v46.0
This release has been tracked in [v46.0
group](https://github.com/orgs/cloud-hypervisor/projects/6/views/4?filterQuery=release%3A%22Release+46%22)
of our [roadmap project](https://github.com/orgs/cloud-hypervisor/projects/6/).
File-level Locking Support with `--disk`
----------------------------------------
Now file-level locking is enforced for disk images, provided by users
with `--disk`. This ensures that only a single Cloud Hypervisor instance
can obtain write access to a given disk image at any time, preventing
misconfiguration and avoiding potential data corruption. (#6974)
Improved Error Reporting with VM Resizing
-----------------------------------------
Instead of returning a generic error `400` (e.g. `BadRequest`), users
now get a more specific error `429` (e.g. `TooManyRequests`) when a
pending VM resizing is not completed. This allows users to better handle
different errors, say retrying the request when applicable. (#7043)
IPv6 Address Support with `--net`
---------------------------------
It is now possible to specify an IPv6 address and mask when creating a
network interface with `--net`. (#7048)
Experimental AArch64 Support with the MSHV Hypervisor
-----------------------------------------------------
It is now possible to start VMs on AArch64 platforms when using MSHV
hypervisor. (#7055)
Deprecated SGX Support
----------------------
The SGX support now is deprecated with a warning message if it being
used, with the intention to remove its support from our code base in two
release cycles (e.g. v48.0). (#7090)
Notable Bug Fixes
-----------------
* Remove `path` as required for `DiskConfig` from the OpenAPI spec file
  (#7017)
* Properly parse PCI capabilities (#7018)
* Reprogram PCI device BAR when its MSE bit is set (#7063)
* Update IOMMU mappings of MMIO regions with BAR reprogram for VFIO
  devices (#7064)
* Avoid resizing VMs to zero vCPUs (#7086)
* Fix extended topology enumeration leaf exposed to the guest (#7087)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Bingxin Li <bl497@cam.ac.uk>
* Bo Chen <bchen@crusoe.ai>
* Fabiano Fidêncio <fidencio@northflank.com>
* Gregory Anders <ganders@cloudflare.com>
* Jinank Jain <jinankjain@microsoft.com>
* Julian Stecklina <julian.stecklina@cyberus-technology.de>
* Muminul Islam <muislam@microsoft.com>
* Paolo Bonzini <pbonzini@redhat.com>
* Philipp Schuster <philipp.schuster@cyberus-technology.de>
* Rob Bradford <rbradford@rivosinc.com>
* Ruoqing He <heruoqing@iscas.ac.cn>
* Thomas Prescher <thomas.prescher@cyberus-technology.de>
* abm-77 <andrewmiller77@protonmail.com>

v45.0
This release has been tracked in [v45.0
group](https://github.com/orgs/cloud-hypervisor/projects/6/views/4?filterQuery=release%3A%22Release+45%22)
of our [roadmap project](https://github.com/orgs/cloud-hypervisor/projects/6/).
Experimental `riscv64` Architecture Support
-------------------------------------------
Cloud Hypervisor now has experimental `riscv64` architecture
support. Details can be found from the [riscv
documentation](docs/riscv.md).
Alphabetically Sorted CLI Options
---------------------------------
To improve the readability of CLI options, the output of the `--help`
now is alphabetically sorted. (#6988)
Improved Downtime of VM Live Migration
--------------------------------------
The downtime of VM live migration is reduced via delaying some of the
tearing down process of the source VM after the destination VM is up and
running. (#6987)
Notable Bug Fixes
-----------------
* Fix seccomp filters related to http-api thread (#6967)
* Handle cross-page access in the emulator for mshv (#6968)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Anatol Belski <anbelski@linux.microsoft.com>
* Andrew Consroe <aconz2@gmail.com>
* Bo Chen <bchen@crusoe.ai>
* Jinank Jain <jinankjain@microsoft.com>
* Jinrong Liang <cloudliang@tencent.com>
* Philipp Schuster <philipp.schuster@cyberus-technology.de>
* Ruoqing He <heruoqing@iscas.ac.cn>
* Stefan Kober <stefan.kober@cyberus-technology.de>
* Wei Liu <liuwe@microsoft.com>

v44.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v44.0. The following user visible changes have been made:
Configurable `virtio-iommu` Address Width
-----------------------------------------
The `iommu_address_width` option has been added to `--platform` to allow users
to limit the `virtio-iommu` address space in the guest. (#6900)
Notable Performance Improvements
--------------------------------
The `VIRTIO_BLK_F_SEG_MAX` feature has been enabled for `virtio-block` devices,
which brings significant performance improvements on throughput. (#6885)
The `io_uring` entries are no longer forced to use async helper workers,
delegating the decision to the kernel. This change resolved the issue of having
excessive amount of worker threads when `io_uring` is being used, which is
expected to improve performance, such as reducing memory usage and reduce CPU
contention.
New Fuzzers
-----------
Our continuous fuzzing infrastructure is augmented with two new fuzzers to cover
x86 instruction emulator and `virtio-vsock`.
Notable Bug Fixes
-----------------
* Fix short read and short write that impact QCOW and VHDX support. (#6884)
* Various bug fixes on VHDX support. (#6890, #6899)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Arvind Vasudev <avasudev@crusoeenergy.com>
* Bo Chen <bo.arvin.chen@gmail.com>
* Nikolay Edigaryev <edigaryev@gmail.com>
* Rob Bradford <rbradford@rivosinc.com>
* Ruoqing He <heruoqing@iscas.ac.cn>
* Wei Liu <liuwe@microsoft.com>

v43.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v43.0. The following user visible changes have been made:
Live Migration over TCP Connections
---- --------- ---- --- -----------
Support has been added to enable direct live migration from two hosts via TCP
connections. This supplements the existing support for migrating over a UNIX
socket which can then be tunnelled as desired. The documentation has been
updated. (#6850)
Notable Performance Improvements
------- ----------- ------------
The `VIRTIO_RING_F_INDIRECT_DESC` feature has been enabled for `virtio-block`
devices. This significantly increases the throughput of the devices with a
small negative impact on latency. (#6826)
Notable Bug Fixes
------- --- -----
* Cloud Hypervisor now accepts VFIO devices that use I/O PCI BARs on non x86-64
  architectures. Whether they function depends on the host PCI host bridge
  support - previously they would be rejected even if the driver did not use
  these BARs. (#6871)
* Command line groups were adjusted to ensure that at least one payload
  parameter was provided if any other VM parameters provided. (#6832)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Alyssa Ross <hi@alyssa.is>
* Andrew Consroe <aconz2@gmail.com>
* Bo Chen <bo.arvin.chen@gmail.com>
* Jinrong Liang <cloudliang@tencent.com>
* Julian Stecklina <julian.stecklina@cyberus-technology.de>
* Muminul Islam <muislam@microsoft.com>
* Rob Bradford <rbradford@rivosinc.com>
* Ruoqing He <heruoqing@iscas.ac.cn>
* Wojtek Czekalski <wczekalski@me.com>

v42.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v42.0. The following user visible changes have been made:
SVE/SVE2 Support on AArch64
-------- ------- -- -------
The SVE and SVE2 feature bits are now propagated through to the guest on
AArch64. (#6678, #6691)
Notable Bug Fixes
------- --- -----
* Reduce latency notification when rate limited (#6672)
* Fix `virtio-console` resizing (#6704)
* Fix resizing when console uses TTY (#6754)
* Avoid deadlock in PCI BAR reprogramming that can occur when adding a new
  `virtio` device to a VM that has been restored (#6775)
* Fix console resizing after VM restore (#6748)
* Fix memory resize error due to incorrect bounds checks (#6736)
Sponsorships
------------
During this release cycle a new VFIO CI worker has been provided by Crusoe
Energy and a new ARM64 CI worker has been provided by Ubicloud.
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Alexandru Matei <alexandru.matei@uipath.com>
* Alyssa Ross <hi@alyssa.is>
* Anirudh Rayabharam <anrayabh@microsoft.com>
* BharatNarasimman <bharatn@microsoft.com>
* Bo Chen <chen.bo@intel.com>
* Jinank Jain <jinankjain@microsoft.com>
* Jonas Scholz <Jonas.Scholz@bbscholz.de>
* Nuno Das Neves <nudasnev@microsoft.com>
* Praveen K Paladugu <prapal@linux.microsoft.com>
* Purna Pavan Chandra <paekkaladevi@microsoft.com>
* Rob Bradford <rbradford@rivosinc.com>
* Ruoqing He <heruoqing@iscas.ac.cn>
* Songqian Li <sionli@tencent.com>
* Tom Dohrmann <erbse.13@gmx.de>
* Wei Liu <liuwe@microsoft.com>
* Wenyu Huang <huangwenyuu@outlook.com>
* Yuhong Zhong <yz@cs.columbia.edu>
* wuxinyue <wuxinyue.wxy@antgroup.com>

v41.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v41.0. The following user visible changes have been made:
Experimental "Pvmemcontrol" Support
------------ -------------- -------
VMM support has been added for this experimental functionality (requires
currently out of tree Linux kernel patches) to allow guests to control its
physical memory properties to allow optimisations and security features.
(#6318, #6467)
Sandboxing With Landlock Support
---------- ---- -------- -------
Support for restricting the VMM process using the Linux kernel "Landlock" API
has been added  - this can be used to restrict the files (and the read/write
permissions) that the VMM process can access. This adds another layer of
security alongside the existing sycall filters (`seccomp`) - this can be
enabled with `--landlock` and [fully documentated](docs/landlock.md). (#5170)
Notable Performance Improvements
------- ----------- ------------
* Reduced heap allocations in `virtio-net` via the use of a cache of `Iovec`
  structures (#6636)
* Notification suppression ("`EVENT_IDX`") support has been added to
  `virtio-block` giving a 60% improvement in single queue block throughput and
  IOPs performance (#6580)
* Correct size used for `status` field in `virtio-block` state (#6586)
Notable Bug Fixes
------- --- -----
* Avoid panic on out-of-bounds PCI MSI-X access (#6657)
* Fix undefined behaviour on AArch64 leading to wrong optimisation on KVM API
  access (#6647)
* Rust v1.80.0 added use of `fcntl` syscall on debug assertions so this is now
  included in the virtio-device seccomp filters for tests that use this (#6648)
* Short reads are now handled correctly in the `virtio-vsock` device (#6621)
* Fix undefined behaviour on TTY ioctl leading to wrong optimisation (#6568)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Alyssa Ross <hi@alyssa.is>
* Bo Chen <chen.bo@intel.com>
* Changyuan Lyu <changyuanl@google.com>
* Jinank Jain <jinankjain@microsoft.com>
* Julian Stecklina <julian.stecklina@cyberus-technology.de>
* Muminul Islam <muislam@microsoft.com>
* Nuno Das Neves <nudasnev@microsoft.com>
* Praveen K Paladugu <prapal@linux.microsoft.com>
* Rob Bradford <rbradford@rivosinc.com>
* Songqian Li <sionli@tencent.com>
* Wei Liu <liuwe@microsoft.com>
* Yuanchu Xie <yuanchu@google.com>
* ihciah <ihciah@gmail.com>
* wuxinyue <wuxinyue.wxy@antgroup.com>

v40.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v40.0. The following user visible changes have been made:
Support for Restoring File Descriptor Backed Network Devices
------- --- --------- ---- ---------- ------ ------- -------
It is now possible to pass file descriptors over the HTTP API (and using
`ch-remote`) when restoring to update the file descriptors for network devices.
This enables snapshot & restore functionality for guests using `macvtap` or
other file descriptor backed network devices. (#6286)
Notable Bug Fixes
------- --- -----
* Default values have been removed from required fields in the OpenAPI metadata
  (#6495)
* The help syntax of `ch-remote remove-device` has been improved (#6456)
* A double close of file descriptors has been fixed when using `--serial`
  (#6486)
* To prevent loops a limit on the nesting level for QCOW2 backing files has
  been introduced (#6482)
* Boot time performance has been improved with multiple cores by avoiding
  `cpuid` instructions and by seeding the in kernel file descriptor table
  (#6498, #6478)
* L1 cache details are more likely to be propagated into the guest (#6523)
* The default topology for guests now uses multiple cores rather than sockets
  (#6504)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Alexandru Matei <alexandru.matei@uipath.com>
* Bo Chen <chen.bo@intel.com>
* Jinank Jain <jinankjain@microsoft.com>
* Josh Soref <2119212+jsoref@users.noreply.github.com>
* Muminul Islam <muislam@microsoft.com>
* Nuno Das Neves <nudasnev@microsoft.com>
* Omer Faruk Bayram <omer.faruk@sartura.hr>
* Praveen K Paladugu <prapal@linux.microsoft.com>
* Purna Pavan Chandra <paekkaladevi@linux.microsoft.com>
* Rob Bradford <rbradford@rivosinc.com>
* SamrutGadde <samrut.gadde@gmail.com>
* Sean Banko <sbanko@crusoe.ai>
* Songqian Li <sionli@tencent.com>
* Wei Liu <liuwe@microsoft.com>
* Yi Wang <foxywang@tencent.com>
* Yu Li <liyu.yukiteru@bytedance.com>

v39.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v39.0. The following user visible changes have been made:
Variable Sizing of PCI Apertures for Segments
-------- ------ -- --- --------- --- --------
It is now possible to use `--pci-segment` to adjust the aperture size that
devices 32-bit and 64-bit PCI device BARs will be allocated from. Previously
the address space was equally distributed across all the segments which may
leave insufficient space for devices that require a large 32-bit space. With
this change the weighting per segment can be adjusted. (#6387)
Direct Booting with bzImages
------ ------- ---- --------
Support for directly booting Linux from bzImages has been added.(#6200)
Support for NVIDIA GPUDirect P2P Support
------- --- ------ --------- --- -------
The `x_nv_gpudirect_clique` option was added to `--device` to allow the
configuration of device P2P support with NVIDIA GPUs. (#6235)
Guest NMI Injection Support
----- --- --------- -------
A new API endpoint and `ch-remote` option added for injecting an NMI into the
guest. (#6047)
Notable Bug Fixes
------- --- -----
* Workaround for kernel bug affecting guest IRQ masking on AMD (#6353)
* Correctly cleanup `sigwinch_listener` process (#6208)
* Graceful shutdown of HTTP API thread (#6248, #6247)
* Fix `queue_affinity` option in OpenAPI metadata (#6268)
* Fix documentation to indicate only stream mode is supported by `virtio-vsock`
  (#6306)
* Fix `virtio-fs` tag validation (#6358, #6359)
* Add missing `pvpanic` device to OpenAPI metadata (#6372)
* Fixes for nested virtualization with VFIO devices (#6110, #6298, #6297,
  #6319)
* Fix for backing file for `virtio-mem` regions with snapshot/restore (#6337,
  #6338)
* Explicitly mark FDs used for network devices as invalid across
  snapshot/restore (#6332, #6286)
* Improve `event-monitor` events around reboot (#6277, #6274)
* Fix potential deadlock around paused devices during live migration (#6293)
* Fix panic when running `ch-remote` with no subcommand (#6230)
* Fix hotplug of `virtio` devices after snapshot/restore and live migration
  (#6326, #6265)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Alexandru Matei <alexandru.matei@uipath.com>
* Andrew Carp <acarp@crusoeenergy.com>
* Bo Chen <chen.bo@intel.com>
* Bouke van der Bijl <i@bou.ke>
* Chris Webb <chris@arachsys.com>
* Jinank Jain <jinankjain@microsoft.com>
* Lucas Jacques <contact@lucasjacques.com>
* Muminul Islam <muislam@microsoft.com>
* Nuno Das Neves <nudasnev@microsoft.com>
* Ravi kumar Veeramally <ravikumar.veeramally@intel.com>
* Rob Bradford <rbradford@rivosinc.com>
* Ruslan Mstoi <ruslan.mstoi@intel.com>
* Stefan Nuernberger <stefan.nuernberger@cyberus-technology.de>
* Thomas Barrett <tbarrett@crusoeenergy.com>
* Wei Liu <liuwe@microsoft.com>
* Yi Wang <foxywang@tencent.com>

This is a bug fix release. The following issues have been addressed:
* Fix several security advisories from dependencies (#6134, #6141)
* Enable HTT flag to avoid crashing cpu topology enumeration software
such as hwloc in the guest (#6146)
* Enable nested virtualization on AMD if supported (#6106)
* Handle non-power-of-two CPU topology properly (#6062)
* Various bug fixes around virtio-vsock(#6080, #6091, #6095)
* Align VFIO devices PCI BARs naturally (#6196)

v38.0
This release has been tracked in our [roadmap
project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
v38.0. The following user visible changes have been made:
Group Rate Limiter on Block Devices
-----------------------------------
Users now can throttle a group of block devices with the new
`--rate-limiter-group` option. Details can be found from the [I/O
Throttling documentation](docs/io_throttling.md)
CPU Pinning Support for Block Device Worker Thread
--------------------------------------------------
Users now have the option to pin virt-queue threads for block devices
to specific host cpus.
Optimized Boot Time with Parallel Memory Prefault
-------------------------------------------------
The boot time with `prefault` option enabled is optimized via parallel
memory prefault.
New 'debug-console' Device
--------------------------
A 'debug-console' device is added to provide a user-configurable debug
port for logging guest information. Details can be found from the [Debug
IO Ports documentation](docs/debug-port.md).
Improved VFIO Device Support
----------------------------
All non-emulated MMIO regions of VFIO devices are now mapped to the VFIO
container, allowing PCIe P2P between all VFIO devices on the same
VM. This is required for a wide variety of multi-GPU workloads involving
GPUDirect P2P (DMA between two GPUs), GPUDirect RDMA (DMA between a GPU
and an IB device).
Extended CPU Affinity Support
-----------------------------
Users now can set the vcpu affinity to a host CPU with index larger
than 255.
Notable Bug Fixes
-----------------
* Enable HTT flag to avoid crashing cpu topology enumeration software
such as hwloc in the guest (#6146)
* Fix several security advisories from dependencies (#6134, #6141)
* Handle non-power-of-two CPU topology properly (#6062)
* Various bug fixes around `virtio-vsock`(#6080, #6091, #6095)
* Enable nested virtualization on AMD if supported (#6106)
* Align VFIO devices PCI BARs naturally (#6196)
Contributors
------------
Many thanks to everyone who has contributed to our release:
* Alyssa Ross <hi@alyssa.is>
* Bo Chen <chen.bo@intel.com>
* Daniel Farina <daniel@ubicloud.com>
* Jinank Jain <jinankjain@microsoft.com>
* Muminul Islam <muislam@microsoft.com>
* Peteris Rudzusiks <rye@stripe.com>
* Philipp Schuster <philipp.schuster@cyberus-technology.de>
* Ravi kumar Veeramally <ravikumar.veeramally@intel.com>
* Rob Bradford <rbradford@rivosinc.com>
* Ruslan Mstoi <ruslan.mstoi@intel.com>
* Sean Banko <sbanko@crusoeenergy.com>
* Thomas Barrett <tbarrett@crusoeenergy.com>
* Wei Liu <liuwe@microsoft.com>
* Yi Wang <foxywang@tencent.com>
* acarp <acarp@crusoeenergy.com>