As an eMMC block device image may consist of more than just the user
data partition, provide a helper script that can compose the image from
boot partitions, an RPMB partition and the user data image. The script
also does the required size validation and/or rounding.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <eecefa8e-44ae-45ff-85d0-3f9b786948e0@siemens.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Ubuntu is now including updated versions of Rust (up to 1.85) for
its LTS releases. Adjust the CI containers and re-add --enable-rust
to the Ubuntu jobs.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add explicit validation for QAPI documentation formatting rules:
1. Lines must not exceed 70 columns in width (including '# ' prefix)
2. Sentences must be separated by two spaces
Example sections and literal :: blocks (seldom case) are excluded, we
don't require them to be <= 70, that would be too restrictive. Anyway,
they share common 80-columns recommendations (not requirements).
Add two simple tests, illustrating the change.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Message-ID: <20251031183129.246814-1-vsementsov@yandex-team.ru>
The detection of example and literal blocks isn't quite correct, but
it works well enough, and we can improve on top.
Reviewed-by: Markus Armbruster <armbru@redhat.com>
[Comments, error messages, and test file names tweaked]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
qmp_marshal_output_T() is only ever called by qmp_marshal_C() for a
command C that returns type T.
We've always generated it as a static function on demand, i.e. when we
generate a call.
Since we split up monolithic generated code into modules (commit
252dc3105f "qapi: Generate separate .h, .c for each module"), we do
this per module. As noted in the commit message, this can result in
identical (static) qmp_marshal_output_T() in several modules. Was
deemed not worth avoiding.
A bit later, we added 'if' conditionals to the schema language (merge
commit 5dafaf4fbc).
When a conditional definition uses a type, then its condition must
imply the type's condition. We made this the user's responsibility.
Hasn't been an issue in practice.
However, the sharing of qmp_marshal_output_T() among commands
complicates matters. To avoid both undefined function errors and
unused function warnings, qmp_marshal_output_T() must be defined
exactly when it's used. It is used when any of the qmp_marshal_C()
calling it is defined, i.e. when any C's condition holds.
The generator uses T's condition instead. To avoid both error and
warning, T's condition must be the conjunction of all C's conditions.
Unfortunately, this can be impossible:
* Conditional command returning a builtin type
A builtin type cannot be conditional. This is noted in a FIXME
comment.
* Commands in multiple modules where the conjunction differs between
modules
An instance of this came up recently. we have unconditional
commands returning HumanReadableText. If we add a conditional one
to a module that does not have unconditional ones, compilation fails
with "defined but not used". If we make HumanReadableText
conditional to fix this module, we break the others.
Instead of complicating the code to compute the conjunction, simplify
it: generate the output marshaling code right into qmp_marshal_C().
This duplicates it when multiple commands return the same type. The
impact on code size is negligible: qemu-system-x86_64's text segment
grows by 1448 bytes.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-ID: <20250804130602.903904-1-armbru@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
[Commit message typos fixed]
Remove the 'patch prefix exists, appears to be a -p0 patch' warning
entirely as it is fundamentally flawed and can only produce false
positives.
Sometimes I create test files with names 'a' and 'b', and then get
surprised seeing this warning. It was not easy to understand where it
comes from.
How it works:
1. It extracts prefixes (a/, b/) from standard diff output
2. Checks if files/directories with these names exist in the project
root
3. Warns if they exist, claiming it's a '-p0 patch' issue
This logic is wrong because:
- Standard diff/patch tools always use a/ and b/ prefixes by default
- The existence of files named 'a' or 'b' in the working directory is
completely unrelated to patch format
- The working directory state may not correspond to the patch content
(different commits, branches, etc.)
- In QEMU project, there are no single-letter files/directories in root,
so this check can only generate false positives
The correct way to detect -p0 patches would be to analyze the path
format within the patch itself (e.g., absolute paths or paths without
prefixes), not check filesystem state.
So, let's finally drop it.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Link: https://lore.kernel.org/r/20251030201319.858480-1-vsementsov@yandex-team.ru
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The argparse.FileType() type has been deprecated in the latest argparse
version (e.g. the one from Fedora 43), now causing the test_bad_vmstate
functional test to fail since there are unexpected strings in the output.
Change the script to use pathlib.Path instead to fix the test_bad_vmstate
test and to be prepared for the future when the deprecated FileType gets
removed completely.
Reported-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Link: https://lore.kernel.org/r/20251030092638.39505-1-thuth@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
When the QMP library was updated to match the standalone repository in
094ded52, I neglected to update the logging filter(s) in
device-crash-test, which allowed the spurious messages to leak through.
Update the log filter to re-suppress these messages.
Fixes: 094ded52
Reported-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: John Snow <jsnow@redhat.com>
Message-ID: <20251022213109.395149-1-jsnow@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
With the current wording, users might think that the -F option is not
required as long as the script is placed in the default path. Be clear
that the option is always required. Also includes some minor language
improvements in the rest of the comment.
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Reviewed-by: Kostiantyn Kostiuk <kkostiuk@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250916122111.36019-1-f.ebner@proxmox.com
Signed-off-by: Kostiantyn Kostiuk <kkostiuk@redhat.com>
All the functions are about "-audio model=" handling, a simpler
way to setup audio. Rename functions/variables to reflect this better.
audio_register_model_with_cb() dropped "pci" from the name, since it
will be generalized next.
deprecated_register_soundhw() was actually not a function to be
removed since it's used for "-audio model=" aliasing.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Both Debian and Ubuntu are setup the same way.
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Message-ID: <20251027110344.2289945-7-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Unlike the Aarch64 runners this comes with pure Debian out of the box.
We need a minor tweak to build-environment to deal with the
differences in naming convention.
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Message-ID: <20251027110344.2289945-6-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
There is no practical difference between the systems when it comes to
updating the installed system.
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Message-ID: <20251027110344.2289945-5-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
We can share the setup of the build environment with multiple
operating systems as we just need to check the YAML for each env is
present in the directory structure.
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Message-ID: <20251027110344.2289945-4-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
We inadvertently updated the base libvirt-ci project which has
resulted in changes. Make sure the output matches what we generate.
Fixes: 0d4fb8f746 (configure: set the bindgen cross target)
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Message-ID: <20251027110344.2289945-3-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
We no longer need to support 32 bit builds and we missed this while
cleaning up.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20251027110344.2289945-2-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
While working out what hoops to jump through to get a full set of
aarch32 packages installed on the aarch64 runner it was pointed out 32
bit host support is deprecated. As the extra packages where needed for
system emulation (marked deprecated since 8.0!) there didn't seem much
point keeping this in.
While the full expunging of 32 bit host support will probably be done
for 11.0 we can at least reduce the CI burden a bit now.
Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Message-ID: <20251016150357.876415-3-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
The download cache of the functional tests is currently only growing.
But sometimes tests get removed or changed to use different assets,
thus we should clean up the stale old assets after a while when they
are not in use anymore. So add a script that looks at the time stamps
of the assets and removes them if they haven't been touched for more
than half of a year. Since there might also be some assets around that
have been added to the cache before we added the time stamp files,
assume a default time stamp that is close to the creation date of this
patch, so that we don't delete these files too early (so we still have
all assets around in case we have to bisect an issue in the recent past
of QEMU).
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-ID: <20251014083424.103202-3-thuth@redhat.com>
Introduce headers for the Microsoft Hypervisor (MSHV) userspace ABI,
including IOCTLs and structures used to interface with the hypervisor.
These definitions are based on the upstream Linux MSHV interface and
will be used by the MSHV accelerator backend in later patches.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-6-magnuskulke@linux.microsoft.com
[Do not use __uN types. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Introduce a Meson feature option and default-config entry to allow
building QEMU with MSHV (Microsoft Hypervisor) acceleration support.
This is the first step toward implementing an MSHV backend in QEMU.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Link: https://lore.kernel.org/r/20250916164847.77883-2-magnuskulke@linux.microsoft.com
[Add error for unavailable accelerator. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The probe of GDB is done in 'configure' and the full path is passed to
meson.build via the -Dgdb=option.
Meson then can pass the location of GDB to the functional tests via an
environment variable: QEMU_TEST_GDB.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Gustavo Romero <gustavo.romero@linaro.org>
Message-ID: <20251003141820.85278-4-gustavo.romero@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
The registration-token method is being deprecated:
https://docs.gitlab.com/ci/runners/new_creation_workflow/
As a result we can drop a bunch of the descriptive stuff as that is
entered on the web UI. We don't need a secondary runner if we just
create one with both aarch64 and aarch32 tags.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-ID: <20251001170947.2769296-8-alex.bennee@linaro.org>
In anticipation of new runners lets move to a newer Ubuntu LTS.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-ID: <20251001170947.2769296-6-alex.bennee@linaro.org>
The legacy cpu_physical_memory_rw() method is no more used,
remove it.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20251002084203.63899-16-philmd@linaro.org>
Following the mechanical changes of commit adeefe0167 ("Avoid
cpu_physical_memory_rw() with a constant is_write argument"),
replace:
- cpu_physical_memory_rw(, is_write=false) -> address_space_read()
- cpu_physical_memory_rw(, is_write=true) -> address_space_write()
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20251002084203.63899-15-philmd@linaro.org>
qemu_bh_new_guarded() is considered legacy since commit 9c86c97f12
("async: Add an optional reentrancy guard to the BH API"); recommend
the new API: aio_bh_new_guarded().
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20250924163911.51479-1-philmd@linaro.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Such annotation is present into the kernel uAPI headers since
v6.7, and will be used soon by the vhost_type.h. Deal with it
just stripping it.
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a1430f43cc954d2a931fa60581bda6d6af4bc771.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The syslog backend needs the syslog function from libc and the LOG_INFO enum
value; they are re-exported as "::trace::syslog" and "::trace::LOG_INFO"
so that device crates do not all have to add the libc dependency, but
otherwise there is nothing special.
Signed-off-by: Tanish Desai <tanishdesai37@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250929154938.594389-17-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Generating .rs files makes it possible to support tracing in rust.
This support comprises a new format, and common code that converts
the C expressions in trace-events to Rust. In particular, types
need to be converted, and PRI macros expanded.
As of this commit no backend generates Rust code, but it is already
possible to use tracetool to generate Rust sources; they are not
functional but they compile and contain tracepoint functions.
[Move Rust argument conversion from Event to Arguments; string
support. - Paolo]
Signed-off-by: Tanish Desai <tanishdesai37@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250929154938.594389-9-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Use CHECK_TRACE_EVENT_GET_STATE in log, syslog, dtrace and simple
backend, so that the "if (trace_event_get_state)" is created from common
code and unified when multiple backends are active.
When a single backend is active there is no code change (except
for the log backend, as shown in tests/tracetool/log.h), but the
code in the backends is simpler.
Signed-off-by: Tanish Desai <tanishdesai37@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20250929154938.594389-8-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Add a new attribute CHECK_TRACE_EVENT_GET_STATE to the backends.
When present and True, the code generated by the generate function
is wrapped in a conditional that checks whether the event is enabled;
this removes the need for repeating the same conditional in multiple
backends.
Signed-off-by: Tanish Desai <tanishdesai37@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20250929154938.594389-7-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This simplifies the Python code and reduces the size of the tracepoints.
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20250929154938.594389-6-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250929154938.594389-5-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The "-*- coding: utf-8 -*-" header was needed in Python 2,
but in Python 3 UTF-8 is already the default encoding of
source files.
It is even less necessary in .css files that do not have UTF-8
sequences at all.
Suggested-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250929154938.594389-4-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Remove a bunch of dead code from tracetool.
In particular, there are no tcg-exec events anymore and the sub-event
functionality was only used for it.
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250929154938.594389-3-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
try_import returns a tuple of a boolean and the requested module or attribute.
exists() functions return tracetool.try_import("tracetool.format." + name)[1]
but they should return the boolean value instead.
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250929154938.594389-2-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Some distros/targets may pull it by default, but some don't.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20250924120426.2158655-16-marcandre.lureau@redhat.com>
Newer lcitool version has various fixes helping QEMU CI and this series.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20250924120426.2158655-13-marcandre.lureau@redhat.com>
Implement a bash version of rust-bindgen rust_to_clang_target() to
convert from rust target to clang target.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250924120426.2158655-8-marcandre.lureau@redhat.com>
Running meson on each subproject is quite slow.
According to Paolo, meson will run download tasks in parallel.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-ID: <20250924120426.2158655-4-marcandre.lureau@redhat.com>
Jan Kiszka
Paolo Bonzini
Vladimir Sementsov-Ogievskiy
Markus Armbruster
Thomas Huth
John Snow
Marc-André Lureau
Fiona Ebner
Alex Bennée
Stefan Hajnoczi
Magnus Kulke
Gustavo Romero
Philippe Mathieu-Daudé
Mauro Carvalho Chehab
Paolo Abeni
Tanish Desai