++++++++----------------------
- vma.h        |   2 +-
- 3 files changed, 126 insertions(+), 97 deletions(-)
-
-diff --git a/vma-reader.c b/vma-reader.c
-index e65f1e8415..81a891c6b1 100644
---- a/vma-reader.c
-+++ b/vma-reader.c
-@@ -28,6 +28,7 @@ typedef struct VmaRestoreState {
-     bool write_zeroes;
-     unsigned long *bitmap;
-     int bitmap_size;
-+    bool skip;
- }  VmaRestoreState;
- 
- struct VmaReader {
-@@ -425,13 +426,14 @@ VmaDeviceInfo *vma_reader_get_device_info(VmaReader *vmar, guint8 dev_id)
- }
- 
- static void allocate_rstate(VmaReader *vmar,  guint8 dev_id,
--                            BlockBackend *target, bool write_zeroes)
-+                            BlockBackend *target, bool write_zeroes, bool skip)
- {
-     assert(vmar);
-     assert(dev_id);
- 
-     vmar->rstate[dev_id].target = target;
-     vmar->rstate[dev_id].write_zeroes = write_zeroes;
-+    vmar->rstate[dev_id].skip = skip;
- 
-     int64_t size = vmar->devinfo[dev_id].size;
- 
-@@ -446,28 +448,30 @@ static void allocate_rstate(VmaReader *vmar,  guint8 dev_id,
- }
- 
- int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id, BlockBackend *target,
--                           bool write_zeroes, Error **errp)
-+                           bool write_zeroes, bool skip, Error **errp)
- {
-     assert(vmar);
--    assert(target != NULL);
-+    assert(target != NULL || skip);
-     assert(dev_id);
--    assert(vmar->rstate[dev_id].target == NULL);
--
--    int64_t size = blk_getlength(target);
--    int64_t size_diff = size - vmar->devinfo[dev_id].size;
--
--    /* storage types can have different size restrictions, so it
--     * is not always possible to create an image with exact size.
--     * So we tolerate a size difference up to 4MB.
--     */
--    if ((size_diff < 0) || (size_diff > 4*1024*1024)) {
--        error_setg(errp, "vma_reader_register_bs for stream %s failed - "
--                   "unexpected size %zd != %zd", vmar->devinfo[dev_id].devname,
--                   size, vmar->devinfo[dev_id].size);
--        return -1;
-+    assert(vmar->rstate[dev_id].target == NULL && !vmar->rstate[dev_id].skip);
-+
-+    if (target != NULL) {
-+        int64_t size = blk_getlength(target);
-+        int64_t size_diff = size - vmar->devinfo[dev_id].size;
-+
-+        /* storage types can have different size restrictions, so it
-+         * is not always possible to create an image with exact size.
-+         * So we tolerate a size difference up to 4MB.
-+         */
-+        if ((size_diff < 0) || (size_diff > 4*1024*1024)) {
-+            error_setg(errp, "vma_reader_register_bs for stream %s failed - "
-+                       "unexpected size %zd != %zd", vmar->devinfo[dev_id].devname,
-+                       size, vmar->devinfo[dev_id].size);
-+            return -1;
-+        }
-     }
- 
--    allocate_rstate(vmar, dev_id, target, write_zeroes);
-+    allocate_rstate(vmar, dev_id, target, write_zeroes, skip);
- 
-     return 0;
- }
-@@ -560,19 +564,23 @@ static int restore_extent(VmaReader *vmar, unsigned char *buf,
-         VmaRestoreState *rstate = &vmar->rstate[dev_id];
-         BlockBackend *target = NULL;
- 
-+        bool skip = rstate->skip;
-+
-         if (dev_id != vmar->vmstate_stream) {
-             target = rstate->target;
--            if (!verify && !target) {
-+            if (!verify && !target && !skip) {
-                 error_setg(errp, "got wrong dev id %d", dev_id);
-                 return -1;
-             }
- 
--            if (vma_reader_get_bitmap(rstate, cluster_num)) {
--                error_setg(errp, "found duplicated cluster %zd for stream %s",
--                          cluster_num, vmar->devinfo[dev_id].devname);
--                return -1;
-+            if (!skip) {
-+                if (vma_reader_get_bitmap(rstate, cluster_num)) {
-+                    error_setg(errp, "found duplicated cluster %zd for stream %s",
-+                              cluster_num, vmar->devinfo[dev_id].devname);
-+                    return -1;
-+                }
-+                vma_reader_set_bitmap(rstate, cluster_num, 1);
-             }
--            vma_reader_set_bitmap(rstate, cluster_num, 1);
- 
-             max_sector = vmar->devinfo[dev_id].size/BDRV_SECTOR_SIZE;
-         } else {
-@@ -618,7 +626,7 @@ static int restore_extent(VmaReader *vmar, unsigned char *buf,
-                 return -1;
-             }
- 
--            if (!verify) {
-+            if (!verify && !skip) {
-                 int nb_sectors = end_sector - sector_num;
-                 if (restore_write_data(vmar, dev_id, target, vmstate_fd,
-                                        buf + start, sector_num, nb_sectors,
-@@ -654,7 +662,7 @@ static int restore_extent(VmaReader *vmar, unsigned char *buf,
-                         return -1;
-                     }
- 
--                    if (!verify) {
-+                    if (!verify && !skip) {
-                         int nb_sectors = end_sector - sector_num;
-                         if (restore_write_data(vmar, dev_id, target, vmstate_fd,
-                                                buf + start, sector_num,
-@@ -679,7 +687,7 @@ static int restore_extent(VmaReader *vmar, unsigned char *buf,
-                             vmar->partial_zero_cluster_data += zero_size;
-                         }
- 
--                        if (rstate->write_zeroes && !verify) {
-+                        if (rstate->write_zeroes && !verify && !skip) {
-                             if (restore_write_data(vmar, dev_id, target, vmstate_fd,
-                                                    zero_vma_block, sector_num,
-                                                    nb_sectors, errp) < 0) {
-@@ -850,7 +858,7 @@ int vma_reader_verify(VmaReader *vmar, bool verbose, Error **errp)
- 
-     for (dev_id = 1; dev_id < 255; dev_id++) {
-         if (vma_reader_get_device_info(vmar, dev_id)) {
--            allocate_rstate(vmar, dev_id, NULL, false);
-+            allocate_rstate(vmar, dev_id, NULL, false, false);
-         }
-     }
- 
-diff --git a/vma.c b/vma.c
-index e8dffb43e0..e6e9ffc7fe 100644
---- a/vma.c
-+++ b/vma.c
-@@ -138,6 +138,7 @@ typedef struct RestoreMap {
-     char *throttling_group;
-     char *cache;
-     bool write_zero;
-+    bool skip;
- } RestoreMap;
- 
- static bool try_parse_option(char **line, const char *optname, char **out, const char *inbuf) {
-@@ -245,47 +246,61 @@ static int extract_content(int argc, char **argv)
-             char *bps = NULL;
-             char *group = NULL;
-             char *cache = NULL;
-+            char *devname = NULL;
-+            bool skip = false;
-+            uint64_t bps_value = 0;
-+            const char *path = NULL;
-+            bool write_zero = true;
-+
-             if (!line || line[0] == '\0' || !strcmp(line, "done\n")) {
-                 break;
-             }
-             int len = strlen(line);
-             if (line[len - 1] == '\n') {
-                 line[len - 1] = '\0';
--                if (len == 1) {
-+                len = len - 1;
-+                if (len == 0) {
-                     break;
-                 }
-             }
- 
--            while (1) {
--                if (!try_parse_option(&line, "format", &format, inbuf) &&
--                    !try_parse_option(&line, "throttling.bps", &bps, inbuf) &&
--                    !try_parse_option(&line, "throttling.group", &group, inbuf) &&
--                    !try_parse_option(&line, "cache", &cache, inbuf))
--                {
--                    break;
-+            if (strncmp(line, "skip", 4) == 0) {
-+                if (len < 6 || line[4] != '=') {
-+                    g_error("read map failed - option 'skip' has no value ('%s')",
-+                            inbuf);
-+                } else {
-+                    devname = line + 5;
-+                    skip = true;
-+                }
-+            } else {
-+                while (1) {
-+                    if (!try_parse_option(&line, "format", &format, inbuf) &&
-+                        !try_parse_option(&line, "throttling.bps", &bps, inbuf) &&
-+                        !try_parse_option(&line, "throttling.group", &group, inbuf) &&
-+                        !try_parse_option(&line, "cache", &cache, inbuf))
-+                    {
-+                        break;
-+                    }
-                 }
--            }
- 
--            uint64_t bps_value = 0;
--            if (bps) {
--                bps_value = verify_u64(bps);
--                g_free(bps);
--            }
-+                if (bps) {
-+                    bps_value = verify_u64(bps);
-+                    g_free(bps);
-+                }
- 
--            const char *path;
--            bool write_zero;
--            if (line[0] == '0' && line[1] == ':') {
--                path = line + 2;
--                write_zero = false;
--            } else if (line[0] == '1' && line[1] == ':') {
--                path = line + 2;
--                write_zero = true;
--            } else {
--                g_error("read map failed - parse error ('%s')", inbuf);
-+                if (line[0] == '0' && line[1] == ':') {
-+                    path = line + 2;
-+                    write_zero = false;
-+                } else if (line[0] == '1' && line[1] == ':') {
-+                    path = line + 2;
-+                    write_zero = true;
-+                } else {
-+                    g_error("read map failed - parse error ('%s')", inbuf);
-+                }
-+
-+                path = extract_devname(path, &devname, -1);
-             }
- 
--            char *devname = NULL;
--            path = extract_devname(path, &devname, -1);
-             if (!devname) {
-                 g_error("read map failed - no dev name specified ('%s')",
-                         inbuf);
-@@ -299,6 +314,7 @@ static int extract_content(int argc, char **argv)
-             map->throttling_group = group;
-             map->cache = cache;
-             map->write_zero = write_zero;
-+            map->skip = skip;
- 
-             g_hash_table_insert(devmap, map->devname, map);
- 
-@@ -328,6 +344,7 @@ static int extract_content(int argc, char **argv)
-             const char *cache = NULL;
-             int flags = BDRV_O_RDWR;
-             bool write_zero = true;
-+            bool skip = false;
- 
-             BlockBackend *blk = NULL;
- 
-@@ -343,6 +360,7 @@ static int extract_content(int argc, char **argv)
-                 throttling_group = map->throttling_group;
-                 cache = map->cache;
-                 write_zero = map->write_zero;
-+                skip = map->skip;
-             } else {
-                 devfn = g_strdup_printf("%s/tmp-disk-%s.raw",
-                                         dirname, di->devname);
-@@ -361,57 +379,60 @@ static int extract_content(int argc, char **argv)
-                 write_zero = false;
-             }
- 
--	    size_t devlen = strlen(devfn);
--	    QDict *options = NULL;
--            bool writethrough;
--            if (format) {
--                /* explicit format from commandline */
--                options = qdict_new();
--                qdict_put_str(options, "driver", format);
--            } else if ((devlen > 4 && strcmp(devfn+devlen-4, ".raw") == 0) ||
--	               strncmp(devfn, "/dev/", 5) == 0)
--	    {
--                /* This part is now deprecated for PVE as well (just as qemu
--                 * deprecated not specifying an explicit raw format, too.
--                 */
--		/* explicit raw format */
--		options = qdict_new();
--		qdict_put_str(options, "driver", "raw");
--	    }
--            if (cache && bdrv_parse_cache_mode(cache, &flags, &writethrough)) {
--                g_error("invalid cache option: %s\n", cache);
--            }
-+            if (!skip) {
-+                size_t devlen = strlen(devfn);
-+                QDict *options = NULL;
-+                bool writethrough;
-+                if (format) {
-+                    /* explicit format from commandline */
-+                    options = qdict_new();
-+                    qdict_put_str(options, "driver", format);
-+                } else if ((devlen > 4 && strcmp(devfn+devlen-4, ".raw") == 0) ||
-+                    strncmp(devfn, "/dev/", 5) == 0)
-+                {
-+                    /* This part is now deprecated for PVE as well (just as qemu
-+                     * deprecated not specifying an explicit raw format, too.
-+                     */
-+                    /* explicit raw format */
-+                    options = qdict_new();
-+                    qdict_put_str(options, "driver", "raw");
-+                }
- 
--	    if (errp || !(blk = blk_new_open(devfn, NULL, options, flags, &errp))) {
--                g_error("can't open file %s - %s", devfn,
--                        error_get_pretty(errp));
--            }
-+                if (cache && bdrv_parse_cache_mode(cache, &flags, &writethrough)) {
-+                    g_error("invalid cache option: %s\n", cache);
-+                }
- 
--            if (cache) {
--                blk_set_enable_write_cache(blk, !writethrough);
--            }
-+                if (errp || !(blk = blk_new_open(devfn, NULL, options, flags, &errp))) {
-+                    g_error("can't open file %s - %s", devfn,
-+                            error_get_pretty(errp));
-+                }
- 
--            if (throttling_group) {
--                blk_io_limits_enable(blk, throttling_group);
--            }
-+                if (cache) {
-+                    blk_set_enable_write_cache(blk, !writethrough);
-+                }
- 
--            if (throttling_bps) {
--                if (!throttling_group) {
--                    blk_io_limits_enable(blk, devfn);
-+                if (throttling_group) {
-+                    blk_io_limits_enable(blk, throttling_group);
-                 }
- 
--                ThrottleConfig cfg;
--                throttle_config_init(&cfg);
--                cfg.buckets[THROTTLE_BPS_WRITE].avg = throttling_bps;
--                Error *err = NULL;
--                if (!throttle_is_valid(&cfg, &err)) {
--                    error_report_err(err);
--                    g_error("failed to apply throttling");
-+                if (throttling_bps) {
-+                    if (!throttling_group) {
-+                        blk_io_limits_enable(blk, devfn);
-+                    }
-+
-+                    ThrottleConfig cfg;
-+                    throttle_config_init(&cfg);
-+                    cfg.buckets[THROTTLE_BPS_WRITE].avg = throttling_bps;
-+                    Error *err = NULL;
-+                    if (!throttle_is_valid(&cfg, &err)) {
-+                        error_report_err(err);
-+                        g_error("failed to apply throttling");
-+                    }
-+                    blk_set_io_limits(blk, &cfg);
-                 }
--                blk_set_io_limits(blk, &cfg);
-             }
- 
--            if (vma_reader_register_bs(vmar, i, blk, write_zero, &errp) < 0) {
-+            if (vma_reader_register_bs(vmar, i, blk, write_zero, skip, &errp) < 0) {
-                 g_error("%s", error_get_pretty(errp));
-             }
- 
-diff --git a/vma.h b/vma.h
-index c895c97f6d..1b62859165 100644
---- a/vma.h
-+++ b/vma.h
-@@ -142,7 +142,7 @@ GList *vma_reader_get_config_data(VmaReader *vmar);
- VmaDeviceInfo *vma_reader_get_device_info(VmaReader *vmar, guint8 dev_id);
- int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id,
-                            BlockBackend *target, bool write_zeroes,
--                           Error **errp);
-+                           bool skip, Error **errp);
- int vma_reader_restore(VmaReader *vmar, int vmstate_fd, bool verbose,
-                        Error **errp);
- int vma_reader_verify(VmaReader *vmar, bool verbose, Error **errp);

debian/patches/pve/0053-pbs-namespace-support.patch

@@ -1,233 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Tue, 26 Apr 2022 16:06:28 +0200
-Subject: [PATCH] pbs: namespace support
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- block/monitor/block-hmp-cmds.c |  1 +
- block/pbs.c                    | 25 +++++++++++++++++++++----
- pbs-restore.c                  | 19 ++++++++++++++++---
- pve-backup.c                   |  6 +++++-
- qapi/block-core.json           |  5 ++++-
- 5 files changed, 47 insertions(+), 9 deletions(-)
-
-diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
-index 4c799f00d9..0502f42be6 100644
---- a/block/monitor/block-hmp-cmds.c
-+++ b/block/monitor/block-hmp-cmds.c
-@@ -1041,6 +1041,7 @@ void coroutine_fn hmp_backup(Monitor *mon, const QDict *qdict)
-         false, NULL, // PBS key_password
-         false, NULL, // PBS master_keyfile
-         false, NULL, // PBS fingerprint
-+        false, NULL, // PBS backup-ns
-         false, NULL, // PBS backup-id
-         false, 0, // PBS backup-time
-         false, false, // PBS use-dirty-bitmap
-diff --git a/block/pbs.c b/block/pbs.c
-index c5eb4d5bad..7471e2ef9d 100644
---- a/block/pbs.c
-+++ b/block/pbs.c
-@@ -14,6 +14,7 @@
- #include <proxmox-backup-qemu.h>
- 
- #define PBS_OPT_REPOSITORY "repository"
-+#define PBS_OPT_NAMESPACE "namespace"
- #define PBS_OPT_SNAPSHOT "snapshot"
- #define PBS_OPT_ARCHIVE "archive"
- #define PBS_OPT_KEYFILE "keyfile"
-@@ -27,6 +28,7 @@ typedef struct {
-     int64_t length;
- 
-     char *repository;
-+    char *namespace;
-     char *snapshot;
-     char *archive;
- } BDRVPBSState;
-@@ -40,6 +42,11 @@ static QemuOptsList runtime_opts = {
-             .type = QEMU_OPT_STRING,
-             .help = "The server address and repository to connect to.",
-         },
-+        {
-+            .name = PBS_OPT_NAMESPACE,
-+            .type = QEMU_OPT_STRING,
-+            .help = "Optional: The snapshot's namespace.",
-+        },
-         {
-             .name = PBS_OPT_SNAPSHOT,
-             .type = QEMU_OPT_STRING,
-@@ -76,7 +83,7 @@ static QemuOptsList runtime_opts = {
- 
- 
- // filename format:
--// pbs:repository=<repo>,snapshot=<snap>,password=<pw>,key_password=<kpw>,fingerprint=<fp>,archive=<archive>
-+// pbs:repository=<repo>,namespace=<ns>,snapshot=<snap>,password=<pw>,key_password=<kpw>,fingerprint=<fp>,archive=<archive>
- static void pbs_parse_filename(const char *filename, QDict *options,
-                                      Error **errp)
- {
-@@ -112,6 +119,7 @@ static int pbs_open(BlockDriverState *bs, QDict *options, int flags,
-     s->archive = g_strdup(qemu_opt_get(opts, PBS_OPT_ARCHIVE));
-     const char *keyfile = qemu_opt_get(opts, PBS_OPT_KEYFILE);
-     const char *password = qemu_opt_get(opts, PBS_OPT_PASSWORD);
-+    const char *namespace = qemu_opt_get(opts, PBS_OPT_NAMESPACE);
-     const char *fingerprint = qemu_opt_get(opts, PBS_OPT_FINGERPRINT);
-     const char *key_password = qemu_opt_get(opts, PBS_OPT_ENCRYPTION_PASSWORD);
- 
-@@ -124,9 +132,12 @@ static int pbs_open(BlockDriverState *bs, QDict *options, int flags,
-     if (!key_password) {
-         key_password = getenv("PBS_ENCRYPTION_PASSWORD");
-     }
-+    if (namespace) {
-+        s->namespace = g_strdup(namespace);
-+    }
- 
-     /* connect to PBS server in read mode */
--    s->conn = proxmox_restore_new(s->repository, s->snapshot, password,
-+    s->conn = proxmox_restore_new_ns(s->repository, s->snapshot, s->namespace, password,
-         keyfile, key_password, fingerprint, &pbs_error);
- 
-     /* invalidates qemu_opt_get char pointers from above */
-@@ -171,6 +182,7 @@ static int pbs_file_open(BlockDriverState *bs, QDict *options, int flags,
- static void pbs_close(BlockDriverState *bs) {
-     BDRVPBSState *s = bs->opaque;
-     g_free(s->repository);
-+    g_free(s->namespace);
-     g_free(s->snapshot);
-     g_free(s->archive);
-     proxmox_restore_disconnect(s->conn);
-@@ -252,8 +264,13 @@ static coroutine_fn int pbs_co_pwritev(BlockDriverState *bs,
- static void pbs_refresh_filename(BlockDriverState *bs)
- {
-     BDRVPBSState *s = bs->opaque;
--    snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s/%s(%s)",
--             s->repository, s->snapshot, s->archive);
-+    if (s->namespace) {
-+        snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s/%s:%s(%s)",
-+                 s->repository, s->namespace, s->snapshot, s->archive);
-+    } else {
-+        snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s/%s(%s)",
-+                 s->repository, s->snapshot, s->archive);
-+    }
- }
- 
- static const char *const pbs_strong_runtime_opts[] = {
-diff --git a/pbs-restore.c b/pbs-restore.c
-index 2f834cf42e..f03d9bab8d 100644
---- a/pbs-restore.c
-+++ b/pbs-restore.c
-@@ -29,7 +29,7 @@
- static void help(void)
- {
-     const char *help_msg =
--        "usage: pbs-restore [--repository <repo>] snapshot archive-name target [command options]\n"
-+        "usage: pbs-restore [--repository <repo>] [--ns namespace] snapshot archive-name target [command options]\n"
-         ;
- 
-     printf("%s", help_msg);
-@@ -77,6 +77,7 @@ int main(int argc, char **argv)
-     Error *main_loop_err = NULL;
-     const char *format = "raw";
-     const char *repository = NULL;
-+    const char *backup_ns = NULL;
-     const char *keyfile = NULL;
-     int verbose = false;
-     bool skip_zero = false;
-@@ -90,6 +91,7 @@ int main(int argc, char **argv)
-             {"verbose", no_argument, 0, 'v'},
-             {"format", required_argument, 0, 'f'},
-             {"repository", required_argument, 0, 'r'},
-+            {"ns", required_argument, 0, 'n'},
-             {"keyfile", required_argument, 0, 'k'},
-             {0, 0, 0, 0}
-         };
-@@ -110,6 +112,9 @@ int main(int argc, char **argv)
-             case 'r':
-                 repository = g_strdup(argv[optind - 1]);
-                 break;
-+            case 'n':
-+                backup_ns = g_strdup(argv[optind - 1]);
-+                break;
-             case 'k':
-                 keyfile = g_strdup(argv[optind - 1]);
-                 break;
-@@ -160,8 +165,16 @@ int main(int argc, char **argv)
-         fprintf(stderr, "connecting to repository '%s'\n", repository);
-     }
-     char *pbs_error = NULL;
--    ProxmoxRestoreHandle *conn = proxmox_restore_new(
--        repository, snapshot, password, keyfile, key_password, fingerprint, &pbs_error);
-+    ProxmoxRestoreHandle *conn = proxmox_restore_new_ns(
-+        repository,
-+        snapshot,
-+        backup_ns,
-+        password,
-+        keyfile,
-+        key_password,
-+        fingerprint,
-+        &pbs_error
-+    );
-     if (conn == NULL) {
-         fprintf(stderr, "restore failed: %s\n", pbs_error);
-         return -1;
-diff --git a/pve-backup.c b/pve-backup.c
-index 9f6c04a512..f6a5f8c785 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -10,6 +10,8 @@
- #include "qapi/qmp/qerror.h"
- #include "qemu/cutils.h"
- 
-+#include <proxmox-backup-qemu.h>
-+
- /* PVE backup state and related function */
- 
- /*
-@@ -535,6 +537,7 @@ UuidInfo coroutine_fn *qmp_backup(
-     bool has_key_password, const char *key_password,
-     bool has_master_keyfile, const char *master_keyfile,
-     bool has_fingerprint, const char *fingerprint,
-+    bool has_backup_ns, const char *backup_ns,
-     bool has_backup_id, const char *backup_id,
-     bool has_backup_time, int64_t backup_time,
-     bool has_use_dirty_bitmap, bool use_dirty_bitmap,
-@@ -674,8 +677,9 @@ UuidInfo coroutine_fn *qmp_backup(
-         firewall_name = "fw.conf";
- 
-         char *pbs_err = NULL;
--        pbs = proxmox_backup_new(
-+        pbs = proxmox_backup_new_ns(
-             backup_file,
-+            has_backup_ns ? backup_ns : NULL,
-             backup_id,
-             backup_time,
-             dump_cb_block_size,
-diff --git a/qapi/block-core.json b/qapi/block-core.json
-index fc8a125451..cc2ead0b75 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -817,6 +817,8 @@
- #
- # @fingerprint: server cert fingerprint (optional for format 'pbs')
- #
-+# @backup-ns: backup namespace (required for format 'pbs')
-+#
- # @backup-id: backup ID (required for format 'pbs')
- #
- # @backup-time: backup timestamp (Unix epoch, required for format 'pbs')
-@@ -836,6 +838,7 @@
-                                     '*key-password': 'str',
-                                     '*master-keyfile': 'str',
-                                     '*fingerprint': 'str',
-+                                    '*backup-ns': 'str',
-                                     '*backup-id': 'str',
-                                     '*backup-time': 'int',
-                                     '*use-dirty-bitmap': 'bool',
-@@ -3282,7 +3285,7 @@
- { 'struct': 'BlockdevOptionsPbs',
-   'data': { 'repository': 'str', 'snapshot': 'str', 'archive': 'str',
-             '*keyfile': 'str', '*password': 'str', '*fingerprint': 'str',
--            '*key_password': 'str' } }
-+            '*key_password': 'str', '*namespace': 'str' } }
- 
- ##
- # @BlockdevOptionsNVMe:

debian/patches/pve/0057-PVE-Backup-create-jobs-correctly-cancel-in-error-sce.patch

@@ -1,59 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fabian Ebner <f.ebner@proxmox.com>
-Date: Wed, 25 May 2022 13:59:37 +0200
-Subject: [PATCH] PVE-Backup: create jobs: correctly cancel in error scenario
-
-The first call to job_cancel_sync() will cancel and free all jobs in
-the transaction, so ensure that it's called only once and get rid of
-the job_unref() that would operate on freed memory.
-
-It's also necessary to NULL backup_state.pbs in the error scenario,
-because a subsequent backup_cancel QMP call (as happens in PVE when
-the backup QMP command fails) would try to call proxmox_backup_abort()
-and run into a segfault.
-
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- pve-backup.c | 10 ++++++++--
- 1 file changed, 8 insertions(+), 2 deletions(-)
-
-diff --git a/pve-backup.c b/pve-backup.c
-index f6a5f8c785..5bed6f4014 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -506,6 +506,11 @@ static void create_backup_jobs_bh(void *opaque) {
-     }
- 
-     if (*errp) {
-+        /*
-+         * It's enough to cancel one job in the transaction, the rest will
-+         * follow automatically.
-+         */
-+        bool canceled = false;
-         l = backup_state.di_list;
-         while (l) {
-             PVEBackupDevInfo *di = (PVEBackupDevInfo *)l->data;
-@@ -516,12 +521,12 @@ static void create_backup_jobs_bh(void *opaque) {
-                 di->target = NULL;
-             }
- 
--            if (di->job) {
-+            if (!canceled && di->job) {
-                 AioContext *ctx = di->job->job.aio_context;
-                 aio_context_acquire(ctx);
-                 job_cancel_sync(&di->job->job, true);
--                job_unref(&di->job->job);
-                 aio_context_release(ctx);
-+                canceled = true;
-             }
-         }
-     }
-@@ -947,6 +952,7 @@ err:
- 
-     if (pbs) {
-         proxmox_backup_disconnect(pbs);
-+        backup_state.pbs = NULL;
-     }
- 
-     if (backup_dir) {

debian/patches/pve/0058-PVE-Backup-ensure-jobs-in-di_list-are-referenced.patch

@@ -1,76 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fabian Ebner <f.ebner@proxmox.com>
-Date: Wed, 25 May 2022 13:59:38 +0200
-Subject: [PATCH] PVE-Backup: ensure jobs in di_list are referenced
-
-Ensures that qmp_backup_cancel doesn't pick a job that's already been
-freed. With unlucky timings it seems possible that:
-1. job_exit -> job_completed -> job_finalize_single starts
-2. pvebackup_co_complete_stream gets spawned in completion callback
-3. job finalize_single finishes -> job's refcount hits zero -> job is
-   freed
-4. qmp_backup_cancel comes in and locks backup_state.backup_mutex
-   before pvebackup_co_complete_stream can remove the job from the
-   di_list
-5. qmp_backup_cancel will pick a job that's already been freed
-
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- pve-backup.c | 25 ++++++++++++++++++++-----
- 1 file changed, 20 insertions(+), 5 deletions(-)
-
-diff --git a/pve-backup.c b/pve-backup.c
-index 5bed6f4014..0c34428713 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -316,6 +316,14 @@ static void coroutine_fn pvebackup_co_complete_stream(void *opaque)
-         }
-     }
- 
-+    if (di->job) {
-+        AioContext *ctx = di->job->job.aio_context;
-+        aio_context_acquire(ctx);
-+        job_unref(&di->job->job);
-+        di->job = NULL;
-+        aio_context_release(ctx);
-+    }
-+
-     // remove self from job list
-     backup_state.di_list = g_list_remove(backup_state.di_list, di);
- 
-@@ -491,9 +499,12 @@ static void create_backup_jobs_bh(void *opaque) {
-             bitmap_mode, false, NULL, &perf, BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
-             JOB_DEFAULT, pvebackup_complete_cb, di, backup_state.txn, &local_err);
- 
--        aio_context_release(aio_context);
--
-         di->job = job;
-+        if (job) {
-+            job_ref(&job->job);
-+        }
-+
-+        aio_context_release(aio_context);
- 
-         if (!job || local_err) {
-             error_setg(errp, "backup_job_create failed: %s",
-@@ -521,12 +532,16 @@ static void create_backup_jobs_bh(void *opaque) {
-                 di->target = NULL;
-             }
- 
--            if (!canceled && di->job) {
-+            if (di->job) {
-                 AioContext *ctx = di->job->job.aio_context;
-                 aio_context_acquire(ctx);
--                job_cancel_sync(&di->job->job, true);
-+                if (!canceled) {
-+                    job_cancel_sync(&di->job->job, true);
-+                    canceled = true;
-+                }
-+                job_unref(&di->job->job);
-+                di->job = NULL;
-                 aio_context_release(ctx);
--                canceled = true;
-             }
-         }
-     }

debian/patches/pve/0059-PVE-Backup-avoid-segfault-issues-upon-backup-cancel.patch

@@ -1,120 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fabian Ebner <f.ebner@proxmox.com>
-Date: Wed, 25 May 2022 13:59:39 +0200
-Subject: [PATCH] PVE-Backup: avoid segfault issues upon backup-cancel
-
-When canceling a backup in PVE via a signal it's easy to run into a
-situation where the job is already failing when the backup_cancel QMP
-command comes in. With a bit of unlucky timing on top, it can happen
-that job_exit() runs between schedulung of job_cancel_bh() and
-execution of job_cancel_bh(). But job_cancel_sync() does not expect
-that the job is already finalized (in fact, the job might've been
-freed already, but even if it isn't, job_cancel_sync() would try to
-deref job->txn which would be NULL at that point).
-
-It is not possible to simply use the job_cancel() (which is advertised
-as being async but isn't in all cases) in qmp_backup_cancel() for the
-same reason job_cancel_sync() cannot be used. Namely, because it can
-invoke job_finish_sync() (which uses AIO_WAIT_WHILE and thus hangs if
-called from a coroutine). This happens when there's multiple jobs in
-the transaction and job->deferred_to_main_loop is true (is set before
-scheduling job_exit()) or if the job was not started yet.
-
-Fix the issue by selecting the job to cancel in job_cancel_bh() itself
-using the first job that's not completed yet. This is not necessarily
-the first job in the list, because pvebackup_co_complete_stream()
-might not yet have removed a completed job when job_cancel_bh() runs.
-
-An alternative would be to continue using only the first job and
-checking against JOB_STATUS_CONCLUDED or JOB_STATUS_NULL to decide if
-it's still necessary and possible to cancel, but the approach with
-using the first non-completed job seemed more robust.
-
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- pve-backup.c | 61 +++++++++++++++++++++++++++++++++-------------------
- 1 file changed, 39 insertions(+), 22 deletions(-)
-
-diff --git a/pve-backup.c b/pve-backup.c
-index 0c34428713..2e22030eec 100644
---- a/pve-backup.c
-+++ b/pve-backup.c
-@@ -355,15 +355,42 @@ static void pvebackup_complete_cb(void *opaque, int ret)
- 
- /*
-  * job_cancel(_sync) does not like to be called from coroutines, so defer to
-- * main loop processing via a bottom half.
-+ * main loop processing via a bottom half. Assumes that caller holds
-+ * backup_mutex.
-  */
- static void job_cancel_bh(void *opaque) {
-     CoCtxData *data = (CoCtxData*)opaque;
--    Job *job = (Job*)data->data;
--    AioContext *job_ctx = job->aio_context;
--    aio_context_acquire(job_ctx);
--    job_cancel_sync(job, true);
--    aio_context_release(job_ctx);
-+
-+    /*
-+     * Be careful to pick a valid job to cancel:
-+     * 1. job_cancel_sync() does not expect the job to be finalized already.
-+     * 2. job_exit() might run between scheduling and running job_cancel_bh()
-+     *    and pvebackup_co_complete_stream() might not have removed the job from
-+     *    the list yet (in fact, cannot, because it waits for the backup_mutex).
-+     * Requiring !job_is_completed() ensures that no finalized job is picked.
-+     */
-+    GList *bdi = g_list_first(backup_state.di_list);
-+    while (bdi) {
-+        if (bdi->data) {
-+            BlockJob *bj = ((PVEBackupDevInfo *)bdi->data)->job;
-+            if (bj) {
-+                Job *job = &bj->job;
-+                if (!job_is_completed(job)) {
-+                    AioContext *job_ctx = job->aio_context;
-+                    aio_context_acquire(job_ctx);
-+                    job_cancel_sync(job, true);
-+                    aio_context_release(job_ctx);
-+                    /*
-+                     * It's enough to cancel one job in the transaction, the
-+                     * rest will follow automatically.
-+                     */
-+                    break;
-+                }
-+            }
-+        }
-+        bdi = g_list_next(bdi);
-+    }
-+
-     aio_co_enter(data->ctx, data->co);
- }
- 
-@@ -384,22 +411,12 @@ void coroutine_fn qmp_backup_cancel(Error **errp)
-         proxmox_backup_abort(backup_state.pbs, "backup canceled");
-     }
- 
--    /* it's enough to cancel one job in the transaction, the rest will follow
--     * automatically */
--    GList *bdi = g_list_first(backup_state.di_list);
--    BlockJob *cancel_job = bdi && bdi->data ?
--        ((PVEBackupDevInfo *)bdi->data)->job :
--        NULL;
--
--    if (cancel_job) {
--        CoCtxData data = {
--            .ctx = qemu_get_current_aio_context(),
--            .co = qemu_coroutine_self(),
--            .data = &cancel_job->job,
--        };
--        aio_bh_schedule_oneshot(data.ctx, job_cancel_bh, &data);
--        qemu_coroutine_yield();
--    }
-+    CoCtxData data = {
-+        .ctx = qemu_get_current_aio_context(),
-+        .co = qemu_coroutine_self(),
-+    };
-+    aio_bh_schedule_oneshot(data.ctx, job_cancel_bh, &data);
-+    qemu_coroutine_yield();
- 
-     qemu_co_mutex_unlock(&backup_state.backup_mutex);
- }

debian/patches/pve/0060-vma-create-support-64KiB-unaligned-input-images.patch

@@ -1,57 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fabian Ebner <f.ebner@proxmox.com>
-Date: Wed, 22 Jun 2022 10:45:11 +0200
-Subject: [PATCH] vma: create: support 64KiB-unaligned input images
-
-which fixes backing up templates with such disks in PVE, for example
-efitype=4m EFI disks on a file-based storage (size = 540672).
-
-If there is not enough left to read, blk_co_preadv will return -EIO,
-so limit the size in the last iteration.
-
-For writing, an unaligned end is already handled correctly.
-
-The call to memset is not strictly necessary, because writing also
-checks that it doesn't write data beyond the end of the image. But
-there are two reasons to do it:
-1. It's cleaner that way.
-2. It allows detecting when the final piece is all zeroes, which might
-   not happen if the buffer still contains data from the previous
-   iteration.
-
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- vma.c | 12 ++++++++++--
- 1 file changed, 10 insertions(+), 2 deletions(-)
-
-diff --git a/vma.c b/vma.c
-index e6e9ffc7fe..304f02bc84 100644
---- a/vma.c
-+++ b/vma.c
-@@ -548,7 +548,7 @@ static void coroutine_fn backup_run(void *opaque)
-     struct iovec iov;
-     QEMUIOVector qiov;
- 
--    int64_t start, end;
-+    int64_t start, end, readlen;
-     int ret = 0;
- 
-     unsigned char *buf = blk_blockalign(job->target, VMA_CLUSTER_SIZE);
-@@ -562,8 +562,16 @@ static void coroutine_fn backup_run(void *opaque)
-         iov.iov_len = VMA_CLUSTER_SIZE;
-         qemu_iovec_init_external(&qiov, &iov, 1);
- 
-+        if (start + 1 == end) {
-+            memset(buf, 0, VMA_CLUSTER_SIZE);
-+            readlen = job->len - start * VMA_CLUSTER_SIZE;
-+            assert(readlen > 0 && readlen <= VMA_CLUSTER_SIZE);
-+        } else {
-+            readlen = VMA_CLUSTER_SIZE;
-+        }
-+
-         ret = blk_co_preadv(job->target, start * VMA_CLUSTER_SIZE,
--                            VMA_CLUSTER_SIZE, &qiov, 0);
-+                            readlen, &qiov, 0);
-         if (ret < 0) {
-             vma_writer_set_error(job->vmaw, "read error", -1);
-             goto out;