Re: [RFC PATCH 00/47] Patch Round-up for stable 7.2.1

[Thomas Huth <thuth@redhat.com>]

On 08/03/2023 17.57, Michael Tokarev wrote:
> Hello!
> 
> This is my first attempt to perform a stable qemu release.
> Doing it in a way similar to how Michael Roth did it before :)
> But since this is my first attempt, this is an RFC for now.
> 
> The following new patches are queued for QEMU stable v7.2.1:
> 
>    https://gitlab.com/mjt0k/qemu/-/commits/stable-7.2-staging/
> 
> Please respond here or CC qemu-stable@nongnu.org on any additional patches
> you think should (or shouldn't) be included in the release.
> 
> About some of the patches.
> 
> I picked up a few more than minimally necessary so that some of the CI
> tests are fixed. These are the curl forward compat change, two changes
> for tests/, and also "build-sys: fix crlf-ending C code" (fixes build
> failure on msys-win32). The same failures exists on 7.2.0 now, while
> the proposed 7.2.1 passes all tests I've tried so far (will try avocado
> tests too once additional hdd will arrive).
> 
> Two patches ("vdpa: stop all svq on device deletion" and "Revert "hw/i386:
> pass RNG seed via setup_data entry"") required conflict resolution when
> cherry-picking.
> 
> 2 virtio-rng-pci migration fixes makes certain v7.2.0 VMs non-migratable
> to v7.2.1.
> 
> -----------------------------------------------------------------------
> 
> Akihiko Odaki (4):
>    vhost-user-gpio: Configure vhost_dev when connecting
>    vhost-user-i2c: Back up vqs before cleaning up vhost_dev
>    vhost-user-rng: Back up vqs before cleaning up vhost_dev
>    hw/timer/hpet: Fix expiration time overflow
> 
> Alex Bennée (2):
>    target/arm: fix handling of HLT semihosting in system mode
>    tests/tcg: fix unused variable in linux-test
> 
> Anton Johansson (1):
>    block: Handle curl 7.55.0, 7.85.0 version changes
> 
> Carlos López (2):
>    vhost: avoid a potential use of an uninitialized variable in
>      vhost_svq_poll()
>    libvhost-user: check for NULL when allocating a virtqueue element
> 
> Chenyi Qiang (2):
>    virtio-mem: Fix the bitmap index of the section offset
>    virtio-mem: Fix the iterator variable in a vmem->rdl_list loop
> 
> David Hildenbrand (2):
>    migration/ram: Fix error handling in ram_write_tracking_start()
>    migration/ram: Fix populate_read_range()
> 
> Dr. David Alan Gilbert (2):
>    virtio-rng-pci: fix migration compat for vectors
>    virtio-rng-pci: fix transitional migration compat for vectors
> 
> Eugenio Pérez (1):
>    vdpa: stop all svq on device deletion
> 
> Evgeny Iakovlev (1):
>    target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled
> 
> Guenter Roeck (1):
>    target/sh4: Mask restore of env->flags from tb->flags
> 
> Jason Wang (3):
>    vhost: fix vq dirty bitmap syncing when vIOMMU is enabled
>    intel-iommu: fail MAP notifier without caching mode
>    intel-iommu: fail DEVIOTLB_UNMAP without dt mode
> 
> Julia Suvorova (1):
>    hw/smbios: fix field corruption in type 4 table
> 
> Kevin Wolf (1):
>    qcow2: Fix theoretical corruption in store_bitmap() error path
> 
> Klaus Jensen (2):
>    hw/nvme: fix missing endian conversions for doorbell buffers
>    hw/nvme: fix missing cq eventidx update
> 
> Laszlo Ersek (1):
>    acpi: cpuhp: fix guest-visible maximum access size to the legacy reg
>      block
> 
> Marc-André Lureau (1):
>    build-sys: fix crlf-ending C code
> 
> Michael S. Tsirkin (6):
>    Revert "x86: do not re-randomize RNG seed on snapshot load"
>    Revert "x86: re-initialize RNG seed when selecting kernel"
>    Revert "x86: reinitialize RNG seed on system reboot"
>    Revert "x86: use typedef for SetupData struct"
>    Revert "x86: return modified setup_data only if read as memory, not as
>      file"
>    Revert "hw/i386: pass RNG seed via setup_data entry"
> 
> Paolo Bonzini (4):
>    meson: accept relative symlinks in "meson introspect --installed" data
>    configure: fix GLIB_VERSION for cross-compilation
>    target/i386: fix ADOX followed by ADCX
>    block/iscsi: fix double-free on BUSY or similar statuses
> 
> Richard Henderson (8):
>    target/riscv: Set pc_succ_insn for !rvc illegal insn
>    target/arm: Fix sve_probe_page
>    target/arm: Fix in_debug path in S1_ptw_translate
>    target/arm: Fix physical address resolution for Stage2
>    tests/tcg/i386: Introduce and use reg_t consistently
>    target/i386: Fix BEXTR instruction
>    target/i386: Fix C flag for BLSI, BLSMSK, BLSR
>    target/i386: Fix BZHI instruction
> 
> Stefan Hajnoczi (1):
>    block: fix detect-zeroes= with BDRV_REQ_REGISTERED_BUF
> 
> Yajun Wu (1):
>    chardev/char-socket: set s->listener = NULL in char_socket_finalize

Maybe pick also these patches that mention "CVE" in the description:

  qga/win32: Remove change action from MSI installer
  qga/win32: Use rundll for VSS installation
  hw/net/vmxnet3: allow VMXNET3_MAX_MTU itself as a value
  hw/pvrdma: Protect against buggy or malicious guest driver

 From my s390x perspective, I'd like to suggest the following
patches (if they can be applied cleanly):

  target/s390x/arch_dump: Fix memory corruption in s390x_write_elf64_notes()
  target/s390x: Fix emulation of C(G)HRL
  target/s390x: Fix R[NOX]SBG with T=1
  target/s390x: Fix EXECUTE of relative long instructions

  Thanks,
   Thomas