bump version to 9.0.2-5

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
 	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 +1,445 @@
+pve-qemu-kvm (9.0.2-5) bookworm; urgency=medium
+
+  * async snapshot: explicitly specify raw format when loading the VM state
+    file
+
+  * vma create: rework CLI parameters for passing disk to a more structured
+    style and use that to allow explicitly specifying the format
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 24 Jan 2025 14:59:17 +0100
+
+pve-qemu-kvm (9.0.2-4) bookworm; urgency=medium
+
+  * async snapshot: ensure any dynamic vCPU-throttling applied for
+    auto-converge gets always disabled again after finishing the snapshot.
+
+ -- Proxmox Support Team <support@proxmox.com>  Sun, 10 Nov 2024 11:23:09 +0100
+
+pve-qemu-kvm (9.0.2-3) bookworm; urgency=medium
+
+  * pick up fix for VirtIO PCI regressions
+
+  * pick up stable fixes for 9.0, including fixes for VirtIO-net, ARM and
+    x86(_64) emulation, CVEs to harden NBD server against malicious clients,
+    as well as a few others (VNC, physmem, Intel IOMMU, ...).
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 06 Sep 2024 16:21:42 +0200
+
+pve-qemu-kvm (9.0.2-2) bookworm; urgency=medium
+
+  * actually update submodule to QEMU 9.0.2. The previous release was still
+    based on 9.0.0 by mistake.
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 07 Aug 2024 10:16:01 +0200
+
+pve-qemu-kvm (9.0.2-1) bookworm; urgency=medium
+
+  * update submodule and patches to QEMU 9.0.2. While our version had most
+    stable fixes included already, there are new fixes for VirtIO and VGA
+    display screen blanking (#4786)
+
+  * backport fix for a regression with the LSI-53c895a controller and one for
+    the boot order getting ignored for USB storage
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 29 Jul 2024 18:59:40 +0200
+
+pve-qemu-kvm (9.0.0-6) bookworm; urgency=medium
+
+  * fix a regression in the zeroinit block driver that prevented importing and
+    cloning disks to RBD storages which are not using the krbd setting
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 08 Jul 2024 16:11:15 +0200
+
+pve-qemu-kvm (9.0.0-5) bookworm; urgency=medium
+
+  * backport fix for CVE-2024-4467 to prevent malicious qcow2 image files from
+    already causing bad effects if being queried via 'qemu-img info'. For
+    Proxmox VE, this is an additional safe guard, as currently it directly
+    creates and manages the qcow2 images used by VMs and does not allow
+    unprivileged users to import them
+
+  * fix #4726: code cleanup: avoid superfluous check in vma backup code
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 03 Jul 2024 13:13:35 +0200
+
+pve-qemu-kvm (9.0.0-4) bookworm; urgency=medium
+
+  * fix crash after saving a snapshot without including VM state when a VirtIO
+    block device with iothread is configured.
+
+  * fix edge case in error handling when opening a block device from PBS fails
+
+  * minor code cleanup in backup code
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 01 Jul 2024 11:26:11 +0200
+
+pve-qemu-kvm (9.0.0-3) bookworm; urgency=medium
+
+  * fix crash when doing resize after hotplugging a disk using io_uring
+
+  * fix some minor issues in software CPU emulation (i.e. non-KVM) for ARM and
+    x86(_64)
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 29 May 2024 15:55:44 +0200
+
+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 (8.1.5-6) bookworm; urgency=medium
+
+  * fix #5409: backup: fix copy-before-write timeout
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 29 Apr 2024 16:39:38 +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"
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 22 Nov 2022 09:21:06 +0100
+
+pve-qemu-kvm (7.1.0-3) bullseye; urgency=medium
+
+  * init: daemonize: defuse PID file resolve error to a warning at max, fixing
+    some usecases that regressed with 7.1, like tracking start up in our
+    file-restore VM.
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 28 Oct 2022 10:27:49 +0200
+
+pve-qemu-kvm (7.1.0-2) bullseye; urgency=medium
+
+  * fix an issue with error handling in async backup code
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 18 Oct 2022 15:33:44 +0200
+
+pve-qemu-kvm (7.1.0-1) bullseye; urgency=medium
+
+  * update to QEMU stable release 7.1.0
+
+  * add fix for io_uring_register_ring_fd from upstream
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 14 Oct 2022 14:54:09 +0200
+
+pve-qemu-kvm (7.0.0-4) bullseye; urgency=medium
+
+  * add revision to version output
+
+  * PVE Backup: allow passing max-workers performance setting
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 10 Oct 2022 11:55:37 +0200
+
+pve-qemu-kvm (7.0.0-3) bullseye; urgency=medium
+
+  * savevm-async: avoid segfault when aborting snapshot creation task
+
+  * savevm-async: set SAVE_STATE_DONE when closing state file was successful
+    allowing one to start a new snapshot task after aborting one.
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 30 Aug 2022 12:54:03 +0200
+
+pve-qemu-kvm (7.0.0-2) bullseye; urgency=medium
+
+  * backport "io_uring: fix short read slow path"
+
+  * backport "e1000: set RX descriptor status in a separate operation"
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 20 Jul 2022 09:17:07 +0200
+
+pve-qemu-kvm (7.0.0-1) bullseye; urgency=medium
+
+  * update to QEMU stable release 7.0.0
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 30 Jun 2022 11:07:37 +0200
+
 pve-qemu-kvm (6.2.0-11) bullseye; urgency=medium
 
   * add 'namespace' to BlockdevOptionsPbs for live-restore support

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
@@ -57,7 +55,6 @@ 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),
@@ -65,8 +62,8 @@ Depends: ceph-common (>= 0.48),
          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 +71,17 @@ 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

@@ -27,19 +27,21 @@ 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 ++++++++++++-
- include/block/block_int.h        |  4 +-
- qapi/block-core.json             | 29 ++++++++--
- tests/unit/test-block-iothread.c |  4 +-
- 5 files changed, 145 insertions(+), 29 deletions(-)
+ block/mirror.c                         | 99 ++++++++++++++++++++------
+ blockdev.c                             | 38 +++++++++-
+ include/block/block_int-global-state.h |  4 +-
+ qapi/block-core.json                   | 25 ++++++-
+ tests/unit/test-block-iothread.c       |  4 +-
+ 5 files changed, 142 insertions(+), 28 deletions(-)
 
 diff --git a/block/mirror.c b/block/mirror.c
-index efec2c7674..f7804638f9 100644
+index 1bdce3b657..0c5c72df2e 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -50,7 +50,7 @@ typedef struct MirrorBlockJob {
+@@ -51,7 +51,7 @@ typedef struct MirrorBlockJob {
      BlockDriverState *to_replace;
      /* Used to block operations on the drive-mirror-replace target */
      Error *replace_blocker;
@@ -48,7 +50,7 @@ index efec2c7674..f7804638f9 100644
      BlockMirrorBackingMode backing_mode;
      /* Whether the target image requires explicit zero-initialization */
      bool zero_target;
-@@ -64,6 +64,8 @@ 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 efec2c7674..f7804638f9 100644
      BdrvDirtyBitmap *dirty_bitmap;
      BdrvDirtyBitmapIter *dbi;
      uint8_t *buf;
-@@ -695,7 +697,8 @@ 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 efec2c7674..f7804638f9 100644
          BlockDriverState *unfiltered_target = bdrv_skip_filters(target_bs);
  
          if (bdrv_cow_bs(unfiltered_target) != backing) {
-@@ -800,6 +803,16 @@ static void mirror_abort(Job *job)
+@@ -819,6 +822,16 @@ static void mirror_abort(Job *job)
      assert(ret == 0);
  }
  
@@ -84,7 +86,7 @@ index efec2c7674..f7804638f9 100644
  static void coroutine_fn mirror_throttle(MirrorBlockJob *s)
  {
      int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-@@ -979,7 +992,8 @@ 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 efec2c7674..f7804638f9 100644
          ret = mirror_dirty_init(s);
          if (ret < 0 || job_is_cancelled(&s->common.job)) {
              goto immediate_exit;
-@@ -1221,6 +1235,7 @@ 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 efec2c7674..f7804638f9 100644
          .pause                  = mirror_pause,
          .complete               = mirror_complete,
          .cancel                 = mirror_cancel,
-@@ -1237,6 +1252,7 @@ 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 efec2c7674..f7804638f9 100644
          .pause                  = mirror_pause,
          .complete               = mirror_complete,
          .cancel                 = commit_active_cancel,
-@@ -1602,7 +1618,10 @@ static BlockJob *mirror_start_job(
+@@ -1714,7 +1730,10 @@ static BlockJob *mirror_start_job(
                               BlockCompletionFunc *cb,
                               void *opaque,
                               const BlockJobDriver *driver,
@@ -122,11 +124,12 @@ index efec2c7674..f7804638f9 100644
                               bool auto_complete, const char *filter_node_name,
                               bool is_mirror, MirrorCopyMode copy_mode,
                               Error **errp)
-@@ -1614,10 +1633,39 @@ 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);
 +    if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
 +        error_setg(errp, "Sync mode '%s' not supported",
 +                   MirrorSyncMode_str(sync_mode));
@@ -147,8 +150,8 @@ index efec2c7674..f7804638f9 100644
 +                   "sync mode '%s' is not compatible with bitmaps",
 +                   MirrorSyncMode_str(sync_mode));
 +        return NULL;
-+    }
-+
+     }
+ 
 +    if (bitmap) {
 +        if (granularity) {
 +            error_setg(errp, "granularity (%d)"
@@ -158,13 +161,12 @@ index efec2c7674..f7804638f9 100644
 +        }
 +        granularity = bdrv_dirty_bitmap_granularity(bitmap);
 +    } else if (granularity == 0) {
-         granularity = bdrv_get_default_bitmap_granularity(target);
-     }
--
++        granularity = bdrv_get_default_bitmap_granularity(target);
++    }
      assert(is_power_of_2(granularity));
  
      if (buf_size < 0) {
-@@ -1755,7 +1803,9 @@ 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 efec2c7674..f7804638f9 100644
 +    s->bitmap_mode = bitmap_mode;
      s->backing_mode = backing_mode;
      s->zero_target = zero_target;
-     s->copy_mode = copy_mode;
-@@ -1776,6 +1826,18 @@ 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 efec2c7674..f7804638f9 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,
-@@ -1853,6 +1915,9 @@ fail:
+@@ -1979,6 +2041,9 @@ fail:
          if (s->dirty_bitmap) {
              bdrv_release_dirty_bitmap(s->dirty_bitmap);
          }
@@ -204,7 +206,7 @@ index efec2c7674..f7804638f9 100644
          job_early_fail(&s->common.job);
      }
  
-@@ -1870,29 +1935,23 @@ 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,
@@ -221,14 +223,20 @@ index efec2c7674..f7804638f9 100644
 -    bool is_none_mode;
      BlockDriverState *base;
  
+     GLOBAL_STATE_CODE();
+ 
 -    if ((mode == MIRROR_SYNC_MODE_INCREMENTAL) ||
 -        (mode == MIRROR_SYNC_MODE_BITMAP)) {
 -        error_setg(errp, "Sync mode '%s' not supported",
 -                   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,
@@ -239,7 +247,7 @@ index efec2c7674..f7804638f9 100644
  }
  
  BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
-@@ -1917,7 +1976,8 @@ 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,
@@ -250,33 +258,32 @@ index efec2c7674..f7804638f9 100644
                       errp);
      if (!job) {
 diff --git a/blockdev.c b/blockdev.c
-index b35072644e..9940116fe0 100644
+index 4c33c3f5f0..f3e508a6a7 100644
 --- a/blockdev.c
 +++ b/blockdev.c
-@@ -2956,6 +2956,10 @@ 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,
-@@ -2975,6 +2979,7 @@ 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;
-@@ -3029,6 +3034,29 @@ 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;
@@ -299,53 +306,53 @@ index b35072644e..9940116fe0 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);
-@@ -3075,8 +3103,8 @@ 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);
  }
-@@ -3221,6 +3249,8 @@ 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,
-@@ -3242,6 +3272,8 @@ 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,
-@@ -3291,7 +3323,8 @@ 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.h b/include/block/block_int.h
-index f4c75e8ba9..ee0aeb1414 100644
---- a/include/block/block_int.h
-+++ b/include/block/block_int.h
-@@ -1287,7 +1287,9 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
+diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h
+index eb2d92a226..f0c642b194 100644
+--- a/include/block/block_int-global-state.h
++++ b/include/block/block_int-global-state.h
+@@ -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,
@@ -357,31 +364,26 @@ index f4c75e8ba9..ee0aeb1414 100644
                    BlockdevOnError on_source_error,
                    BlockdevOnError on_target_error,
 diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 1d3dd9cb48..da5dca1e3b 100644
+index b179d65520..905da8be72 100644
 --- a/qapi/block-core.json
 +++ b/qapi/block-core.json
-@@ -1995,10 +1995,19 @@
- #        (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).
-@@ -2036,7 +2045,9 @@
+ # @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',
@@ -392,28 +394,23 @@ index 1d3dd9cb48..da5dca1e3b 100644
              '*speed': 'int', '*granularity': 'uint32',
              '*buf-size': 'int', '*on-source-error': 'BlockdevOnError',
              '*on-target-error': 'BlockdevOnError',
-@@ -2308,10 +2319,19 @@
- #        (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
-@@ -2360,7 +2380,8 @@
+ # @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',
@@ -424,10 +421,10 @@ index 1d3dd9cb48..da5dca1e3b 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 aea660aeed..22b9770a3e 100644
+index 3766d5de6b..afa44cbd34 100644
 --- a/tests/unit/test-block-iothread.c
 +++ b/tests/unit/test-block-iothread.c
-@@ -626,8 +626,8 @@ 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,
@@ -437,4 +434,4 @@ index aea660aeed..22b9770a3e 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 f7804638f9..4f5f74e2cf 100644
+index 0c5c72df2e..37fee3fa25 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -672,8 +672,6 @@ 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 f7804638f9..4f5f74e2cf 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);
-@@ -781,6 +779,18 @@ static int mirror_exit_common(Job *job)
-     blk_set_perm(bjob->blk, 0, BLK_PERM_ALL, &error_abort);
-     blk_insert_bs(bjob->blk, mirror_top_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 f7804638f9..4f5f74e2cf 100644
      bs_opaque->job = NULL;
  
      bdrv_drained_end(src);
-@@ -1643,10 +1653,6 @@ 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 f7804638f9..4f5f74e2cf 100644
          }
      } else if (bitmap) {
          error_setg(errp,
-@@ -1663,6 +1669,12 @@ 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 9940116fe0..b113e57d68 100644
+index f3e508a6a7..37b8437f3e 100644
 --- a/blockdev.c
 +++ b/blockdev.c
-@@ -3055,6 +3055,9 @@ 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 9940116fe0..b113e57d68 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 4f5f74e2cf..7024f3bbf0 100644
+index 37fee3fa25..6b3cce1007 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -785,8 +785,8 @@ 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 4f5f74e2cf..7024f3bbf0 100644
          }
      }
      bdrv_release_dirty_bitmap(s->dirty_bitmap);
-@@ -1843,11 +1843,8 @@ 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 4f5f74e2cf..7024f3bbf0 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 7024f3bbf0..6211ff22fc 100644
+index 6b3cce1007..2f1223852b 100644
 --- a/block/mirror.c
 +++ b/block/mirror.c
-@@ -1643,31 +1643,13 @@ 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 7024f3bbf0..6211ff22fc 100644
  
          if (bitmap_mode != BITMAP_SYNC_MODE_NEVER) {
 diff --git a/blockdev.c b/blockdev.c
-index b113e57d68..4be0863050 100644
+index 37b8437f3e..ed8198f351 100644
 --- a/blockdev.c
 +++ b/blockdev.c
-@@ -3034,7 +3034,36 @@ 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 b113e57d68..4be0863050 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 12d395d62d..b182943324 100644
+index 965f5d5450..e04bd059b6 100644
 --- a/include/monitor/monitor.h
 +++ b/include/monitor/monitor.h
 @@ -16,6 +16,7 @@ extern QemuOptsList qemu_mon_opts;
@@ -60,7 +60,7 @@ index 12d395d62d..b182943324 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 3da3f86c6a..9953e0cd2d 100644
+index 252de85681..8db28f9272 100644
 --- a/monitor/monitor-internal.h
 +++ b/monitor/monitor-internal.h
 @@ -151,6 +151,13 @@ typedef struct {
@@ -78,10 +78,10 @@ index 3da3f86c6a..9953e0cd2d 100644
  
  /**
 diff --git a/monitor/monitor.c b/monitor/monitor.c
-index 21c7a68758..ad9813567a 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 21c7a68758..ad9813567a 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:
@@ -144,10 +144,10 @@ 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 d378bccac7..fb8936e7cd 100644
+index 176b549473..790bb7d1da 100644
 --- a/qapi/qmp-dispatch.c
 +++ b/qapi/qmp-dispatch.c
-@@ -118,16 +118,28 @@ typedef struct QmpDispatchBH {
+@@ -117,16 +117,28 @@ typedef struct QmpDispatchBH {
      QObject **ret;
      Error **errp;
      Coroutine *co;
@@ -180,19 +180,19 @@ index d378bccac7..fb8936e7cd 100644
      aio_co_wake(data->co);
  }
  
-@@ -232,6 +244,7 @@ QDict *qmp_dispatch(const QmpCommandList *cmds, QObject *request,
+@@ -253,6 +265,7 @@ 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 d058a2a00d..3290b58120 100644
+index afa477aae6..d3ff124bf3 100644
 --- a/stubs/monitor-core.c
 +++ b/stubs/monitor-core.c
-@@ -13,6 +13,11 @@ Monitor *monitor_set_cur(Coroutine *co, Monitor *mon)
+@@ -12,6 +12,11 @@ Monitor *monitor_set_cur(Coroutine *co, Monitor *mon)
      return NULL;
  }
  

debian/patches/extra/0002-monitor-hmp-add-support-for-flag-argument-with-value.patch

@@ -1,55 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 1 Sep 2021 16:51:04 +0200
-Subject: [PATCH] monitor/hmp: add support for flag argument with value
-
-Adds support for the "-xS" parameter type, where "-x" denotes a flag
-name and the "S" suffix indicates that this flag is supposed to take an
-arbitrary string parameter.
-
-These parameters are always optional, the entry in the qdict will be
-omitted if the flag is not given.
-
-Reviewed-by: Eric Blake <eblake@redhat.com>
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- monitor/hmp.c | 17 ++++++++++++++++-
- 1 file changed, 16 insertions(+), 1 deletion(-)
-
-diff --git a/monitor/hmp.c b/monitor/hmp.c
-index b20737e63c..b29dbb1833 100644
---- a/monitor/hmp.c
-+++ b/monitor/hmp.c
-@@ -981,6 +981,7 @@ static QDict *monitor_parse_arguments(Monitor *mon,
-             {
-                 const char *tmp = p;
-                 int skip_key = 0;
-+                int ret;
-                 /* option */
- 
-                 c = *typestr++;
-@@ -1003,8 +1004,22 @@ static QDict *monitor_parse_arguments(Monitor *mon,
-                     }
-                     if (skip_key) {
-                         p = tmp;
-+                    } else if (*typestr == 'S') {
-+                        /* has option with string value */
-+                        typestr++;
-+                        tmp = p++;
-+                        while (qemu_isspace(*p)) {
-+                            p++;
-+                        }
-+                        ret = get_str(buf, sizeof(buf), &p);
-+                        if (ret < 0) {
-+                            monitor_printf(mon, "%s: value expected for -%c\n",
-+                                           cmd->name, *tmp);
-+                            goto fail;
-+                        }
-+                        qdict_put_str(qdict, key, buf);
-                     } else {
--                        /* has option */
-+                        /* has boolean option */
-                         p++;
-                         qdict_put_bool(qdict, key, true);
-                     }

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-monitor-refactor-set-expire_password-and-allow-VNC-d.patch

@@ -1,477 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefan Reiter <s.reiter@proxmox.com>
-Date: Wed, 25 Aug 2021 11:14:13 +0200
-Subject: [PATCH] monitor: refactor set/expire_password and allow VNC display
- id
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-It is possible to specify more than one VNC server on the command line,
-either with an explicit ID or the auto-generated ones à la "default",
-"vnc2", "vnc3", ...
-
-It is not possible to change the password on one of these extra VNC
-displays though. Fix this by adding a "display" parameter to the
-"set_password" and "expire_password" QMP and HMP commands.
-
-For HMP, the display is specified using the "-d" value flag.
-
-For QMP, the schema is updated to explicitly express the supported
-variants of the commands with protocol-discriminated unions.
-
-Suggested-by: Eric Blake <eblake@redhat.com>
-Suggested-by: Markus Armbruster <armbru@redhat.com>
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- hmp-commands.hx    |  24 ++++---
- monitor/hmp-cmds.c |  57 +++++++++++++++-
- monitor/qmp-cmds.c |  62 ++++++-----------
- qapi/ui.json       | 165 ++++++++++++++++++++++++++++++++++++++-------
- 4 files changed, 231 insertions(+), 77 deletions(-)
-
-diff --git a/hmp-commands.hx b/hmp-commands.hx
-index 70a9136ac2..5efb47fc32 100644
---- a/hmp-commands.hx
-+++ b/hmp-commands.hx
-@@ -1514,33 +1514,35 @@ ERST
- 
-     {
-         .name       = "set_password",
--        .args_type  = "protocol:s,password:s,connected:s?",
--        .params     = "protocol password action-if-connected",
-+        .args_type  = "protocol:s,password:s,display:-dS,connected:s?",
-+        .params     = "protocol password [-d display] [action-if-connected]",
-         .help       = "set spice/vnc password",
-         .cmd        = hmp_set_password,
-     },
- 
- SRST
--``set_password [ vnc | spice ] password [ action-if-connected ]``
--  Change spice/vnc password.  *action-if-connected* specifies what
--  should happen in case a connection is established: *fail* makes the
--  password change fail.  *disconnect* changes the password and
-+``set_password [ vnc | spice ] password [ -d display ] [ action-if-connected ]``
-+  Change spice/vnc password.  *display* can be used with 'vnc' to specify
-+  which display to set the password on.  *action-if-connected* specifies
-+  what should happen in case a connection is established: *fail* makes
-+  the password change fail.  *disconnect* changes the password and
-   disconnects the client.  *keep* changes the password and keeps the
-   connection up.  *keep* is the default.
- ERST
- 
-     {
-         .name       = "expire_password",
--        .args_type  = "protocol:s,time:s",
--        .params     = "protocol time",
-+        .args_type  = "protocol:s,time:s,display:-dS",
-+        .params     = "protocol time [-d display]",
-         .help       = "set spice/vnc password expire-time",
-         .cmd        = hmp_expire_password,
-     },
- 
- SRST
--``expire_password [ vnc | spice ]`` *expire-time*
--  Specify when a password for spice/vnc becomes
--  invalid. *expire-time* accepts:
-+``expire_password [ vnc | spice ] expire-time [ -d display ]``
-+  Specify when a password for spice/vnc becomes invalid.
-+  *display* behaves the same as in ``set_password``.
-+  *expire-time* accepts:
- 
-   ``now``
-     Invalidate password instantly.
-diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
-index 9c91bf93e9..2e91ccb738 100644
---- a/monitor/hmp-cmds.c
-+++ b/monitor/hmp-cmds.c
-@@ -1384,10 +1384,41 @@ void hmp_set_password(Monitor *mon, const QDict *qdict)
- {
-     const char *protocol  = qdict_get_str(qdict, "protocol");
-     const char *password  = qdict_get_str(qdict, "password");
-+    const char *display = qdict_get_try_str(qdict, "display");
-     const char *connected = qdict_get_try_str(qdict, "connected");
-     Error *err = NULL;
-+    DisplayProtocol proto;
- 
--    qmp_set_password(protocol, password, !!connected, connected, &err);
-+    SetPasswordOptions opts = {
-+        .password = g_strdup(password),
-+        .u.vnc.display = NULL,
-+    };
-+
-+    proto = qapi_enum_parse(&DisplayProtocol_lookup, protocol,
-+                            DISPLAY_PROTOCOL_VNC, &err);
-+    if (err) {
-+        hmp_handle_error(mon, err);
-+        return;
-+    }
-+    opts.protocol = proto;
-+
-+    if (proto == DISPLAY_PROTOCOL_VNC) {
-+        opts.u.vnc.has_display = !!display;
-+        opts.u.vnc.display = g_strdup(display);
-+    } else if (proto == DISPLAY_PROTOCOL_SPICE) {
-+        opts.u.spice.has_connected = !!connected;
-+        opts.u.spice.connected =
-+            qapi_enum_parse(&SetPasswordAction_lookup, connected,
-+                            SET_PASSWORD_ACTION_KEEP, &err);
-+        if (err) {
-+            hmp_handle_error(mon, err);
-+            return;
-+        }
-+    }
-+
-+    qmp_set_password(&opts, &err);
-+    g_free(opts.password);
-+    g_free(opts.u.vnc.display);
-     hmp_handle_error(mon, err);
- }
- 
-@@ -1395,9 +1426,31 @@ void hmp_expire_password(Monitor *mon, const QDict *qdict)
- {
-     const char *protocol  = qdict_get_str(qdict, "protocol");
-     const char *whenstr = qdict_get_str(qdict, "time");
-+    const char *display = qdict_get_try_str(qdict, "display");
-     Error *err = NULL;
-+    DisplayProtocol proto;
- 
--    qmp_expire_password(protocol, whenstr, &err);
-+    ExpirePasswordOptions opts = {
-+        .time = g_strdup(whenstr),
-+        .u.vnc.display = NULL,
-+    };
-+
-+    proto = qapi_enum_parse(&DisplayProtocol_lookup, protocol,
-+                            DISPLAY_PROTOCOL_VNC, &err);
-+    if (err) {
-+        hmp_handle_error(mon, err);
-+        return;
-+    }
-+    opts.protocol = proto;
-+
-+    if (proto == DISPLAY_PROTOCOL_VNC) {
-+        opts.u.vnc.has_display = !!display;
-+        opts.u.vnc.display = g_strdup(display);
-+    }
-+
-+    qmp_expire_password(&opts, &err);
-+    g_free(opts.time);
-+    g_free(opts.u.vnc.display);
-     hmp_handle_error(mon, err);
- }
- 
-diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
-index 343353e27a..729ca7cceb 100644
---- a/monitor/qmp-cmds.c
-+++ b/monitor/qmp-cmds.c
-@@ -167,45 +167,30 @@ void qmp_system_wakeup(Error **errp)
-     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, errp);
- }
- 
--void qmp_set_password(const char *protocol, const char *password,
--                      bool has_connected, const char *connected, Error **errp)
-+void qmp_set_password(SetPasswordOptions *opts, Error **errp)
- {
--    int disconnect_if_connected = 0;
--    int fail_if_connected = 0;
--    int rc;
-+    bool disconnect_if_connected = false;
-+    bool fail_if_connected = false;
-+    int rc = 0;
- 
--    if (has_connected) {
--        if (strcmp(connected, "fail") == 0) {
--            fail_if_connected = 1;
--        } else if (strcmp(connected, "disconnect") == 0) {
--            disconnect_if_connected = 1;
--        } else if (strcmp(connected, "keep") == 0) {
--            /* nothing */
--        } else {
--            error_setg(errp, QERR_INVALID_PARAMETER, "connected");
--            return;
--        }
--    }
--
--    if (strcmp(protocol, "spice") == 0) {
-+    if (opts->protocol == DISPLAY_PROTOCOL_SPICE) {
-         if (!qemu_using_spice(errp)) {
-             return;
-         }
--        rc = qemu_spice.set_passwd(password, fail_if_connected,
-+        if (opts->u.spice.has_connected) {
-+            fail_if_connected =
-+                opts->u.spice.connected == SET_PASSWORD_ACTION_FAIL;
-+            disconnect_if_connected =
-+                opts->u.spice.connected == SET_PASSWORD_ACTION_DISCONNECT;
-+        }
-+        rc = qemu_spice.set_passwd(opts->password, fail_if_connected,
-                                    disconnect_if_connected);
--    } else if (strcmp(protocol, "vnc") == 0) {
--        if (fail_if_connected || disconnect_if_connected) {
--            /* vnc supports "connected=keep" only */
--            error_setg(errp, QERR_INVALID_PARAMETER, "connected");
--            return;
--        }
-+    } else if (opts->protocol == DISPLAY_PROTOCOL_VNC) {
-         /* Note that setting an empty password will not disable login through
-          * this interface. */
--        rc = vnc_display_password(NULL, password);
--    } else {
--        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "protocol",
--                   "'vnc' or 'spice'");
--        return;
-+        rc = vnc_display_password(
-+                opts->u.vnc.has_display ? opts->u.vnc.display : NULL,
-+                opts->password);
-     }
- 
-     if (rc != 0) {
-@@ -213,11 +198,11 @@ void qmp_set_password(const char *protocol, const char *password,
-     }
- }
- 
--void qmp_expire_password(const char *protocol, const char *whenstr,
--                         Error **errp)
-+void qmp_expire_password(ExpirePasswordOptions *opts, Error **errp)
- {
-     time_t when;
-     int rc;
-+    const char* whenstr = opts->time;
- 
-     if (strcmp(whenstr, "now") == 0) {
-         when = 0;
-@@ -229,17 +214,14 @@ void qmp_expire_password(const char *protocol, const char *whenstr,
-         when = strtoull(whenstr, NULL, 10);
-     }
- 
--    if (strcmp(protocol, "spice") == 0) {
-+    if (opts->protocol == DISPLAY_PROTOCOL_SPICE) {
-         if (!qemu_using_spice(errp)) {
-             return;
-         }
-         rc = qemu_spice.set_pw_expire(when);
--    } else if (strcmp(protocol, "vnc") == 0) {
--        rc = vnc_display_pw_expire(NULL, when);
--    } else {
--        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "protocol",
--                   "'vnc' or 'spice'");
--        return;
-+    } else if (opts->protocol == DISPLAY_PROTOCOL_VNC) {
-+        rc = vnc_display_pw_expire(
-+                opts->u.vnc.has_display ? opts->u.vnc.display : NULL, when);
-     }
- 
-     if (rc != 0) {
-diff --git a/qapi/ui.json b/qapi/ui.json
-index d7567ac866..4244c62c30 100644
---- a/qapi/ui.json
-+++ b/qapi/ui.json
-@@ -9,22 +9,23 @@
- { 'include': 'common.json' }
- { 'include': 'sockets.json' }
- 
-+##
-+# @DisplayProtocol:
-+#
-+# Display protocols which support changing password options.
-+#
-+# Since: 6.2
-+#
-+##
-+{ 'enum': 'DisplayProtocol',
-+  'data': [ { 'name': 'vnc', 'if': 'CONFIG_VNC' },
-+            { 'name': 'spice', 'if': 'CONFIG_SPICE' } ] }
-+
- ##
- # @set_password:
- #
- # Sets the password of a remote display session.
- #
--# @protocol: - 'vnc' to modify the VNC server password
--#            - 'spice' to modify the Spice server password
--#
--# @password: the new password
--#
--# @connected: how to handle existing clients when changing the
--#             password.  If nothing is specified, defaults to 'keep'
--#             'fail' to fail the command if clients are connected
--#             'disconnect' to disconnect existing clients
--#             'keep' to maintain existing clients
--#
- # Returns: - Nothing on success
- #          - If Spice is not enabled, DeviceNotFound
- #
-@@ -37,16 +38,123 @@
- # <- { "return": {} }
- #
- ##
--{ 'command': 'set_password',
--  'data': {'protocol': 'str', 'password': 'str', '*connected': 'str'} }
-+{ 'command': 'set_password', 'boxed': true, 'data': 'SetPasswordOptions' }
-+
-+##
-+# @SetPasswordOptions:
-+#
-+# Data required to set a new password on a display server protocol.
-+#
-+# @protocol: - 'vnc' to modify the VNC server password
-+#            - 'spice' to modify the Spice server password
-+#
-+# @password: the new password
-+#
-+# Since: 6.2
-+#
-+##
-+{ 'union': 'SetPasswordOptions',
-+  'base': { 'protocol': 'DisplayProtocol',
-+            'password': 'str' },
-+  'discriminator': 'protocol',
-+  'data': { 'vnc': 'SetPasswordOptionsVnc',
-+            'spice': 'SetPasswordOptionsSpice' } }
-+
-+##
-+# @SetPasswordAction:
-+#
-+# An action to take on changing a password on a connection with active clients.
-+#
-+# @fail: fail the command if clients are connected
-+#
-+# @disconnect: disconnect existing clients
-+#
-+# @keep: maintain existing clients
-+#
-+# Since: 6.2
-+#
-+##
-+{ 'enum': 'SetPasswordAction',
-+  'data': [ 'fail', 'disconnect', 'keep' ] }
-+
-+##
-+# @SetPasswordActionVnc:
-+#
-+# See @SetPasswordAction. VNC only supports the keep action. 'connection'
-+# should just be omitted for VNC, this is kept for backwards compatibility.
-+#
-+# @keep: maintain existing clients
-+#
-+# Since: 6.2
-+#
-+##
-+{ 'enum': 'SetPasswordActionVnc',
-+  'data': [ 'keep' ] }
-+
-+##
-+# @SetPasswordOptionsSpice:
-+#
-+# Options for set_password specific to the VNC procotol.
-+#
-+# @connected: How to handle existing clients when changing the
-+#             password. If nothing is specified, defaults to 'keep'.
-+#
-+# Since: 6.2
-+#
-+##
-+{ 'struct': 'SetPasswordOptionsSpice',
-+  'data': { '*connected': 'SetPasswordAction' } }
-+
-+##
-+# @SetPasswordOptionsVnc:
-+#
-+# Options for set_password specific to the VNC procotol.
-+#
-+# @display: The id of the display where the password should be changed.
-+#           Defaults to the first.
-+#
-+# @connected: How to handle existing clients when changing the
-+#             password.
-+#
-+# Features:
-+# @deprecated: For VNC, @connected will always be 'keep', parameter should be
-+#              omitted.
-+#
-+# Since: 6.2
-+#
-+##
-+{ 'struct': 'SetPasswordOptionsVnc',
-+  'data': { '*display': 'str',
-+            '*connected': { 'type': 'SetPasswordActionVnc',
-+                            'features': ['deprecated'] } } }
- 
- ##
- # @expire_password:
- #
- # Expire the password of a remote display server.
- #
--# @protocol: the name of the remote display protocol 'vnc' or 'spice'
-+# Returns: - Nothing on success
-+#          - If @protocol is 'spice' and Spice is not active, DeviceNotFound
- #
-+# Since: 0.14
-+#
-+# Example:
-+#
-+# -> { "execute": "expire_password", "arguments": { "protocol": "vnc",
-+#                                                   "time": "+60" } }
-+# <- { "return": {} }
-+#
-+##
-+{ 'command': 'expire_password', 'boxed': true, 'data': 'ExpirePasswordOptions' }
-+
-+##
-+# @ExpirePasswordOptions:
-+#
-+# Data required to set password expiration on a display server protocol.
-+#
-+# @protocol: - 'vnc' to modify the VNC server expiration
-+#            - 'spice' to modify the Spice server expiration
-+
- # @time: when to expire the password.
- #
- #        - 'now' to expire the password immediately
-@@ -54,24 +162,33 @@
- #        - '+INT' where INT is the number of seconds from now (integer)
- #        - 'INT' where INT is the absolute time in seconds
- #
--# Returns: - Nothing on success
--#          - If @protocol is 'spice' and Spice is not active, DeviceNotFound
--#
--# Since: 0.14
--#
- # Notes: Time is relative to the server and currently there is no way to
- #        coordinate server time with client time.  It is not recommended to
- #        use the absolute time version of the @time parameter unless you're
- #        sure you are on the same machine as the QEMU instance.
- #
--# Example:
-+# Since: 6.2
- #
--# -> { "execute": "expire_password", "arguments": { "protocol": "vnc",
--#                                                   "time": "+60" } }
--# <- { "return": {} }
-+##
-+{ 'union': 'ExpirePasswordOptions',
-+  'base': { 'protocol': 'DisplayProtocol',
-+            'time': 'str' },
-+  'discriminator': 'protocol',
-+  'data': { 'vnc': 'ExpirePasswordOptionsVnc' } }
-+
-+##
-+# @ExpirePasswordOptionsVnc:
-+#
-+# Options for expire_password specific to the VNC procotol.
-+#
-+# @display: The id of the display where the expiration should be changed.
-+#           Defaults to the first.
-+#
-+# Since: 6.2
- #
- ##
--{ 'command': 'expire_password', 'data': {'protocol': 'str', 'time': 'str'} }
-+{ 'struct': 'ExpirePasswordOptionsVnc',
-+  'data': { '*display': 'str' } }
- 
- ##
- # @screendump:

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/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/0006-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/extra/0006-block-io-Update-BSC-only-if-want_zero-is-true.patch

@@ -1,43 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Hanna Reitz <hreitz@redhat.com>
-Date: Tue, 18 Jan 2022 17:59:59 +0100
-Subject: [PATCH] block/io: Update BSC only if want_zero is true
-
-We update the block-status cache whenever we get new information from a
-bdrv_co_block_status() call to the block driver.  However, if we have
-passed want_zero=false to that call, it may flag areas containing zeroes
-as data, and so we would update the block-status cache with wrong
-information.
-
-Therefore, we should not update the cache with want_zero=false.
-
-Reported-by: Nir Soffer <nsoffer@redhat.com>
-Fixes: 0bc329fbb00 ("block: block-status cache for data regions")
-Reviewed-by: Nir Soffer <nsoffer@redhat.com>
-Cc: qemu-stable@nongnu.org
-Signed-off-by: Hanna Reitz <hreitz@redhat.com>
-Message-Id: <20220118170000.49423-2-hreitz@redhat.com>
-Reviewed-by: Eric Blake <eblake@redhat.com>
-Signed-off-by: Eric Blake <eblake@redhat.com>
----
- block/io.c | 6 +++++-
- 1 file changed, 5 insertions(+), 1 deletion(-)
-
-diff --git a/block/io.c b/block/io.c
-index bb0a254def..4e4cb556c5 100644
---- a/block/io.c
-+++ b/block/io.c
-@@ -2497,8 +2497,12 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
-              * non-protocol nodes, and then it is never used.  However, filling
-              * the cache requires an RCU update, so double check here to avoid
-              * such an update if possible.
-+             *
-+             * Check want_zero, because we only want to update the cache when we
-+             * have accurate information about what is zero and what is data.
-              */
--            if (ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) &&
-+            if (want_zero &&
-+                ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) &&
-                 QLIST_EMPTY(&bs->children))
-             {
-                 /*

debian/patches/extra/0007-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/extra/0007-block-nbd-Delete-reconnect-delay-timer-when-done.patch

@@ -1,40 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Hanna Reitz <hreitz@redhat.com>
-Date: Wed, 9 Feb 2022 15:02:52 +0100
-Subject: [PATCH] block/nbd: Delete reconnect delay timer when done
-
-We start the reconnect delay timer to cancel the reconnection attempt
-after a while.  Once nbd_co_do_establish_connection() has returned, this
-attempt is over, and we no longer need the timer.
-
-Delete it before returning from nbd_reconnect_attempt(), so that it does
-not persist beyond the I/O request that was paused for reconnecting; we
-do not want it to fire in a drained section, because all sort of things
-can happen in such a section (e.g. the AioContext might be changed, and
-we do not want the timer to fire in the wrong context; or the BDS might
-even be deleted, and so the timer CB would access already-freed data).
-
-Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
-Signed-off-by: Hanna Reitz <hreitz@redhat.com>
----
- block/nbd.c | 7 +++++++
- 1 file changed, 7 insertions(+)
-
-diff --git a/block/nbd.c b/block/nbd.c
-index 5ef462db1b..b8e5a9b4cc 100644
---- a/block/nbd.c
-+++ b/block/nbd.c
-@@ -353,6 +353,13 @@ static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s)
-     }
- 
-     nbd_co_do_establish_connection(s->bs, NULL);
-+
-+    /*
-+     * The reconnect attempt is done (maybe successfully, maybe not), so
-+     * we no longer need this timer.  Delete it so it will not outlive
-+     * this I/O request (so draining removes all timers).
-+     */
-+    reconnect_delay_timer_del(s);
- }
- 
- static coroutine_fn int nbd_receive_replies(BDRVNBDState *s, uint64_t handle)

debian/patches/extra/0008-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/extra/0008-block-nbd-Assert-there-are-no-timers-when-closed.patch

@@ -1,34 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Hanna Reitz <hreitz@redhat.com>
-Date: Wed, 9 Feb 2022 15:02:54 +0100
-Subject: [PATCH] block/nbd: Assert there are no timers when closed
-
-Our two timers must not remain armed beyond nbd_clear_bdrvstate(), or
-they will access freed data when they fire.
-
-This patch is separate from the patches that actually fix the issue
-(HEAD^^ and HEAD^) so that you can run the associated regression iotest
-(281) on a configuration that reproducibly exposes the bug.
-
-Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
-Signed-off-by: Hanna Reitz <hreitz@redhat.com>
-[FE: backport (open_timer doesn't exist yet in 6.2.0)]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- block/nbd.c | 3 +++
- 1 file changed, 3 insertions(+)
-
-diff --git a/block/nbd.c b/block/nbd.c
-index b8e5a9b4cc..aab20125d8 100644
---- a/block/nbd.c
-+++ b/block/nbd.c
-@@ -108,6 +108,9 @@ static void nbd_clear_bdrvstate(BlockDriverState *bs)
- 
-     yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name));
- 
-+    /* Must not leave timers behind that would access freed data */
-+    assert(!s->reconnect_delay_timer);
-+
-     object_unref(OBJECT(s->tlscreds));
-     qapi_free_SocketAddress(s->saddr);
-     s->saddr = NULL;

debian/patches/extra/0009-block-nbd-Move-s-ioc-on-AioContext-change.patch

@@ -1,90 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Hanna Reitz <hreitz@redhat.com>
-Date: Wed, 9 Feb 2022 15:02:57 +0100
-Subject: [PATCH] block/nbd: Move s->ioc on AioContext change
-
-s->ioc must always be attached to the NBD node's AioContext.  If that
-context changes, s->ioc must be attached to the new context.
-
-Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2033626
-Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
-Signed-off-by: Hanna Reitz <hreitz@redhat.com>
-[FE: backport (open_timer doesn't exist yet in 6.2.0)]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- block/nbd.c | 41 +++++++++++++++++++++++++++++++++++++++++
- 1 file changed, 41 insertions(+)
-
-diff --git a/block/nbd.c b/block/nbd.c
-index aab20125d8..a3896c7f5f 100644
---- a/block/nbd.c
-+++ b/block/nbd.c
-@@ -2003,6 +2003,38 @@ static void nbd_cancel_in_flight(BlockDriverState *bs)
-     nbd_co_establish_connection_cancel(s->conn);
- }
- 
-+static void nbd_attach_aio_context(BlockDriverState *bs,
-+                                   AioContext *new_context)
-+{
-+    BDRVNBDState *s = bs->opaque;
-+
-+    /*
-+     * The reconnect_delay_timer is scheduled in I/O paths when the
-+     * connection is lost, to cancel the reconnection attempt after a
-+     * given time.  Once this attempt is done (successfully or not),
-+     * nbd_reconnect_attempt() ensures the timer is deleted before the
-+     * respective I/O request is resumed.
-+     * Since the AioContext can only be changed when a node is drained,
-+     * the reconnect_delay_timer cannot be active here.
-+     */
-+    assert(!s->reconnect_delay_timer);
-+
-+    if (s->ioc) {
-+        qio_channel_attach_aio_context(s->ioc, new_context);
-+    }
-+}
-+
-+static void nbd_detach_aio_context(BlockDriverState *bs)
-+{
-+    BDRVNBDState *s = bs->opaque;
-+
-+    assert(!s->reconnect_delay_timer);
-+
-+    if (s->ioc) {
-+        qio_channel_detach_aio_context(s->ioc);
-+    }
-+}
-+
- static BlockDriver bdrv_nbd = {
-     .format_name                = "nbd",
-     .protocol_name              = "nbd",
-@@ -2026,6 +2058,9 @@ static BlockDriver bdrv_nbd = {
-     .bdrv_dirname               = nbd_dirname,
-     .strong_runtime_opts        = nbd_strong_runtime_opts,
-     .bdrv_cancel_in_flight      = nbd_cancel_in_flight,
-+
-+    .bdrv_attach_aio_context    = nbd_attach_aio_context,
-+    .bdrv_detach_aio_context    = nbd_detach_aio_context,
- };
- 
- static BlockDriver bdrv_nbd_tcp = {
-@@ -2051,6 +2086,9 @@ static BlockDriver bdrv_nbd_tcp = {
-     .bdrv_dirname               = nbd_dirname,
-     .strong_runtime_opts        = nbd_strong_runtime_opts,
-     .bdrv_cancel_in_flight      = nbd_cancel_in_flight,
-+
-+    .bdrv_attach_aio_context    = nbd_attach_aio_context,
-+    .bdrv_detach_aio_context    = nbd_detach_aio_context,
- };
- 
- static BlockDriver bdrv_nbd_unix = {
-@@ -2076,6 +2114,9 @@ static BlockDriver bdrv_nbd_unix = {
-     .bdrv_dirname               = nbd_dirname,
-     .strong_runtime_opts        = nbd_strong_runtime_opts,
-     .bdrv_cancel_in_flight      = nbd_cancel_in_flight,
-+
-+    .bdrv_attach_aio_context    = nbd_attach_aio_context,
-+    .bdrv_detach_aio_context    = nbd_detach_aio_context,
- };
- 
- static void bdrv_nbd_init(void)

debian/patches/extra/0009-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 ec29d6b810..3dd2e229d2 100644
+--- a/block/backup.c
++++ b/block/backup.c
+@@ -356,7 +356,7 @@ 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,
+@@ -457,7 +457,8 @@ 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 057601dcf0..4c33c3f5f0 100644
+--- a/blockdev.c
++++ b/blockdev.c
+@@ -2726,7 +2726,7 @@ 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 d2201e27f4..eb2d92a226 100644
+--- a/include/block/block_int-global-state.h
++++ b/include/block/block_int-global-state.h
+@@ -193,7 +193,7 @@ 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 4b18e01b85..b179d65520 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -1610,6 +1610,9 @@
+ #     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:
+@@ -1631,6 +1634,7 @@
+             '*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/extra/0010-acpi-fix-QEMU-crash-when-started-with-SLIC-table.patch

@@ -1,89 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Igor Mammedov <imammedo@redhat.com>
-Date: Mon, 27 Dec 2021 14:31:17 -0500
-Subject: [PATCH] acpi: fix QEMU crash when started with SLIC table
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-if QEMU is started with used provided SLIC table blob,
-
-  -acpitable sig=SLIC,oem_id='CRASH ',oem_table_id="ME",oem_rev=00002210,asl_compiler_id="",asl_compiler_rev=00000000,data=/dev/null
-it will assert with:
-
-  hw/acpi/aml-build.c:61:build_append_padded_str: assertion failed: (len <= maxlen)
-
-and following backtrace:
-
-  ...
-  build_append_padded_str (array=0x555556afe320, str=0x555556afdb2e "CRASH ME", maxlen=0x6, pad=0x20) at hw/acpi/aml-build.c:61
-  acpi_table_begin (desc=0x7fffffffd1b0, array=0x555556afe320) at hw/acpi/aml-build.c:1727
-  build_fadt (tbl=0x555556afe320, linker=0x555557ca3830, f=0x7fffffffd318, oem_id=0x555556afdb2e "CRASH ME", oem_table_id=0x555556afdb34 "ME") at hw/acpi/aml-build.c:2064
-  ...
-
-which happens due to acpi_table_begin() expecting NULL terminated
-oem_id and oem_table_id strings, which is normally the case, but
-in case of user provided SLIC table, oem_id points to table's blob
-directly and as result oem_id became longer than expected.
-
-Fix issue by handling oem_id consistently and make acpi_get_slic_oem()
-return NULL terminated strings.
-
-PS:
-After [1] refactoring, oem_id semantics became inconsistent, where
-NULL terminated string was coming from machine and old way pointer
-into byte array coming from -acpitable option. That used to work
-since build_header() wasn't expecting NULL terminated string and
-blindly copied the 1st 6 bytes only.
-
-However commit [2] broke that by replacing build_header() with
-acpi_table_begin(), which was expecting NULL terminated string
-and was checking oem_id size.
-
-1) 602b45820 ("acpi: Permit OEM ID and OEM table ID fields to be changed")
-2)
-Fixes: 4b56e1e4eb08 ("acpi: build_fadt: use acpi_table_begin()/acpi_table_end() instead of build_header()")
-Resolves: https://gitlab.com/qemu-project/qemu/-/issues/786
-Signed-off-by: Igor Mammedov <imammedo@redhat.com>
-Message-Id: <20211227193120.1084176-2-imammedo@redhat.com>
-Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
-Tested-by: Denis Lisov <dennis.lissov@gmail.com>
-Tested-by: Alexander Tsoy <alexander@tsoy.me>
-Cc: qemu-stable@nongnu.org
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-(cherry picked from commit 8cdb99af45365727ac17f45239a9b8c1d5155c6d)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/acpi/core.c       | 4 ++--
- hw/i386/acpi-build.c | 2 ++
- 2 files changed, 4 insertions(+), 2 deletions(-)
-
-diff --git a/hw/acpi/core.c b/hw/acpi/core.c
-index 1e004d0078..3e811bf03c 100644
---- a/hw/acpi/core.c
-+++ b/hw/acpi/core.c
-@@ -345,8 +345,8 @@ int acpi_get_slic_oem(AcpiSlicOem *oem)
-         struct acpi_table_header *hdr = (void *)(u - sizeof(hdr->_length));
- 
-         if (memcmp(hdr->sig, "SLIC", 4) == 0) {
--            oem->id = hdr->oem_id;
--            oem->table_id = hdr->oem_table_id;
-+            oem->id = g_strndup(hdr->oem_id, 6);
-+            oem->table_id = g_strndup(hdr->oem_table_id, 8);
-             return 0;
-         }
-     }
-diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
-index a99c6e4fe3..570f82997b 100644
---- a/hw/i386/acpi-build.c
-+++ b/hw/i386/acpi-build.c
-@@ -2721,6 +2721,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
- 
-     /* Cleanup memory that's no longer used. */
-     g_array_free(table_offsets, true);
-+    g_free(slic_oem.id);
-+    g_free(slic_oem.table_id);
- }
- 
- static void acpi_ram_update(MemoryRegion *mr, GArray *data)

debian/patches/extra/0010-hw-virtio-Fix-the-de-initialization-of-vhost-user-de.patch

@@ -0,0 +1,92 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Tue, 18 Jun 2024 14:19:58 +0200
+Subject: [PATCH] hw/virtio: Fix the de-initialization of vhost-user devices
+
+The unrealize functions of the various vhost-user devices are
+calling the corresponding vhost_*_set_status() functions with a
+status of 0 to shut down the device correctly.
+
+Now these vhost_*_set_status() functions all follow this scheme:
+
+    bool should_start = virtio_device_should_start(vdev, status);
+
+    if (vhost_dev_is_started(&vvc->vhost_dev) == should_start) {
+        return;
+    }
+
+    if (should_start) {
+        /* ... do the initialization stuff ... */
+    } else {
+        /* ... do the cleanup stuff ... */
+    }
+
+The problem here is virtio_device_should_start(vdev, 0) currently
+always returns "true" since it internally only looks at vdev->started
+instead of looking at the "status" parameter. Thus once the device
+got started once, virtio_device_should_start() always returns true
+and thus the vhost_*_set_status() functions return early, without
+ever doing any clean-up when being called with status == 0. This
+causes e.g. problems when trying to hot-plug and hot-unplug a vhost
+user devices multiple times since the de-initialization step is
+completely skipped during the unplug operation.
+
+This bug has been introduced in commit 9f6bcfd99f ("hw/virtio: move
+vm_running check to virtio_device_started") which replaced
+
+ should_start = status & VIRTIO_CONFIG_S_DRIVER_OK;
+
+with
+
+ should_start = virtio_device_started(vdev, status);
+
+which later got replaced by virtio_device_should_start(). This blocked
+the possibility to set should_start to false in case the status flag
+VIRTIO_CONFIG_S_DRIVER_OK was not set.
+
+Fix it by adjusting the virtio_device_should_start() function to
+only consider the status flag instead of vdev->started. Since this
+function is only used in the various vhost_*_set_status() functions
+for exactly the same purpose, it should be fine to fix it in this
+central place there without any risk to change the behavior of other
+code.
+
+Fixes: 9f6bcfd99f ("hw/virtio: move vm_running check to virtio_device_started")
+Buglink: https://issues.redhat.com/browse/RHEL-40708
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+Message-Id: <20240618121958.88673-1-thuth@redhat.com>
+Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
+Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
+Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
+(cherry picked from commit d72479b11797c28893e1e3fc565497a9cae5ca16)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ include/hw/virtio/virtio.h | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
+index 7d5ffdc145..2eafad17b8 100644
+--- a/include/hw/virtio/virtio.h
++++ b/include/hw/virtio/virtio.h
+@@ -470,9 +470,9 @@ static inline bool virtio_device_started(VirtIODevice *vdev, uint8_t status)
+  * @vdev - the VirtIO device
+  * @status - the devices status bits
+  *
+- * This is similar to virtio_device_started() but also encapsulates a
+- * check on the VM status which would prevent a device starting
+- * anyway.
++ * This is similar to virtio_device_started() but ignores vdev->started
++ * and also encapsulates a check on the VM status which would prevent a
++ * device from starting anyway.
+  */
+ static inline bool virtio_device_should_start(VirtIODevice *vdev, uint8_t status)
+ {
+@@ -480,7 +480,7 @@ static inline bool virtio_device_should_start(VirtIODevice *vdev, uint8_t status
+         return false;
+     }
+ 
+-    return virtio_device_started(vdev, status);
++    return status & VIRTIO_CONFIG_S_DRIVER_OK;
+ }
+ 
+ static inline void virtio_set_started(VirtIODevice *vdev, bool started)

debian/patches/extra/0011-target-arm-Use-float_status-copy-in-sme_fmopa_s.patch

@@ -0,0 +1,43 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Daniyal Khan <danikhan632@gmail.com>
+Date: Wed, 17 Jul 2024 16:01:47 +1000
+Subject: [PATCH] target/arm: Use float_status copy in sme_fmopa_s
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+We made a copy above because the fp exception flags
+are not propagated back to the FPST register, but
+then failed to use the copy.
+
+Cc: qemu-stable@nongnu.org
+Fixes: 558e956c719 ("target/arm: Implement FMOPA, FMOPS (non-widening)")
+Signed-off-by: Daniyal Khan <danikhan632@gmail.com>
+Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
+Message-id: 20240717060149.204788-2-richard.henderson@linaro.org
+[rth: Split from a larger patch]
+Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+(cherry picked from commit 31d93fedf41c24b0badb38cd9317590d1ef74e37)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/tcg/sme_helper.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
+index e2e0575039..5a6dd76489 100644
+--- a/target/arm/tcg/sme_helper.c
++++ b/target/arm/tcg/sme_helper.c
+@@ -916,7 +916,7 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
+                         if (pb & 1) {
+                             uint32_t *a = vza_row + H1_4(col);
+                             uint32_t *m = vzm + H1_4(col);
+-                            *a = float32_muladd(n, *m, *a, 0, vst);
++                            *a = float32_muladd(n, *m, *a, 0, &fpst);
+                         }
+                         col += 4;
+                         pb >>= 4;

debian/patches/extra/0011-virtio-net-fix-map-leaking-on-error-during-receive.patch

@@ -1,38 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Jason Wang <jasowang@redhat.com>
-Date: Tue, 8 Mar 2022 10:42:51 +0800
-Subject: [PATCH] virtio-net: fix map leaking on error during receive
-
-Commit bedd7e93d0196 ("virtio-net: fix use after unmap/free for sg")
-tries to fix the use after free of the sg by caching the virtqueue
-elements in an array and unmap them at once after receiving the
-packets, But it forgot to unmap the cached elements on error which
-will lead to leaking of mapping and other unexpected results.
-
-Fixing this by detaching the cached elements on error. This addresses
-CVE-2022-26353.
-
-Reported-by: Victor Tom <vv474172261@gmail.com>
-Cc: qemu-stable@nongnu.org
-Fixes: CVE-2022-26353
-Fixes: bedd7e93d0196 ("virtio-net: fix use after unmap/free for sg")
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
-(cherry picked from commit abe300d9d894f7138e1af7c8e9c88c04bfe98b37)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/net/virtio-net.c | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
-index f2014d5ea0..e1f4748831 100644
---- a/hw/net/virtio-net.c
-+++ b/hw/net/virtio-net.c
-@@ -1862,6 +1862,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
- 
- err:
-     for (j = 0; j < i; j++) {
-+        virtqueue_detach_element(q->rx_vq, elems[j], lens[j]);
-         g_free(elems[j]);
-     }
- 

debian/patches/extra/0012-memory-Fix-incorrect-calls-of-log_global_start-stop.patch

@@ -1,86 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Peter Xu <peterx@redhat.com>
-Date: Tue, 30 Nov 2021 16:00:28 +0800
-Subject: [PATCH] memory: Fix incorrect calls of log_global_start/stop
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-We should only call the log_global_start/stop when the global dirty track
-bitmask changes from zero<->non-zero.
-
-No real issue reported for this yet probably because no immediate user to
-enable both dirty rate measurement and migration at the same time.  However
-it'll be good to be prepared for it.
-
-Fixes: 63b41db4bc ("memory: make global_dirty_tracking a bitmask")
-Cc: qemu-stable@nongnu.org
-Cc: Hyman Huang <huangy81@chinatelecom.cn>
-Cc: Paolo Bonzini <pbonzini@redhat.com>
-Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
-Cc: Juan Quintela <quintela@redhat.com>
-Cc: David Hildenbrand <david@redhat.com>
-Signed-off-by: Peter Xu <peterx@redhat.com>
-Reviewed-by: David Hildenbrand <david@redhat.com>
-Message-Id: <20211130080028.6474-1-peterx@redhat.com>
-Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
-(cherry picked from commit 7b0538ed3a22ce30817f818449d10701fb0821f9)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- softmmu/memory.c | 27 ++++++++++++++-------------
- 1 file changed, 14 insertions(+), 13 deletions(-)
-
-diff --git a/softmmu/memory.c b/softmmu/memory.c
-index 7340e19ff5..81d4bf1454 100644
---- a/softmmu/memory.c
-+++ b/softmmu/memory.c
-@@ -2773,6 +2773,8 @@ static VMChangeStateEntry *vmstate_change;
- 
- void memory_global_dirty_log_start(unsigned int flags)
- {
-+    unsigned int old_flags = global_dirty_tracking;
-+
-     if (vmstate_change) {
-         qemu_del_vm_change_state_handler(vmstate_change);
-         vmstate_change = NULL;
-@@ -2781,15 +2783,14 @@ void memory_global_dirty_log_start(unsigned int flags)
-     assert(flags && !(flags & (~GLOBAL_DIRTY_MASK)));
-     assert(!(global_dirty_tracking & flags));
-     global_dirty_tracking |= flags;
--
-     trace_global_dirty_changed(global_dirty_tracking);
- 
--    MEMORY_LISTENER_CALL_GLOBAL(log_global_start, Forward);
--
--    /* Refresh DIRTY_MEMORY_MIGRATION bit.  */
--    memory_region_transaction_begin();
--    memory_region_update_pending = true;
--    memory_region_transaction_commit();
-+    if (!old_flags) {
-+        MEMORY_LISTENER_CALL_GLOBAL(log_global_start, Forward);
-+        memory_region_transaction_begin();
-+        memory_region_update_pending = true;
-+        memory_region_transaction_commit();
-+    }
- }
- 
- static void memory_global_dirty_log_do_stop(unsigned int flags)
-@@ -2800,12 +2801,12 @@ static void memory_global_dirty_log_do_stop(unsigned int flags)
- 
-     trace_global_dirty_changed(global_dirty_tracking);
- 
--    /* Refresh DIRTY_MEMORY_MIGRATION bit.  */
--    memory_region_transaction_begin();
--    memory_region_update_pending = true;
--    memory_region_transaction_commit();
--
--    MEMORY_LISTENER_CALL_GLOBAL(log_global_stop, Reverse);
-+    if (!global_dirty_tracking) {
-+        memory_region_transaction_begin();
-+        memory_region_update_pending = true;
-+        memory_region_transaction_commit();
-+        MEMORY_LISTENER_CALL_GLOBAL(log_global_stop, Reverse);
-+    }
- }
- 
- static void memory_vm_change_state_handler(void *opaque, bool running,

debian/patches/extra/0012-target-arm-Use-FPST_F16-for-SME-FMOPA-widening.patch

@@ -0,0 +1,62 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Richard Henderson <richard.henderson@linaro.org>
+Date: Wed, 17 Jul 2024 16:01:48 +1000
+Subject: [PATCH] target/arm: Use FPST_F16 for SME FMOPA (widening)
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+This operation has float16 inputs and thus must use
+the FZ16 control not the FZ control.
+
+Cc: qemu-stable@nongnu.org
+Fixes: 3916841ac75 ("target/arm: Implement FMOPA, FMOPS (widening)")
+Reported-by: Daniyal Khan <danikhan632@gmail.com>
+Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
+Message-id: 20240717060149.204788-3-richard.henderson@linaro.org
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2374
+Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+(cherry picked from commit 207d30b5fdb5b45a36f26eefcf52fe2c1714dd4f)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/tcg/translate-sme.c | 12 ++++++++----
+ 1 file changed, 8 insertions(+), 4 deletions(-)
+
+diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
+index 46c7fce8b4..185a8a917b 100644
+--- a/target/arm/tcg/translate-sme.c
++++ b/target/arm/tcg/translate-sme.c
+@@ -304,6 +304,7 @@ static bool do_outprod(DisasContext *s, arg_op *a, MemOp esz,
+ }
+ 
+ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz,
++                            ARMFPStatusFlavour e_fpst,
+                             gen_helper_gvec_5_ptr *fn)
+ {
+     int svl = streaming_vec_reg_size(s);
+@@ -319,15 +320,18 @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz,
+     zm = vec_full_reg_ptr(s, a->zm);
+     pn = pred_full_reg_ptr(s, a->pn);
+     pm = pred_full_reg_ptr(s, a->pm);
+-    fpst = fpstatus_ptr(FPST_FPCR);
++    fpst = fpstatus_ptr(e_fpst);
+ 
+     fn(za, zn, zm, pn, pm, fpst, tcg_constant_i32(desc));
+     return true;
+ }
+ 
+-TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_h)
+-TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s)
+-TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d)
++TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a,
++           MO_32, FPST_FPCR_F16, gen_helper_sme_fmopa_h)
++TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
++           MO_32, FPST_FPCR, gen_helper_sme_fmopa_s)
++TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
++           MO_64, FPST_FPCR, gen_helper_sme_fmopa_d)
+ 
+ /* TODO: FEAT_EBF16 */
+ TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa)

debian/patches/extra/0013-acpi-fix-OEM-ID-OEM-Table-ID-padding.patch

@@ -1,59 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Igor Mammedov <imammedo@redhat.com>
-Date: Wed, 12 Jan 2022 08:03:31 -0500
-Subject: [PATCH] acpi: fix OEM ID/OEM Table ID padding
-
-Commit [2] broke original '\0' padding of OEM ID and OEM Table ID
-fields in headers of ACPI tables. While it doesn't have impact on
-default values since QEMU uses 6 and 8 characters long values
-respectively, it broke usecase where IDs are provided on QEMU CLI.
-It shouldn't affect guest (but may cause licensing verification
-issues in guest OS).
-One of the broken usecases is user supplied SLIC table with IDs
-shorter than max possible length, where [2] mangles IDs with extra
-spaces in RSDT and FADT tables whereas guest OS expects those to
-mirror the respective values of the used SLIC table.
-
-Fix it by replacing whitespace padding with '\0' padding in
-accordance with [1] and expectations of guest OS
-
-1) ACPI spec, v2.0b
-       17.2 AML Grammar Definition
-       ...
-       //OEM ID of up to 6 characters. If the OEM ID is
-       //shorter than 6 characters, it can be terminated
-       //with a NULL character.
-
-2)
-Fixes: 602b458201 ("acpi: Permit OEM ID and OEM table ID fields to be changed")
-Resolves: https://gitlab.com/qemu-project/qemu/-/issues/707
-Reported-by: Dmitry V. Orekhov <dima.orekhov@gmail.com>
-Signed-off-by: Igor Mammedov <imammedo@redhat.com>
-Cc: qemu-stable@nongnu.org
-Message-Id: <20220112130332.1648664-4-imammedo@redhat.com>
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-Reviewed-by: Ani Sinha <ani@anisinha.ca>
-Tested-by: Dmitry V. Orekhov dima.orekhov@gmail.com
-(cherry picked from commit 748c030f360a940fe0c9382c8ca1649096c3a80d)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/acpi/aml-build.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
-index b3b3310df3..65148d5b9d 100644
---- a/hw/acpi/aml-build.c
-+++ b/hw/acpi/aml-build.c
-@@ -1724,9 +1724,9 @@ void acpi_table_begin(AcpiTable *desc, GArray *array)
-     build_append_int_noprefix(array, 0, 4); /* Length */
-     build_append_int_noprefix(array, desc->rev, 1); /* Revision */
-     build_append_int_noprefix(array, 0, 1); /* Checksum */
--    build_append_padded_str(array, desc->oem_id, 6, ' '); /* OEMID */
-+    build_append_padded_str(array, desc->oem_id, 6, '\0'); /* OEMID */
-     /* OEM Table ID */
--    build_append_padded_str(array, desc->oem_table_id, 8, ' ');
-+    build_append_padded_str(array, desc->oem_table_id, 8, '\0');
-     build_append_int_noprefix(array, 1, 4); /* OEM Revision */
-     g_array_append_vals(array, ACPI_BUILD_APPNAME8, 4); /* Creator ID */
-     build_append_int_noprefix(array, 1, 4); /* Creator Revision */

debian/patches/extra/0013-scsi-fix-regression-and-honor-bootindex-again-for-le.patch

@@ -0,0 +1,60 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Wed, 10 Jul 2024 17:25:29 +0200
+Subject: [PATCH] scsi: fix regression and honor bootindex again for legacy
+ drives
+
+Commit 3089637461 ("scsi: Don't ignore most usb-storage properties")
+removed the call to object_property_set_int() and thus the 'set'
+method for the bootindex property was also not called anymore. Here
+that method is device_set_bootindex() (as configured by
+scsi_dev_instance_init() -> device_add_bootindex_property()) which as
+a side effect registers the device via add_boot_device_path().
+
+As reported by a downstream user [0], the bootindex property did not
+have the desired effect anymore for legacy drives. Fix the regression
+by explicitly calling the add_boot_device_path() function after
+checking that the bootindex is not yet used (to avoid
+add_boot_device_path() calling exit()).
+
+[0]: https://forum.proxmox.com/threads/149772/post-679433
+
+Cc: qemu-stable@nongnu.org
+Fixes: 3089637461 ("scsi: Don't ignore most usb-storage properties")
+Suggested-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Link: https://lore.kernel.org/r/20240710152529.1737407-1-f.ebner@proxmox.com
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 57a8a80d1a5b28797b21d30bfc60601945820e51)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/scsi/scsi-bus.c | 9 +++++++++
+ 1 file changed, 9 insertions(+)
+
+diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
+index 9e40b0c920..53eff5dd3d 100644
+--- a/hw/scsi/scsi-bus.c
++++ b/hw/scsi/scsi-bus.c
+@@ -384,6 +384,7 @@ SCSIDevice *scsi_bus_legacy_add_drive(SCSIBus *bus, BlockBackend *blk,
+     DeviceState *dev;
+     SCSIDevice *s;
+     DriveInfo *dinfo;
++    Error *local_err = NULL;
+ 
+     if (blk_is_sg(blk)) {
+         driver = "scsi-generic";
+@@ -403,6 +404,14 @@ SCSIDevice *scsi_bus_legacy_add_drive(SCSIBus *bus, BlockBackend *blk,
+     s = SCSI_DEVICE(dev);
+     s->conf = *conf;
+ 
++    check_boot_index(conf->bootindex, &local_err);
++    if (local_err) {
++        object_unparent(OBJECT(dev));
++        error_propagate(errp, local_err);
++        return NULL;
++    }
++    add_boot_device_path(conf->bootindex, dev, NULL);
++
+     qdev_prop_set_uint32(dev, "scsi-id", unit);
+     if (object_property_find(OBJECT(dev), "removable")) {
+         qdev_prop_set_bit(dev, "removable", removable);

debian/patches/extra/0014-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 b866e42271..3ee95c0e7a 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/0014-hw-scsi-lsi53c895a-bump-instruction-limit-in-scripts.patch

@@ -0,0 +1,48 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Mon, 15 Jul 2024 15:14:03 +0200
+Subject: [PATCH] hw/scsi/lsi53c895a: bump instruction limit in scripts
+ processing to fix regression
+
+Commit 9876359990 ("hw/scsi/lsi53c895a: add timer to scripts
+processing") reduced the maximum allowed instruction count by
+a factor of 100 all the way down to 100.
+
+This causes the "Check Point R81.20 Gaia" appliance [0] to fail to
+boot after fully finishing the installation via the appliance's web
+interface (there is already one reboot before that).
+
+With a limit of 150, the appliance still fails to boot, while with a
+limit of 200, it works. Bump to 500 to fix the regression and be on
+the safe side.
+
+Originally reported in the Proxmox community forum[1].
+
+[0]: https://support.checkpoint.com/results/download/124397
+[1]: https://forum.proxmox.com/threads/149772/post-683459
+
+Cc: qemu-stable@nongnu.org
+Fixes: 9876359990 ("hw/scsi/lsi53c895a: add timer to scripts processing")
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+Acked-by: Sven Schnelle <svens@stackframe.org>
+Link: https://lore.kernel.org/r/20240715131403.223239-1-f.ebner@proxmox.com
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit a4975023fb13cf229bd59c9ceec1b8cbdc5b9a20)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/scsi/lsi53c895a.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c
+index eb9828dd5e..f1935e5328 100644
+--- a/hw/scsi/lsi53c895a.c
++++ b/hw/scsi/lsi53c895a.c
+@@ -188,7 +188,7 @@ static const char *names[] = {
+ #define LSI_TAG_VALID     (1 << 16)
+ 
+ /* Maximum instructions to process. */
+-#define LSI_MAX_INSN    100
++#define LSI_MAX_INSN    500
+ 
+ typedef struct lsi_request {
+     SCSIRequest *req;

debian/patches/extra/0014-vhost-vsock-detach-the-virqueue-element-in-case-of-e.patch

@@ -1,55 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Stefano Garzarella <sgarzare@redhat.com>
-Date: Mon, 28 Feb 2022 10:50:58 +0100
-Subject: [PATCH] vhost-vsock: detach the virqueue element in case of error
-
-In vhost_vsock_common_send_transport_reset(), if an element popped from
-the virtqueue is invalid, we should call virtqueue_detach_element() to
-detach it from the virtqueue before freeing its memory.
-
-Fixes: fc0b9b0e1c ("vhost-vsock: add virtio sockets device")
-Fixes: CVE-2022-26354
-Cc: qemu-stable@nongnu.org
-Reported-by: VictorV <vv474172261@gmail.com>
-Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
-Message-Id: <20220228095058.27899-1-sgarzare@redhat.com>
-Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-(cherry picked from commit 8d1b247f3748ac4078524130c6d7ae42b6140aaf)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/virtio/vhost-vsock-common.c | 10 +++++++---
- 1 file changed, 7 insertions(+), 3 deletions(-)
-
-diff --git a/hw/virtio/vhost-vsock-common.c b/hw/virtio/vhost-vsock-common.c
-index 3f3771274e..ed706681ac 100644
---- a/hw/virtio/vhost-vsock-common.c
-+++ b/hw/virtio/vhost-vsock-common.c
-@@ -153,19 +153,23 @@ static void vhost_vsock_common_send_transport_reset(VHostVSockCommon *vvc)
-     if (elem->out_num) {
-         error_report("invalid vhost-vsock event virtqueue element with "
-                      "out buffers");
--        goto out;
-+        goto err;
-     }
- 
-     if (iov_from_buf(elem->in_sg, elem->in_num, 0,
-                      &event, sizeof(event)) != sizeof(event)) {
-         error_report("vhost-vsock event virtqueue element is too short");
--        goto out;
-+        goto err;
-     }
- 
-     virtqueue_push(vq, elem, sizeof(event));
-     virtio_notify(VIRTIO_DEVICE(vvc), vq);
- 
--out:
-+    g_free(elem);
-+    return;
-+
-+err:
-+    virtqueue_detach_element(vq, elem, 0);
-     g_free(elem);
- }
- 

debian/patches/extra/0015-block-copy-Fix-missing-graph-lock.patch

@@ -0,0 +1,38 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Kevin Wolf <kwolf@redhat.com>
+Date: Thu, 27 Jun 2024 20:12:44 +0200
+Subject: [PATCH] block-copy: Fix missing graph lock
+
+The graph lock needs to be held when calling bdrv_co_pdiscard(). Fix
+block_copy_task_entry() to take it for the call.
+
+WITH_GRAPH_RDLOCK_GUARD() was implemented in a weak way because of
+limitations in clang's Thread Safety Analysis at the time, so that it
+only asserts that the lock is held (which allows calling functions that
+require the lock), but we never deal with the unlocking (so even after
+the scope of the guard, the compiler assumes that the lock is still
+held). This is why the compiler didn't catch this locking error.
+
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+(picked from https://lore.kernel.org/qemu-devel/20240627181245.281403-2-kwolf@redhat.com/)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ block/block-copy.c | 4 +++-
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+diff --git a/block/block-copy.c b/block/block-copy.c
+index 7e3b378528..cc618e4561 100644
+--- a/block/block-copy.c
++++ b/block/block-copy.c
+@@ -595,7 +595,9 @@ static coroutine_fn int block_copy_task_entry(AioTask *task)
+     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);
++        WITH_GRAPH_RDLOCK_GUARD() {
++            bdrv_co_pdiscard(s->source, t->req.offset, nbytes);
++        }
+     }
+ 
+     return ret;

debian/patches/extra/0015-vhost-user-remove-VirtQ-notifier-restore.patch

@@ -1,98 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Xueming Li <xuemingl@nvidia.com>
-Date: Mon, 7 Feb 2022 15:19:28 +0800
-Subject: [PATCH] vhost-user: remove VirtQ notifier restore
-
-Notifier set when vhost-user backend asks qemu to mmap an FD and
-offset. When vhost-user backend restart or getting killed, VQ notifier
-FD and mmap addresses become invalid. After backend restart, MR contains
-the invalid address will be restored and fail on notifier access.
-
-On the other hand, qemu should munmap the notifier, release underlying
-hardware resources to enable backend restart and allocate hardware
-notifier resources correctly.
-
-Qemu shouldn't reference and use resources of disconnected backend.
-
-This patch removes VQ notifier restore, uses the default vhost-user
-notifier to avoid invalid address access.
-
-After backend restart, the backend should ask qemu to install a hardware
-notifier if needed.
-
-Fixes: 44866521bd6e ("vhost-user: support registering external host notifiers")
-Cc: qemu-stable@nongnu.org
-Signed-off-by: Xueming Li <xuemingl@nvidia.com>
-Message-Id: <20220207071929.527149-2-xuemingl@nvidia.com>
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-(cherry picked from commit e867144b73b3c5009266b6df07d5ff44acfb82c3)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/virtio/vhost-user.c         | 19 +------------------
- include/hw/virtio/vhost-user.h |  1 -
- 2 files changed, 1 insertion(+), 19 deletions(-)
-
-diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
-index bf6e50223c..c671719e9b 100644
---- a/hw/virtio/vhost-user.c
-+++ b/hw/virtio/vhost-user.c
-@@ -1143,19 +1143,6 @@ static int vhost_user_set_vring_num(struct vhost_dev *dev,
-     return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring);
- }
- 
--static void vhost_user_host_notifier_restore(struct vhost_dev *dev,
--                                             int queue_idx)
--{
--    struct vhost_user *u = dev->opaque;
--    VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
--    VirtIODevice *vdev = dev->vdev;
--
--    if (n->addr && !n->set) {
--        virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true);
--        n->set = true;
--    }
--}
--
- static void vhost_user_host_notifier_remove(struct vhost_dev *dev,
-                                             int queue_idx)
- {
-@@ -1163,17 +1150,14 @@ static void vhost_user_host_notifier_remove(struct vhost_dev *dev,
-     VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
-     VirtIODevice *vdev = dev->vdev;
- 
--    if (n->addr && n->set) {
-+    if (n->addr) {
-         virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
--        n->set = false;
-     }
- }
- 
- static int vhost_user_set_vring_base(struct vhost_dev *dev,
-                                      struct vhost_vring_state *ring)
- {
--    vhost_user_host_notifier_restore(dev, ring->index);
--
-     return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring);
- }
- 
-@@ -1538,7 +1522,6 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev,
-     }
- 
-     n->addr = addr;
--    n->set = true;
- 
-     return 0;
- }
-diff --git a/include/hw/virtio/vhost-user.h b/include/hw/virtio/vhost-user.h
-index a9abca3288..f6012b2078 100644
---- a/include/hw/virtio/vhost-user.h
-+++ b/include/hw/virtio/vhost-user.h
-@@ -14,7 +14,6 @@
- typedef struct VhostUserHostNotifier {
-     MemoryRegion mr;
-     void *addr;
--    bool set;
- } VhostUserHostNotifier;
- 
- typedef struct VhostUserState {

debian/patches/extra/0016-Revert-qemu-char-do-not-operate-on-sources-from-fina.patch

@@ -0,0 +1,93 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Sergey Dyasli <sergey.dyasli@nutanix.com>
+Date: Fri, 12 Jul 2024 09:26:59 +0000
+Subject: [PATCH] Revert "qemu-char: do not operate on sources from finalize
+ callbacks"
+
+This reverts commit 2b316774f60291f57ca9ecb6a9f0712c532cae34.
+
+After 038b4217884c ("Revert "chardev: use a child source for qio input
+source"") we've been observing the "iwp->src == NULL" assertion
+triggering periodically during the initial capabilities querying by
+libvirtd. One of possible backtraces:
+
+Thread 1 (Thread 0x7f16cd4f0700 (LWP 43858)):
+0  __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50
+1  0x00007f16c6c21e65 in __GI_abort () at abort.c:79
+2  0x00007f16c6c21d39 in __assert_fail_base  at assert.c:92
+3  0x00007f16c6c46e86 in __GI___assert_fail (assertion=assertion@entry=0x562e9bcdaadd "iwp->src == NULL", file=file@entry=0x562e9bcdaac8 "../chardev/char-io.c", line=line@entry=99, function=function@entry=0x562e9bcdab10 <__PRETTY_FUNCTION__.20549> "io_watch_poll_finalize") at assert.c:101
+4  0x0000562e9ba20c2c in io_watch_poll_finalize (source=<optimized out>) at ../chardev/char-io.c:99
+5  io_watch_poll_finalize (source=<optimized out>) at ../chardev/char-io.c:88
+6  0x00007f16c904aae0 in g_source_unref_internal () from /lib64/libglib-2.0.so.0
+7  0x00007f16c904baf9 in g_source_destroy_internal () from /lib64/libglib-2.0.so.0
+8  0x0000562e9ba20db0 in io_remove_watch_poll (source=0x562e9d6720b0) at ../chardev/char-io.c:147
+9  remove_fd_in_watch (chr=chr@entry=0x562e9d5f3800) at ../chardev/char-io.c:153
+10 0x0000562e9ba23ffb in update_ioc_handlers (s=0x562e9d5f3800) at ../chardev/char-socket.c:592
+11 0x0000562e9ba2072f in qemu_chr_fe_set_handlers_full at ../chardev/char-fe.c:279
+12 0x0000562e9ba207a9 in qemu_chr_fe_set_handlers at ../chardev/char-fe.c:304
+13 0x0000562e9ba2ca75 in monitor_qmp_setup_handlers_bh (opaque=0x562e9d4c2c60) at ../monitor/qmp.c:509
+14 0x0000562e9bb6222e in aio_bh_poll (ctx=ctx@entry=0x562e9d4c2f20) at ../util/async.c:216
+15 0x0000562e9bb4de0a in aio_poll (ctx=0x562e9d4c2f20, blocking=blocking@entry=true) at ../util/aio-posix.c:722
+16 0x0000562e9b99dfaa in iothread_run (opaque=0x562e9d4c26f0) at ../iothread.c:63
+17 0x0000562e9bb505a4 in qemu_thread_start (args=0x562e9d4c7ea0) at ../util/qemu-thread-posix.c:543
+18 0x00007f16c70081ca in start_thread (arg=<optimized out>) at pthread_create.c:479
+19 0x00007f16c6c398d3 in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95
+
+io_remove_watch_poll(), which makes sure that iwp->src is NULL, calls
+g_source_destroy() which finds that iwp->src is not NULL in the finalize
+callback. This can only happen if another thread has managed to trigger
+io_watch_poll_prepare() callback in the meantime.
+
+Move iwp->src destruction back to the finalize callback to prevent the
+described race, and also remove the stale comment. The deadlock glib bug
+was fixed back in 2010 by b35820285668 ("gmain: move finalization of
+GSource outside of context lock").
+
+Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sergey Dyasli <sergey.dyasli@nutanix.com>
+Link: https://lore.kernel.org/r/20240712092659.216206-1-sergey.dyasli@nutanix.com
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit e0bf95443ee9326d44031373420cf9f3513ee255)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ chardev/char-io.c | 19 +++++--------------
+ 1 file changed, 5 insertions(+), 14 deletions(-)
+
+diff --git a/chardev/char-io.c b/chardev/char-io.c
+index dab77b112e..3be17b51ca 100644
+--- a/chardev/char-io.c
++++ b/chardev/char-io.c
+@@ -87,16 +87,12 @@ static gboolean io_watch_poll_dispatch(GSource *source, GSourceFunc callback,
+ 
+ static void io_watch_poll_finalize(GSource *source)
+ {
+-    /*
+-     * Due to a glib bug, removing the last reference to a source
+-     * inside a finalize callback causes recursive locking (and a
+-     * deadlock).  This is not a problem inside other callbacks,
+-     * including dispatch callbacks, so we call io_remove_watch_poll
+-     * to remove this source.  At this point, iwp->src must
+-     * be NULL, or we would leak it.
+-     */
+     IOWatchPoll *iwp = io_watch_poll_from_source(source);
+-    assert(iwp->src == NULL);
++    if (iwp->src) {
++        g_source_destroy(iwp->src);
++        g_source_unref(iwp->src);
++        iwp->src = NULL;
++    }
+ }
+ 
+ static GSourceFuncs io_watch_poll_funcs = {
+@@ -139,11 +135,6 @@ static void io_remove_watch_poll(GSource *source)
+     IOWatchPoll *iwp;
+ 
+     iwp = io_watch_poll_from_source(source);
+-    if (iwp->src) {
+-        g_source_destroy(iwp->src);
+-        g_source_unref(iwp->src);
+-        iwp->src = NULL;
+-    }
+     g_source_destroy(&iwp->parent);
+ }
+ 

debian/patches/extra/0016-vhost-user-fix-VirtQ-notifier-cleanup.patch

@@ -1,149 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Xueming Li <xuemingl@nvidia.com>
-Date: Mon, 7 Feb 2022 15:19:29 +0800
-Subject: [PATCH] vhost-user: fix VirtQ notifier cleanup
-
-When vhost-user device cleanup, remove notifier MR and munmaps notifier
-address in the event-handling thread, VM CPU thread writing the notifier
-in concurrent fails with an error of accessing invalid address. It
-happens because MR is still being referenced and accessed in another
-thread while the underlying notifier mmap address is being freed and
-becomes invalid.
-
-This patch calls RCU and munmap notifiers in the callback after the
-memory flatview update finish.
-
-Fixes: 44866521bd6e ("vhost-user: support registering external host notifiers")
-Cc: qemu-stable@nongnu.org
-Signed-off-by: Xueming Li <xuemingl@nvidia.com>
-Message-Id: <20220207071929.527149-3-xuemingl@nvidia.com>
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-(cherry picked from commit 0b0af4d62f7002b31cd7b2762b26d2fcb76bb2ba)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/virtio/vhost-user.c         | 48 ++++++++++++++++++++--------------
- include/hw/virtio/vhost-user.h |  2 ++
- 2 files changed, 31 insertions(+), 19 deletions(-)
-
-diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
-index c671719e9b..ed5f9a5471 100644
---- a/hw/virtio/vhost-user.c
-+++ b/hw/virtio/vhost-user.c
-@@ -25,6 +25,7 @@
- #include "migration/migration.h"
- #include "migration/postcopy-ram.h"
- #include "trace.h"
-+#include "exec/ramblock.h"
- 
- #include <sys/ioctl.h>
- #include <sys/socket.h>
-@@ -1143,15 +1144,26 @@ static int vhost_user_set_vring_num(struct vhost_dev *dev,
-     return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring);
- }
- 
--static void vhost_user_host_notifier_remove(struct vhost_dev *dev,
--                                            int queue_idx)
-+static void vhost_user_host_notifier_free(VhostUserHostNotifier *n)
- {
--    struct vhost_user *u = dev->opaque;
--    VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
--    VirtIODevice *vdev = dev->vdev;
-+    assert(n && n->unmap_addr);
-+    munmap(n->unmap_addr, qemu_real_host_page_size);
-+    n->unmap_addr = NULL;
-+}
-+
-+static void vhost_user_host_notifier_remove(VhostUserState *user,
-+                                            VirtIODevice *vdev, int queue_idx)
-+{
-+    VhostUserHostNotifier *n = &user->notifier[queue_idx];
- 
-     if (n->addr) {
--        virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
-+        if (vdev) {
-+            virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
-+        }
-+        assert(!n->unmap_addr);
-+        n->unmap_addr = n->addr;
-+        n->addr = NULL;
-+        call_rcu(n, vhost_user_host_notifier_free, rcu);
-     }
- }
- 
-@@ -1190,8 +1202,9 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev,
-         .payload.state = *ring,
-         .hdr.size = sizeof(msg.payload.state),
-     };
-+    struct vhost_user *u = dev->opaque;
- 
--    vhost_user_host_notifier_remove(dev, ring->index);
-+    vhost_user_host_notifier_remove(u->user, dev->vdev, ring->index);
- 
-     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
-         return -1;
-@@ -1486,12 +1499,7 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev,
- 
-     n = &user->notifier[queue_idx];
- 
--    if (n->addr) {
--        virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
--        object_unparent(OBJECT(&n->mr));
--        munmap(n->addr, page_size);
--        n->addr = NULL;
--    }
-+    vhost_user_host_notifier_remove(user, vdev, queue_idx);
- 
-     if (area->u64 & VHOST_USER_VRING_NOFD_MASK) {
-         return 0;
-@@ -1510,9 +1518,12 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev,
- 
-     name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]",
-                            user, queue_idx);
--    if (!n->mr.ram) /* Don't init again after suspend. */
-+    if (!n->mr.ram) { /* Don't init again after suspend. */
-         memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name,
-                                           page_size, addr);
-+    } else {
-+        n->mr.ram_block->host = addr;
-+    }
-     g_free(name);
- 
-     if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) {
-@@ -2460,17 +2471,16 @@ bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp)
- void vhost_user_cleanup(VhostUserState *user)
- {
-     int i;
-+    VhostUserHostNotifier *n;
- 
-     if (!user->chr) {
-         return;
-     }
-     memory_region_transaction_begin();
-     for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
--        if (user->notifier[i].addr) {
--            object_unparent(OBJECT(&user->notifier[i].mr));
--            munmap(user->notifier[i].addr, qemu_real_host_page_size);
--            user->notifier[i].addr = NULL;
--        }
-+        n = &user->notifier[i];
-+        vhost_user_host_notifier_remove(user, NULL, i);
-+        object_unparent(OBJECT(&n->mr));
-     }
-     memory_region_transaction_commit();
-     user->chr = NULL;
-diff --git a/include/hw/virtio/vhost-user.h b/include/hw/virtio/vhost-user.h
-index f6012b2078..e44a41bb70 100644
---- a/include/hw/virtio/vhost-user.h
-+++ b/include/hw/virtio/vhost-user.h
-@@ -12,8 +12,10 @@
- #include "hw/virtio/virtio.h"
- 
- typedef struct VhostUserHostNotifier {
-+    struct rcu_head rcu;
-     MemoryRegion mr;
-     void *addr;
-+    void *unmap_addr;
- } VhostUserHostNotifier;
- 
- typedef struct VhostUserState {

debian/patches/extra/0017-virtio-fix-the-condition-for-iommu_platform-not-supp.patch

@@ -1,101 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Halil Pasic <pasic@linux.ibm.com>
-Date: Mon, 7 Feb 2022 12:28:57 +0100
-Subject: [PATCH] virtio: fix the condition for iommu_platform not supported
-
-The commit 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but
-unsupported") claims to fail the device hotplug when iommu_platform
-is requested, but not supported by the (vhost) device. On the first
-glance the condition for detecting that situation looks perfect, but
-because a certain peculiarity of virtio_platform it ain't.
-
-In fact the aforementioned commit introduces a regression. It breaks
-virtio-fs support for Secure Execution, and most likely also for AMD SEV
-or any other confidential guest scenario that relies encrypted guest
-memory.  The same also applies to any other vhost device that does not
-support _F_ACCESS_PLATFORM.
-
-The peculiarity is that iommu_platform and _F_ACCESS_PLATFORM collates
-"device can not access all of the guest RAM" and "iova != gpa, thus
-device needs to translate iova".
-
-Confidential guest technologies currently rely on the device/hypervisor
-offering _F_ACCESS_PLATFORM, so that, after the feature has been
-negotiated, the guest  grants access to the portions of memory the
-device needs to see. So in for confidential guests, generally,
-_F_ACCESS_PLATFORM is about the restricted access to memory, but not
-about the addresses used being something else than guest physical
-addresses.
-
-This is the very reason for which commit f7ef7e6e3b ("vhost: correctly
-turn on VIRTIO_F_IOMMU_PLATFORM") fences _F_ACCESS_PLATFORM from the
-vhost device that does not need it, because on the vhost interface it
-only means "I/O address translation is needed".
-
-This patch takes inspiration from f7ef7e6e3b ("vhost: correctly turn on
-VIRTIO_F_IOMMU_PLATFORM"), and uses the same condition for detecting the
-situation when _F_ACCESS_PLATFORM is requested, but no I/O translation
-by the device, and thus no device capability is needed. In this
-situation claiming that the device does not support iommu_plattform=on
-is counter-productive. So let us stop doing that!
-
-Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
-Reported-by: Jakob Naucke <Jakob.Naucke@ibm.com>
-Fixes: 04ceb61a40 ("virtio: Fail if iommu_platform is requested, but
-unsupported")
-Acked-by: Cornelia Huck <cohuck@redhat.com>
-Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com>
-Tested-by: Daniel Henrique Barboza <danielhb413@gmail.com>
-Cc: Kevin Wolf <kwolf@redhat.com>
-Cc: qemu-stable@nongnu.org
-
-Message-Id: <20220207112857.607829-1-pasic@linux.ibm.com>
-Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-Acked-by: Jason Wang <jasowang@redhat.com>
-(cherry picked from commit e65902a913bf31ba79a83a3bd3621108b85cf645)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/virtio/virtio-bus.c | 12 +++++++-----
- 1 file changed, 7 insertions(+), 5 deletions(-)
-
-diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c
-index d23db98c56..0f69d1c742 100644
---- a/hw/virtio/virtio-bus.c
-+++ b/hw/virtio/virtio-bus.c
-@@ -48,6 +48,7 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp)
-     VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
-     VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
-     bool has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
-+    bool vdev_has_iommu;
-     Error *local_err = NULL;
- 
-     DPRINTF("%s: plug device.\n", qbus->name);
-@@ -69,11 +70,6 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp)
-         return;
-     }
- 
--    if (has_iommu && !virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) {
--        error_setg(errp, "iommu_platform=true is not supported by the device");
--        return;
--    }
--
-     if (klass->device_plugged != NULL) {
-         klass->device_plugged(qbus->parent, &local_err);
-     }
-@@ -82,9 +78,15 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp)
-         return;
-     }
- 
-+    vdev_has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
-     if (klass->get_dma_as != NULL && has_iommu) {
-         virtio_add_feature(&vdev->host_features, VIRTIO_F_IOMMU_PLATFORM);
-         vdev->dma_as = klass->get_dma_as(qbus->parent);
-+        if (!vdev_has_iommu && vdev->dma_as != &address_space_memory) {
-+            error_setg(errp,
-+                       "iommu_platform=true is not supported by the device");
-+            return;
-+        }
-     } else {
-         vdev->dma_as = &address_space_memory;
-     }

debian/patches/extra/0017-virtio-pci-Fix-the-use-of-an-uninitialized-irqfd.patch

@@ -0,0 +1,77 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Cindy Lu <lulu@redhat.com>
+Date: Tue, 6 Aug 2024 17:37:12 +0800
+Subject: [PATCH] virtio-pci: Fix the use of an uninitialized irqfd
+
+The crash was reported in MAC OS and NixOS, here is the link for this bug
+https://gitlab.com/qemu-project/qemu/-/issues/2334
+https://gitlab.com/qemu-project/qemu/-/issues/2321
+
+In this bug, they are using the virtio_input device. The guest notifier was
+not supported for this device, The function virtio_pci_set_guest_notifiers()
+was not called, and the vector_irqfd was not initialized.
+
+So the fix is adding the check for vector_irqfd in virtio_pci_get_notifier()
+
+The function virtio_pci_get_notifier() can be used in various devices.
+It could also be called when VIRTIO_CONFIG_S_DRIVER_OK is not set. In this situation,
+the vector_irqfd being NULL is acceptable. We can allow the device continue to boot
+
+If the vector_irqfd still hasn't been initialized after VIRTIO_CONFIG_S_DRIVER_OK
+is set, it means that the function set_guest_notifiers was not called before the
+driver started. This indicates that the device is not using the notifier.
+At this point, we will let the check fail.
+
+This fix is verified in vyatta,MacOS,NixOS,fedora system.
+
+The bt tree for this bug is:
+Thread 6 "CPU 0/KVM" received signal SIGSEGV, Segmentation fault.
+[Switching to Thread 0x7c817be006c0 (LWP 1269146)]
+kvm_virtio_pci_vq_vector_use () at ../qemu-9.0.0/hw/virtio/virtio-pci.c:817
+817         if (irqfd->users == 0) {
+(gdb) thread apply all bt
+...
+Thread 6 (Thread 0x7c817be006c0 (LWP 1269146) "CPU 0/KVM"):
+0  kvm_virtio_pci_vq_vector_use () at ../qemu-9.0.0/hw/virtio/virtio-pci.c:817
+1  kvm_virtio_pci_vector_use_one () at ../qemu-9.0.0/hw/virtio/virtio-pci.c:893
+2  0x00005983657045e2 in memory_region_write_accessor () at ../qemu-9.0.0/system/memory.c:497
+3  0x0000598365704ba6 in access_with_adjusted_size () at ../qemu-9.0.0/system/memory.c:573
+4  0x0000598365705059 in memory_region_dispatch_write () at ../qemu-9.0.0/system/memory.c:1528
+5  0x00005983659b8e1f in flatview_write_continue_step.isra.0 () at ../qemu-9.0.0/system/physmem.c:2713
+6  0x000059836570ba7d in flatview_write_continue () at ../qemu-9.0.0/system/physmem.c:2743
+7  flatview_write () at ../qemu-9.0.0/system/physmem.c:2774
+8  0x000059836570bb76 in address_space_write () at ../qemu-9.0.0/system/physmem.c:2894
+9  0x0000598365763afe in address_space_rw () at ../qemu-9.0.0/system/physmem.c:2904
+10 kvm_cpu_exec () at ../qemu-9.0.0/accel/kvm/kvm-all.c:2917
+11 0x000059836576656e in kvm_vcpu_thread_fn () at ../qemu-9.0.0/accel/kvm/kvm-accel-ops.c:50
+12 0x0000598365926ca8 in qemu_thread_start () at ../qemu-9.0.0/util/qemu-thread-posix.c:541
+13 0x00007c8185bcd1cf in ??? () at /usr/lib/libc.so.6
+14 0x00007c8185c4e504 in clone () at /usr/lib/libc.so.6
+
+Fixes: 2ce6cff94d ("virtio-pci: fix use of a released vector")
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Cindy Lu <lulu@redhat.com>
+Message-Id: <20240806093715.65105-1-lulu@redhat.com>
+Acked-by: Jason Wang <jasowang@redhat.com>
+Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
+Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
+(cherry picked from commit a8e63ff289d137197ad7a701a587cc432872d798)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/virtio/virtio-pci.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
+index e04218a9fb..389bab003f 100644
+--- a/hw/virtio/virtio-pci.c
++++ b/hw/virtio/virtio-pci.c
+@@ -860,6 +860,9 @@ static int virtio_pci_get_notifier(VirtIOPCIProxy *proxy, int queue_no,
+     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+     VirtQueue *vq;
+ 
++    if (!proxy->vector_irqfd && vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)
++        return -1;
++
+     if (queue_no == VIRTIO_CONFIG_IRQ_IDX) {
+         *n = virtio_config_get_guest_notifier(vdev);
+         *vector = vdev->config_vector;

debian/patches/extra/0018-block-gluster-correctly-set-max_pdiscard-which-is-in.patch

@@ -1,38 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Fabian Ebner <f.ebner@proxmox.com>
-Date: Fri, 6 May 2022 14:38:35 +0200
-Subject: [PATCH] block/gluster: correctly set max_pdiscard which is int64_t
-
-Previously, max_pdiscard would be zero in the following assertion:
-qemu-system-x86_64: ../block/io.c:3166: bdrv_co_pdiscard: Assertion
-`max_pdiscard >= bs->bl.request_alignment' failed.
-
-Fixes: 0c8022876f ("block: use int64_t instead of int in driver discard handlers")
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- block/gluster.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/block/gluster.c b/block/gluster.c
-index 398976bc66..592e71b22a 100644
---- a/block/gluster.c
-+++ b/block/gluster.c
-@@ -891,7 +891,7 @@ out:
- static void qemu_gluster_refresh_limits(BlockDriverState *bs, Error **errp)
- {
-     bs->bl.max_transfer = GLUSTER_MAX_TRANSFER;
--    bs->bl.max_pdiscard = SIZE_MAX;
-+    bs->bl.max_pdiscard = INT64_MAX;
- }
- 
- static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
-@@ -1304,7 +1304,7 @@ static coroutine_fn int qemu_gluster_co_pdiscard(BlockDriverState *bs,
-     GlusterAIOCB acb;
-     BDRVGlusterState *s = bs->opaque;
- 
--    assert(bytes <= SIZE_MAX); /* rely on max_pdiscard */
-+    assert(bytes <= INT64_MAX); /* rely on max_pdiscard */
- 
-     acb.size = 0;
-     acb.ret = 0;

debian/patches/extra/0018-virtio-net-Ensure-queue-index-fits-with-RSS.patch

@@ -0,0 +1,35 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
+Date: Mon, 1 Jul 2024 20:58:04 +0900
+Subject: [PATCH] virtio-net: Ensure queue index fits with RSS
+
+Ensure the queue index points to a valid queue when software RSS
+enabled. The new calculation matches with the behavior of Linux's TAP
+device with the RSS eBPF program.
+
+Fixes: 4474e37a5b3a ("virtio-net: implement RX RSS processing")
+Reported-by: Zhibin Hu <huzhibin5@huawei.com>
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
+Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+(cherry picked from commit f1595ceb9aad36a6c1da95bcb77ab9509b38822d)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/net/virtio-net.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+index 3644bfd91b..f48588638d 100644
+--- a/hw/net/virtio-net.c
++++ b/hw/net/virtio-net.c
+@@ -1949,7 +1949,8 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
+     if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
+         int index = virtio_net_process_rss(nc, buf, size);
+         if (index >= 0) {
+-            NetClientState *nc2 = qemu_get_subqueue(n->nic, index);
++            NetClientState *nc2 =
++                qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
+             return virtio_net_receive_rcu(nc2, buf, size, true);
+         }
+     }

debian/patches/extra/0019-ui-vnc.c-Fixed-a-deadlock-bug.patch

@@ -1,72 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Rao Lei <lei.rao@intel.com>
-Date: Fri, 6 May 2022 14:38:36 +0200
-Subject: [PATCH] ui/vnc.c: Fixed a deadlock bug.
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-The GDB statck is as follows:
-(gdb) bt
-0  __lll_lock_wait (futex=futex@entry=0x56211df20360, private=0) at lowlevellock.c:52
-1  0x00007f263caf20a3 in __GI___pthread_mutex_lock (mutex=0x56211df20360) at ../nptl/pthread_mutex_lock.c:80
-2  0x000056211a757364 in qemu_mutex_lock_impl (mutex=0x56211df20360, file=0x56211a804857 "../ui/vnc-jobs.h", line=60)
-    at ../util/qemu-thread-posix.c:80
-3  0x000056211a0ef8c7 in vnc_lock_output (vs=0x56211df14200) at ../ui/vnc-jobs.h:60
-4  0x000056211a0efcb7 in vnc_clipboard_send (vs=0x56211df14200, count=1, dwords=0x7ffdf1701338) at ../ui/vnc-clipboard.c:138
-5  0x000056211a0f0129 in vnc_clipboard_notify (notifier=0x56211df244c8, data=0x56211dd1bbf0) at ../ui/vnc-clipboard.c:209
-6  0x000056211a75dde8 in notifier_list_notify (list=0x56211afa17d0 <clipboard_notifiers>, data=0x56211dd1bbf0) at ../util/notify.c:39
-7  0x000056211a0bf0e6 in qemu_clipboard_update (info=0x56211dd1bbf0) at ../ui/clipboard.c:50
-8  0x000056211a0bf05d in qemu_clipboard_peer_release (peer=0x56211df244c0, selection=QEMU_CLIPBOARD_SELECTION_CLIPBOARD)
-    at ../ui/clipboard.c:41
-9  0x000056211a0bef9b in qemu_clipboard_peer_unregister (peer=0x56211df244c0) at ../ui/clipboard.c:19
-10 0x000056211a0d45f3 in vnc_disconnect_finish (vs=0x56211df14200) at ../ui/vnc.c:1358
-11 0x000056211a0d4c9d in vnc_client_read (vs=0x56211df14200) at ../ui/vnc.c:1611
-12 0x000056211a0d4df8 in vnc_client_io (ioc=0x56211ce70690, condition=G_IO_IN, opaque=0x56211df14200) at ../ui/vnc.c:1649
-13 0x000056211a5b976c in qio_channel_fd_source_dispatch
-    (source=0x56211ce50a00, callback=0x56211a0d4d71 <vnc_client_io>, user_data=0x56211df14200) at ../io/channel-watch.c:84
-14 0x00007f263ccede8e in g_main_context_dispatch () at /lib/x86_64-linux-gnu/libglib-2.0.so.0
-15 0x000056211a77d4a1 in glib_pollfds_poll () at ../util/main-loop.c:232
-16 0x000056211a77d51f in os_host_main_loop_wait (timeout=958545) at ../util/main-loop.c:255
-17 0x000056211a77d630 in main_loop_wait (nonblocking=0) at ../util/main-loop.c:531
-18 0x000056211a45bc8e in qemu_main_loop () at ../softmmu/runstate.c:726
-19 0x000056211a0b45fa in main (argc=69, argv=0x7ffdf1701778, envp=0x7ffdf17019a8) at ../softmmu/main.c:50
-
-From the call trace, we can see it is a deadlock bug.
-vnc_disconnect_finish will acquire the output_mutex.
-But, the output_mutex will be acquired again in vnc_clipboard_send.
-Repeated locking will cause deadlock. So, I move
-qemu_clipboard_peer_unregister() behind vnc_unlock_output();
-
-Fixes: 0bf41cab93e ("ui/vnc: clipboard support")
-Signed-off-by: Lei Rao <lei.rao@intel.com>
-Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
-Message-Id: <20220105020808.597325-1-lei.rao@intel.com>
-Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
-(cherry-picked from commit 1dbbe6f172810026c51dc84ed927a3cc23017949)
-[FE: trivial backport for 6.2]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- ui/vnc.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/ui/vnc.c b/ui/vnc.c
-index af02522e84..b253e85c65 100644
---- a/ui/vnc.c
-+++ b/ui/vnc.c
-@@ -1354,12 +1354,12 @@ void vnc_disconnect_finish(VncState *vs)
-         /* last client gone */
-         vnc_update_server_surface(vs->vd);
-     }
-+    vnc_unlock_output(vs);
-+
-     if (vs->cbpeer.update.notify) {
-         qemu_clipboard_peer_unregister(&vs->cbpeer);
-     }
- 
--    vnc_unlock_output(vs);
--
-     qemu_mutex_destroy(&vs->output_mutex);
-     if (vs->bh != NULL) {
-         qemu_bh_delete(vs->bh);

debian/patches/extra/0019-virtio-net-Fix-network-stall-at-the-host-side-waitin.patch

@@ -0,0 +1,338 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: thomas <east.moutain.yang@gmail.com>
+Date: Fri, 12 Jul 2024 11:10:53 +0800
+Subject: [PATCH] virtio-net: Fix network stall at the host side waiting for
+ kick
+
+Patch 06b12970174 ("virtio-net: fix network stall under load")
+added double-check to test whether the available buffer size
+can satisfy the request or not, in case the guest has added
+some buffers to the avail ring simultaneously after the first
+check. It will be lucky if the available buffer size becomes
+okay after the double-check, then the host can send the packet
+to the guest. If the buffer size still can't satisfy the request,
+even if the guest has added some buffers, viritio-net would
+stall at the host side forever.
+
+The patch enables notification and checks whether the guest has
+added some buffers since last check of available buffers when
+the available buffers are insufficient. If no buffer is added,
+return false, else recheck the available buffers in the loop.
+If the available buffers are sufficient, disable notification
+and return true.
+
+Changes:
+1. Change the return type of virtqueue_get_avail_bytes() from void
+   to int, it returns an opaque that represents the shadow_avail_idx
+   of the virtqueue on success, else -1 on error.
+2. Add a new API: virtio_queue_enable_notification_and_check(),
+   it takes an opaque as input arg which is returned from
+   virtqueue_get_avail_bytes(). It enables notification firstly,
+   then checks whether the guest has added some buffers since
+   last check of available buffers or not by virtio_queue_poll(),
+   return ture if yes.
+
+The patch also reverts patch "06b12970174".
+
+The case below can reproduce the stall.
+
+                                       Guest 0
+                                     +--------+
+                                     | iperf  |
+                    ---------------> | server |
+         Host       |                +--------+
+       +--------+   |                    ...
+       | iperf  |----
+       | client |----                  Guest n
+       +--------+   |                +--------+
+                    |                | iperf  |
+                    ---------------> | server |
+                                     +--------+
+
+Boot many guests from qemu with virtio network:
+ qemu ... -netdev tap,id=net_x \
+    -device virtio-net-pci-non-transitional,\
+    iommu_platform=on,mac=xx:xx:xx:xx:xx:xx,netdev=net_x
+
+Each guest acts as iperf server with commands below:
+ iperf3 -s -D -i 10 -p 8001
+ iperf3 -s -D -i 10 -p 8002
+
+The host as iperf client:
+ iperf3 -c guest_IP -p 8001 -i 30 -w 256k -P 20 -t 40000
+ iperf3 -c guest_IP -p 8002 -i 30 -w 256k -P 20 -t 40000
+
+After some time, the host loses connection to the guest,
+the guest can send packet to the host, but can't receive
+packet from the host.
+
+It's more likely to happen if SWIOTLB is enabled in the guest,
+allocating and freeing bounce buffer takes some CPU ticks,
+copying from/to bounce buffer takes more CPU ticks, compared
+with that there is no bounce buffer in the guest.
+Once the rate of producing packets from the host approximates
+the rate of receiveing packets in the guest, the guest would
+loop in NAPI.
+
+         receive packets    ---
+               |             |
+               v             |
+           free buf      virtnet_poll
+               |             |
+               v             |
+     add buf to avail ring  ---
+               |
+               |  need kick the host?
+               |  NAPI continues
+               v
+         receive packets    ---
+               |             |
+               v             |
+           free buf      virtnet_poll
+               |             |
+               v             |
+     add buf to avail ring  ---
+               |
+               v
+              ...           ...
+
+On the other hand, the host fetches free buf from avail
+ring, if the buf in the avail ring is not enough, the
+host notifies the guest the event by writing the avail
+idx read from avail ring to the event idx of used ring,
+then the host goes to sleep, waiting for the kick signal
+from the guest.
+
+Once the guest finds the host is waiting for kick singal
+(in virtqueue_kick_prepare_split()), it kicks the host.
+
+The host may stall forever at the sequences below:
+
+         Host                        Guest
+     ------------                 -----------
+ fetch buf, send packet           receive packet ---
+         ...                          ...         |
+ fetch buf, send packet             add buf       |
+         ...                        add buf   virtnet_poll
+    buf not enough      avail idx-> add buf       |
+    read avail idx                  add buf       |
+                                    add buf      ---
+                                  receive packet ---
+    write event idx                   ...         |
+    wait for kick                   add buf   virtnet_poll
+                                      ...         |
+                                                 ---
+                                 no more packet, exit NAPI
+
+In the first loop of NAPI above, indicated in the range of
+virtnet_poll above, the host is sending packets while the
+guest is receiving packets and adding buffers.
+ step 1: The buf is not enough, for example, a big packet
+         needs 5 buf, but the available buf count is 3.
+         The host read current avail idx.
+ step 2: The guest adds some buf, then checks whether the
+         host is waiting for kick signal, not at this time.
+         The used ring is not empty, the guest continues
+         the second loop of NAPI.
+ step 3: The host writes the avail idx read from avail
+         ring to used ring as event idx via
+         virtio_queue_set_notification(q->rx_vq, 1).
+ step 4: At the end of the second loop of NAPI, recheck
+         whether kick is needed, as the event idx in the
+         used ring written by the host is beyound the
+         range of kick condition, the guest will not
+         send kick signal to the host.
+
+Fixes: 06b12970174 ("virtio-net: fix network stall under load")
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Wencheng Yang <east.moutain.yang@gmail.com>
+Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+(cherry picked from commit f937309fbdbb48c354220a3e7110c202ae4aa7fa)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/net/virtio-net.c        | 28 ++++++++++-------
+ hw/virtio/virtio.c         | 64 +++++++++++++++++++++++++++++++++++---
+ include/hw/virtio/virtio.h | 21 +++++++++++--
+ 3 files changed, 94 insertions(+), 19 deletions(-)
+
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+index f48588638d..d4b979d343 100644
+--- a/hw/net/virtio-net.c
++++ b/hw/net/virtio-net.c
+@@ -1680,24 +1680,28 @@ static bool virtio_net_can_receive(NetClientState *nc)
+ 
+ static int virtio_net_has_buffers(VirtIONetQueue *q, int bufsize)
+ {
++    int opaque;
++    unsigned int in_bytes;
+     VirtIONet *n = q->n;
+-    if (virtio_queue_empty(q->rx_vq) ||
+-        (n->mergeable_rx_bufs &&
+-         !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
+-        virtio_queue_set_notification(q->rx_vq, 1);
+-
+-        /* To avoid a race condition where the guest has made some buffers
+-         * available after the above check but before notification was
+-         * enabled, check for available buffers again.
+-         */
+-        if (virtio_queue_empty(q->rx_vq) ||
+-            (n->mergeable_rx_bufs &&
+-             !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
++
++    while (virtio_queue_empty(q->rx_vq) || n->mergeable_rx_bufs) {
++        opaque = virtqueue_get_avail_bytes(q->rx_vq, &in_bytes, NULL,
++                                           bufsize, 0);
++        /* Buffer is enough, disable notifiaction */
++        if (bufsize <= in_bytes) {
++            break;
++        }
++
++        if (virtio_queue_enable_notification_and_check(q->rx_vq, opaque)) {
++            /* Guest has added some buffers, try again */
++            continue;
++        } else {
+             return 0;
+         }
+     }
+ 
+     virtio_queue_set_notification(q->rx_vq, 0);
++
+     return 1;
+ }
+ 
+diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
+index fd2dfe3a6b..08fba6b2d8 100644
+--- a/hw/virtio/virtio.c
++++ b/hw/virtio/virtio.c
+@@ -743,6 +743,60 @@ int virtio_queue_empty(VirtQueue *vq)
+     }
+ }
+ 
++static bool virtio_queue_split_poll(VirtQueue *vq, unsigned shadow_idx)
++{
++    if (unlikely(!vq->vring.avail)) {
++        return false;
++    }
++
++    return (uint16_t)shadow_idx != vring_avail_idx(vq);
++}
++
++static bool virtio_queue_packed_poll(VirtQueue *vq, unsigned shadow_idx)
++{
++    VRingPackedDesc desc;
++    VRingMemoryRegionCaches *caches;
++
++    if (unlikely(!vq->vring.desc)) {
++        return false;
++    }
++
++    caches = vring_get_region_caches(vq);
++    if (!caches) {
++        return false;
++    }
++
++    vring_packed_desc_read(vq->vdev, &desc, &caches->desc,
++                           shadow_idx, true);
++
++    return is_desc_avail(desc.flags, vq->shadow_avail_wrap_counter);
++}
++
++static bool virtio_queue_poll(VirtQueue *vq, unsigned shadow_idx)
++{
++    if (virtio_device_disabled(vq->vdev)) {
++        return false;
++    }
++
++    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
++        return virtio_queue_packed_poll(vq, shadow_idx);
++    } else {
++        return virtio_queue_split_poll(vq, shadow_idx);
++    }
++}
++
++bool virtio_queue_enable_notification_and_check(VirtQueue *vq,
++                                                int opaque)
++{
++    virtio_queue_set_notification(vq, 1);
++
++    if (opaque >= 0) {
++        return virtio_queue_poll(vq, (unsigned)opaque);
++    } else {
++        return false;
++    }
++}
++
+ static void virtqueue_unmap_sg(VirtQueue *vq, const VirtQueueElement *elem,
+                                unsigned int len)
+ {
+@@ -1330,9 +1384,9 @@ err:
+     goto done;
+ }
+ 
+-void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
+-                               unsigned int *out_bytes,
+-                               unsigned max_in_bytes, unsigned max_out_bytes)
++int virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
++                              unsigned int *out_bytes, unsigned max_in_bytes,
++                              unsigned max_out_bytes)
+ {
+     uint16_t desc_size;
+     VRingMemoryRegionCaches *caches;
+@@ -1365,7 +1419,7 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
+                                         caches);
+     }
+ 
+-    return;
++    return (int)vq->shadow_avail_idx;
+ err:
+     if (in_bytes) {
+         *in_bytes = 0;
+@@ -1373,6 +1427,8 @@ err:
+     if (out_bytes) {
+         *out_bytes = 0;
+     }
++
++    return -1;
+ }
+ 
+ int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes,
+diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
+index 2eafad17b8..8b4da92889 100644
+--- a/include/hw/virtio/virtio.h
++++ b/include/hw/virtio/virtio.h
+@@ -271,9 +271,13 @@ void qemu_put_virtqueue_element(VirtIODevice *vdev, QEMUFile *f,
+                                 VirtQueueElement *elem);
+ int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes,
+                           unsigned int out_bytes);
+-void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
+-                               unsigned int *out_bytes,
+-                               unsigned max_in_bytes, unsigned max_out_bytes);
++/**
++ * Return <0 on error or an opaque >=0 to pass to
++ * virtio_queue_enable_notification_and_check on success.
++ */
++int virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
++                              unsigned int *out_bytes, unsigned max_in_bytes,
++                              unsigned max_out_bytes);
+ 
+ void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq);
+ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq);
+@@ -307,6 +311,17 @@ int virtio_queue_ready(VirtQueue *vq);
+ 
+ int virtio_queue_empty(VirtQueue *vq);
+ 
++/**
++ * Enable notification and check whether guest has added some
++ * buffers since last call to virtqueue_get_avail_bytes.
++ *
++ * @opaque: value returned from virtqueue_get_avail_bytes
++ */
++bool virtio_queue_enable_notification_and_check(VirtQueue *vq,
++                                                int opaque);
++
++void virtio_queue_set_shadow_avail_idx(VirtQueue *vq, uint16_t idx);
++
+ /* Host binding interface.  */
+ 
+ uint32_t virtio_config_readb(VirtIODevice *vdev, uint32_t addr);

debian/patches/extra/0020-display-qxl-render-fix-race-condition-in-qxl_cursor-.patch

@@ -1,37 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Mauro Matteo Cascella <mcascell@redhat.com>
-Date: Thu, 7 Apr 2022 10:11:06 +0200
-Subject: [PATCH] display/qxl-render: fix race condition in qxl_cursor
- (CVE-2021-4207)
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Avoid fetching 'width' and 'height' a second time to prevent possible
-race condition. Refer to security advisory
-https://starlabs.sg/advisories/22-4207/ for more information.
-
-Fixes: CVE-2021-4207
-Signed-off-by: Mauro Matteo Cascella <mcascell@redhat.com>
-Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
-Message-Id: <20220407081106.343235-1-mcascell@redhat.com>
-Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
-(cherry picked from commit 9569f5cb5b4bffa9d3ebc8ba7da1e03830a9a895)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/display/qxl-render.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/hw/display/qxl-render.c b/hw/display/qxl-render.c
-index d28849b121..237ed293ba 100644
---- a/hw/display/qxl-render.c
-+++ b/hw/display/qxl-render.c
-@@ -266,7 +266,7 @@ static QEMUCursor *qxl_cursor(PCIQXLDevice *qxl, QXLCursor *cursor,
-         }
-         break;
-     case SPICE_CURSOR_TYPE_ALPHA:
--        size = sizeof(uint32_t) * cursor->header.width * cursor->header.height;
-+        size = sizeof(uint32_t) * c->width * c->height;
-         qxl_unpack_chunks(c->data, size, qxl, &cursor->chunk, group_id);
-         if (qxl->debug > 2) {
-             cursor_print_ascii_art(c, "qxl/alpha");

debian/patches/extra/0020-net-Reinstate-net-nic-model-help-output-as-documente.patch

@@ -0,0 +1,70 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: David Woodhouse <dwmw@amazon.co.uk>
+Date: Tue, 9 Jul 2024 13:34:44 +0100
+Subject: [PATCH] net: Reinstate '-net nic, model=help' output as documented in
+ man page
+
+While refactoring the NIC initialization code, I broke '-net nic,model=help'
+which no longer outputs a list of available NIC models.
+
+Fixes: 2cdeca04adab ("net: report list of available models according to platform")
+Cc: qemu-stable@nongnu.org
+Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
+Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+(cherry picked from commit 64f75f57f9d2c8c12ac6d9355fa5d3a2af5879ca)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ net/net.c | 25 ++++++++++++++++++++++---
+ 1 file changed, 22 insertions(+), 3 deletions(-)
+
+diff --git a/net/net.c b/net/net.c
+index a2f0c828bb..e6ca2529bb 100644
+--- a/net/net.c
++++ b/net/net.c
+@@ -1150,6 +1150,21 @@ NICInfo *qemu_find_nic_info(const char *typename, bool match_default,
+     return NULL;
+ }
+ 
++static bool is_nic_model_help_option(const char *model)
++{
++    if (model && is_help_option(model)) {
++        /*
++         * Trigger the help output by instantiating the hash table which
++         * will gather tha available models as they get registered.
++         */
++        if (!nic_model_help) {
++            nic_model_help = g_hash_table_new_full(g_str_hash, g_str_equal,
++                                                   g_free, NULL);
++        }
++        return true;
++    }
++    return false;
++}
+ 
+ /* "I have created a device. Please configure it if you can" */
+ bool qemu_configure_nic_device(DeviceState *dev, bool match_default,
+@@ -1733,6 +1748,12 @@ void net_check_clients(void)
+ 
+ static int net_init_client(void *dummy, QemuOpts *opts, Error **errp)
+ {
++    const char *model = qemu_opt_get_del(opts, "model");
++
++    if (is_nic_model_help_option(model)) {
++        return 0;
++    }
++
+     return net_client_init(opts, false, errp);
+ }
+ 
+@@ -1789,9 +1810,7 @@ static int net_param_nic(void *dummy, QemuOpts *opts, Error **errp)
+     memset(ni, 0, sizeof(*ni));
+     ni->model = qemu_opt_get_del(opts, "model");
+ 
+-    if (!nic_model_help && !g_strcmp0(ni->model, "help")) {
+-        nic_model_help = g_hash_table_new_full(g_str_hash, g_str_equal,
+-                                               g_free, NULL);
++    if (is_nic_model_help_option(ni->model)) {
+         return 0;
+     }
+ 

debian/patches/extra/0021-net-Fix-net-nic-model-for-non-help-arguments.patch

@@ -0,0 +1,32 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: David Woodhouse <dwmw@amazon.co.uk>
+Date: Tue, 6 Aug 2024 18:21:37 +0100
+Subject: [PATCH] net: Fix '-net nic,model=' for non-help arguments
+
+Oops, don't *delete* the model option when checking for 'help'.
+
+Fixes: 64f75f57f9d2 ("net: Reinstate '-net nic, model=help' output as documented in man page")
+Reported-by: Hans <sungdgdhtryrt@gmail.com>
+Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
+Cc: qemu-stable@nongnu.org
+Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+(cherry picked from commit fa62cb989a9146c82f8f172715042852f5d36200)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ net/net.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/net/net.c b/net/net.c
+index e6ca2529bb..897bb936cf 100644
+--- a/net/net.c
++++ b/net/net.c
+@@ -1748,7 +1748,7 @@ void net_check_clients(void)
+ 
+ static int net_init_client(void *dummy, QemuOpts *opts, Error **errp)
+ {
+-    const char *model = qemu_opt_get_del(opts, "model");
++    const char *model = qemu_opt_get(opts, "model");
+ 
+     if (is_nic_model_help_option(model)) {
+         return 0;

debian/patches/extra/0021-ui-cursor-fix-integer-overflow-in-cursor_alloc-CVE-2.patch

@@ -1,83 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Mauro Matteo Cascella <mcascell@redhat.com>
-Date: Thu, 7 Apr 2022 10:17:12 +0200
-Subject: [PATCH] ui/cursor: fix integer overflow in cursor_alloc
- (CVE-2021-4206)
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Prevent potential integer overflow by limiting 'width' and 'height' to
-512x512. Also change 'datasize' type to size_t. Refer to security
-advisory https://starlabs.sg/advisories/22-4206/ for more information.
-
-Fixes: CVE-2021-4206
-Signed-off-by: Mauro Matteo Cascella <mcascell@redhat.com>
-Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
-Message-Id: <20220407081712.345609-1-mcascell@redhat.com>
-Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
-(cherry picked from commit fa892e9abb728e76afcf27323ab29c57fb0fe7aa)
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- hw/display/qxl-render.c | 7 +++++++
- hw/display/vmware_vga.c | 2 ++
- ui/cursor.c             | 8 +++++++-
- 3 files changed, 16 insertions(+), 1 deletion(-)
-
-diff --git a/hw/display/qxl-render.c b/hw/display/qxl-render.c
-index 237ed293ba..ca217004bf 100644
---- a/hw/display/qxl-render.c
-+++ b/hw/display/qxl-render.c
-@@ -247,6 +247,13 @@ static QEMUCursor *qxl_cursor(PCIQXLDevice *qxl, QXLCursor *cursor,
-     size_t size;
- 
-     c = cursor_alloc(cursor->header.width, cursor->header.height);
-+
-+    if (!c) {
-+        qxl_set_guest_bug(qxl, "%s: cursor %ux%u alloc error", __func__,
-+                cursor->header.width, cursor->header.height);
-+        goto fail;
-+    }
-+
-     c->hot_x = cursor->header.hot_spot_x;
-     c->hot_y = cursor->header.hot_spot_y;
-     switch (cursor->header.type) {
-diff --git a/hw/display/vmware_vga.c b/hw/display/vmware_vga.c
-index e2969a6c81..2b81d6122f 100644
---- a/hw/display/vmware_vga.c
-+++ b/hw/display/vmware_vga.c
-@@ -509,6 +509,8 @@ static inline void vmsvga_cursor_define(struct vmsvga_state_s *s,
-     int i, pixels;
- 
-     qc = cursor_alloc(c->width, c->height);
-+    assert(qc != NULL);
-+
-     qc->hot_x = c->hot_x;
-     qc->hot_y = c->hot_y;
-     switch (c->bpp) {
-diff --git a/ui/cursor.c b/ui/cursor.c
-index 1d62ddd4d0..835f0802f9 100644
---- a/ui/cursor.c
-+++ b/ui/cursor.c
-@@ -46,6 +46,8 @@ static QEMUCursor *cursor_parse_xpm(const char *xpm[])
- 
-     /* parse pixel data */
-     c = cursor_alloc(width, height);
-+    assert(c != NULL);
-+
-     for (pixel = 0, y = 0; y < height; y++, line++) {
-         for (x = 0; x < height; x++, pixel++) {
-             idx = xpm[line][x];
-@@ -91,7 +93,11 @@ QEMUCursor *cursor_builtin_left_ptr(void)
- QEMUCursor *cursor_alloc(int width, int height)
- {
-     QEMUCursor *c;
--    int datasize = width * height * sizeof(uint32_t);
-+    size_t datasize = width * height * sizeof(uint32_t);
-+
-+    if (width > 512 || height > 512) {
-+        return NULL;
-+    }
- 
-     c = g_malloc0(sizeof(QEMUCursor) + datasize);
-     c->width  = width;

debian/patches/extra/0022-target-arm-Don-t-assert-for-128-bit-tile-accesses-wh.patch

@@ -0,0 +1,57 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Peter Maydell <peter.maydell@linaro.org>
+Date: Mon, 22 Jul 2024 18:29:54 +0100
+Subject: [PATCH] target/arm: Don't assert for 128-bit tile accesses when SVL
+ is 128
+
+For an instruction which accesses a 128-bit element tile when
+the SVL is also 128 (for example MOV z0.Q, p0/M, ZA0H.Q[w0,0]),
+we will assert in get_tile_rowcol():
+
+qemu-system-aarch64: ../../tcg/tcg-op.c:926: tcg_gen_deposit_z_i32: Assertion `len > 0' failed.
+
+This happens because we calculate
+    len = ctz32(streaming_vec_reg_size(s)) - esz;$
+but if the SVL and the element size are the same len is 0, and
+the deposit operation asserts.
+
+In this case the ZA storage contains exactly one 128 bit
+element ZA tile, and the horizontal or vertical slice is just
+that tile. This means that regardless of the index value in
+the Ws register, we always access that tile. (In pseudocode terms,
+we calculate (index + offset) MOD 1, which is 0.)
+
+Special case the len == 0 case to avoid hitting the assertion
+in tcg_gen_deposit_z_i32().
+
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-id: 20240722172957.1041231-2-peter.maydell@linaro.org
+(cherry picked from commit 56f1c0db928aae0b83fd91c89ddb226b137e2b21)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/tcg/translate-sme.c | 10 +++++++++-
+ 1 file changed, 9 insertions(+), 1 deletion(-)
+
+diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
+index 185a8a917b..a50a419af2 100644
+--- a/target/arm/tcg/translate-sme.c
++++ b/target/arm/tcg/translate-sme.c
+@@ -49,7 +49,15 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
+     /* Prepare a power-of-two modulo via extraction of @len bits. */
+     len = ctz32(streaming_vec_reg_size(s)) - esz;
+ 
+-    if (vertical) {
++    if (!len) {
++        /*
++         * SVL is 128 and the element size is 128. There is exactly
++         * one 128x128 tile in the ZA storage, and so we calculate
++         * (Rs + imm) MOD 1, which is always 0. We need to special case
++         * this because TCG doesn't allow deposit ops with len 0.
++         */
++        tcg_gen_movi_i32(tmp, 0);
++    } else if (vertical) {
+         /*
+          * Compute the byte offset of the index within the tile:
+          *     (index % (svl / size)) * size

debian/patches/extra/0023-target-arm-Fix-UMOPA-UMOPS-of-16-bit-values.patch

@@ -0,0 +1,59 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Peter Maydell <peter.maydell@linaro.org>
+Date: Mon, 22 Jul 2024 18:29:55 +0100
+Subject: [PATCH] target/arm: Fix UMOPA/UMOPS of 16-bit values
+
+The UMOPA/UMOPS instructions are supposed to multiply unsigned 8 or
+16 bit elements and accumulate the products into a 64-bit element.
+In the Arm ARM pseudocode, this is done with the usual
+infinite-precision signed arithmetic.  However our implementation
+doesn't quite get it right, because in the DEF_IMOP_64() macro we do:
+  sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0);
+
+where NTYPE and MTYPE are uint16_t or int16_t.  In the uint16_t case,
+the C usual arithmetic conversions mean the values are converted to
+"int" type and the multiply is done as a 32-bit multiply.  This means
+that if the inputs are, for example, 0xffff and 0xffff then the
+result is 0xFFFE0001 as an int, which is then promoted to uint64_t
+for the accumulation into sum; this promotion incorrectly sign
+extends the multiply.
+
+Avoid the incorrect sign extension by casting to int64_t before
+the multiply, so we do the multiply as 64-bit signed arithmetic,
+which is a type large enough that the multiply can never
+overflow into the sign bit.
+
+(The equivalent 8-bit operations in DEF_IMOP_32() are fine, because
+the 8-bit multiplies can never overflow into the sign bit of a
+32-bit integer.)
+
+Cc: qemu-stable@nongnu.org
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2372
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-id: 20240722172957.1041231-3-peter.maydell@linaro.org
+(cherry picked from commit ea3f5a90f036734522e9af3bffd77e69e9f47355)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/tcg/sme_helper.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
+index 5a6dd76489..f9001f5213 100644
+--- a/target/arm/tcg/sme_helper.c
++++ b/target/arm/tcg/sme_helper.c
+@@ -1146,10 +1146,10 @@ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \
+     uint64_t sum = 0;                                                       \
+     /* Apply P to N as a mask, making the inactive elements 0. */           \
+     n &= expand_pred_h(p);                                                  \
+-    sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0);                               \
+-    sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16);                             \
+-    sum += (NTYPE)(n >> 32) * (MTYPE)(m >> 32);                             \
+-    sum += (NTYPE)(n >> 48) * (MTYPE)(m >> 48);                             \
++    sum += (int64_t)(NTYPE)(n >> 0) * (MTYPE)(m >> 0);                      \
++    sum += (int64_t)(NTYPE)(n >> 16) * (MTYPE)(m >> 16);                    \
++    sum += (int64_t)(NTYPE)(n >> 32) * (MTYPE)(m >> 32);                    \
++    sum += (int64_t)(NTYPE)(n >> 48) * (MTYPE)(m >> 48);                    \
+     return neg ? a - sum : a + sum;                                         \
+ }
+ 

debian/patches/extra/0024-target-arm-Avoid-shifts-by-1-in-tszimm_shr-and-tszim.patch

@@ -0,0 +1,62 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Peter Maydell <peter.maydell@linaro.org>
+Date: Mon, 22 Jul 2024 18:29:56 +0100
+Subject: [PATCH] target/arm: Avoid shifts by -1 in tszimm_shr() and
+ tszimm_shl()
+
+The function tszimm_esz() returns a shift amount, or possibly -1 in
+certain cases that correspond to unallocated encodings in the
+instruction set.  We catch these later in the trans_ functions
+(generally with an "a-esz < 0" check), but before we do the
+decodetree-generated code will also call tszimm_shr() or tszimm_sl(),
+which will use the tszimm_esz() return value as a shift count without
+checking that it is not negative, which is undefined behaviour.
+
+Avoid the UB by checking the return value in tszimm_shr() and
+tszimm_shl().
+
+Cc: qemu-stable@nongnu.org
+Resolves: Coverity CID 1547617, 1547694
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-id: 20240722172957.1041231-4-peter.maydell@linaro.org
+(cherry picked from commit 76916dfa89e8900639c1055c07a295c06628a0bc)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/tcg/translate-sve.c | 18 ++++++++++++++++--
+ 1 file changed, 16 insertions(+), 2 deletions(-)
+
+diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
+index ada05aa530..466a19c25a 100644
+--- a/target/arm/tcg/translate-sve.c
++++ b/target/arm/tcg/translate-sve.c
+@@ -50,13 +50,27 @@ static int tszimm_esz(DisasContext *s, int x)
+ 
+ static int tszimm_shr(DisasContext *s, int x)
+ {
+-    return (16 << tszimm_esz(s, x)) - x;
++    /*
++     * We won't use the tszimm_shr() value if tszimm_esz() returns -1 (the
++     * trans function will check for esz < 0), so we can return any
++     * value we like from here in that case as long as we avoid UB.
++     */
++    int esz = tszimm_esz(s, x);
++    if (esz < 0) {
++        return esz;
++    }
++    return (16 << esz) - x;
+ }
+ 
+ /* See e.g. LSL (immediate, predicated).  */
+ static int tszimm_shl(DisasContext *s, int x)
+ {
+-    return x - (8 << tszimm_esz(s, x));
++    /* As with tszimm_shr(), value will be unused if esz < 0 */
++    int esz = tszimm_esz(s, x);
++    if (esz < 0) {
++        return esz;
++    }
++    return x - (8 << esz);
+ }
+ 
+ /* The SH bit is in bit 8.  Extract the low 8 and shift.  */

debian/patches/extra/0025-target-arm-Ignore-SMCR_EL2.LEN-and-SVCR_EL2.LEN-if-E.patch

@@ -0,0 +1,41 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Peter Maydell <peter.maydell@linaro.org>
+Date: Mon, 22 Jul 2024 18:29:57 +0100
+Subject: [PATCH] target/arm: Ignore SMCR_EL2.LEN and SVCR_EL2.LEN if EL2 is
+ not enabled
+
+When determining the current vector length, the SMCR_EL2.LEN and
+SVCR_EL2.LEN settings should only be considered if EL2 is enabled
+(compare the pseudocode CurrentSVL and CurrentNSVL which call
+EL2Enabled()).
+
+We were checking against ARM_FEATURE_EL2 rather than calling
+arm_is_el2_enabled(), which meant that we would look at
+SMCR_EL2/SVCR_EL2 when in Secure EL1 or Secure EL0 even if Secure EL2
+was not enabled.
+
+Use the correct check in sve_vqm1_for_el_sm().
+
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-id: 20240722172957.1041231-5-peter.maydell@linaro.org
+(cherry picked from commit f573ac059ed060234fcef4299fae9e500d357c33)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/helper.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/target/arm/helper.c b/target/arm/helper.c
+index a620481d7c..42044ae14b 100644
+--- a/target/arm/helper.c
++++ b/target/arm/helper.c
+@@ -7191,7 +7191,7 @@ uint32_t sve_vqm1_for_el_sm(CPUARMState *env, int el, bool sm)
+     if (el <= 1 && !el_is_in_host(env, el)) {
+         len = MIN(len, 0xf & (uint32_t)cr[1]);
+     }
+-    if (el <= 2 && arm_feature(env, ARM_FEATURE_EL2)) {
++    if (el <= 2 && arm_is_el2_enabled(env)) {
+         len = MIN(len, 0xf & (uint32_t)cr[2]);
+     }
+     if (arm_feature(env, ARM_FEATURE_EL3)) {

debian/patches/extra/0026-target-arm-Handle-denormals-correctly-for-FMOPA-wide.patch

@@ -0,0 +1,164 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Peter Maydell <peter.maydell@linaro.org>
+Date: Thu, 1 Aug 2024 10:15:03 +0100
+Subject: [PATCH] target/arm: Handle denormals correctly for FMOPA (widening)
+
+The FMOPA (widening) SME instruction takes pairs of half-precision
+floating point values, widens them to single-precision, does a
+two-way dot product and accumulates the results into a
+single-precision destination.  We don't quite correctly handle the
+FPCR bits FZ and FZ16 which control flushing of denormal inputs and
+outputs.  This is because at the moment we pass a single float_status
+value to the helper function, which then uses that configuration for
+all the fp operations it does.  However, because the inputs to this
+operation are float16 and the outputs are float32 we need to use the
+fp_status_f16 for the float16 input widening but the normal fp_status
+for everything else.  Otherwise we will apply the flushing control
+FPCR.FZ16 to the 32-bit output rather than the FPCR.FZ control, and
+incorrectly flush a denormal output to zero when we should not (or
+vice-versa).
+
+(In commit 207d30b5fdb5b we tried to fix the FZ handling but
+didn't get it right, switching from "use FPCR.FZ for everything" to
+"use FPCR.FZ16 for everything".)
+
+Pass the CPU env to the sme_fmopa_h helper instead of an fp_status
+pointer, and have the helper pass an extra fp_status into the
+f16_dotadd() function so that we can use the right status for the
+right parts of this operation.
+
+Cc: qemu-stable@nongnu.org
+Fixes: 207d30b5fdb5 ("target/arm: Use FPST_F16 for SME FMOPA (widening)")
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2373
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+(cherry picked from commit 55f9f4ee018c5ccea81d8c8c586756d7711ae46f)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/arm/tcg/helper-sme.h    |  2 +-
+ target/arm/tcg/sme_helper.c    | 39 +++++++++++++++++++++++-----------
+ target/arm/tcg/translate-sme.c | 25 ++++++++++++++++++++--
+ 3 files changed, 51 insertions(+), 15 deletions(-)
+
+diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
+index 27eef49a11..d22bf9d21b 100644
+--- a/target/arm/tcg/helper-sme.h
++++ b/target/arm/tcg/helper-sme.h
+@@ -121,7 +121,7 @@ DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+ DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+ 
+ DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG,
+-                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
++                   void, ptr, ptr, ptr, ptr, ptr, env, i32)
+ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
+                    void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
+diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
+index f9001f5213..3906bb51c0 100644
+--- a/target/arm/tcg/sme_helper.c
++++ b/target/arm/tcg/sme_helper.c
+@@ -976,12 +976,23 @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg)
+ }
+ 
+ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
+-                          float_status *s_std, float_status *s_odd)
++                          float_status *s_f16, float_status *s_std,
++                          float_status *s_odd)
+ {
+-    float64 e1r = float16_to_float64(e1 & 0xffff, true, s_std);
+-    float64 e1c = float16_to_float64(e1 >> 16, true, s_std);
+-    float64 e2r = float16_to_float64(e2 & 0xffff, true, s_std);
+-    float64 e2c = float16_to_float64(e2 >> 16, true, s_std);
++    /*
++     * We need three different float_status for different parts of this
++     * operation:
++     *  - the input conversion of the float16 values must use the
++     *    f16-specific float_status, so that the FPCR.FZ16 control is applied
++     *  - operations on float32 including the final accumulation must use
++     *    the normal float_status, so that FPCR.FZ is applied
++     *  - we have pre-set-up copy of s_std which is set to round-to-odd,
++     *    for the multiply (see below)
++     */
++    float64 e1r = float16_to_float64(e1 & 0xffff, true, s_f16);
++    float64 e1c = float16_to_float64(e1 >> 16, true, s_f16);
++    float64 e2r = float16_to_float64(e2 & 0xffff, true, s_f16);
++    float64 e2c = float16_to_float64(e2 >> 16, true, s_f16);
+     float64 t64;
+     float32 t32;
+ 
+@@ -1003,20 +1014,23 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
+ }
+ 
+ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
+-                         void *vpm, void *vst, uint32_t desc)
++                         void *vpm, CPUARMState *env, uint32_t desc)
+ {
+     intptr_t row, col, oprsz = simd_maxsz(desc);
+     uint32_t neg = simd_data(desc) * 0x80008000u;
+     uint16_t *pn = vpn, *pm = vpm;
+-    float_status fpst_odd, fpst_std;
++    float_status fpst_odd, fpst_std, fpst_f16;
+ 
+     /*
+-     * Make a copy of float_status because this operation does not
+-     * update the cumulative fp exception status.  It also produces
+-     * default nans.  Make a second copy with round-to-odd -- see above.
++     * Make copies of fp_status and fp_status_f16, because this operation
++     * does not update the cumulative fp exception status.  It also
++     * produces default NaNs. We also need a second copy of fp_status with
++     * round-to-odd -- see above.
+      */
+-    fpst_std = *(float_status *)vst;
++    fpst_f16 = env->vfp.fp_status_f16;
++    fpst_std = env->vfp.fp_status;
+     set_default_nan_mode(true, &fpst_std);
++    set_default_nan_mode(true, &fpst_f16);
+     fpst_odd = fpst_std;
+     set_float_rounding_mode(float_round_to_odd, &fpst_odd);
+ 
+@@ -1036,7 +1050,8 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
+                         uint32_t m = *(uint32_t *)(vzm + H1_4(col));
+ 
+                         m = f16mop_adj_pair(m, pcol, 0);
+-                        *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd);
++                        *a = f16_dotadd(*a, n, m,
++                                        &fpst_f16, &fpst_std, &fpst_odd);
+                     }
+                     col += 4;
+                     pcol >>= 4;
+diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
+index a50a419af2..ae42ddef7b 100644
+--- a/target/arm/tcg/translate-sme.c
++++ b/target/arm/tcg/translate-sme.c
+@@ -334,8 +334,29 @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz,
+     return true;
+ }
+ 
+-TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a,
+-           MO_32, FPST_FPCR_F16, gen_helper_sme_fmopa_h)
++static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
++                           gen_helper_gvec_5_ptr *fn)
++{
++    int svl = streaming_vec_reg_size(s);
++    uint32_t desc = simd_desc(svl, svl, a->sub);
++    TCGv_ptr za, zn, zm, pn, pm;
++
++    if (!sme_smza_enabled_check(s)) {
++        return true;
++    }
++
++    za = get_tile(s, esz, a->zad);
++    zn = vec_full_reg_ptr(s, a->zn);
++    zm = vec_full_reg_ptr(s, a->zm);
++    pn = pred_full_reg_ptr(s, a->pn);
++    pm = pred_full_reg_ptr(s, a->pm);
++
++    fn(za, zn, zm, pn, pm, tcg_env, tcg_constant_i32(desc));
++    return true;
++}
++
++TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a,
++           MO_32, gen_helper_sme_fmopa_h)
+ TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
+            MO_32, FPST_FPCR, gen_helper_sme_fmopa_s)
+ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,

debian/patches/extra/0027-intel_iommu-fix-FRCD-construction-macro.patch

@@ -0,0 +1,39 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Cl=C3=A9ment=20Mathieu--Drif?=
+ <clement.mathieu--drif@eviden.com>
+Date: Tue, 9 Jul 2024 14:26:08 +0000
+Subject: [PATCH] intel_iommu: fix FRCD construction macro
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+The constant must be unsigned, otherwise the two's complement
+overrides the other fields when a PASID is present.
+
+Fixes: 1b2b12376c8a ("intel-iommu: PASID support")
+Signed-off-by: Clément Mathieu--Drif <clement.mathieu--drif@eviden.com>
+Reviewed-by: Yi Liu <yi.l.liu@intel.com>
+Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
+Reviewed-by: Minwoo Im <minwoo.im@samsung.com>
+Message-Id: <20240709142557.317271-2-clement.mathieu--drif@eviden.com>
+Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
+Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
+(cherry picked from commit a3c8d7e38550c3d5a46e6fa94ffadfa625a4861d)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ hw/i386/intel_iommu_internal.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
+index f8cf99bddf..cbc4030031 100644
+--- a/hw/i386/intel_iommu_internal.h
++++ b/hw/i386/intel_iommu_internal.h
+@@ -267,7 +267,7 @@
+ /* For the low 64-bit of 128-bit */
+ #define VTD_FRCD_FI(val)        ((val) & ~0xfffULL)
+ #define VTD_FRCD_PV(val)        (((val) & 0xffffULL) << 40)
+-#define VTD_FRCD_PP(val)        (((val) & 0x1) << 31)
++#define VTD_FRCD_PP(val)        (((val) & 0x1ULL) << 31)
+ #define VTD_FRCD_IR_IDX(val)    (((val) & 0xffffULL) << 48)
+ 
+ /* DMA Remapping Fault Conditions */

debian/patches/extra/0028-target-i386-Do-not-apply-REX-to-MMX-operands.patch

@@ -0,0 +1,33 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Richard Henderson <richard.henderson@linaro.org>
+Date: Mon, 12 Aug 2024 12:58:42 +1000
+Subject: [PATCH] target/i386: Do not apply REX to MMX operands
+
+Cc: qemu-stable@nongnu.org
+Fixes: b3e22b2318a ("target/i386: add core of new i386 decoder")
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2495
+Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
+Link: https://lore.kernel.org/r/20240812025844.58956-2-richard.henderson@linaro.org
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 416f2b16c02c618c0f233372ebfe343f9ee667d4)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ target/i386/tcg/decode-new.c.inc | 5 ++++-
+ 1 file changed, 4 insertions(+), 1 deletion(-)
+
+diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.c.inc
+index 4209d59ca8..09b8d2314a 100644
+--- a/target/i386/tcg/decode-new.c.inc
++++ b/target/i386/tcg/decode-new.c.inc
+@@ -1271,7 +1271,10 @@ static bool decode_op(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode,
+             op->unit = X86_OP_SSE;
+         }
+     get_reg:
+-        op->n = ((get_modrm(s, env) >> 3) & 7) | REX_R(s);
++        op->n = ((get_modrm(s, env) >> 3) & 7);
++        if (op->unit != X86_OP_MMX) {
++            op->n |= REX_R(s);
++        }
+         break;
+ 
+     case X86_TYPE_E:  /* ALU modrm operand */

debian/patches/extra/0029-module-Prevent-crash-by-resetting-local_err-in-modul.patch

@@ -0,0 +1,42 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
+Date: Fri, 9 Aug 2024 14:13:40 +0200
+Subject: [PATCH] module: Prevent crash by resetting local_err in
+ module_load_qom_all()
+
+Set local_err to NULL after it has been freed in error_report_err(). This
+avoids triggering assert(*errp == NULL) failure in error_setv() when
+local_err is reused in the loop.
+
+Signed-off-by: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
+Reviewed-by: Claudio Fontana <cfontana@suse.de>
+Reviewed-by: Denis V. Lunev <den@openvz.org>
+Link: https://lore.kernel.org/r/20240809121340.992049-2-alexander.ivanov@virtuozzo.com
+[Do the same by moving the declaration instead. - Paolo]
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 940d802b24e63650e0eacad3714e2ce171cba17c)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ util/module.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/util/module.c b/util/module.c
+index 32e263163c..3eb0f06df1 100644
+--- a/util/module.c
++++ b/util/module.c
+@@ -354,13 +354,13 @@ int module_load_qom(const char *type, Error **errp)
+ void module_load_qom_all(void)
+ {
+     const QemuModinfo *modinfo;
+-    Error *local_err = NULL;
+ 
+     if (module_loaded_qom_all) {
+         return;
+     }
+ 
+     for (modinfo = module_info; modinfo->name != NULL; modinfo++) {
++        Error *local_err = NULL;
+         if (!modinfo->objs) {
+             continue;
+         }

debian/patches/extra/0030-nbd-server-Plumb-in-new-args-to-nbd_client_add.patch

@@ -0,0 +1,164 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Wed, 7 Aug 2024 08:50:01 -0500
+Subject: [PATCH] nbd/server: Plumb in new args to nbd_client_add()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Upcoming patches to fix a CVE need to track an opaque pointer passed
+in by the owner of a client object, as well as request for a time
+limit on how fast negotiation must complete.  Prepare for that by
+changing the signature of nbd_client_new() and adding an accessor to
+get at the opaque pointer, although for now the two servers
+(qemu-nbd.c and blockdev-nbd.c) do not change behavior even though
+they pass in a new default timeout value.
+
+Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-ID: <20240807174943.771624-11-eblake@redhat.com>
+Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
+[eblake: s/LIMIT/MAX_SECS/ as suggested by Dan]
+Signed-off-by: Eric Blake <eblake@redhat.com>
+(cherry picked from commit fb1c2aaa981e0a2fa6362c9985f1296b74f055ac)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ blockdev-nbd.c      |  6 ++++--
+ include/block/nbd.h | 11 ++++++++++-
+ nbd/server.c        | 20 +++++++++++++++++---
+ qemu-nbd.c          |  4 +++-
+ 4 files changed, 34 insertions(+), 7 deletions(-)
+
+diff --git a/blockdev-nbd.c b/blockdev-nbd.c
+index 213012435f..267a1de903 100644
+--- a/blockdev-nbd.c
++++ b/blockdev-nbd.c
+@@ -64,8 +64,10 @@ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
+     nbd_update_server_watch(nbd_server);
+ 
+     qio_channel_set_name(QIO_CHANNEL(cioc), "nbd-server");
+-    nbd_client_new(cioc, nbd_server->tlscreds, nbd_server->tlsauthz,
+-                   nbd_blockdev_client_closed);
++    /* TODO - expose handshake timeout as QMP option */
++    nbd_client_new(cioc, NBD_DEFAULT_HANDSHAKE_MAX_SECS,
++                   nbd_server->tlscreds, nbd_server->tlsauthz,
++                   nbd_blockdev_client_closed, NULL);
+ }
+ 
+ static void nbd_update_server_watch(NBDServerData *s)
+diff --git a/include/block/nbd.h b/include/block/nbd.h
+index 4e7bd6342f..1d4d65922d 100644
+--- a/include/block/nbd.h
++++ b/include/block/nbd.h
+@@ -33,6 +33,12 @@ typedef struct NBDMetaContexts NBDMetaContexts;
+ 
+ extern const BlockExportDriver blk_exp_nbd;
+ 
++/*
++ * NBD_DEFAULT_HANDSHAKE_MAX_SECS: Number of seconds in which client must
++ * succeed at NBD_OPT_GO before being forcefully dropped as too slow.
++ */
++#define NBD_DEFAULT_HANDSHAKE_MAX_SECS 10
++
+ /* Handshake phase structs - this struct is passed on the wire */
+ 
+ typedef struct NBDOption {
+@@ -403,9 +409,12 @@ AioContext *nbd_export_aio_context(NBDExport *exp);
+ NBDExport *nbd_export_find(const char *name);
+ 
+ void nbd_client_new(QIOChannelSocket *sioc,
++                    uint32_t handshake_max_secs,
+                     QCryptoTLSCreds *tlscreds,
+                     const char *tlsauthz,
+-                    void (*close_fn)(NBDClient *, bool));
++                    void (*close_fn)(NBDClient *, bool),
++                    void *owner);
++void *nbd_client_owner(NBDClient *client);
+ void nbd_client_get(NBDClient *client);
+ void nbd_client_put(NBDClient *client);
+ 
+diff --git a/nbd/server.c b/nbd/server.c
+index 892797bb11..e50012499f 100644
+--- a/nbd/server.c
++++ b/nbd/server.c
+@@ -124,12 +124,14 @@ struct NBDMetaContexts {
+ struct NBDClient {
+     int refcount; /* atomic */
+     void (*close_fn)(NBDClient *client, bool negotiated);
++    void *owner;
+ 
+     QemuMutex lock;
+ 
+     NBDExport *exp;
+     QCryptoTLSCreds *tlscreds;
+     char *tlsauthz;
++    uint32_t handshake_max_secs;
+     QIOChannelSocket *sioc; /* The underlying data channel */
+     QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
+ 
+@@ -3191,6 +3193,7 @@ static coroutine_fn void nbd_co_client_start(void *opaque)
+ 
+     qemu_co_mutex_init(&client->send_lock);
+ 
++    /* TODO - utilize client->handshake_max_secs */
+     if (nbd_negotiate(client, &local_err)) {
+         if (local_err) {
+             error_report_err(local_err);
+@@ -3205,14 +3208,17 @@ static coroutine_fn void nbd_co_client_start(void *opaque)
+ }
+ 
+ /*
+- * Create a new client listener using the given channel @sioc.
++ * Create a new client listener using the given channel @sioc and @owner.
+  * Begin servicing it in a coroutine.  When the connection closes, call
+- * @close_fn with an indication of whether the client completed negotiation.
++ * @close_fn with an indication of whether the client completed negotiation
++ * within @handshake_max_secs seconds (0 for unbounded).
+  */
+ void nbd_client_new(QIOChannelSocket *sioc,
++                    uint32_t handshake_max_secs,
+                     QCryptoTLSCreds *tlscreds,
+                     const char *tlsauthz,
+-                    void (*close_fn)(NBDClient *, bool))
++                    void (*close_fn)(NBDClient *, bool),
++                    void *owner)
+ {
+     NBDClient *client;
+     Coroutine *co;
+@@ -3225,13 +3231,21 @@ void nbd_client_new(QIOChannelSocket *sioc,
+         object_ref(OBJECT(client->tlscreds));
+     }
+     client->tlsauthz = g_strdup(tlsauthz);
++    client->handshake_max_secs = handshake_max_secs;
+     client->sioc = sioc;
+     qio_channel_set_delay(QIO_CHANNEL(sioc), false);
+     object_ref(OBJECT(client->sioc));
+     client->ioc = QIO_CHANNEL(sioc);
+     object_ref(OBJECT(client->ioc));
+     client->close_fn = close_fn;
++    client->owner = owner;
+ 
+     co = qemu_coroutine_create(nbd_co_client_start, client);
+     qemu_coroutine_enter(co);
+ }
++
++void *
++nbd_client_owner(NBDClient *client)
++{
++    return client->owner;
++}
+diff --git a/qemu-nbd.c b/qemu-nbd.c
+index d7b3ccab21..48e2fa5858 100644
+--- a/qemu-nbd.c
++++ b/qemu-nbd.c
+@@ -390,7 +390,9 @@ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
+ 
+     nb_fds++;
+     nbd_update_server_watch();
+-    nbd_client_new(cioc, tlscreds, tlsauthz, nbd_client_closed);
++    /* TODO - expose handshake timeout as command line option */
++    nbd_client_new(cioc, NBD_DEFAULT_HANDSHAKE_MAX_SECS,
++                   tlscreds, tlsauthz, nbd_client_closed, NULL);
+ }
+ 
+ static void nbd_update_server_watch(void)

debian/patches/extra/0031-nbd-server-CVE-2024-7409-Cap-default-max-connections.patch

@@ -0,0 +1,172 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Tue, 6 Aug 2024 13:53:00 -0500
+Subject: [PATCH] nbd/server: CVE-2024-7409: Cap default max-connections to 100
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Allowing an unlimited number of clients to any web service is a recipe
+for a rudimentary denial of service attack: the client merely needs to
+open lots of sockets without closing them, until qemu no longer has
+any more fds available to allocate.
+
+For qemu-nbd, we default to allowing only 1 connection unless more are
+explicitly asked for (-e or --shared); this was historically picked as
+a nice default (without an explicit -t, a non-persistent qemu-nbd goes
+away after a client disconnects, without needing any additional
+follow-up commands), and we are not going to change that interface now
+(besides, someday we want to point people towards qemu-storage-daemon
+instead of qemu-nbd).
+
+But for qemu proper, and the newer qemu-storage-daemon, the QMP
+nbd-server-start command has historically had a default of unlimited
+number of connections, in part because unlike qemu-nbd it is
+inherently persistent until nbd-server-stop.  Allowing multiple client
+sockets is particularly useful for clients that can take advantage of
+MULTI_CONN (creating parallel sockets to increase throughput),
+although known clients that do so (such as libnbd's nbdcopy) typically
+use only 8 or 16 connections (the benefits of scaling diminish once
+more sockets are competing for kernel attention).  Picking a number
+large enough for typical use cases, but not unlimited, makes it
+slightly harder for a malicious client to perform a denial of service
+merely by opening lots of connections withot progressing through the
+handshake.
+
+This change does not eliminate CVE-2024-7409 on its own, but reduces
+the chance for fd exhaustion or unlimited memory usage as an attack
+surface.  On the other hand, by itself, it makes it more obvious that
+with a finite limit, we have the problem of an unauthenticated client
+holding 100 fds opened as a way to block out a legitimate client from
+being able to connect; thus, later patches will further add timeouts
+to reject clients that are not making progress.
+
+This is an INTENTIONAL change in behavior, and will break any client
+of nbd-server-start that was not passing an explicit max-connections
+parameter, yet expects more than 100 simultaneous connections.  We are
+not aware of any such client (as stated above, most clients aware of
+MULTI_CONN get by just fine on 8 or 16 connections, and probably cope
+with later connections failing by relying on the earlier connections;
+libvirt has not yet been passing max-connections, but generally
+creates NBD servers with the intent for a single client for the sake
+of live storage migration; meanwhile, the KubeSAN project anticipates
+a large cluster sharing multiple clients [up to 8 per node, and up to
+100 nodes in a cluster], but it currently uses qemu-nbd with an
+explicit --shared=0 rather than qemu-storage-daemon with
+nbd-server-start).
+
+We considered using a deprecation period (declare that omitting
+max-parameters is deprecated, and make it mandatory in 3 releases -
+then we don't need to pick an arbitrary default); that has zero risk
+of breaking any apps that accidentally depended on more than 100
+connections, and where such breakage might not be noticed under unit
+testing but only under the larger loads of production usage.  But it
+does not close the denial-of-service hole until far into the future,
+and requires all apps to change to add the parameter even if 100 was
+good enough.  It also has a drawback that any app (like libvirt) that
+is accidentally relying on an unlimited default should seriously
+consider their own CVE now, at which point they are going to change to
+pass explicit max-connections sooner than waiting for 3 qemu releases.
+Finally, if our changed default breaks an app, that app can always
+pass in an explicit max-parameters with a larger value.
+
+It is also intentional that the HMP interface to nbd-server-start is
+not changed to expose max-connections (any client needing to fine-tune
+things should be using QMP).
+
+Suggested-by: Daniel P. Berrangé <berrange@redhat.com>
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-ID: <20240807174943.771624-12-eblake@redhat.com>
+Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
+[ericb: Expand commit message to summarize Dan's argument for why we
+break corner-case back-compat behavior without a deprecation period]
+Signed-off-by: Eric Blake <eblake@redhat.com>
+(cherry picked from commit c8a76dbd90c2f48df89b75bef74917f90a59b623)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ block/monitor/block-hmp-cmds.c | 3 ++-
+ blockdev-nbd.c                 | 8 ++++++++
+ include/block/nbd.h            | 7 +++++++
+ qapi/block-export.json         | 4 ++--
+ 4 files changed, 19 insertions(+), 3 deletions(-)
+
+diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
+index d954bec6f1..bdf2eb50b6 100644
+--- a/block/monitor/block-hmp-cmds.c
++++ b/block/monitor/block-hmp-cmds.c
+@@ -402,7 +402,8 @@ void hmp_nbd_server_start(Monitor *mon, const QDict *qdict)
+         goto exit;
+     }
+ 
+-    nbd_server_start(addr, NULL, NULL, 0, &local_err);
++    nbd_server_start(addr, NULL, NULL, NBD_DEFAULT_MAX_CONNECTIONS,
++                     &local_err);
+     qapi_free_SocketAddress(addr);
+     if (local_err != NULL) {
+         goto exit;
+diff --git a/blockdev-nbd.c b/blockdev-nbd.c
+index 267a1de903..24ba5382db 100644
+--- a/blockdev-nbd.c
++++ b/blockdev-nbd.c
+@@ -170,6 +170,10 @@ void nbd_server_start(SocketAddress *addr, const char *tls_creds,
+ 
+ void nbd_server_start_options(NbdServerOptions *arg, Error **errp)
+ {
++    if (!arg->has_max_connections) {
++        arg->max_connections = NBD_DEFAULT_MAX_CONNECTIONS;
++    }
++
+     nbd_server_start(arg->addr, arg->tls_creds, arg->tls_authz,
+                      arg->max_connections, errp);
+ }
+@@ -182,6 +186,10 @@ void qmp_nbd_server_start(SocketAddressLegacy *addr,
+ {
+     SocketAddress *addr_flat = socket_address_flatten(addr);
+ 
++    if (!has_max_connections) {
++        max_connections = NBD_DEFAULT_MAX_CONNECTIONS;
++    }
++
+     nbd_server_start(addr_flat, tls_creds, tls_authz, max_connections, errp);
+     qapi_free_SocketAddress(addr_flat);
+ }
+diff --git a/include/block/nbd.h b/include/block/nbd.h
+index 1d4d65922d..d4f8b21aec 100644
+--- a/include/block/nbd.h
++++ b/include/block/nbd.h
+@@ -39,6 +39,13 @@ extern const BlockExportDriver blk_exp_nbd;
+  */
+ #define NBD_DEFAULT_HANDSHAKE_MAX_SECS 10
+ 
++/*
++ * NBD_DEFAULT_MAX_CONNECTIONS: Number of client sockets to allow at
++ * once; must be large enough to allow a MULTI_CONN-aware client like
++ * nbdcopy to create its typical number of 8-16 sockets.
++ */
++#define NBD_DEFAULT_MAX_CONNECTIONS 100
++
+ /* Handshake phase structs - this struct is passed on the wire */
+ 
+ typedef struct NBDOption {
+diff --git a/qapi/block-export.json b/qapi/block-export.json
+index 3919a2d5b9..f45e4fd481 100644
+--- a/qapi/block-export.json
++++ b/qapi/block-export.json
+@@ -28,7 +28,7 @@
+ # @max-connections: The maximum number of connections to allow at the
+ #     same time, 0 for unlimited.  Setting this to 1 also stops the
+ #     server from advertising multiple client support (since 5.2;
+-#     default: 0)
++#     default: 100)
+ #
+ # Since: 4.2
+ ##
+@@ -63,7 +63,7 @@
+ # @max-connections: The maximum number of connections to allow at the
+ #     same time, 0 for unlimited.  Setting this to 1 also stops the
+ #     server from advertising multiple client support (since 5.2;
+-#     default: 0).
++#     default: 100).
+ #
+ # Errors:
+ #     - if the server is already running

debian/patches/extra/0032-nbd-server-CVE-2024-7409-Drop-non-negotiating-client.patch

@@ -0,0 +1,123 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Thu, 8 Aug 2024 16:05:08 -0500
+Subject: [PATCH] nbd/server: CVE-2024-7409: Drop non-negotiating clients
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+A client that opens a socket but does not negotiate is merely hogging
+qemu's resources (an open fd and a small amount of memory); and a
+malicious client that can access the port where NBD is listening can
+attempt a denial of service attack by intentionally opening and
+abandoning lots of unfinished connections.  The previous patch put a
+default bound on the number of such ongoing connections, but once that
+limit is hit, no more clients can connect (including legitimate ones).
+The solution is to insist that clients complete handshake within a
+reasonable time limit, defaulting to 10 seconds.  A client that has
+not successfully completed NBD_OPT_GO by then (including the case of
+where the client didn't know TLS credentials to even reach the point
+of NBD_OPT_GO) is wasting our time and does not deserve to stay
+connected.  Later patches will allow fine-tuning the limit away from
+the default value (including disabling it for doing integration
+testing of the handshake process itself).
+
+Note that this patch in isolation actually makes it more likely to see
+qemu SEGV after nbd-server-stop, as any client socket still connected
+when the server shuts down will now be closed after 10 seconds rather
+than at the client's whims.  That will be addressed in the next patch.
+
+For a demo of this patch in action:
+$ qemu-nbd -f raw -r -t -e 10 file &
+$ nbdsh --opt-mode -c '
+H = list()
+for i in range(20):
+  print(i)
+  H.insert(i, nbd.NBD())
+  H[i].set_opt_mode(True)
+  H[i].connect_uri("nbd://localhost")
+'
+$ kill $!
+
+where later connections get to start progressing once earlier ones are
+forcefully dropped for taking too long, rather than hanging.
+
+Suggested-by: Daniel P. Berrangé <berrange@redhat.com>
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-ID: <20240807174943.771624-13-eblake@redhat.com>
+Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
+[eblake: rebase to changes earlier in series, reduce scope of timer]
+Signed-off-by: Eric Blake <eblake@redhat.com>
+(cherry picked from commit b9b72cb3ce15b693148bd09cef7e50110566d8a0)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ nbd/server.c     | 28 +++++++++++++++++++++++++++-
+ nbd/trace-events |  1 +
+ 2 files changed, 28 insertions(+), 1 deletion(-)
+
+diff --git a/nbd/server.c b/nbd/server.c
+index e50012499f..39285cc971 100644
+--- a/nbd/server.c
++++ b/nbd/server.c
+@@ -3186,22 +3186,48 @@ static void nbd_client_receive_next_request(NBDClient *client)
+     }
+ }
+ 
++static void nbd_handshake_timer_cb(void *opaque)
++{
++    QIOChannel *ioc = opaque;
++
++    trace_nbd_handshake_timer_cb();
++    qio_channel_shutdown(ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
++}
++
+ static coroutine_fn void nbd_co_client_start(void *opaque)
+ {
+     NBDClient *client = opaque;
+     Error *local_err = NULL;
++    QEMUTimer *handshake_timer = NULL;
+ 
+     qemu_co_mutex_init(&client->send_lock);
+ 
+-    /* TODO - utilize client->handshake_max_secs */
++    /*
++     * Create a timer to bound the time spent in negotiation. If the
++     * timer expires, it is likely nbd_negotiate will fail because the
++     * socket was shutdown.
++     */
++    if (client->handshake_max_secs > 0) {
++        handshake_timer = aio_timer_new(qemu_get_aio_context(),
++                                        QEMU_CLOCK_REALTIME,
++                                        SCALE_NS,
++                                        nbd_handshake_timer_cb,
++                                        client->sioc);
++        timer_mod(handshake_timer,
++                  qemu_clock_get_ns(QEMU_CLOCK_REALTIME) +
++                  client->handshake_max_secs * NANOSECONDS_PER_SECOND);
++    }
++
+     if (nbd_negotiate(client, &local_err)) {
+         if (local_err) {
+             error_report_err(local_err);
+         }
++        timer_free(handshake_timer);
+         client_close(client, false);
+         return;
+     }
+ 
++    timer_free(handshake_timer);
+     WITH_QEMU_LOCK_GUARD(&client->lock) {
+         nbd_client_receive_next_request(client);
+     }
+diff --git a/nbd/trace-events b/nbd/trace-events
+index 00ae3216a1..cbd0a4ab7e 100644
+--- a/nbd/trace-events
++++ b/nbd/trace-events
+@@ -76,6 +76,7 @@ nbd_co_receive_request_payload_received(uint64_t cookie, uint64_t len) "Payload
+ nbd_co_receive_ext_payload_compliance(uint64_t from, uint64_t len) "client sent non-compliant write without payload flag: from=0x%" PRIx64 ", len=0x%" PRIx64
+ nbd_co_receive_align_compliance(const char *op, uint64_t from, uint64_t len, uint32_t align) "client sent non-compliant unaligned %s request: from=0x%" PRIx64 ", len=0x%" PRIx64 ", align=0x%" PRIx32
+ nbd_trip(void) "Reading request"
++nbd_handshake_timer_cb(void) "client took too long to negotiate"
+ 
+ # client-connection.c
+ nbd_connect_thread_sleep(uint64_t timeout) "timeout %" PRIu64

debian/patches/extra/0033-nbd-server-CVE-2024-7409-Close-stray-clients-at-serv.patch

@@ -0,0 +1,161 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Wed, 7 Aug 2024 12:23:13 -0500
+Subject: [PATCH] nbd/server: CVE-2024-7409: Close stray clients at server-stop
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+A malicious client can attempt to connect to an NBD server, and then
+intentionally delay progress in the handshake, including if it does
+not know the TLS secrets.  Although the previous two patches reduce
+this behavior by capping the default max-connections parameter and
+killing slow clients, they did not eliminate the possibility of a
+client waiting to close the socket until after the QMP nbd-server-stop
+command is executed, at which point qemu would SEGV when trying to
+dereference the NULL nbd_server global which is no longer present.
+This amounts to a denial of service attack.  Worse, if another NBD
+server is started before the malicious client disconnects, I cannot
+rule out additional adverse effects when the old client interferes
+with the connection count of the new server (although the most likely
+is a crash due to an assertion failure when checking
+nbd_server->connections > 0).
+
+For environments without this patch, the CVE can be mitigated by
+ensuring (such as via a firewall) that only trusted clients can
+connect to an NBD server.  Note that using frameworks like libvirt
+that ensure that TLS is used and that nbd-server-stop is not executed
+while any trusted clients are still connected will only help if there
+is also no possibility for an untrusted client to open a connection
+but then stall on the NBD handshake.
+
+Given the previous patches, it would be possible to guarantee that no
+clients remain connected by having nbd-server-stop sleep for longer
+than the default handshake deadline before finally freeing the global
+nbd_server object, but that could make QMP non-responsive for a long
+time.  So intead, this patch fixes the problem by tracking all client
+sockets opened while the server is running, and forcefully closing any
+such sockets remaining without a completed handshake at the time of
+nbd-server-stop, then waiting until the coroutines servicing those
+sockets notice the state change.  nbd-server-stop now has a second
+AIO_WAIT_WHILE_UNLOCKED (the first is indirectly through the
+blk_exp_close_all_type() that disconnects all clients that completed
+handshakes), but forced socket shutdown is enough to progress the
+coroutines and quickly tear down all clients before the server is
+freed, thus finally fixing the CVE.
+
+This patch relies heavily on the fact that nbd/server.c guarantees
+that it only calls nbd_blockdev_client_closed() from the main loop
+(see the assertion in nbd_client_put() and the hoops used in
+nbd_client_put_nonzero() to achieve that); if we did not have that
+guarantee, we would also need a mutex protecting our accesses of the
+list of connections to survive re-entrancy from independent iothreads.
+
+Although I did not actually try to test old builds, it looks like this
+problem has existed since at least commit 862172f45c (v2.12.0, 2017) -
+even back when that patch started using a QIONetListener to handle
+listening on multiple sockets, nbd_server_free() was already unaware
+that the nbd_blockdev_client_closed callback can be reached later by a
+client thread that has not completed handshakes (and therefore the
+client's socket never got added to the list closed in
+nbd_export_close_all), despite that patch intentionally tearing down
+the QIONetListener to prevent new clients.
+
+Reported-by: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
+Fixes: CVE-2024-7409
+CC: qemu-stable@nongnu.org
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-ID: <20240807174943.771624-14-eblake@redhat.com>
+Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
+(cherry picked from commit 3e7ef738c8462c45043a1d39f702a0990406a3b3)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ blockdev-nbd.c | 35 ++++++++++++++++++++++++++++++++++-
+ 1 file changed, 34 insertions(+), 1 deletion(-)
+
+diff --git a/blockdev-nbd.c b/blockdev-nbd.c
+index 24ba5382db..f73409ae49 100644
+--- a/blockdev-nbd.c
++++ b/blockdev-nbd.c
+@@ -21,12 +21,18 @@
+ #include "io/channel-socket.h"
+ #include "io/net-listener.h"
+ 
++typedef struct NBDConn {
++    QIOChannelSocket *cioc;
++    QLIST_ENTRY(NBDConn) next;
++} NBDConn;
++
+ typedef struct NBDServerData {
+     QIONetListener *listener;
+     QCryptoTLSCreds *tlscreds;
+     char *tlsauthz;
+     uint32_t max_connections;
+     uint32_t connections;
++    QLIST_HEAD(, NBDConn) conns;
+ } NBDServerData;
+ 
+ static NBDServerData *nbd_server;
+@@ -51,6 +57,14 @@ int nbd_server_max_connections(void)
+ 
+ static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
+ {
++    NBDConn *conn = nbd_client_owner(client);
++
++    assert(qemu_in_main_thread() && nbd_server);
++
++    object_unref(OBJECT(conn->cioc));
++    QLIST_REMOVE(conn, next);
++    g_free(conn);
++
+     nbd_client_put(client);
+     assert(nbd_server->connections > 0);
+     nbd_server->connections--;
+@@ -60,14 +74,20 @@ static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
+ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
+                        gpointer opaque)
+ {
++    NBDConn *conn = g_new0(NBDConn, 1);
++
++    assert(qemu_in_main_thread() && nbd_server);
+     nbd_server->connections++;
++    object_ref(OBJECT(cioc));
++    conn->cioc = cioc;
++    QLIST_INSERT_HEAD(&nbd_server->conns, conn, next);
+     nbd_update_server_watch(nbd_server);
+ 
+     qio_channel_set_name(QIO_CHANNEL(cioc), "nbd-server");
+     /* TODO - expose handshake timeout as QMP option */
+     nbd_client_new(cioc, NBD_DEFAULT_HANDSHAKE_MAX_SECS,
+                    nbd_server->tlscreds, nbd_server->tlsauthz,
+-                   nbd_blockdev_client_closed, NULL);
++                   nbd_blockdev_client_closed, conn);
+ }
+ 
+ static void nbd_update_server_watch(NBDServerData *s)
+@@ -81,12 +101,25 @@ static void nbd_update_server_watch(NBDServerData *s)
+ 
+ static void nbd_server_free(NBDServerData *server)
+ {
++    NBDConn *conn, *tmp;
++
+     if (!server) {
+         return;
+     }
+ 
++    /*
++     * Forcefully close the listener socket, and any clients that have
++     * not yet disconnected on their own.
++     */
+     qio_net_listener_disconnect(server->listener);
+     object_unref(OBJECT(server->listener));
++    QLIST_FOREACH_SAFE(conn, &server->conns, next, tmp) {
++        qio_channel_shutdown(QIO_CHANNEL(conn->cioc), QIO_CHANNEL_SHUTDOWN_BOTH,
++                             NULL);
++    }
++
++    AIO_WAIT_WHILE_UNLOCKED(NULL, server->connections > 0);
++
+     if (server->tlscreds) {
+         object_unref(OBJECT(server->tlscreds));
+     }

debian/patches/extra/0034-vnc-fix-crash-when-no-console-attached.patch

@@ -0,0 +1,47 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= <marcandre.lureau@redhat.com>
+Date: Tue, 20 Aug 2024 17:11:12 +0400
+Subject: [PATCH] vnc: fix crash when no console attached
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Since commit e99441a3793b5 ("ui/curses: Do not use console_select()")
+qemu_text_console_put_keysym() no longer checks for NULL console
+argument, which leads to a later crash:
+
+Thread 1 "qemu-system-x86" received signal SIGSEGV, Segmentation fault.
+0x00005555559ee186 in qemu_text_console_handle_keysym (s=0x0, keysym=31) at ../ui/console-vc.c:332
+332	        } else if (s->echo && (keysym == '\r' || keysym == '\n')) {
+(gdb) bt
+ #0  0x00005555559ee186 in qemu_text_console_handle_keysym (s=0x0, keysym=31) at ../ui/console-vc.c:332
+ #1  0x00005555559e18e5 in qemu_text_console_put_keysym (s=<optimized out>, keysym=<optimized out>) at ../ui/console.c:303
+ #2  0x00005555559f2e88 in do_key_event (vs=vs@entry=0x5555579045c0, down=down@entry=1, keycode=keycode@entry=60, sym=sym@entry=65471) at ../ui/vnc.c:2034
+ #3  0x00005555559f845c in ext_key_event (vs=0x5555579045c0, down=1, sym=65471, keycode=<optimized out>) at ../ui/vnc.c:2070
+ #4  protocol_client_msg (vs=0x5555579045c0, data=<optimized out>, len=<optimized out>) at ../ui/vnc.c:2514
+ #5  0x00005555559f515c in vnc_client_read (vs=0x5555579045c0) at ../ui/vnc.c:1607
+
+Fixes: e99441a3793b5 ("ui/curses: Do not use console_select()")
+Fixes: https://issues.redhat.com/browse/RHEL-50529
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com>
+(picked from https://lore.kernel.org/qemu-devel/20240820131112.1267954-1-marcandre.lureau@redhat.com/)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ ui/vnc.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/ui/vnc.c b/ui/vnc.c
+index b3fd78022b..953ea38318 100644
+--- a/ui/vnc.c
++++ b/ui/vnc.c
+@@ -1935,7 +1935,7 @@ static void do_key_event(VncState *vs, int down, int keycode, int sym)
+     }
+ 
+     qkbd_state_key_event(vs->vd->kbd, qcode, down);
+-    if (!qemu_console_is_graphic(vs->vd->dcl.con)) {
++    if (QEMU_IS_TEXT_CONSOLE(vs->vd->dcl.con)) {
+         QemuTextConsole *con = QEMU_TEXT_CONSOLE(vs->vd->dcl.con);
+         bool numlock = qkbd_state_modifier_get(vs->vd->kbd, QKBD_MOD_NUMLOCK);
+         bool control = qkbd_state_modifier_get(vs->vd->kbd, QKBD_MOD_CTRL);

debian/patches/extra/0035-nbd-server-CVE-2024-7409-Avoid-use-after-free-when-c.patch

@@ -0,0 +1,89 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Thu, 22 Aug 2024 09:35:29 -0500
+Subject: [PATCH] nbd/server: CVE-2024-7409: Avoid use-after-free when closing
+ server
+
+Commit 3e7ef738 plugged the use-after-free of the global nbd_server
+object, but overlooked a use-after-free of nbd_server->listener.
+Although this race is harder to hit, notice that our shutdown path
+first drops the reference count of nbd_server->listener, then triggers
+actions that can result in a pending client reaching the
+nbd_blockdev_client_closed() callback, which in turn calls
+qio_net_listener_set_client_func on a potentially stale object.
+
+If we know we don't want any more clients to connect, and have already
+told the listener socket to shut down, then we should not be trying to
+update the listener socket's associated function.
+
+Reproducer:
+
+> #!/usr/bin/python3
+>
+> import os
+> from threading import Thread
+>
+> def start_stop():
+>     while 1:
+>         os.system('virsh qemu-monitor-command VM \'{"execute": "nbd-server-start",
++"arguments":{"addr":{"type":"unix","data":{"path":"/tmp/nbd-sock"}}}}\'')
+>         os.system('virsh qemu-monitor-command VM \'{"execute": "nbd-server-stop"}\'')
+>
+> def nbd_list():
+>     while 1:
+>         os.system('/path/to/build/qemu-nbd -L -k /tmp/nbd-sock')
+>
+> def test():
+>     sst = Thread(target=start_stop)
+>     sst.start()
+>     nlt = Thread(target=nbd_list)
+>     nlt.start()
+>
+>     sst.join()
+>     nlt.join()
+>
+> test()
+
+Fixes: CVE-2024-7409
+Fixes: 3e7ef738c8 ("nbd/server: CVE-2024-7409: Close stray clients at server-stop")
+CC: qemu-stable@nongnu.org
+Reported-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-ID: <20240822143617.800419-2-eblake@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+(cherry picked from commit 3874f5f73c441c52f1c699c848d463b0eda01e4c)
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ blockdev-nbd.c | 12 ++++++++----
+ 1 file changed, 8 insertions(+), 4 deletions(-)
+
+diff --git a/blockdev-nbd.c b/blockdev-nbd.c
+index f73409ae49..b36f41b7c5 100644
+--- a/blockdev-nbd.c
++++ b/blockdev-nbd.c
+@@ -92,10 +92,13 @@ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
+ 
+ static void nbd_update_server_watch(NBDServerData *s)
+ {
+-    if (!s->max_connections || s->connections < s->max_connections) {
+-        qio_net_listener_set_client_func(s->listener, nbd_accept, NULL, NULL);
+-    } else {
+-        qio_net_listener_set_client_func(s->listener, NULL, NULL, NULL);
++    if (s->listener) {
++        if (!s->max_connections || s->connections < s->max_connections) {
++            qio_net_listener_set_client_func(s->listener, nbd_accept, NULL,
++                                             NULL);
++        } else {
++            qio_net_listener_set_client_func(s->listener, NULL, NULL, NULL);
++        }
+     }
+ }
+ 
+@@ -113,6 +116,7 @@ static void nbd_server_free(NBDServerData *server)
+      */
+     qio_net_listener_disconnect(server->listener);
+     object_unref(OBJECT(server->listener));
++    server->listener = NULL;
+     QLIST_FOREACH_SAFE(conn, &server->conns, next, tmp) {
+         qio_channel_shutdown(QIO_CHANNEL(conn->cioc), QIO_CHANNEL_SHUTDOWN_BOTH,
+                              NULL);

debian/patches/extra/0036-softmmu-physmem-fix-memory-leak-in-dirty_memory_exte.patch

@@ -0,0 +1,134 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: David Hildenbrand <david@redhat.com>
+Date: Wed, 28 Aug 2024 11:07:43 +0200
+Subject: [PATCH] softmmu/physmem: fix memory leak in dirty_memory_extend()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+As reported by Peter, we might be leaking memory when removing the
+highest RAMBlock (in the weird ram_addr_t space), and adding a new one.
+
+We will fail to realize that we already allocated bitmaps for more
+dirty memory blocks, and effectively discard the pointers to them.
+
+Fix it by getting rid of last_ram_page() and by remembering the number
+of dirty memory blocks that have been allocated already.
+
+While at it, let's use "unsigned int" for the number of blocks, which
+should be sufficient until we reach ~32 exabytes.
+
+Looks like this leak was introduced as we switched from using a single
+bitmap_zero_extend() to allocating multiple bitmaps:
+bitmap_zero_extend() relies on g_renew() which should have taken care of
+this.
+
+Resolves: https://lkml.kernel.org/r/CAFEAcA-k7a+VObGAfCFNygQNfCKL=AfX6A4kScq=VSSK0peqPg@mail.gmail.com
+Reported-by: Peter Maydell <peter.maydell@linaro.org>
+Fixes: 5b82b703b69a ("memory: RCU ram_list.dirty_memory[] for safe RAM hotplug")
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: Peter Xu <peterx@redhat.com>
+Tested-by: Peter Maydell <peter.maydell@linaro.org>
+Cc: qemu-stable@nongnu.org
+Cc: Stefan Hajnoczi <stefanha@redhat.com>
+Cc: Paolo Bonzini <pbonzini@redhat.com>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: "Philippe Mathieu-Daudé" <philmd@linaro.org>
+Signed-off-by: David Hildenbrand <david@redhat.com>
+(picked from https://lore.kernel.org/qemu-devel/20240828090743.128647-1-david@redhat.com/)
+[FE: backport - remove not-yet-existing variable in context of hunk touching ram_block_add()]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+---
+ include/exec/ramlist.h |  1 +
+ system/physmem.c       | 35 +++++++++--------------------------
+ 2 files changed, 10 insertions(+), 26 deletions(-)
+
+diff --git a/include/exec/ramlist.h b/include/exec/ramlist.h
+index 2ad2a81acc..d9cfe530be 100644
+--- a/include/exec/ramlist.h
++++ b/include/exec/ramlist.h
+@@ -50,6 +50,7 @@ typedef struct RAMList {
+     /* RCU-enabled, writes protected by the ramlist lock. */
+     QLIST_HEAD(, RAMBlock) blocks;
+     DirtyMemoryBlocks *dirty_memory[DIRTY_MEMORY_NUM];
++    unsigned int num_dirty_blocks;
+     uint32_t version;
+     QLIST_HEAD(, RAMBlockNotifier) ramblock_notifiers;
+ } RAMList;
+diff --git a/system/physmem.c b/system/physmem.c
+index a4fe3d2bf8..78f7db1121 100644
+--- a/system/physmem.c
++++ b/system/physmem.c
+@@ -1497,18 +1497,6 @@ static ram_addr_t find_ram_offset(ram_addr_t size)
+     return offset;
+ }
+ 
+-static unsigned long last_ram_page(void)
+-{
+-    RAMBlock *block;
+-    ram_addr_t last = 0;
+-
+-    RCU_READ_LOCK_GUARD();
+-    RAMBLOCK_FOREACH(block) {
+-        last = MAX(last, block->offset + block->max_length);
+-    }
+-    return last >> TARGET_PAGE_BITS;
+-}
+-
+ static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
+ {
+     int ret;
+@@ -1762,13 +1750,11 @@ void qemu_ram_msync(RAMBlock *block, ram_addr_t start, ram_addr_t length)
+ }
+ 
+ /* Called with ram_list.mutex held */
+-static void dirty_memory_extend(ram_addr_t old_ram_size,
+-                                ram_addr_t new_ram_size)
++static void dirty_memory_extend(ram_addr_t new_ram_size)
+ {
+-    ram_addr_t old_num_blocks = DIV_ROUND_UP(old_ram_size,
+-                                             DIRTY_MEMORY_BLOCK_SIZE);
+-    ram_addr_t new_num_blocks = DIV_ROUND_UP(new_ram_size,
+-                                             DIRTY_MEMORY_BLOCK_SIZE);
++    unsigned int old_num_blocks = ram_list.num_dirty_blocks;
++    unsigned int new_num_blocks = DIV_ROUND_UP(new_ram_size,
++                                               DIRTY_MEMORY_BLOCK_SIZE);
+     int i;
+ 
+     /* Only need to extend if block count increased */
+@@ -1800,6 +1786,8 @@ static void dirty_memory_extend(ram_addr_t old_ram_size,
+             g_free_rcu(old_blocks, rcu);
+         }
+     }
++
++    ram_list.num_dirty_blocks = new_num_blocks;
+ }
+ 
+ static void ram_block_add(RAMBlock *new_block, Error **errp)
+@@ -1808,11 +1796,9 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
+     const bool shared = qemu_ram_is_shared(new_block);
+     RAMBlock *block;
+     RAMBlock *last_block = NULL;
+-    ram_addr_t old_ram_size, new_ram_size;
++    ram_addr_t ram_size;
+     Error *err = NULL;
+ 
+-    old_ram_size = last_ram_page();
+-
+     qemu_mutex_lock_ramlist();
+     new_block->offset = find_ram_offset(new_block->max_length);
+ 
+@@ -1840,11 +1826,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
+         }
+     }
+ 
+-    new_ram_size = MAX(old_ram_size,
+-              (new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS);
+-    if (new_ram_size > old_ram_size) {
+-        dirty_memory_extend(old_ram_size, new_ram_size);
+-    }
++    ram_size = (new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS;
++    dirty_memory_extend(ram_size);
+     /* Keep the list sorted from biggest to smallest block.  Unlike QTAILQ,
+      * QLIST (which has an RCU-friendly variant) does not have insertion at
+      * tail, so save the last element in last_block.

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 b283093e5b..821405fd02 100644
+index 35684f7e21..43bc0bd520 100644
 --- a/block/file-posix.c
 +++ b/block/file-posix.c
-@@ -552,7 +552,7 @@ 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 b283093e5b..821405fd02 100644
          },
          {
              .name = "pr-manager",
-@@ -652,7 +652,7 @@ 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 04f2b790c9..19fdbb981c 100644
+index 6b05738079..d82869900a 100644
 --- a/target/i386/cpu.h
 +++ b/target/i386/cpu.h
-@@ -2039,9 +2039,9 @@ 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 31974b8d6c..a3acdbd682 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 592e71b22a..aebfece6eb 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 592e71b22a..aebfece6eb 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 def96292e0..a4b8fb482c 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 aebfece6eb..3b7ee2f649 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 aebfece6eb..3b7ee2f649 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 aebfece6eb..3b7ee2f649 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 aebfece6eb..3b7ee2f649 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 aebfece6eb..3b7ee2f649 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 f0d14dbfc1..6d476c47ef 100644
---- a/net/net.c
-+++ b/net/net.c
-@@ -1334,6 +1334,33 @@ 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 7fab2e7cd8..74c9a6109e 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 3bc0335d1f..7c91ea3685 100644
---- a/qapi/pragma.json
-+++ b/qapi/pragma.json
-@@ -22,6 +22,7 @@
-         'system_reset',
-         'system_wakeup' ],
-     '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 f036a1d428..080ad9bca7 100644
+index 7668f86769..2575e97b43 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -2989,7 +2989,8 @@ 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

@@ -31,16 +31,17 @@ override the output file's size.
 
 Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  qemu-img-cmds.hx |   4 +-
- qemu-img.c       | 187 +++++++++++++++++++++++++++++------------------
- 2 files changed, 119 insertions(+), 72 deletions(-)
+ qemu-img.c       | 202 ++++++++++++++++++++++++++++++-----------------
+ 2 files changed, 133 insertions(+), 73 deletions(-)
 
 diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
-index 72bcdcfbfa..0b2999f3ab 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,
@@ -53,10 +54,10 @@ index 72bcdcfbfa..0b2999f3ab 100644
  
  DEF("info", img_info,
 diff --git a/qemu-img.c b/qemu-img.c
-index 080ad9bca7..1f457d9e80 100644
+index 2575e97b43..8ec68b346f 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4805,10 +4805,12 @@ 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
@@ -69,7 +70,7 @@ index 080ad9bca7..1f457d9e80 100644
  };
  
  struct DdIo {
-@@ -4884,6 +4886,19 @@ static int img_dd_skip(const char *arg,
+@@ -5072,6 +5074,19 @@ static int img_dd_skip(const char *arg,
      return 0;
  }
  
@@ -89,7 +90,7 @@ index 080ad9bca7..1f457d9e80 100644
  static int img_dd(int argc, char **argv)
  {
      int ret = 0;
-@@ -4924,6 +4939,7 @@ 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 },
@@ -97,7 +98,7 @@ index 080ad9bca7..1f457d9e80 100644
          { NULL, NULL, 0 }
      };
      const struct option long_options[] = {
-@@ -4999,91 +5015,112 @@ static int img_dd(int argc, char **argv)
+@@ -5187,91 +5203,112 @@ static int img_dd(int argc, char **argv)
          arg = NULL;
      }
  
@@ -153,9 +154,9 @@ index 080ad9bca7..1f457d9e80 100644
      }
 -    create_opts = qemu_opts_append(create_opts, drv->create_opts);
 -    create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
- 
--    opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
 -
+-    opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
+ 
 -    size = blk_getlength(blk1);
 -    if (size < 0) {
 -        error_report("Failed to get size for '%s'", in.filename);
@@ -274,41 +275,54 @@ index 080ad9bca7..1f457d9e80 100644
      }
  
      if (dd.flags & C_SKIP && (in.offset > INT64_MAX / in.bsz ||
-@@ -5101,11 +5138,17 @@ 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++) {
-         int in_ret, out_ret;
+     for (out_pos = 0; in_pos < size; ) {
++        int in_ret, out_ret;
+         int bytes = (in_pos + in.bsz > size) ? size - in_pos : in.bsz;
 -
--        if (in_pos + in.bsz > size) {
--            in_ret = blk_pread(blk1, in_pos, in.buf, size - in_pos);
-+        size_t in_bsz = in_pos + in.bsz > size ? size - in_pos : in.bsz;
+-        ret = blk_pread(blk1, in_pos, bytes, in.buf, 0);
+-        if (ret < 0) {
 +        if (blk1) {
-+            in_ret = blk_pread(blk1, in_pos, in.buf, in_bsz);
-         } else {
--            in_ret = blk_pread(blk1, in_pos, in.buf, in.bsz);
-+            in_ret = read(STDIN_FILENO, in.buf, in_bsz);
++            in_ret = blk_pread(blk1, in_pos, bytes, in.buf, 0);
++            if (in_ret == 0) {
++                in_ret = bytes;
++            }
++        } else {
++            in_ret = read(STDIN_FILENO, in.buf, bytes);
 +            if (in_ret == 0) {
 +                /* early EOF is considered an error */
 +                error_report("Input ended unexpectedly");
 +                ret = -1;
 +                goto out;
 +            }
-         }
-         if (in_ret < 0) {
++        }
++        if (in_ret < 0) {
              error_report("error while reading from input image file: %s",
-@@ -5115,9 +5158,13 @@ static int img_dd(int argc, char **argv)
+-                         strerror(-ret));
++                         strerror(-in_ret));
++            ret = -1;
+             goto out;
          }
-         in_pos += in_ret;
+         in_pos += bytes;
  
--        out_ret = blk_pwrite(blk2, out_pos, in.buf, in_ret, 0);
+-        ret = blk_pwrite(blk2, out_pos, bytes, in.buf, 0);
+-        if (ret < 0) {
 +        if (blk2) {
-+            out_ret = blk_pwrite(blk2, out_pos, in.buf, in_ret, 0);
++            out_ret = blk_pwrite(blk2, out_pos, in_ret, in.buf, 0);
++            if (out_ret == 0) {
++                out_ret = in_ret;
++            }
 +        } else {
 +            out_ret = write(STDOUT_FILENO, in.buf, in_ret);
 +        }
- 
--        if (out_ret < 0) {
++
 +        if (out_ret != in_ret) {
              error_report("error while writing to output image file: %s",
-                          strerror(-out_ret));
-             ret = -1;
+-                         strerror(-ret));
++                         strerror(-out_ret));
++            ret = -1;
+             goto out;
+         }
+         out_pos += bytes;

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

@@ -10,15 +10,16 @@ an expected end of input.
 
 Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  qemu-img.c | 28 +++++++++++++++++++++++++---
  1 file changed, 25 insertions(+), 3 deletions(-)
 
 diff --git a/qemu-img.c b/qemu-img.c
-index 1f457d9e80..d9e8a8c4d4 100644
+index 8ec68b346f..b98184bba1 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4806,11 +4806,13 @@ 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
@@ -32,7 +33,7 @@ index 1f457d9e80..d9e8a8c4d4 100644
  };
  
  struct DdIo {
-@@ -4899,6 +4901,19 @@ static int img_dd_osize(const char *arg,
+@@ -5087,6 +5089,19 @@ static int img_dd_osize(const char *arg,
      return 0;
  }
  
@@ -52,13 +53,13 @@ index 1f457d9e80..d9e8a8c4d4 100644
  static int img_dd(int argc, char **argv)
  {
      int ret = 0;
-@@ -4913,12 +4928,14 @@ 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,
@@ -68,7 +69,7 @@ index 1f457d9e80..d9e8a8c4d4 100644
      };
      struct DdIo in = {
          .bsz = 512, /* Block size is by default 512 bytes */
-@@ -4940,6 +4957,7 @@ 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 },
@@ -76,20 +77,22 @@ index 1f457d9e80..d9e8a8c4d4 100644
          { NULL, NULL, 0 }
      };
      const struct option long_options[] = {
-@@ -5136,14 +5154,18 @@ 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;
--        size_t in_bsz = in_pos + in.bsz > size ? size - in_pos : in.bsz;
-+        size_t in_bsz = in_pos + in.bsz > readsize ? readsize - in_pos : in.bsz;
+-        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, in.buf, in_bsz);
+             in_ret = blk_pread(blk1, in_pos, bytes, in.buf, 0);
+             if (in_ret == 0) {
+@@ -5335,6 +5354,9 @@ static int img_dd(int argc, char **argv)
          } else {
-             in_ret = read(STDIN_FILENO, in.buf, in_bsz);
+             in_ret = read(STDIN_FILENO, in.buf, bytes);
              if (in_ret == 0) {
 +                if (dd.isize == 0) {
 +                    goto out;

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 d663dd92bd..a49badb158 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 d663dd92bd..a49badb158 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 d663dd92bd..a49badb158 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 d663dd92bd..a49badb158 100644
  
    Give information about the disk image *FILENAME*. Use it in
 diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
-index 0b2999f3ab..f3b2b1b4de 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 0b2999f3ab..f3b2b1b4de 100644
  
  DEF("info", img_info,
 diff --git a/qemu-img.c b/qemu-img.c
-index d9e8a8c4d4..015d6d2ce4 100644
+index b98184bba1..6fc8384f64 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4930,7 +4930,7 @@ 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,
-@@ -4968,7 +4968,7 @@ 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 d9e8a8c4d4..015d6d2ce4 100644
          if (c == EOF) {
              break;
          }
-@@ -4988,6 +4988,9 @@ 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 d9e8a8c4d4..015d6d2ce4 100644
          case 'U':
              force_share = true;
              break;
-@@ -5118,13 +5121,15 @@ 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 a49badb158..1039aec01c 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 a49badb158..1039aec01c 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 f3b2b1b4de..e77ed9347f 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 f3b2b1b4de..e77ed9347f 100644
  
  DEF("info", img_info,
 diff --git a/qemu-img.c b/qemu-img.c
-index 015d6d2ce4..7031195e32 100644
+index 6fc8384f64..a6c88e0860 100644
 --- a/qemu-img.c
 +++ b/qemu-img.c
-@@ -4922,6 +4922,7 @@ 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 015d6d2ce4..7031195e32 100644
      QemuOptsList *create_opts = NULL;
      Error *local_err = NULL;
      bool image_opts = false;
-@@ -4931,6 +4932,7 @@ 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,
-@@ -4968,7 +4970,7 @@ 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 015d6d2ce4..7031195e32 100644
          if (c == EOF) {
              break;
          }
-@@ -4991,6 +4993,19 @@ 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 015d6d2ce4..7031195e32 100644
          case 'U':
              force_share = true;
              break;
-@@ -5050,11 +5065,24 @@ 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 015d6d2ce4..7031195e32 100644
      }
  
      if (dd.flags & C_OSIZE) {
-@@ -5203,6 +5231,7 @@ 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 9a4f491b54..1faa16234e 100644
+index 609e39a821..8cb6dfcac3 100644
 --- a/hw/virtio/virtio-balloon.c
 +++ b/hw/virtio/virtio-balloon.c
-@@ -812,8 +812,37 @@ 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 9a4f491b54..1faa16234e 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 2e91ccb738..e9fa9af6bd 100644
---- a/monitor/hmp-cmds.c
-+++ b/monitor/hmp-cmds.c
-@@ -696,7 +696,35 @@ 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 067e3f5378..91f3be6f44 100644
+index e8b60641f2..2054cdc70d 100644
 --- a/qapi/machine.json
 +++ b/qapi/machine.json
-@@ -1018,10 +1018,30 @@
- # @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
 +#
@@ -123,7 +127,6 @@ index 067e3f5378..91f3be6f44 100644
 +# @max_mem: amount of memory (in bytes) assigned to the guest
 +#
  # Since: 0.14
- #
  ##
 -{ 'struct': 'BalloonInfo', 'data': {'actual': 'int' } }
 +{ 'struct': 'BalloonInfo',
@@ -134,3 +137,15 @@ index 067e3f5378..91f3be6f44 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 91f3be6f44..0905618e25 100644
+index 2054cdc70d..a024d5b05d 100644
 --- a/qapi/machine.json
 +++ b/qapi/machine.json
-@@ -141,6 +141,8 @@
+@@ -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)
  #
-@@ -162,7 +164,7 @@
+@@ -170,7 +172,7 @@
  ##
  { 'struct': 'MachineInfo',
    'data': { 'name': 'str', '*alias': 'str',
@@ -50,4 +50,4 @@ index 91f3be6f44..0905618e25 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 4244c62c30..f946fbd8c1 100644
+index f610bce118..6ea26a9acb 100644
 --- a/qapi/ui.json
 +++ b/qapi/ui.json
-@@ -333,11 +333,14 @@
+@@ -314,11 +314,14 @@
  #
  # @channels: a list of @SpiceChannel for each active spice channel
  #
@@ -31,15 +33,14 @@ index 4244c62c30..f946fbd8c1 100644
    'if': 'CONFIG_SPICE' }
  
 diff --git a/ui/spice-core.c b/ui/spice-core.c
-index a3acdbd682..756776778d 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

@@ -0,0 +1,284 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Fiona Ebner <f.ebner@proxmox.com>
+Date: Thu, 13 Oct 2022 11:33:50 +0200
+Subject: [PATCH] PVE: add IOChannel implementation for savevm-async
+
+based on migration/channel-block.c and the implementation that was
+present in migration/savevm-async.c before QEMU 7.1.
+
+Passes along read/write requests to the given BlockBackend, while
+ensuring that a read request going beyond the end results in a
+graceful short read.
+
+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 | 184 +++++++++++++++++++++++++++++++
+ migration/channel-savevm-async.h |  51 +++++++++
+ migration/meson.build            |   1 +
+ 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..081a192f49
+--- /dev/null
++++ b/migration/channel-savevm-async.c
+@@ -0,0 +1,184 @@
++/*
++ * QIO Channel implementation to be used by savevm-async QMP calls
++ */
++#include "qemu/osdep.h"
++#include "migration/channel-savevm-async.h"
++#include "qapi/error.h"
++#include "sysemu/block-backend.h"
++#include "trace.h"
++
++QIOChannelSavevmAsync *
++qio_channel_savevm_async_new(BlockBackend *be, size_t *bs_pos)
++{
++    QIOChannelSavevmAsync *ioc;
++
++    ioc = QIO_CHANNEL_SAVEVM_ASYNC(object_new(TYPE_QIO_CHANNEL_SAVEVM_ASYNC));
++
++    bdrv_ref(blk_bs(be));
++    ioc->be = be;
++    ioc->bs_pos = bs_pos;
++
++    return ioc;
++}
++
++
++static void
++qio_channel_savevm_async_finalize(Object *obj)
++{
++    QIOChannelSavevmAsync *ioc = QIO_CHANNEL_SAVEVM_ASYNC(obj);
++
++    if (ioc->be) {
++        bdrv_unref(blk_bs(ioc->be));
++        ioc->be = NULL;
++    }
++    ioc->bs_pos = NULL;
++}
++
++
++static ssize_t
++qio_channel_savevm_async_readv(QIOChannel *ioc,
++                               const struct iovec *iov,
++                               size_t niov,
++                               int **fds,
++                               size_t *nfds,
++                               int flags,
++                               Error **errp)
++{
++    QIOChannelSavevmAsync *saioc = QIO_CHANNEL_SAVEVM_ASYNC(ioc);
++    BlockBackend *be = saioc->be;
++    int64_t maxlen = blk_getlength(be);
++    QEMUIOVector qiov;
++    size_t size;
++    int ret;
++
++    qemu_iovec_init_external(&qiov, (struct iovec *)iov, niov);
++
++    if (*saioc->bs_pos >= maxlen) {
++        error_setg(errp, "cannot read beyond maxlen");
++        return -1;
++    }
++
++    if (maxlen - *saioc->bs_pos < qiov.size) {
++        size = maxlen - *saioc->bs_pos;
++    } else {
++        size = qiov.size;
++    }
++
++    // returns 0 on success
++    ret = blk_preadv(be, *saioc->bs_pos, size, &qiov, 0);
++    if (ret < 0) {
++        error_setg_errno(errp, -ret, "blk_preadv failed");
++        return -1;
++    }
++
++    *saioc->bs_pos += size;
++    return size;
++}
++
++
++static ssize_t
++qio_channel_savevm_async_writev(QIOChannel *ioc,
++                                const struct iovec *iov,
++                                size_t niov,
++                                int *fds,
++                                size_t nfds,
++                                int flags,
++                                Error **errp)
++{
++    QIOChannelSavevmAsync *saioc = QIO_CHANNEL_SAVEVM_ASYNC(ioc);
++    BlockBackend *be = saioc->be;
++    QEMUIOVector qiov;
++    int ret;
++
++    qemu_iovec_init_external(&qiov, (struct iovec *)iov, niov);
++
++    if (qemu_in_coroutine()) {
++        ret = blk_co_pwritev(be, *saioc->bs_pos, qiov.size, &qiov, 0);
++        aio_wait_kick();
++    } else {
++        ret = blk_pwritev(be, *saioc->bs_pos, qiov.size, &qiov, 0);
++    }
++
++    if (ret < 0) {
++        error_setg_errno(errp, -ret, "blk(_co)_pwritev failed");
++        return -1;
++    }
++
++    *saioc->bs_pos += qiov.size;
++    return qiov.size;
++}
++
++
++static int
++qio_channel_savevm_async_set_blocking(QIOChannel *ioc,
++                                      bool enabled,
++                                      Error **errp)
++{
++    if (!enabled) {
++        error_setg(errp, "Non-blocking mode not supported for savevm-async");
++        return -1;
++    }
++    return 0;
++}
++
++
++static int
++qio_channel_savevm_async_close(QIOChannel *ioc,
++                               Error **errp)
++{
++    QIOChannelSavevmAsync *saioc = QIO_CHANNEL_SAVEVM_ASYNC(ioc);
++    int rv = bdrv_flush(blk_bs(saioc->be));
++
++    if (rv < 0) {
++        error_setg_errno(errp, -rv, "Unable to flush VMState");
++        return -1;
++    }
++
++    bdrv_unref(blk_bs(saioc->be));
++    saioc->be = NULL;
++    saioc->bs_pos = NULL;
++
++    return 0;
++}
++
++
++static void
++qio_channel_savevm_async_set_aio_fd_handler(QIOChannel *ioc,
++                                            AioContext *read_ctx,
++                                            IOHandler *io_read,
++                                            AioContext *write_ctx,
++                                            IOHandler *io_write,
++                                            void *opaque)
++{
++    // if channel-block starts doing something, check if this needs adaptation
++}
++
++
++static void
++qio_channel_savevm_async_class_init(ObjectClass *klass,
++                             void *class_data G_GNUC_UNUSED)
++{
++    QIOChannelClass *ioc_klass = QIO_CHANNEL_CLASS(klass);
++
++    ioc_klass->io_writev = qio_channel_savevm_async_writev;
++    ioc_klass->io_readv = qio_channel_savevm_async_readv;
++    ioc_klass->io_set_blocking = qio_channel_savevm_async_set_blocking;
++    ioc_klass->io_close = qio_channel_savevm_async_close;
++    ioc_klass->io_set_aio_fd_handler = qio_channel_savevm_async_set_aio_fd_handler;
++}
++
++static const TypeInfo qio_channel_savevm_async_info = {
++    .parent = TYPE_QIO_CHANNEL,
++    .name = TYPE_QIO_CHANNEL_SAVEVM_ASYNC,
++    .instance_size = sizeof(QIOChannelSavevmAsync),
++    .instance_finalize = qio_channel_savevm_async_finalize,
++    .class_init = qio_channel_savevm_async_class_init,
++};
++
++static void
++qio_channel_savevm_async_register_types(void)
++{
++    type_register_static(&qio_channel_savevm_async_info);
++}
++
++type_init(qio_channel_savevm_async_register_types);
+diff --git a/migration/channel-savevm-async.h b/migration/channel-savevm-async.h
+new file mode 100644
+index 0000000000..17ae2cb261
+--- /dev/null
++++ b/migration/channel-savevm-async.h
+@@ -0,0 +1,51 @@
++/*
++ * QEMU I/O channels driver for savevm-async.c
++ *
++ * Copyright (c) 2022 Proxmox Server Solutions
++ *
++ * Authors:
++ *  Fiona Ebner (f.ebner@proxmox.com)
++ *
++ * This work is licensed under the terms of the GNU GPL, version 2 or later.
++ * See the COPYING file in the top-level directory.
++ */
++
++#ifndef QIO_CHANNEL_SAVEVM_ASYNC_H
++#define QIO_CHANNEL_SAVEVM_ASYNC_H
++
++#include "io/channel.h"
++#include "qom/object.h"
++
++#define TYPE_QIO_CHANNEL_SAVEVM_ASYNC "qio-channel-savevm-async"
++OBJECT_DECLARE_SIMPLE_TYPE(QIOChannelSavevmAsync, QIO_CHANNEL_SAVEVM_ASYNC)
++
++
++/**
++ * QIOChannelSavevmAsync:
++ *
++ * The QIOChannelBlock object provides a channel implementation that is able to
++ * perform I/O on any BlockBackend whose BlockDriverState directly contains a
++ * VMState (as opposed to indirectly, like qcow2). It allows tracking the
++ * current position from the outside.
++ */
++struct QIOChannelSavevmAsync {
++    QIOChannel parent;
++    BlockBackend *be;
++    size_t *bs_pos;
++};
++
++
++/**
++ * qio_channel_savevm_async_new:
++ * @be: the block backend
++ * @bs_pos: used to keep track of the IOChannels current position
++ *
++ * Create a new IO channel object that can perform I/O on a BlockBackend object
++ * whose BlockDriverState directly contains a VMState.
++ *
++ * Returns: the new channel object
++ */
++QIOChannelSavevmAsync *
++qio_channel_savevm_async_new(BlockBackend *be, size_t *bs_pos);
++
++#endif /* QIO_CHANNEL_SAVEVM_ASYNC_H */
+diff --git a/migration/meson.build b/migration/meson.build
+index 1eeb915ff6..95d1cf2250 100644
+--- a/migration/meson.build
++++ b/migration/meson.build
+@@ -13,6 +13,7 @@ system_ss.add(files(
+   'block-dirty-bitmap.c',
+   'channel.c',
+   'channel-block.c',
++  'channel-savevm-async.c',
+   'dirtyrate.c',
+   'exec.c',
+   'fd.c',

debian/patches/pve/0017-PVE-add-optional-buffer-size-to-QEMUFile.patch

@@ -1,188 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Mon, 4 May 2020 11:05:08 +0200
-Subject: [PATCH] PVE: add optional buffer size to QEMUFile
-
-So we can use a 4M buffer for savevm-async which should
-increase performance storing the state onto ceph.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
-[increase max IOV count in QEMUFile to actually write more data]
-Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- migration/qemu-file.c    | 38 +++++++++++++++++++++++++-------------
- migration/qemu-file.h    |  1 +
- migration/savevm-async.c |  4 ++--
- 3 files changed, 28 insertions(+), 15 deletions(-)
-
-diff --git a/migration/qemu-file.c b/migration/qemu-file.c
-index 6338d8e2ff..6697a93a7e 100644
---- a/migration/qemu-file.c
-+++ b/migration/qemu-file.c
-@@ -30,8 +30,8 @@
- #include "trace.h"
- #include "qapi/error.h"
- 
--#define IO_BUF_SIZE 32768
--#define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
-+#define DEFAULT_IO_BUF_SIZE 32768
-+#define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 256)
- 
- struct QEMUFile {
-     const QEMUFileOps *ops;
-@@ -45,7 +45,8 @@ struct QEMUFile {
-                     when reading */
-     int buf_index;
-     int buf_size; /* 0 when writing */
--    uint8_t buf[IO_BUF_SIZE];
-+    size_t buf_allocated_size;
-+    uint8_t *buf;
- 
-     DECLARE_BITMAP(may_free, MAX_IOV_SIZE);
-     struct iovec iov[MAX_IOV_SIZE];
-@@ -103,7 +104,7 @@ bool qemu_file_mode_is_not_valid(const char *mode)
-     return false;
- }
- 
--QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops, bool has_ioc)
-+QEMUFile *qemu_fopen_ops_sized(void *opaque, const QEMUFileOps *ops, bool has_ioc, size_t buffer_size)
- {
-     QEMUFile *f;
- 
-@@ -112,9 +113,17 @@ QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops, bool has_ioc)
-     f->opaque = opaque;
-     f->ops = ops;
-     f->has_ioc = has_ioc;
-+    f->buf_allocated_size = buffer_size;
-+    f->buf = malloc(buffer_size);
-+
-     return f;
- }
- 
-+QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops, bool has_ioc)
-+{
-+    return qemu_fopen_ops_sized(opaque, ops, has_ioc, DEFAULT_IO_BUF_SIZE);
-+}
-+
- 
- void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks)
- {
-@@ -349,7 +358,7 @@ static ssize_t qemu_fill_buffer(QEMUFile *f)
-     }
- 
-     len = f->ops->get_buffer(f->opaque, f->buf + pending, f->pos,
--                             IO_BUF_SIZE - pending, &local_error);
-+                             f->buf_allocated_size - pending, &local_error);
-     if (len > 0) {
-         f->buf_size += len;
-         f->pos += len;
-@@ -389,6 +398,9 @@ int qemu_fclose(QEMUFile *f)
-             ret = ret2;
-         }
-     }
-+
-+    free(f->buf);
-+
-     /* If any error was spotted before closing, we should report it
-      * instead of the close() return value.
-      */
-@@ -443,7 +455,7 @@ 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;
--        if (f->buf_index == IO_BUF_SIZE) {
-+        if (f->buf_index == f->buf_allocated_size) {
-             qemu_fflush(f);
-         }
-     }
-@@ -469,7 +481,7 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
-     }
- 
-     while (size > 0) {
--        l = IO_BUF_SIZE - f->buf_index;
-+        l = f->buf_allocated_size - f->buf_index;
-         if (l > size) {
-             l = size;
-         }
-@@ -516,8 +528,8 @@ size_t qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t size, size_t offset)
-     size_t index;
- 
-     assert(!qemu_file_is_writable(f));
--    assert(offset < IO_BUF_SIZE);
--    assert(size <= IO_BUF_SIZE - offset);
-+    assert(offset < f->buf_allocated_size);
-+    assert(size <= f->buf_allocated_size - offset);
- 
-     /* The 1st byte to read from */
-     index = f->buf_index + offset;
-@@ -567,7 +579,7 @@ size_t qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size)
-         size_t res;
-         uint8_t *src;
- 
--        res = qemu_peek_buffer(f, &src, MIN(pending, IO_BUF_SIZE), 0);
-+        res = qemu_peek_buffer(f, &src, MIN(pending, f->buf_allocated_size), 0);
-         if (res == 0) {
-             return done;
-         }
-@@ -601,7 +613,7 @@ size_t 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)
- {
--    if (size < IO_BUF_SIZE) {
-+    if (size < f->buf_allocated_size) {
-         size_t res;
-         uint8_t *src = NULL;
- 
-@@ -626,7 +638,7 @@ int qemu_peek_byte(QEMUFile *f, int offset)
-     int index = f->buf_index + offset;
- 
-     assert(!qemu_file_is_writable(f));
--    assert(offset < IO_BUF_SIZE);
-+    assert(offset < f->buf_allocated_size);
- 
-     if (index >= f->buf_size) {
-         qemu_fill_buffer(f);
-@@ -778,7 +790,7 @@ 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)
- {
--    ssize_t blen = IO_BUF_SIZE - f->buf_index - sizeof(int32_t);
-+    ssize_t blen = f->buf_allocated_size - f->buf_index - sizeof(int32_t);
- 
-     if (blen < compressBound(size)) {
-         return -1;
-diff --git a/migration/qemu-file.h b/migration/qemu-file.h
-index 3f36d4dc8c..67501fd9cf 100644
---- a/migration/qemu-file.h
-+++ b/migration/qemu-file.h
-@@ -121,6 +121,7 @@ typedef struct QEMUFileHooks {
- } QEMUFileHooks;
- 
- QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops, bool has_ioc);
-+QEMUFile *qemu_fopen_ops_sized(void *opaque, const QEMUFileOps *ops, bool has_ioc, size_t buffer_size);
- void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks);
- int qemu_get_fd(QEMUFile *f);
- int qemu_fclose(QEMUFile *f);
-diff --git a/migration/savevm-async.c b/migration/savevm-async.c
-index 79a0cda906..970ee3b3fc 100644
---- a/migration/savevm-async.c
-+++ b/migration/savevm-async.c
-@@ -418,7 +418,7 @@ void qmp_savevm_start(bool has_statefile, const char *statefile, Error **errp)
-         goto restart;
-     }
- 
--    snap_state.file = qemu_fopen_ops(&snap_state, &block_file_ops);
-+    snap_state.file = qemu_fopen_ops_sized(&snap_state, &block_file_ops, false, 4 * 1024 * 1024);
- 
-     if (!snap_state.file) {
-         error_set(errp, ERROR_CLASS_GENERIC_ERROR, "failed to open '%s'", statefile);
-@@ -567,7 +567,7 @@ int load_snapshot_from_blockdev(const char *filename, Error **errp)
-     blk_op_block_all(be, blocker);
- 
-     /* restore the VM state */
--    f = qemu_fopen_ops(be, &loadstate_file_ops);
-+    f = qemu_fopen_ops_sized(be, &loadstate_file_ops, false, 4 * 1024 * 1024);
-     if (!f) {
-         error_setg(errp, "Could not open VM state file");
-         goto the_end;

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

@@ -21,28 +21,37 @@ 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
+     improve condition for entering final stage
+     adapt to QAPI and other changes for 8.2
+     make sure to not call vm_start() from coroutine
+     stop CPU throttling after finishing
+     force raw format when loading state as suggested by Friedrich Weber]
+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     | 598 +++++++++++++++++++++++++++++++++++
- monitor/hmp-cmds.c           |  57 ++++
- qapi/migration.json          |  34 ++
- qapi/misc.json               |  32 ++
+ migration/savevm-async.c     | 549 +++++++++++++++++++++++++++++++++++
+ monitor/hmp-cmds.c           |  38 +++
+ qapi/migration.json          |  34 +++
+ qapi/misc.json               |  18 ++
  qemu-options.hx              |  12 +
- softmmu/vl.c                 |  10 +
- 11 files changed, 797 insertions(+)
+ system/vl.c                  |  10 +
+ 11 files changed, 697 insertions(+)
  create mode 100644 migration/savevm-async.c
 
 diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx
-index 407a1da800..245f8acc55 100644
+index ad1b1306e3..d5ab880492 100644
 --- a/hmp-commands-info.hx
 +++ b/hmp-commands-info.hx
-@@ -536,6 +536,19 @@ SRST
+@@ -525,6 +525,19 @@ SRST
      Show current migration parameters.
  ERST
  
@@ -63,13 +72,13 @@ index 407a1da800..245f8acc55 100644
          .name       = "balloon",
          .args_type  = "",
 diff --git a/hmp-commands.hx b/hmp-commands.hx
-index 5efb47fc32..1ad13b668b 100644
+index 2e2a3bcf98..7506de251c 100644
 --- a/hmp-commands.hx
 +++ b/hmp-commands.hx
-@@ -1746,3 +1746,36 @@ ERST
-                       "\n\t\t\t -b to specify dirty bitmap as method of calculation)",
-         .cmd        = hmp_calc_dirty_rate,
-     },
+@@ -1862,3 +1862,20 @@ SRST
+   List event channels in the guest
+ ERST
+ #endif
 +
 +    {
 +        .name       = "savevm-start",
@@ -80,22 +89,6 @@ index 5efb47fc32..1ad13b668b 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     = "",
@@ -104,21 +97,21 @@ index 5efb47fc32..1ad13b668b 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 96d014826a..3a39ba41b5 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);
@@ -126,42 +119,44 @@ index 96d014826a..3a39ba41b5 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 f8714dcb15..ea9aedeefc 100644
+index 95d1cf2250..800f12a60d 100644
 --- a/migration/meson.build
 +++ b/migration/meson.build
-@@ -23,6 +23,7 @@ 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..79a0cda906
+index 0000000000..ae7ed68651
 --- /dev/null
 +++ b/migration/savevm-async.c
-@@ -0,0 +1,598 @@
+@@ -0,0 +1,549 @@
 +#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"
 +#include "migration/ram.h"
 +#include "migration/qemu-file.h"
++#include "sysemu/cpu-throttle.h"
 +#include "sysemu/sysemu.h"
 +#include "sysemu/runstate.h"
 +#include "block/block.h"
@@ -176,12 +171,10 @@ index 0000000000..79a0cda906
 +#include "qemu/timer.h"
 +#include "qemu/main-loop.h"
 +#include "qemu/rcu.h"
++#include "qemu/yank.h"
 +
 +/* #define DEBUG_SAVEVM_STATE */
 +
-+/* used while emulated sync operation in progress */
-+#define NOT_DONE -EINPROGRESS
-+
 +#ifdef DEBUG_SAVEVM_STATE
 +#define DPRINTF(fmt, ...) \
 +    do { printf("savevm-async: " fmt, ## __VA_ARGS__); } while (0)
@@ -210,7 +203,7 @@ index 0000000000..79a0cda906
 +    int64_t total_time;
 +    QEMUBH *finalize_bh;
 +    Coroutine *co;
-+    QemuCoSleep *target_close_wait;
++    QemuCoSleep target_close_wait;
 +} snap_state;
 +
 +static bool savevm_aborted(void)
@@ -229,24 +222,20 @@ index 0000000000..79a0cda906
 +        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;
@@ -268,6 +257,7 @@ index 0000000000..79a0cda906
 +
 +    if (snap_state.file) {
 +        ret = qemu_fclose(snap_state.file);
++        snap_state.file = NULL;
 +    }
 +
 +    if (snap_state.target) {
@@ -285,15 +275,13 @@ index 0000000000..79a0cda906
 +        blk_unref(snap_state.target);
 +        snap_state.target = NULL;
 +
-+        if (snap_state.target_close_wait) {
-+            qemu_co_sleep_wake(snap_state.target_close_wait);
-+        }
++        qemu_co_sleep_wake(&snap_state.target_close_wait);
 +    }
 +
 +    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;
@@ -313,64 +301,9 @@ index 0000000000..79a0cda906
 +    snap_state.state = SAVE_STATE_ERROR;
 +}
 +
-+static int block_state_close(void *opaque, Error **errp)
-+{
-+    snap_state.file = NULL;
-+    return blk_flush(snap_state.target);
-+}
-+
-+typedef struct BlkRwCo {
-+    int64_t offset;
-+    QEMUIOVector *qiov;
-+    ssize_t ret;
-+} BlkRwCo;
-+
-+static void coroutine_fn block_state_write_entry(void *opaque) {
-+    BlkRwCo *rwco = opaque;
-+    rwco->ret = blk_co_pwritev(snap_state.target, rwco->offset, rwco->qiov->size,
-+                               rwco->qiov, 0);
-+    aio_wait_kick();
-+}
-+
-+static ssize_t block_state_writev_buffer(void *opaque, struct iovec *iov,
-+                                         int iovcnt, int64_t pos, Error **errp)
-+{
-+    QEMUIOVector qiov;
-+    BlkRwCo rwco;
-+
-+    assert(pos == snap_state.bs_pos);
-+    rwco = (BlkRwCo) {
-+        .offset = pos,
-+        .qiov = &qiov,
-+        .ret = NOT_DONE,
-+    };
-+
-+    qemu_iovec_init_external(&qiov, iov, iovcnt);
-+
-+    if (qemu_in_coroutine()) {
-+        block_state_write_entry(&rwco);
-+    } else {
-+        Coroutine *co = qemu_coroutine_create(&block_state_write_entry, &rwco);
-+        bdrv_coroutine_enter(blk_bs(snap_state.target), co);
-+        BDRV_POLL_WHILE(blk_bs(snap_state.target), rwco.ret == NOT_DONE);
-+    }
-+    if (rwco.ret < 0) {
-+        return rwco.ret;
-+    }
-+
-+    snap_state.bs_pos += qiov.size;
-+    return qiov.size;
-+}
-+
-+static const QEMUFileOps block_file_ops = {
-+    .writev_buffer =  block_state_writev_buffer,
-+    .close =          block_state_close,
-+};
-+
 +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();
@@ -387,9 +320,7 @@ index 0000000000..79a0cda906
 +     * 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) {
@@ -401,7 +332,7 @@ index 0000000000..79a0cda906
 +        (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);
 +        }
 +    }
 +
@@ -414,6 +345,12 @@ index 0000000000..79a0cda906
 +        ret || aborted ? MIGRATION_STATUS_FAILED : MIGRATION_STATUS_COMPLETED);
 +    ms->to_dst_file = NULL;
 +
++    /*
++     * Same as in migration_iteration_finish(): saving RAM might've turned on CPU throttling for
++     * auto-converge, make sure to disable it.
++     */
++    cpu_throttle_stop();
++
 +    qemu_savevm_state_cleanup();
 +
 +    ret = save_snapshot_cleanup();
@@ -422,8 +359,11 @@ index 0000000000..79a0cda906
 +    } else if (snap_state.state == SAVE_STATE_ACTIVE) {
 +        snap_state.state = SAVE_STATE_COMPLETED;
 +    } else if (aborted) {
-+        save_snapshot_error("process_savevm_cleanup: found aborted state: %d",
-+                            snap_state.state);
++        /*
++         * If there was an error, there's no need to set a new one here.
++         * If the snapshot was canceled, leave setting the state to
++         * qmp_savevm_end(), which is waked by save_snapshot_cleanup().
++         */
 +    } else {
 +        save_snapshot_error("process_savevm_cleanup: invalid state: %d",
 +                            snap_state.state);
@@ -455,18 +395,32 @@ index 0000000000..79a0cda906
 +    }
 +
 +    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);
@@ -475,11 +429,7 @@ index 0000000000..79a0cda906
 +            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;
@@ -498,19 +448,25 @@ index 0000000000..79a0cda906
 +     * 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",
@@ -519,7 +475,7 @@ index 0000000000..79a0cda906
 +    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();
@@ -533,12 +489,12 @@ index 0000000000..79a0cda906
 +        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;
@@ -549,13 +505,14 @@ index 0000000000..79a0cda906
 +    snap_state.bs_pos = 0;
 +    snap_state.total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
 +    snap_state.blocker = NULL;
++    snap_state.target_close_wait = (QemuCoSleep){ .to_wake = NULL };
 +
 +    if (snap_state.error) {
 +        error_free(snap_state.error);
 +        snap_state.error = NULL;
 +    }
 +
-+    if (!has_statefile) {
++    if (!statefile) {
 +        vm_stop(RUN_STATE_SAVE_VM);
 +        snap_state.state = SAVE_STATE_COMPLETED;
 +        return;
@@ -575,7 +532,9 @@ index 0000000000..79a0cda906
 +        goto restart;
 +    }
 +
-+    snap_state.file = qemu_fopen_ops(&snap_state, &block_file_ops);
++    QIOChannel *ioc = QIO_CHANNEL(qio_channel_savevm_async_new(snap_state.target,
++                                                               &snap_state.bs_pos));
++    snap_state.file = qemu_file_new_output(ioc);
 +
 +    if (!snap_state.file) {
 +        error_set(errp, ERROR_CLASS_GENERIC_ERROR, "failed to open '%s'", statefile);
@@ -587,8 +546,10 @@ index 0000000000..79a0cda906
 +     * 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");
@@ -597,10 +558,8 @@ index 0000000000..79a0cda906
 +    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.
@@ -621,29 +580,10 @@ index 0000000000..79a0cda906
 +    }
 +}
 +
-+void coroutine_fn qmp_savevm_end(Error **errp)
++static void coroutine_fn wait_for_close_co(void *opaque)
 +{
 +    int64_t timeout;
 +
-+    if (snap_state.state == SAVE_STATE_DONE) {
-+        error_set(errp, ERROR_CLASS_GENERIC_ERROR,
-+                  "VM snapshot not started\n");
-+        return;
-+    }
-+
-+    if (snap_state.state == SAVE_STATE_ACTIVE) {
-+        snap_state.state = SAVE_STATE_CANCELLED;
-+        goto wait_for_close;
-+    }
-+
-+    if (snap_state.saved_vm_running) {
-+        vm_start();
-+        snap_state.saved_vm_running = false;
-+    }
-+
-+    snap_state.state = SAVE_STATE_DONE;
-+
-+wait_for_close:
 +    if (!snap_state.target) {
 +        DPRINTF("savevm-end: no target file open\n");
 +        return;
@@ -653,9 +593,8 @@ index 0000000000..79a0cda906
 +     * call exits the statefile will be closed and can be removed immediately */
 +    DPRINTF("savevm-end: waiting for cleanup\n");
 +    timeout = 30L * 1000 * 1000 * 1000;
-+    qemu_co_sleep_ns_wakeable(snap_state.target_close_wait,
++    qemu_co_sleep_ns_wakeable(&snap_state.target_close_wait,
 +                              QEMU_CLOCK_REALTIME, timeout);
-+    snap_state.target_close_wait = NULL;
 +    if (snap_state.target) {
 +        save_snapshot_error("timeout waiting for target file close in "
 +                            "qmp_savevm_end");
@@ -664,56 +603,55 @@ index 0000000000..79a0cda906
 +        return;
 +    }
 +
++    // File closed and no other error, so ensure next snapshot can be started.
++    if (snap_state.state != SAVE_STATE_ERROR) {
++        snap_state.state = SAVE_STATE_DONE;
++    }
++
 +    DPRINTF("savevm-end: cleanup done\n");
 +}
 +
-+// FIXME: Deprecated
-+void qmp_snapshot_drive(const char *device, const char *name, Error **errp)
++void qmp_savevm_end(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);
-+}
-+
-+static ssize_t loadstate_get_buffer(void *opaque, uint8_t *buf, int64_t pos,
-+                                    size_t size, Error **errp)
-+{
-+    BlockBackend *be = opaque;
-+    int64_t maxlen = blk_getlength(be);
-+    if (pos > maxlen) {
-+        return -EIO;
++    if (snap_state.state == SAVE_STATE_DONE) {
++        error_set(errp, ERROR_CLASS_GENERIC_ERROR,
++                  "VM snapshot not started\n");
++        return;
 +    }
-+    if ((pos + size) > maxlen) {
-+        size = maxlen - pos - 1;
-+    }
-+    if (size == 0) {
-+        return 0;
-+    }
-+    return blk_pread(be, pos, buf, size);
-+}
 +
-+static const QEMUFileOps loadstate_file_ops = {
-+    .get_buffer = loadstate_get_buffer,
-+};
++    Coroutine *wait_for_close = qemu_coroutine_create(wait_for_close_co, NULL);
++
++    if (snap_state.state == SAVE_STATE_ACTIVE) {
++        snap_state.state = SAVE_STATE_CANCELLED;
++        qemu_coroutine_enter(wait_for_close);
++        return;
++    }
++
++    if (snap_state.saved_vm_running) {
++        vm_start();
++        snap_state.saved_vm_running = false;
++    }
++
++    snap_state.state = SAVE_STATE_DONE;
++
++    qemu_coroutine_enter(wait_for_close);
++}
 +
 +int load_snapshot_from_blockdev(const char *filename, Error **errp)
 +{
 +    BlockBackend *be;
 +    Error *local_err = NULL;
 +    Error *blocker = NULL;
++    QDict *options;
 +
 +    QEMUFile *f;
++    size_t bs_pos = 0;
 +    int ret = -EINVAL;
 +
-+    be = blk_new_open(filename, NULL, NULL, 0, &local_err);
++    options = qdict_new();
++    qdict_put_str(options, "driver", "raw");
++
++    be = blk_new_open(filename, NULL, options, 0, &local_err);
 +
 +    if (!be) {
 +        error_setg(errp, "Could not open VM state file");
@@ -724,7 +662,7 @@ index 0000000000..79a0cda906
 +    blk_op_block_all(be, blocker);
 +
 +    /* restore the VM state */
-+    f = qemu_fopen_ops(be, &loadstate_file_ops);
++    f = qemu_file_new_input(QIO_CHANNEL(qio_channel_savevm_async_new(be, &bs_pos)));
 +    if (!f) {
 +        error_setg(errp, "Could not open VM state file");
 +        goto the_end;
@@ -737,6 +675,10 @@ index 0000000000..79a0cda906
 +    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");
@@ -754,39 +696,28 @@ index 0000000000..79a0cda906
 +    return ret;
 +}
 diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
-index e9fa9af6bd..5000ce39d1 100644
+index 871898ac46..ef4634e5c1 100644
 --- a/monitor/hmp-cmds.c
 +++ b/monitor/hmp-cmds.c
-@@ -1903,6 +1903,63 @@ 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);
 +}
 +
@@ -803,7 +734,7 @@ index e9fa9af6bd..5000ce39d1 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);
@@ -813,21 +744,17 @@ index e9fa9af6bd..5000ce39d1 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 bbfd48cf0b..45686390a2 100644
+index 8c65b90328..ed20d066cd 100644
 --- a/qapi/migration.json
 +++ b/qapi/migration.json
-@@ -247,6 +247,40 @@
-            '*compression': 'CompressionStats',
-            '*socket-address': ['SocketAddress'] } }
+@@ -297,6 +297,40 @@
+            '*dirty-limit-throttle-time-per-round': 'uint64',
+            '*dirty-limit-ring-full-time': 'uint64'} }
  
 +##
 +# @SaveVMInfo:
@@ -867,10 +794,10 @@ index bbfd48cf0b..45686390a2 100644
  # @query-migrate:
  #
 diff --git a/qapi/misc.json b/qapi/misc.json
-index 358548abe1..25b3febc52 100644
+index ec30e5c570..3c68633f68 100644
 --- a/qapi/misc.json
 +++ b/qapi/misc.json
-@@ -435,6 +435,38 @@
+@@ -454,6 +454,24 @@
  ##
  { 'command': 'query-fdsets', 'returns': ['FdsetInfo'] }
  
@@ -879,41 +806,27 @@ index 358548abe1..25b3febc52 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.
 +#
 +##
-+{ 'command': 'savevm-end', 'coroutine': true }
++{ 'command': 'savevm-end' }
 +
  ##
  # @CommandLineParameterType:
  #
 diff --git a/qemu-options.hx b/qemu-options.hx
-index ae2c6dbbfc..423144abeb 100644
+index 8ce85d4559..511ab9415e 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
-@@ -4171,6 +4171,18 @@ SRST
+@@ -4610,6 +4610,18 @@ SRST
      Start right away with a saved state (``loadvm`` in monitor)
  ERST
  
@@ -932,22 +845,22 @@ index ae2c6dbbfc..423144abeb 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 620a1f1367..fd82efb8b3 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -156,6 +156,7 @@ static const char *incoming;
- static const char *loadvm;
- 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;
 +static const char *loadstate;
  static QTAILQ_HEAD(, ObjectOption) object_opts = QTAILQ_HEAD_INITIALIZER(object_opts);
  static QTAILQ_HEAD(, DeviceOption) device_opts = QTAILQ_HEAD_INITIALIZER(device_opts);
- static ram_addr_t maxram_size;
-@@ -2743,6 +2744,12 @@ void qmp_x_exit_preconfig(Error **errp)
- 
-     if (loadvm) {
+ static int display_remote;
+@@ -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) {
@@ -957,7 +870,7 @@ index 620a1f1367..fd82efb8b3 100644
      }
      if (replay_mode != REPLAY_MODE_NONE) {
          replay_vmstate_init();
-@@ -3284,6 +3291,9 @@ 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

@@ -0,0 +1,217 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Wolfgang Bumiller <w.bumiller@proxmox.com>
+Date: Mon, 4 May 2020 11:05:08 +0200
+Subject: [PATCH] PVE: add optional buffer size to QEMUFile
+
+So we can use a 4M buffer for savevm-async which should
+increase performance storing the state onto ceph.
+
+Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
+[increase max IOV count in QEMUFile to actually write more data]
+Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
+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    | 50 +++++++++++++++++++++++++++-------------
+ migration/qemu-file.h    |  2 ++
+ migration/savevm-async.c |  5 ++--
+ 3 files changed, 39 insertions(+), 18 deletions(-)
+
+diff --git a/migration/qemu-file.c b/migration/qemu-file.c
+index a10882d47f..19c1de0472 100644
+--- a/migration/qemu-file.c
++++ b/migration/qemu-file.c
+@@ -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)
++#define DEFAULT_IO_BUF_SIZE 32768
++#define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 256)
+ 
+ struct QEMUFile {
+     QIOChannel *ioc;
+@@ -44,7 +44,8 @@ struct QEMUFile {
+ 
+     int buf_index;
+     int buf_size; /* 0 when writing */
+-    uint8_t buf[IO_BUF_SIZE];
++    size_t buf_allocated_size;
++    uint8_t *buf;
+ 
+     DECLARE_BITMAP(may_free, MAX_IOV_SIZE);
+     struct iovec iov[MAX_IOV_SIZE];
+@@ -101,7 +102,9 @@ int qemu_file_shutdown(QEMUFile *f)
+     return 0;
+ }
+ 
+-static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
++static QEMUFile *qemu_file_new_impl(QIOChannel *ioc,
++                                    bool is_writable,
++                                    size_t buffer_size)
+ {
+     QEMUFile *f;
+ 
+@@ -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;
++    f->buf_allocated_size = buffer_size;
++    f->buf = malloc(buffer_size);
+ 
+     return f;
+ }
+@@ -120,17 +125,27 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
+  */
+ QEMUFile *qemu_file_get_return_path(QEMUFile *f)
+ {
+-    return qemu_file_new_impl(f->ioc, !f->is_writable);
++    return qemu_file_new_impl(f->ioc, !f->is_writable, DEFAULT_IO_BUF_SIZE);
+ }
+ 
+ QEMUFile *qemu_file_new_output(QIOChannel *ioc)
+ {
+-    return qemu_file_new_impl(ioc, true);
++    return qemu_file_new_impl(ioc, true, DEFAULT_IO_BUF_SIZE);
++}
++
++QEMUFile *qemu_file_new_output_sized(QIOChannel *ioc, size_t buffer_size)
++{
++    return qemu_file_new_impl(ioc, true, buffer_size);
+ }
+ 
+ QEMUFile *qemu_file_new_input(QIOChannel *ioc)
+ {
+-    return qemu_file_new_impl(ioc, false);
++    return qemu_file_new_impl(ioc, false, DEFAULT_IO_BUF_SIZE);
++}
++
++QEMUFile *qemu_file_new_input_sized(QIOChannel *ioc, size_t buffer_size)
++{
++    return qemu_file_new_impl(ioc, false, buffer_size);
+ }
+ 
+ /*
+@@ -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,
+-                               IO_BUF_SIZE - pending,
++                               f->buf_allocated_size - pending,
+                                &local_error);
+         if (len == QIO_CHANNEL_ERR_BLOCK) {
+             if (qemu_in_coroutine()) {
+@@ -368,6 +383,9 @@ int qemu_fclose(QEMUFile *f)
+         ret = ret2;
+     }
+     g_clear_pointer(&f->ioc, object_unref);
++
++    free(f->buf);
++
+     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;
+-        if (f->buf_index == IO_BUF_SIZE) {
++        if (f->buf_index == f->buf_allocated_size) {
+             qemu_fflush(f);
+         }
+     }
+@@ -441,7 +459,7 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
+     }
+ 
+     while (size > 0) {
+-        l = IO_BUF_SIZE - f->buf_index;
++        l = f->buf_allocated_size - f->buf_index;
+         if (l > size) {
+             l = size;
+         }
+@@ -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));
+-    assert(offset < IO_BUF_SIZE);
+-    assert(size <= IO_BUF_SIZE - offset);
++    assert(offset < f->buf_allocated_size);
++    assert(size <= f->buf_allocated_size - offset);
+ 
+     /* The 1st byte to read from */
+     index = f->buf_index + offset;
+@@ -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;
+ 
+-        res = qemu_peek_buffer(f, &src, MIN(pending, IO_BUF_SIZE), 0);
++        res = qemu_peek_buffer(f, &src, MIN(pending, f->buf_allocated_size), 0);
+         if (res == 0) {
+             return done;
+         }
+@@ -672,7 +690,7 @@ size_t coroutine_mixed_fn qemu_get_buffer(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;
+ 
+@@ -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));
+-    assert(offset < IO_BUF_SIZE);
++    assert(offset < f->buf_allocated_size);
+ 
+     if (index >= f->buf_size) {
+         qemu_fill_buffer(f);
+@@ -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)
+ {
+-    ssize_t blen = IO_BUF_SIZE - f->buf_index - sizeof(int32_t);
++    ssize_t blen = f->buf_allocated_size - f->buf_index - sizeof(int32_t);
+ 
+     if (blen < compressBound(size)) {
+         return -1;
+diff --git a/migration/qemu-file.h b/migration/qemu-file.h
+index 32fd4a34fd..36a0cd8cc8 100644
+--- a/migration/qemu-file.h
++++ b/migration/qemu-file.h
+@@ -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);
+ int qemu_fclose(QEMUFile *f);
+ 
+ /*
+diff --git a/migration/savevm-async.c b/migration/savevm-async.c
+index ae7ed68651..cdd5ea6288 100644
+--- a/migration/savevm-async.c
++++ b/migration/savevm-async.c
+@@ -386,7 +386,7 @@ 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));
+-    snap_state.file = qemu_file_new_output(ioc);
++    snap_state.file = qemu_file_new_output_sized(ioc, 4 * 1024 * 1024);
+ 
+     if (!snap_state.file) {
+         error_set(errp, ERROR_CLASS_GENERIC_ERROR, "failed to open '%s'", statefile);
+@@ -514,7 +514,8 @@ int load_snapshot_from_blockdev(const char *filename, Error **errp)
+     blk_op_block_all(be, blocker);
+ 
+     /* restore the VM state */
+-    f = qemu_file_new_input(QIO_CHANNEL(qio_channel_savevm_async_new(be, &bs_pos)));
++    f = qemu_file_new_input_sized(QIO_CHANNEL(qio_channel_savevm_async_new(be, &bs_pos)),
++                                  4 * 1024 * 1024);
+     if (!f) {
+         error_setg(errp, "Could not open VM state file");
+         goto the_end;

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

@@ -4,32 +4,34 @@ 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
+     use dedicated function to open file child]
+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  | 207 ++++++++++++++++++++++++++++++++++++++++++++++
+ 2 files changed, 208 insertions(+)
  create mode 100644 block/zeroinit.c
 
 diff --git a/block/meson.build b/block/meson.build
-index deb73ca389..c9d1fdca7d 100644
+index e1f03fd773..b530e117b5 100644
 --- a/block/meson.build
 +++ b/block/meson.build
-@@ -41,6 +41,7 @@ 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..7998c9332d
 --- /dev/null
 +++ b/block/zeroinit.c
-@@ -0,0 +1,196 @@
+@@ -0,0 +1,207 @@
 +/*
 + * Filter to fake a zero-initialized block device.
 + *
@@ -43,6 +45,8 @@ 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"
@@ -108,10 +112,9 @@ 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);
-+    if (local_err) {
-+        ret = -EINVAL;
++    ret = bdrv_open_file_child(qemu_opt_get(opts, "x-next"), options, "next",
++                               bs, &local_err);
++    if (ret < 0) {
 +        error_propagate(errp, local_err);
 +        goto fail;
 +    }
@@ -122,7 +125,9 @@ 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 +139,22 @@ 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 +162,9 @@ 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 +173,37 @@ 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 +214,7 @@ 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 +230,7 @@ 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

@@ -10,16 +10,16 @@ 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 423144abeb..4879471aeb 100644
+index 511ab9415e..92e301d545 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
-@@ -1019,6 +1019,9 @@ DEFHEADING()
+@@ -1237,6 +1237,9 @@ legacy PC, they are not recommended for modern configurations.
  
- DEFHEADING(Block device options:)
+ ERST
  
 +DEF("id", HAS_ARG, QEMU_OPTION_id,
 +    "-id n           set the VMID", QEMU_ARCH_ALL)
@@ -27,11 +27,11 @@ index 423144abeb..4879471aeb 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 fd82efb8b3..eb05e5a000 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -2779,6 +2779,7 @@ 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 fd82efb8b3..eb05e5a000 100644
  
      qemu_add_opts(&qemu_drive_opts);
      qemu_add_drive_opts(&qemu_legacy_drive_opts);
-@@ -3421,6 +3422,13 @@ 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 fd82efb8b3..eb05e5a000 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 821405fd02..e3b6c3c524 100644
+index 43bc0bd520..60e98c87f1 100644
 --- a/block/file-posix.c
 +++ b/block/file-posix.c
-@@ -2465,6 +2465,7 @@ 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 821405fd02..e3b6c3c524 100644
  
      /* Validate options and set default values */
      assert(options->driver == BLOCKDEV_DRIVER_FILE);
-@@ -2505,19 +2506,22 @@ 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 821405fd02..e3b6c3c524 100644
      }
  
      /* Clear the file by truncating it to 0 */
-@@ -2571,13 +2575,15 @@ 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 821405fd02..e3b6c3c524 100644
      }
  
  out_close:
-@@ -2602,6 +2608,7 @@ 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 821405fd02..e3b6c3c524 100644
  
      /* Skip file: protocol prefix */
      strstart(filename, "file:", &filename);
-@@ -2624,6 +2631,18 @@ 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 821405fd02..e3b6c3c524 100644
      options = (BlockdevCreateOptions) {
          .driver     = BLOCKDEV_DRIVER_FILE,
          .u.file     = {
-@@ -2635,6 +2654,8 @@ 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 821405fd02..e3b6c3c524 100644
      };
      return raw_co_create(&options, errp);
 diff --git a/qapi/block-core.json b/qapi/block-core.json
-index 1d3dd9cb48..3f81d6a5c0 100644
+index 905da8be72..3db587a6e4 100644
 --- a/qapi/block-core.json
 +++ b/qapi/block-core.json
-@@ -4445,7 +4445,8 @@
+@@ -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 53a99abc56..ad2cb2592e 100644
+index 4273de16a0..83f1fc0293 100644
 --- a/hw/core/machine.c
 +++ b/hw/core/machine.c
-@@ -113,7 +113,8 @@ 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 9c1c190104..51e04bde62 100644
+index 8b8f6d5c00..dd6d0a1447 100644
 --- a/include/hw/boards.h
 +++ b/include/hw/boards.h
-@@ -227,6 +227,8 @@ 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 0905618e25..a05c46e253 100644
+index a024d5b05d..1d69bffaa0 100644
 --- a/qapi/machine.json
 +++ b/qapi/machine.json
-@@ -160,6 +160,8 @@
+@@ -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',
-@@ -167,7 +169,7 @@
+@@ -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 eb05e5a000..f306d21d63 100644
---- a/softmmu/vl.c
-+++ b/softmmu/vl.c
-@@ -1655,6 +1655,7 @@ 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;
-@@ -1672,6 +1673,11 @@ 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 eb05e5a000..f306d21d63 100644
      g_slist_free(machines);
      if (local_err) {
          error_append_hint(&local_err, "Use -machine help to list supported machines\n");
-@@ -3363,12 +3369,31 @@ 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

@@ -25,11 +25,11 @@ 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 21d5983779..47e218857d 100644
+index 3dd2e229d2..eba5b11493 100644
 --- a/block/backup.c
 +++ b/block/backup.c
-@@ -239,8 +239,8 @@ static void backup_init_bcs_bitmap(BackupBlockJob *job)
-         assert(ret);
+@@ -237,8 +237,8 @@ static void backup_init_bcs_bitmap(BackupBlockJob *job)
+                                          true);
      } else if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
          /*
 -         * We can't hog the coroutine to initialize this thoroughly.
@@ -39,7 +39,7 @@ index 21d5983779..47e218857d 100644
           */
          block_copy_set_skip_unallocated(job->bcs, true);
      }
-@@ -254,8 +254,6 @@ static int coroutine_fn backup_run(Job *job, Error **errp)
+@@ -252,8 +252,6 @@ static int coroutine_fn backup_run(Job *job, Error **errp)
      BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
      int ret;
  
@@ -48,9 +48,9 @@ index 21d5983779..47e218857d 100644
      if (s->sync_mode == MIRROR_SYNC_MODE_TOP) {
          int64_t offset = 0;
          int64_t count;
-@@ -493,6 +491,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
-     block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
+@@ -502,6 +500,8 @@ 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 +3,47 @@ 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
+     allow specifying disk formats for create operation]
+Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
 ---
  block/meson.build |   2 +
  meson.build       |   5 +
- vma-reader.c      | 860 ++++++++++++++++++++++++++++++++++++++++++++++
- vma-writer.c      | 790 ++++++++++++++++++++++++++++++++++++++++++
- vma.c             | 849 +++++++++++++++++++++++++++++++++++++++++++++
+ vma-reader.c      | 870 ++++++++++++++++++++++++++++++++++++++++++
+ vma-writer.c      | 817 ++++++++++++++++++++++++++++++++++++++++
+ vma.c             | 941 ++++++++++++++++++++++++++++++++++++++++++++++
  vma.h             | 150 ++++++++
- 6 files changed, 2656 insertions(+)
+ 6 files changed, 2785 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 c9d1fdca7d..72081a9974 100644
+index b530e117b5..b245daa98e 100644
 --- a/block/meson.build
 +++ b/block/meson.build
-@@ -44,6 +44,8 @@ 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'))
  
- block_ss.add(when: 'CONFIG_QCOW1', if_true: files('qcow.c'))
 diff --git a/meson.build b/meson.build
-index 96de1a6ef9..54c23b9567 100644
+index 91a0aa64c6..620cc594b2 100644
 --- a/meson.build
 +++ b/meson.build
-@@ -1202,6 +1202,8 @@ keyutils = dependency('libkeyutils', required: false,
+@@ -1922,6 +1922,8 @@ endif
  
  has_gettid = cc.has_function('gettid')
  
@@ -45,7 +52,7 @@ index 96de1a6ef9..54c23b9567 100644
  # libselinux
  selinux = dependency('libselinux',
                       required: get_option('selinux'),
-@@ -3070,6 +3072,9 @@ if have_tools
+@@ -4023,6 +4025,9 @@ if have_tools
                 dependencies: [blockdev, qemuutil, gnutls, selinux],
                 install: true)
  
@@ -53,14 +60,14 @@ index 96de1a6ef9..54c23b9567 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..4f4ee2b47b
+index 0000000000..d0b6721812
 --- /dev/null
 +++ b/vma-reader.c
-@@ -0,0 +1,860 @@
+@@ -0,0 +1,870 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -78,11 +85,11 @@ index 0000000000..4f4ee2b47b
 +#include <glib.h>
 +#include <uuid/uuid.h>
 +
-+#include "qemu-common.h"
 +#include "qemu/timer.h"
 +#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];
@@ -92,6 +99,7 @@ index 0000000000..4f4ee2b47b
 +    bool write_zeroes;
 +    unsigned long *bitmap;
 +    int bitmap_size;
++    bool skip;
 +}  VmaRestoreState;
 +
 +struct VmaReader {
@@ -489,13 +497,14 @@ index 0000000000..4f4ee2b47b
 +}
 +
 +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;
 +
@@ -510,28 +519,30 @@ index 0000000000..4f4ee2b47b
 +}
 +
 +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;
 +}
@@ -589,10 +600,12 @@ index 0000000000..4f4ee2b47b
 +            }
 +        }
 +    } else {
-+        int res = blk_pwrite(target, sector_num * BDRV_SECTOR_SIZE, buf, nb_sectors * BDRV_SECTOR_SIZE, 0);
++        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;
 +        }
 +    }
@@ -624,19 +637,23 @@ index 0000000000..4f4ee2b47b
 +        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 {
@@ -682,7 +699,7 @@ index 0000000000..4f4ee2b47b
 +                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,
@@ -718,7 +735,7 @@ index 0000000000..4f4ee2b47b
 +                        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,
@@ -743,7 +760,7 @@ index 0000000000..4f4ee2b47b
 +                            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) {
@@ -914,7 +931,7 @@ index 0000000000..4f4ee2b47b
 +
 +    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);
 +        }
 +    }
 +
@@ -923,10 +940,10 @@ index 0000000000..4f4ee2b47b
 +
 diff --git a/vma-writer.c b/vma-writer.c
 new file mode 100644
-index 0000000000..11d8321ffd
+index 0000000000..a466652a5d
 --- /dev/null
 +++ b/vma-writer.c
-@@ -0,0 +1,790 @@
+@@ -0,0 +1,817 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -942,6 +959,8 @@ index 0000000000..11d8321ffd
 +
 +#include "qemu/osdep.h"
 +#include <glib.h>
++#include <linux/magic.h>
++#include <sys/vfs.h>
 +#include <uuid/uuid.h>
 +
 +#include "vma.h"
@@ -950,6 +969,8 @@ index 0000000000..11d8321ffd
 +#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 +1153,10 @@ index 0000000000..11d8321ffd
 +{
 +    assert(qemu_in_coroutine());
 +    AioContext *ctx = qemu_get_current_aio_context();
-+    aio_set_fd_handler(ctx, fd, false, NULL, (IOHandler *)qemu_coroutine_enter,
++    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);
++    aio_set_fd_handler(ctx, fd, NULL, NULL, NULL, NULL, NULL);
 +}
 +
 +static ssize_t coroutine_fn
@@ -1184,6 +1205,23 @@ index 0000000000..11d8321ffd
 +    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 +1271,19 @@ index 0000000000..11d8321ffd
 +            }
 +            /* 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;
@@ -1473,17 +1518,16 @@ index 0000000000..11d8321ffd
 +    int i;
 +
 +    g_assert(vmaw != NULL);
++    g_assert(status != NULL);
 +
-+    if (status) {
-+        status->status = vmaw->status;
-+        g_strlcpy(status->errmsg, vmaw->errmsg, sizeof(status->errmsg));
-+        for (i = 0; i <= 255; i++) {
-+            status->stream_info[i] = vmaw->stream_info[i];
-+        }
-+
-+        uuid_unparse_lower(vmaw->uuid, status->uuid_str);
++    status->status = vmaw->status;
++    g_strlcpy(status->errmsg, vmaw->errmsg, sizeof(status->errmsg));
++    for (i = 0; i <= 255; i++) {
++        status->stream_info[i] = vmaw->stream_info[i];
 +    }
 +
++    uuid_unparse_lower(vmaw->uuid, status->uuid_str);
++
 +    status->closed = vmaw->closed;
 +
 +    return vmaw->status;
@@ -1719,10 +1763,10 @@ index 0000000000..11d8321ffd
 +}
 diff --git a/vma.c b/vma.c
 new file mode 100644
-index 0000000000..89440733b1
+index 0000000000..8d4b4be414
 --- /dev/null
 +++ b/vma.c
-@@ -0,0 +1,849 @@
+@@ -0,0 +1,941 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -1740,11 +1784,11 @@ index 0000000000..89440733b1
 +#include <glib.h>
 +
 +#include "vma.h"
-+#include "qemu-common.h"
 +#include "qemu/module.h"
 +#include "qemu/error-report.h"
 +#include "qemu/main-loop.h"
 +#include "qemu/cutils.h"
++#include "qemu/memalign.h"
 +#include "qapi/qmp/qdict.h"
 +#include "sysemu/block-backend.h"
 +
@@ -1754,9 +1798,9 @@ index 0000000000..89440733b1
 +        "usage: vma command [command options]\n"
 +        "\n"
 +        "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 config <filename> [-c <config>]\n"
++        "vma create <filename> [-c <config>] [-d format=<format>:<device name>=<path> [-d ...]]\n"
++        "vma extract <filename> [-d <drive-list>] [-r <fifo>] <targetdir>\n"
 +        "vma verify <filename> [-v]\n"
 +        ;
 +
@@ -1863,6 +1907,7 @@ index 0000000000..89440733b1
 +    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..89440733b1
 +    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..89440733b1
 +        case 'h':
 +            help();
 +            break;
++        case 'd':
++            drive_list = g_strsplit(optarg, ",", 254);
++            break;
 +        case 'r':
 +            readmap = optarg;
 +            break;
@@ -1970,74 +2019,89 @@ index 0000000000..89440733b1
 +            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..89440733b1
 +            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..89440733b1
 +                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..89440733b1
 +                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..89440733b1
 +        }
 +    }
 +
++    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..89440733b1
 +    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..89440733b1
 +    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..89440733b1
 +        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;
 +        }
 +    }
@@ -2293,14 +2388,16 @@ index 0000000000..89440733b1
 +
 +static int create_archive(int argc, char **argv)
 +{
-+    int i, c;
++    int c;
 +    int verbose = 0;
++    bool expect_format = true;
 +    const char *archivename;
 +    GList *backup_coroutines = NULL;
 +    GList *config_files = NULL;
++    GList *disk_infos = NULL;
 +
 +    for (;;) {
-+        c = getopt(argc, argv, "hvc:");
++        c = getopt(argc, argv, "hvc:d:");
 +        if (c == -1) {
 +            break;
 +        }
@@ -2312,6 +2409,9 @@ index 0000000000..89440733b1
 +        case 'c':
 +            config_files = g_list_append(config_files, optarg);
 +            break;
++        case 'd':
++            disk_infos = g_list_append(disk_infos, optarg);
++            break;
 +        case 'v':
 +            verbose = 1;
 +            break;
@@ -2357,16 +2457,48 @@ index 0000000000..89440733b1
 +        l = g_list_next(l);
 +    }
 +
-+    int devcount = 0;
++    /*
++     * Don't allow mixing new and old way to specifiy disks.
++     * TODO PVE 9 drop old way and always require format.
++     */
++    if (optind < argc && g_list_first(disk_infos)) {
++        unlink(archivename);
++        g_error("Unexpected extra argument - specify all devices via '-d'");
++    }
++
 +    while (optind < argc) {
-+        const char *path = argv[optind++];
++        expect_format = false;
++        disk_infos = g_list_append(disk_infos, argv[optind++]);
++    }
++
++    int devcount = 0;
++    GList *disk_l = disk_infos;
++    while (disk_l && disk_l->data) {
++        char *disk_info = disk_l->data;
++        const char *path = NULL;
 +        char *devname = NULL;
-+        path = extract_devname(path, &devname, devcount++);
++        char *format = NULL;
++        QDict *options = qdict_new();
++
++        if (try_parse_option(&disk_info, "format", &format, disk_info)) {
++            qdict_put_str(options, "driver", format);
++        } else {
++            if (expect_format) {
++                unlink(archivename);
++                g_error("No format specified for device: '%s'", disk_info);
++            } else {
++                g_warning("Specifying a device without a format is deprecated"
++                          " - use '-d format=<format>:%s'",
++                          disk_info);
++            }
++        }
++
++        path = extract_devname(disk_info, &devname, devcount++);
 +
 +        Error *errp = NULL;
 +        BlockBackend *target;
 +
-+        target = blk_new_open(path, NULL, NULL, 0, &errp);
++        target = blk_new_open(path, NULL, options, 0, &errp);
 +        if (!target) {
 +            unlink(archivename);
 +            g_error("bdrv_open '%s' failed - %s", path, error_get_pretty(errp));
@@ -2388,6 +2520,8 @@ index 0000000000..89440733b1
 +        // Don't enter coroutine yet, because it might write the header before
 +        // all streams can be registered.
 +        backup_coroutines = g_list_append(backup_coroutines, co);
++
++        disk_l = g_list_next(disk_l);
 +    }
 +
 +    VmaStatus vmastat;
@@ -2451,6 +2585,7 @@ index 0000000000..89440733b1
 +    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) {
@@ -2468,6 +2603,7 @@ index 0000000000..89440733b1
 +
 +    g_list_free(backup_coroutines);
 +    g_list_free(config_files);
++    g_list_free(disk_infos);
 +    vma_writer_destroy(vmaw);
 +    return 0;
 +}
@@ -2574,7 +2710,7 @@ index 0000000000..89440733b1
 +}
 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 +2848,7 @@ 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 +2858,7 @@ 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       | 168 ++++++++++++++++++++++++++++++++++++++
- block/backup.c            |  30 ++-----
- block/meson.build         |   1 +
- include/block/block_int.h |  35 ++++++++
- job.c                     |   3 +-
- 5 files changed, 214 insertions(+), 23 deletions(-)
+ 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, 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..93d7f46950
+index 0000000000..e46abf1070
 --- /dev/null
 +++ b/block/backup-dump.c
-@@ -0,0 +1,168 @@
+@@ -0,0 +1,172 @@
 +/*
 + * BlockDriver to send backup data stream to a callback function
 + *
@@ -35,7 +37,8 @@ index 0000000000..93d7f46950
 + */
 +
 +#include "qemu/osdep.h"
-+#include "qemu-common.h"
++
++#include "qapi/qmp/qdict.h"
 +#include "qom/object_interfaces.h"
 +#include "block/block_int.h"
 +
@@ -46,7 +49,8 @@ index 0000000000..93d7f46950
 +    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;
 +
@@ -87,7 +91,7 @@ index 0000000000..93d7f46950
 +    /* 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;
 +
@@ -147,8 +151,8 @@ index 0000000000..93d7f46950
 +
 +    .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,
 +
@@ -167,7 +171,7 @@ index 0000000000..93d7f46950
 +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,
@@ -175,9 +179,11 @@ index 0000000000..93d7f46950
 +    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;
 +    }
@@ -193,7 +199,7 @@ index 0000000000..93d7f46950
 +    return bs;
 +}
 diff --git a/block/backup.c b/block/backup.c
-index 47e218857d..4d8fad70c4 100644
+index eba5b11493..1963e47ab9 100644
 --- a/block/backup.c
 +++ b/block/backup.c
 @@ -29,28 +29,6 @@
@@ -225,7 +231,7 @@ index 47e218857d..4d8fad70c4 100644
  static const BlockJobDriver backup_job_driver;
  
  static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
-@@ -455,6 +433,14 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+@@ -462,6 +440,14 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
      }
  
      cluster_size = block_copy_cluster_size(bcs);
@@ -241,7 +247,7 @@ index 47e218857d..4d8fad70c4 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 72081a9974..7883df047c 100644
+index b245daa98e..e99914eaa4 100644
 --- a/block/meson.build
 +++ b/block/meson.build
 @@ -4,6 +4,7 @@ block_ss.add(files(
@@ -249,28 +255,28 @@ index 72081a9974..7883df047c 100644
    'amend.c',
    'backup.c',
 +  'backup-dump.c',
-   'copy-before-write.c',
    'blkdebug.c',
    'blklogwrites.c',
-diff --git a/include/block/block_int.h b/include/block/block_int.h
-index f4c75e8ba9..169dc43d59 100644
---- a/include/block/block_int.h
-+++ b/include/block/block_int.h
+   'blkverify.c',
+diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
+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_backuo_dump_create(
++BlockDriverState *coroutine_fn bdrv_co_backup_dump_create(
 +    int dump_cb_block_size,
 +    uint64_t byte_size,
 +    BackupDumpFunc *dump_cb,
@@ -306,16 +312,16 @@ index f4c75e8ba9..169dc43d59 100644
      BDRV_TRACKED_READ,
      BDRV_TRACKED_WRITE,
 diff --git a/job.c b/job.c
-index dbfa67bb0a..af25dd5b98 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 6e67b6977f..60376c99ee 100644
+index 2b873f2576..528cd6acb9 100644
 --- a/include/qemu/job.h
 +++ b/include/qemu/job.h
-@@ -294,6 +294,18 @@ typedef enum JobCreateFlags {
+@@ -362,6 +362,18 @@ void job_unlock(void);
   */
  JobTxn *job_txn_new(void);
  
@@ -34,10 +34,10 @@ index 6e67b6977f..60376c99ee 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 af25dd5b98..d0d152e697 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 af25dd5b98..d0d152e697 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 af25dd5b98..d0d152e697 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++;
-@@ -888,6 +909,9 @@ 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);
-@@ -1082,6 +1106,13 @@ 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 af25dd5b98..d0d152e697 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/0030-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 f6668ab01d..3c06734e6d 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 b2687eae3a..cfd7a60f32 100644
---- a/monitor/hmp-cmds.c
-+++ b/monitor/hmp-cmds.c
-@@ -221,19 +221,42 @@ 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 551ee28275..b9d6f52f0c 100644
---- a/qapi/block-core.json
-+++ b/qapi/block-core.json
-@@ -757,8 +757,13 @@
- #
- # @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.
-@@ -771,8 +776,8 @@
- #
- ##
- { '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' } }
- 
-@@ -815,6 +820,8 @@
- #
- # @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
- #
- ##
-@@ -825,6 +832,7 @@
-                                     '*fingerprint': 'str',
-                                     '*backup-id': 'str',
-                                     '*backup-time': 'int',
-+                                    '*use-dirty-bitmap': 'bool',
-                                     '*format': 'BackupFormat',
-                                     '*config-file': 'str',
-                                     '*firewall-file': 'str',