Message ID | 20230308165035.2097594-1-mjt@msgid.tls.msk.ru (mailing list archive) |
---|---|
Headers | show |
Series | Patch Round-up for stable 7.2.1 | expand |
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
22.03.2023 12:09, Thomas Huth пишет: ...> 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 Yes, that one is a good idea. > hw/net/vmxnet3: allow VMXNET3_MAX_MTU itself as a value Simple, picked up. > hw/pvrdma: Protect against buggy or malicious guest driver This one has been in debian for quite a long time, it is finally applied upstream, which is very good. > 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 Ok. > target/s390x: Fix R[NOX]SBG with T=1 9701596d821 says, in the commit message: Exposed by commit e2e641fa3d5 ("tcg: Change default temp lifetime to TEMP_TB"). Without this commit (e2e641fa3d5), commit 9701596d821 makes little sense I think. Also, commit 9701596d821 applies after dd161de75f3 "target/s390x: Remove g_out, g_out2, g_in1, g_in2 from DisasContext". > target/s390x: Fix EXECUTE of relative long instructions This one needs "target/s390x: Split out gen_ri2" first, it looks like it's harmless to have. Thank you very much for the suggestions, Thomas! /mjt