diff options
author | Richard Henderson <richard.henderson@linaro.org> | 2021-10-01 13:44:36 -0400 |
---|---|---|
committer | Richard Henderson <richard.henderson@linaro.org> | 2021-10-01 13:44:36 -0400 |
commit | 5f992102383ed8ed97076548e1c897c7034ed8a4 (patch) | |
tree | 7b6919d8de677594a81c98d972ea3533d69214f0 | |
parent | bb4aa8f59e18412cff0d69f14aee7abba153161a (diff) | |
parent | 16e79e1b01a698908e14eda3078d4a8e7b1b9c2b (diff) | |
download | qemu-5f992102383ed8ed97076548e1c897c7034ed8a4.zip qemu-5f992102383ed8ed97076548e1c897c7034ed8a4.tar.gz qemu-5f992102383ed8ed97076548e1c897c7034ed8a4.tar.bz2 |
Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging
* -smp cleanpus
* Hyper-V englightenment functionality
* Documentation cleanups
# gpg: Signature made Fri 01 Oct 2021 01:11:00 PM EDT
# gpg: using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg: issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
* remotes/bonzini/tags/for-upstream: (29 commits)
docs: reorganize testing.rst
docs: move gcov section at the end of testing.rst
docs: reorganize tcg-plugins.rst
docs: reorganize qgraph.rst
docs: put "make" information together in build-system.rst
docs: move notes inside the body of the document
docs: name included files ".rst.inc"
i386: Change the default Hyper-V version to match WS2016
i386: Make Hyper-V version id configurable
i386: Implement pseudo 'hv-avic' ('hv-apicv') enlightenment
i386: Move HV_APIC_ACCESS_RECOMMENDED bit setting to hyperv_fill_cpuids()
i386: Support KVM_CAP_HYPERV_ENFORCE_CPUID
i386: Support KVM_CAP_ENFORCE_PV_FEATURE_CPUID
machine: Put all sanity-check in the generic SMP parser
machine: Use g_autoptr in machine_set_smp
machine: Move smp_prefer_sockets to struct SMPCompatProps
machine: Remove smp_parse callback from MachineClass
machine: Make smp_parse generic enough for all arches
machine: Tweak the order of topology members in struct CpuTopology
machine: Use ms instead of global current_machine in sanity-check
...
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
-rw-r--r-- | docs/about/deprecated.rst | 15 | ||||
-rw-r--r-- | docs/devel/build-system.rst | 21 | ||||
-rw-r--r-- | docs/devel/ci-definitions.rst.inc (renamed from docs/devel/ci-definitions.rst) | 0 | ||||
-rw-r--r-- | docs/devel/ci-jobs.rst.inc (renamed from docs/devel/ci-jobs.rst) | 0 | ||||
-rw-r--r-- | docs/devel/ci-runners.rst.inc (renamed from docs/devel/ci-runners.rst) | 0 | ||||
-rw-r--r-- | docs/devel/ci.rst | 6 | ||||
-rw-r--r-- | docs/devel/multi-process.rst | 20 | ||||
-rw-r--r-- | docs/devel/qgraph.rst | 132 | ||||
-rw-r--r-- | docs/devel/tcg-plugins.rst | 93 | ||||
-rw-r--r-- | docs/devel/testing.rst | 182 | ||||
-rw-r--r-- | docs/hyperv.txt | 41 | ||||
-rw-r--r-- | hw/arm/virt.c | 1 | ||||
-rw-r--r-- | hw/core/machine.c | 199 | ||||
-rw-r--r-- | hw/i386/pc.c | 69 | ||||
-rw-r--r-- | hw/i386/pc_piix.c | 1 | ||||
-rw-r--r-- | hw/i386/pc_q35.c | 1 | ||||
-rw-r--r-- | hw/ppc/spapr.c | 1 | ||||
-rw-r--r-- | hw/s390x/s390-virtio-ccw.c | 1 | ||||
-rw-r--r-- | include/hw/boards.h | 23 | ||||
-rw-r--r-- | qapi/machine.json | 2 | ||||
-rw-r--r-- | qemu-options.hx | 24 | ||||
-rw-r--r-- | target/i386/cpu.c | 22 | ||||
-rw-r--r-- | target/i386/cpu.h | 12 | ||||
-rw-r--r-- | target/i386/kvm/hyperv-proto.h | 1 | ||||
-rw-r--r-- | target/i386/kvm/kvm.c | 62 | ||||
-rw-r--r-- | tests/qtest/numa-test.c | 6 |
26 files changed, 547 insertions, 388 deletions
diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 2f7db9a..0bed6ec 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -160,6 +160,21 @@ Use ``-display sdl`` instead. Use ``-display curses`` instead. +``-smp`` ("parameter=0" SMP configurations) (since 6.2) +''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +Specified CPU topology parameters must be greater than zero. + +In the SMP configuration, users should either provide a CPU topology +parameter with a reasonable value (greater than zero) or just omit it +and QEMU will compute the missing value. + +However, historically it was implicitly allowed for users to provide +a parameter with zero value, which is meaningless and could also possibly +cause unexpected results in the -smp parsing. So support for this kind of +configurations (e.g. -smp 8,sockets=0) is deprecated since 6.2 and will +be removed in the near future, users have to ensure that all the topology +members described with -smp are greater than zero. Plugin argument passing through ``arg=<string>`` (since 6.1) '''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' diff --git a/docs/devel/build-system.rst b/docs/devel/build-system.rst index 3baec15..0f636d6 100644 --- a/docs/devel/build-system.rst +++ b/docs/devel/build-system.rst @@ -380,6 +380,16 @@ phony target, while benchmarks are run with ``make bench``. Meson test suites such as ``unit`` can be ran with ``make check-unit`` too. It is also possible to run tests defined in meson.build with ``meson test``. +Useful make targets +------------------- + +``help`` + Print a help message for the most common build targets. + +``print-VAR`` + Print the value of the variable VAR. Useful for debugging the build + system. + Important files for the build system ==================================== @@ -473,14 +483,3 @@ Built by Makefile: meson.build. The rules are produced from Meson's JSON description of tests (obtained with "meson introspect --tests") through the script scripts/mtest2make.py. - - -Useful make targets -------------------- - -``help`` - Print a help message for the most common build targets. - -``print-VAR`` - Print the value of the variable VAR. Useful for debugging the build - system. diff --git a/docs/devel/ci-definitions.rst b/docs/devel/ci-definitions.rst.inc index 32e22ff..32e22ff 100644 --- a/docs/devel/ci-definitions.rst +++ b/docs/devel/ci-definitions.rst.inc diff --git a/docs/devel/ci-jobs.rst b/docs/devel/ci-jobs.rst.inc index 277975e..277975e 100644 --- a/docs/devel/ci-jobs.rst +++ b/docs/devel/ci-jobs.rst.inc diff --git a/docs/devel/ci-runners.rst b/docs/devel/ci-runners.rst.inc index 7817001..7817001 100644 --- a/docs/devel/ci-runners.rst +++ b/docs/devel/ci-runners.rst.inc diff --git a/docs/devel/ci.rst b/docs/devel/ci.rst index 8d95247..d106610 100644 --- a/docs/devel/ci.rst +++ b/docs/devel/ci.rst @@ -8,6 +8,6 @@ found at:: https://wiki.qemu.org/Testing/CI -.. include:: ci-definitions.rst -.. include:: ci-jobs.rst -.. include:: ci-runners.rst +.. include:: ci-definitions.rst.inc +.. include:: ci-jobs.rst.inc +.. include:: ci-runners.rst.inc diff --git a/docs/devel/multi-process.rst b/docs/devel/multi-process.rst index 6969932..e5758a7 100644 --- a/docs/devel/multi-process.rst +++ b/docs/devel/multi-process.rst @@ -1,15 +1,17 @@ -This is the design document for multi-process QEMU. It does not -necessarily reflect the status of the current implementation, which -may lack features or be considerably different from what is described -in this document. This document is still useful as a description of -the goals and general direction of this feature. - -Please refer to the following wiki for latest details: -https://wiki.qemu.org/Features/MultiProcessQEMU - Multi-process QEMU =================== +.. note:: + + This is the design document for multi-process QEMU. It does not + necessarily reflect the status of the current implementation, which + may lack features or be considerably different from what is described + in this document. This document is still useful as a description of + the goals and general direction of this feature. + + Please refer to the following wiki for latest details: + https://wiki.qemu.org/Features/MultiProcessQEMU + QEMU is often used as the hypervisor for virtual machines running in the Oracle cloud. Since one of the advantages of cloud computing is the ability to run many VMs from different tenants in the same cloud diff --git a/docs/devel/qgraph.rst b/docs/devel/qgraph.rst index c2882c3..db44d71 100644 --- a/docs/devel/qgraph.rst +++ b/docs/devel/qgraph.rst @@ -1,8 +1,7 @@ .. _qgraph: -======================================== Qtest Driver Framework -======================================== +====================== In order to test a specific driver, plain libqos tests need to take care of booting QEMU with the right machine and devices. @@ -31,13 +30,15 @@ so the sdhci-test should only care of linking its qgraph node with that interface. In this way, if the command line of a sdhci driver is changed, only the respective qgraph driver node has to be adjusted. +QGraph concepts +--------------- + The graph is composed by nodes that represent machines, drivers, tests and edges that define the relationships between them (``CONSUMES``, ``PRODUCES``, and ``CONTAINS``). - Nodes -^^^^^^ +~~~~~ A node can be of four types: @@ -64,7 +65,7 @@ Notes for the nodes: drivers name, otherwise they won't be discovered Edges -^^^^^^ +~~~~~ An edge relation between two nodes (drivers or machines) ``X`` and ``Y`` can be: @@ -73,7 +74,7 @@ An edge relation between two nodes (drivers or machines) ``X`` and ``Y`` can be: - ``X CONTAINS Y``: ``Y`` is part of ``X`` component Execution steps -^^^^^^^^^^^^^^^ +~~~~~~~~~~~~~~~ The basic framework steps are the following: @@ -92,8 +93,64 @@ The basic framework steps are the following: Depending on the QEMU binary used, only some drivers/machines will be available and only test that are reached by them will be executed. +Command line +~~~~~~~~~~~~ + +Command line is built by using node names and optional arguments +passed by the user when building the edges. + +There are three types of command line arguments: + +- ``in node`` : created from the node name. For example, machines will + have ``-M <machine>`` to its command line, while devices + ``-device <device>``. It is automatically done by the framework. +- ``after node`` : added as additional argument to the node name. + This argument is added optionally when creating edges, + by setting the parameter ``after_cmd_line`` and + ``extra_edge_opts`` in ``QOSGraphEdgeOptions``. + The framework automatically adds + a comma before ``extra_edge_opts``, + because it is going to add attributes + after the destination node pointed by + the edge containing these options, and automatically + adds a space before ``after_cmd_line``, because it + adds an additional device, not an attribute. +- ``before node`` : added as additional argument to the node name. + This argument is added optionally when creating edges, + by setting the parameter ``before_cmd_line`` in + ``QOSGraphEdgeOptions``. This attribute + is going to add attributes before the destination node + pointed by the edge containing these options. It is + helpful to commands that are not node-representable, + such as ``-fdsev`` or ``-netdev``. + +While adding command line in edges is always used, not all nodes names are +used in every path walk: this is because the contained or produced ones +are already added by QEMU, so only nodes that "consumes" will be used to +build the command line. Also, nodes that will have ``{ "abstract" : true }`` +as QMP attribute will loose their command line, since they are not proper +devices to be added in QEMU. + +Example:: + + QOSGraphEdgeOptions opts = { + .before_cmd_line = "-drive id=drv0,if=none,file=null-co://," + "file.read-zeroes=on,format=raw", + .after_cmd_line = "-device scsi-hd,bus=vs0.0,drive=drv0", + + opts.extra_device_opts = "id=vs0"; + }; + + qos_node_create_driver("virtio-scsi-device", + virtio_scsi_device_create); + qos_node_consumes("virtio-scsi-device", "virtio-bus", &opts); + +Will produce the following command line: +``-drive id=drv0,if=none,file=null-co://, -device virtio-scsi-device,id=vs0 -device scsi-hd,bus=vs0.0,drive=drv0`` + Troubleshooting unavailable tests -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + If there is no path from an available machine to a test then that test will be unavailable and won't execute. This can happen if a test or driver did not set up its qgraph node correctly. It can also happen if the necessary machine type @@ -151,7 +208,7 @@ Typically this is because the QEMU binary lacks support for the necessary machine type or device. Creating a new driver and its interface -""""""""""""""""""""""""""""""""""""""""" +--------------------------------------- Here we continue the ``sdhci`` use case, with the following scenario: @@ -489,7 +546,7 @@ or inverting the consumes edge in consumed_by:: arm/raspi2b --contains--> generic-sdhci Adding a new test -""""""""""""""""" +----------------- Given the above setup, adding a new test is very simple. ``sdhci-test``, taken from ``tests/qtest/sdhci-test.c``:: @@ -565,62 +622,7 @@ and for the binary ``QTEST_QEMU_BINARY=./qemu-system-arm``: Additional examples are also in ``test-qgraph.c`` -Command line: -"""""""""""""" - -Command line is built by using node names and optional arguments -passed by the user when building the edges. - -There are three types of command line arguments: - -- ``in node`` : created from the node name. For example, machines will - have ``-M <machine>`` to its command line, while devices - ``-device <device>``. It is automatically done by the framework. -- ``after node`` : added as additional argument to the node name. - This argument is added optionally when creating edges, - by setting the parameter ``after_cmd_line`` and - ``extra_edge_opts`` in ``QOSGraphEdgeOptions``. - The framework automatically adds - a comma before ``extra_edge_opts``, - because it is going to add attributes - after the destination node pointed by - the edge containing these options, and automatically - adds a space before ``after_cmd_line``, because it - adds an additional device, not an attribute. -- ``before node`` : added as additional argument to the node name. - This argument is added optionally when creating edges, - by setting the parameter ``before_cmd_line`` in - ``QOSGraphEdgeOptions``. This attribute - is going to add attributes before the destination node - pointed by the edge containing these options. It is - helpful to commands that are not node-representable, - such as ``-fdsev`` or ``-netdev``. - -While adding command line in edges is always used, not all nodes names are -used in every path walk: this is because the contained or produced ones -are already added by QEMU, so only nodes that "consumes" will be used to -build the command line. Also, nodes that will have ``{ "abstract" : true }`` -as QMP attribute will loose their command line, since they are not proper -devices to be added in QEMU. - -Example:: - - QOSGraphEdgeOptions opts = { - .before_cmd_line = "-drive id=drv0,if=none,file=null-co://," - "file.read-zeroes=on,format=raw", - .after_cmd_line = "-device scsi-hd,bus=vs0.0,drive=drv0", - - opts.extra_device_opts = "id=vs0"; - }; - - qos_node_create_driver("virtio-scsi-device", - virtio_scsi_device_create); - qos_node_consumes("virtio-scsi-device", "virtio-bus", &opts); - -Will produce the following command line: -``-drive id=drv0,if=none,file=null-co://, -device virtio-scsi-device,id=vs0 -device scsi-hd,bus=vs0.0,drive=drv0`` - Qgraph API reference -^^^^^^^^^^^^^^^^^^^^ +-------------------- .. kernel-doc:: tests/qtest/libqos/qgraph.h diff --git a/docs/devel/tcg-plugins.rst b/docs/devel/tcg-plugins.rst index dac5101..842ae01 100644 --- a/docs/devel/tcg-plugins.rst +++ b/docs/devel/tcg-plugins.rst @@ -3,7 +3,6 @@ Copyright (c) 2019, Linaro Limited Written by Emilio Cota and Alex Bennée -================ QEMU TCG Plugins ================ @@ -16,8 +15,30 @@ only monitor it passively. However they can do this down to an individual instruction granularity including potentially subscribing to all load and store operations. -API Stability -============= +Usage +----- + +Any QEMU binary with TCG support has plugins enabled by default. +Earlier releases needed to be explicitly enabled with:: + + configure --enable-plugins + +Once built a program can be run with multiple plugins loaded each with +their own arguments:: + + $QEMU $OTHER_QEMU_ARGS \ + -plugin tests/plugin/libhowvec.so,inline=on,count=hint \ + -plugin tests/plugin/libhotblocks.so + +Arguments are plugin specific and can be used to modify their +behaviour. In this case the howvec plugin is being asked to use inline +ops to count and break down the hint instructions by type. + +Writing plugins +--------------- + +API versioning +~~~~~~~~~~~~~~ This is a new feature for QEMU and it does allow people to develop out-of-tree plugins that can be dynamically linked into a running QEMU @@ -25,9 +46,6 @@ process. However the project reserves the right to change or break the API should it need to do so. The best way to avoid this is to submit your plugin upstream so they can be updated if/when the API changes. -API versioning --------------- - All plugins need to declare a symbol which exports the plugin API version they were built against. This can be done simply by:: @@ -43,18 +61,8 @@ current API versions supported by QEMU. The API version will be incremented if new APIs are added. The minimum API version will be incremented if existing APIs are changed or removed. -Exposure of QEMU internals --------------------------- - -The plugin architecture actively avoids leaking implementation details -about how QEMU's translation works to the plugins. While there are -conceptions such as translation time and translation blocks the -details are opaque to plugins. The plugin is able to query select -details of instructions and system configuration only through the -exported *qemu_plugin* functions. - -Query Handle Lifetime ---------------------- +Lifetime of the query handle +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Each callback provides an opaque anonymous information handle which can usually be further queried to find out information about a @@ -63,32 +71,8 @@ valid during the lifetime of the callback so it is important that any information that is needed is extracted during the callback and saved by the plugin. -API -=== - -.. kernel-doc:: include/qemu/qemu-plugin.h - -Usage -===== - -Any QEMU binary with TCG support has plugins enabled by default. -Earlier releases needed to be explicitly enabled with:: - - configure --enable-plugins - -Once built a program can be run with multiple plugins loaded each with -their own arguments:: - - $QEMU $OTHER_QEMU_ARGS \ - -plugin tests/plugin/libhowvec.so,inline=on,count=hint \ - -plugin tests/plugin/libhotblocks.so - -Arguments are plugin specific and can be used to modify their -behaviour. In this case the howvec plugin is being asked to use inline -ops to count and break down the hint instructions by type. - -Plugin Life cycle -================= +Plugin life cycle +~~~~~~~~~~~~~~~~~ First the plugin is loaded and the public qemu_plugin_install function is called. The plugin will then register callbacks for various plugin @@ -111,11 +95,26 @@ callback which can then ensure atomicity itself. Finally when QEMU exits all the registered *atexit* callbacks are invoked. +Exposure of QEMU internals +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The plugin architecture actively avoids leaking implementation details +about how QEMU's translation works to the plugins. While there are +conceptions such as translation time and translation blocks the +details are opaque to plugins. The plugin is able to query select +details of instructions and system configuration only through the +exported *qemu_plugin* functions. + +API +~~~ + +.. kernel-doc:: include/qemu/qemu-plugin.h + Internals -========= +--------- Locking -------- +~~~~~~~ We have to ensure we cannot deadlock, particularly under MTTCG. For this we acquire a lock when called from plugin code. We also keep the @@ -142,7 +141,7 @@ requested. The plugin isn't completely uninstalled until the safe work has executed while all vCPUs are quiescent. Example Plugins -=============== +--------------- There are a number of plugins included with QEMU and you are encouraged to contribute your own plugins plugins upstream. There is a diff --git a/docs/devel/testing.rst b/docs/devel/testing.rst index 64c9744..7500f07 100644 --- a/docs/devel/testing.rst +++ b/docs/devel/testing.rst @@ -1,11 +1,10 @@ -=============== Testing in QEMU =============== This document describes the testing infrastructure in QEMU. Testing with "make check" -========================= +------------------------- The "make check" testing family includes most of the C based tests in QEMU. For a quick help, run ``make check-help`` from the source tree. @@ -24,7 +23,7 @@ expect the executables to exist and will fail with obscure messages if they cannot find them. Unit tests ----------- +~~~~~~~~~~ Unit tests, which can be invoked with ``make check-unit``, are simple C tests that typically link to individual QEMU object files and exercise them by @@ -67,7 +66,7 @@ and copy the actual command line which executes the unit test, then run it from the command line. QTest ------ +~~~~~ QTest is a device emulation testing framework. It can be very useful to test device models; it could also control certain aspects of QEMU (such as virtual @@ -81,7 +80,7 @@ QTest cases can be executed with make check-qtest QAPI schema tests ------------------ +~~~~~~~~~~~~~~~~~ The QAPI schema tests validate the QAPI parser used by QMP, by feeding predefined input to the parser and comparing the result with the reference @@ -108,33 +107,14 @@ parser (either fixing a bug or extending/modifying the syntax). To do this: ``qapi-schema += foo.json`` check-block ------------ +~~~~~~~~~~~ ``make check-block`` runs a subset of the block layer iotests (the tests that are in the "auto" group). See the "QEMU iotests" section below for more information. -GCC gcov support ----------------- - -``gcov`` is a GCC tool to analyze the testing coverage by -instrumenting the tested code. To use it, configure QEMU with -``--enable-gcov`` option and build. Then run ``make check`` as usual. - -If you want to gather coverage information on a single test the ``make -clean-gcda`` target can be used to delete any existing coverage -information before running a single test. - -You can generate a HTML coverage report by executing ``make -coverage-html`` which will create -``meson-logs/coveragereport/index.html``. - -Further analysis can be conducted by running the ``gcov`` command -directly on the various .gcda output files. Please read the ``gcov`` -documentation for more information. - QEMU iotests -============ +------------ QEMU iotests, under the directory ``tests/qemu-iotests``, is the testing framework widely used to test block layer related features. It is higher level @@ -171,7 +151,7 @@ More options are supported by the ``./check`` script, run ``./check -h`` for help. Writing a new test case ------------------------ +~~~~~~~~~~~~~~~~~~~~~~~ Consider writing a tests case when you are making any changes to the block layer. An iotest case is usually the choice for that. There are already many @@ -225,7 +205,8 @@ test failure. If using such devices are explicitly desired, consider adding ``locking=off`` option to disable image locking. Debugging a test case ------------------------ +~~~~~~~~~~~~~~~~~~~~~ + The following options to the ``check`` script can be useful when debugging a failing test: @@ -254,7 +235,7 @@ a failing test: ``$TEST_DIR/qemu-machine-<random_string>``. Test case groups ----------------- +~~~~~~~~~~~~~~~~ "Tests may belong to one or more test groups, which are defined in the form of a comment in the test source file. By convention, test groups are listed @@ -304,10 +285,10 @@ Note that the following group names have a special meaning: .. _container-ref: Container based tests -===================== +--------------------- Introduction ------------- +~~~~~~~~~~~~ The container testing framework in QEMU utilizes public images to build and test QEMU in predefined and widely accessible Linux @@ -322,7 +303,7 @@ The container images are also used to augment the generation of tests for testing TCG. See :ref:`checktcg-ref` for more details. Docker Prerequisites --------------------- +~~~~~~~~~~~~~~~~~~~~ Install "docker" with the system package manager and start the Docker service on your development machine, then make sure you have the privilege to run @@ -353,7 +334,7 @@ exploit the whole host with Docker bind mounting or other privileged operations. So only do it on development machines. Podman Prerequisites --------------------- +~~~~~~~~~~~~~~~~~~~~ Install "podman" with the system package manager. @@ -365,7 +346,7 @@ Install "podman" with the system package manager. The last command should print an empty table, to verify the system is ready. Quickstart ----------- +~~~~~~~~~~ From source tree, type ``make docker-help`` to see the help. Testing can be started without configuring or building QEMU (``configure`` and @@ -381,7 +362,7 @@ is downloaded and initialized automatically), in which the ``test-build`` job is executed. Registry --------- +~~~~~~~~ The QEMU project has a container registry hosted by GitLab at ``registry.gitlab.com/qemu-project/qemu`` which will automatically be @@ -395,7 +376,7 @@ locally by using the ``NOCACHE`` build option: make docker-image-debian10 NOCACHE=1 Images ------- +~~~~~~ Along with many other images, the ``centos8`` image is defined in a Dockerfile in ``tests/docker/dockerfiles/``, called ``centos8.docker``. ``make docker-help`` @@ -410,7 +391,7 @@ mainly used to do necessary host side setup. One such setup is ``binfmt_misc``, for example, to make qemu-user powered cross build containers work. Tests ------ +~~~~~ Different tests are added to cover various configurations to build and test QEMU. Docker tests are the executables under ``tests/docker`` named @@ -421,7 +402,7 @@ source and build it. The full list of tests is printed in the ``make docker-help`` help. Debugging a Docker test failure -------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ When CI tasks, maintainers or yourself report a Docker test failure, follow the below steps to debug it: @@ -438,7 +419,7 @@ below steps to debug it: the prompt for debug. Options -------- +~~~~~~~ Various options can be used to affect how Docker tests are done. The full list is in the ``make docker`` help text. The frequently used ones are: @@ -452,7 +433,7 @@ list is in the ``make docker`` help text. The frequently used ones are: failure" section. Thread Sanitizer -================ +---------------- Thread Sanitizer (TSan) is a tool which can detect data races. QEMU supports building and testing with this tool. @@ -462,7 +443,7 @@ For more information on TSan: https://github.com/google/sanitizers/wiki/ThreadSanitizerCppManual Thread Sanitizer in Docker ---------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~ TSan is currently supported in the ubuntu2004 docker. The test-tsan test will build using TSan and then run make check. @@ -477,7 +458,7 @@ We recommend using DEBUG=1 to allow launching the test from inside the docker, and to allow review of the warnings generated by TSan. Building and Testing with TSan ------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ It is possible to build and test with TSan, with a few additional steps. These steps are normally done automatically in the docker. @@ -516,7 +497,7 @@ This allows for running the test and then checking the warnings afterwards. If you want TSan to stop and exit with error on warnings, use exitcode=66. TSan Suppressions ------------------ +~~~~~~~~~~~~~~~~~ Keep in mind that for any data race warning, although there might be a data race detected by TSan, there might be no actual bug here. TSan provides several different mechanisms for suppressing warnings. In general it is recommended @@ -542,7 +523,7 @@ More information on the file format can be found here under "Blacklist Format": https://github.com/google/sanitizers/wiki/ThreadSanitizerFlags TSan Annotations ----------------- +~~~~~~~~~~~~~~~~ include/qemu/tsan.h defines annotations. See this file for more descriptions of the annotations themselves. Annotations can be used to suppress TSan warnings or give TSan more information so that it can detect proper @@ -559,14 +540,14 @@ The full set of annotations can be found here: https://github.com/llvm/llvm-project/blob/master/compiler-rt/lib/tsan/rtl/tsan_interface_ann.cpp VM testing -========== +---------- This test suite contains scripts that bootstrap various guest images that have necessary packages to build QEMU. The basic usage is documented in ``Makefile`` help which is displayed with ``make vm-help``. Quickstart ----------- +~~~~~~~~~~ Run ``make vm-help`` to list available make targets. Invoke a specific make command to run build test in an image. For example, ``make vm-build-freebsd`` @@ -581,7 +562,7 @@ concerned about attackers taking control of the guest and potentially exploiting a QEMU security bug to compromise the host. QEMU binaries -------------- +~~~~~~~~~~~~~ By default, qemu-system-x86_64 is searched in $PATH to run the guest. If there isn't one, or if it is older than 2.10, the test won't work. In this case, @@ -590,20 +571,20 @@ provide the QEMU binary in env var: ``QEMU=/path/to/qemu-2.10+``. Likewise the path to qemu-img can be set in QEMU_IMG environment variable. Make jobs ---------- +~~~~~~~~~ The ``-j$X`` option in the make command line is not propagated into the VM, specify ``J=$X`` to control the make jobs in the guest. Debugging ---------- +~~~~~~~~~ Add ``DEBUG=1`` and/or ``V=1`` to the make command to allow interactive debugging and verbose output. If this is not enough, see the next section. ``V=1`` will be propagated down into the make jobs in the guest. Manual invocation ------------------ +~~~~~~~~~~~~~~~~~ Each guest script is an executable script with the same command line options. For example to work with the netbsd guest, use ``$QEMU_SRC/tests/vm/netbsd``: @@ -627,7 +608,7 @@ For example to work with the netbsd guest, use ``$QEMU_SRC/tests/vm/netbsd``: $ ./netbsd --interactive --image /var/tmp/netbsd.img sh Adding new guests ------------------ +~~~~~~~~~~~~~~~~~ Please look at existing guest scripts for how to add new guests. @@ -660,7 +641,7 @@ the script's ``main()``. recommended. Image fuzzer testing -==================== +-------------------- An image fuzzer was added to exercise format drivers. Currently only qcow2 is supported. To start the fuzzer, run @@ -673,7 +654,7 @@ Alternatively, some command different from "qemu-img info" can be tested, by changing the ``-c`` option. Acceptance tests using the Avocado Framework -============================================ +-------------------------------------------- The ``tests/acceptance`` directory hosts functional tests, also known as acceptance level tests. They're usually higher level tests, and @@ -712,7 +693,7 @@ Tests based on ``avocado_qemu.Test`` can easily: - http://avocado-framework.readthedocs.io/en/latest/api/utils/avocado.utils.html Running tests -------------- +~~~~~~~~~~~~~ You can run the acceptance tests simply by executing: @@ -810,7 +791,7 @@ of Avocado or ``make check-acceptance``, and can also be queried using: tests/venv/bin/avocado list tests/acceptance Manual Installation -------------------- +~~~~~~~~~~~~~~~~~~~ To manually install Avocado and its dependencies, run: @@ -823,7 +804,7 @@ Alternatively, follow the instructions on this link: https://avocado-framework.readthedocs.io/en/latest/guides/user/chapters/installing.html Overview --------- +~~~~~~~~ The ``tests/acceptance/avocado_qemu`` directory provides the ``avocado_qemu`` Python module, containing the ``avocado_qemu.Test`` @@ -859,7 +840,7 @@ in the current directory, tagged as "quick", run: avocado run -t quick . The ``avocado_qemu.Test`` base test class ------------------------------------------ +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The ``avocado_qemu.Test`` class has a number of characteristics that are worth being mentioned right away. @@ -909,7 +890,7 @@ At test "tear down", ``avocado_qemu.Test`` handles all the QEMUMachines shutdown. The ``avocado_qemu.LinuxTest`` base test class -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The ``avocado_qemu.LinuxTest`` is further specialization of the ``avocado_qemu.Test`` class, so it contains all the characteristics of @@ -952,7 +933,7 @@ execution of a QEMU binary, giving its users: a more succinct and intuitive way QEMU binary selection -~~~~~~~~~~~~~~~~~~~~~ +^^^^^^^^^^^^^^^^^^^^^ The QEMU binary used for the ``self.vm`` QEMUMachine instance will primarily depend on the value of the ``qemu_bin`` parameter. If it's @@ -973,20 +954,23 @@ The resulting ``qemu_bin`` value will be preserved in the ``avocado_qemu.Test`` as an attribute with the same name. Attribute reference -------------------- +~~~~~~~~~~~~~~~~~~~ + +Test +^^^^ Besides the attributes and methods that are part of the base ``avocado.Test`` class, the following attributes are available on any ``avocado_qemu.Test`` instance. vm -~~ +'' A QEMUMachine instance, initially configured according to the given ``qemu_bin`` parameter. arch -~~~~ +'''' The architecture can be used on different levels of the stack, e.g. by the framework or by the test itself. At the framework level, it will @@ -1003,7 +987,7 @@ name. If one is not given explicitly, it will either be set to ``:avocado: tags=arch:VALUE`` tag, it will be set to ``VALUE``. cpu -~~~ +''' The cpu model that will be set to all QEMUMachine instances created by the test. @@ -1014,7 +998,7 @@ name. If one is not given explicitly, it will either be set to ``:avocado: tags=cpu:VALUE`` tag, it will be set to ``VALUE``. machine -~~~~~~~ +''''''' The machine type that will be set to all QEMUMachine instances created by the test. @@ -1025,20 +1009,20 @@ name. If one is not given explicitly, it will either be set to ``:avocado: tags=machine:VALUE`` tag, it will be set to ``VALUE``. qemu_bin -~~~~~~~~ +'''''''' The preserved value of the ``qemu_bin`` parameter or the result of the dynamic probe for a QEMU binary in the current working directory or source tree. LinuxTest -~~~~~~~~~ +^^^^^^^^^ Besides the attributes present on the ``avocado_qemu.Test`` base class, the ``avocado_qemu.LinuxTest`` adds the following attributes: distro -...... +'''''' The name of the Linux distribution used as the guest image for the test. The name should match the **Provider** column on the list @@ -1047,7 +1031,7 @@ of images supported by the avocado.utils.vmimage library: https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images distro_version -.............. +'''''''''''''' The version of the Linux distribution as the guest image for the test. The name should match the **Version** column on the list @@ -1056,7 +1040,7 @@ of images supported by the avocado.utils.vmimage library: https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images distro_checksum -............... +''''''''''''''' The sha256 hash of the guest image file used for the test. @@ -1065,7 +1049,7 @@ same name), no validation on the integrity of the image will be performed. Parameter reference -------------------- +~~~~~~~~~~~~~~~~~~~ To understand how Avocado parameters are accessed by tests, and how they can be passed to tests, please refer to:: @@ -1079,8 +1063,11 @@ like the following: PARAMS (key=qemu_bin, path=*, default=./qemu-system-x86_64) => './qemu-system-x86_64 +Test +^^^^ + arch -~~~~ +'''' The architecture that will influence the selection of a QEMU binary (when one is not explicitly given). @@ -1093,31 +1080,30 @@ This parameter has a direct relation with the ``arch`` attribute. If not given, it will default to None. cpu -~~~ +''' The cpu model that will be set to all QEMUMachine instances created by the test. machine -~~~~~~~ +''''''' The machine type that will be set to all QEMUMachine instances created by the test. - qemu_bin -~~~~~~~~ +'''''''' The exact QEMU binary to be used on QEMUMachine. LinuxTest -~~~~~~~~~ +^^^^^^^^^ Besides the parameters present on the ``avocado_qemu.Test`` base class, the ``avocado_qemu.LinuxTest`` adds the following parameters: distro -...... +'''''' The name of the Linux distribution used as the guest image for the test. The name should match the **Provider** column on the list @@ -1126,7 +1112,7 @@ of images supported by the avocado.utils.vmimage library: https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images distro_version -.............. +'''''''''''''' The version of the Linux distribution as the guest image for the test. The name should match the **Version** column on the list @@ -1135,7 +1121,7 @@ of images supported by the avocado.utils.vmimage library: https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images distro_checksum -............... +''''''''''''''' The sha256 hash of the guest image file used for the test. @@ -1143,7 +1129,8 @@ If this value is not set in the code or by this parameter no validation on the integrity of the image will be performed. Skipping tests --------------- +~~~~~~~~~~~~~~ + The Avocado framework provides Python decorators which allow for easily skip tests running under certain conditions. For example, on the lack of a binary on the test system or when the running environment is a CI system. For further @@ -1158,7 +1145,7 @@ environment variables became a kind of standard way to enable/disable tests. Here is a list of the most used variables: AVOCADO_ALLOW_LARGE_STORAGE -~~~~~~~~~~~~~~~~~~~~~~~~~~~ +^^^^^^^^^^^^^^^^^^^^^^^^^^^ Tests which are going to fetch or produce assets considered *large* are not going to run unless that ``AVOCADO_ALLOW_LARGE_STORAGE=1`` is exported on the environment. @@ -1167,7 +1154,7 @@ The definition of *large* is a bit arbitrary here, but it usually means an asset which occupies at least 1GB of size on disk when uncompressed. AVOCADO_ALLOW_UNTRUSTED_CODE -~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ There are tests which will boot a kernel image or firmware that can be considered not safe to run on the developer's workstation, thus they are skipped by default. The definition of *not safe* is also arbitrary but @@ -1178,7 +1165,7 @@ You should export ``AVOCADO_ALLOW_UNTRUSTED_CODE=1`` on the environment in order to allow tests which make use of those kind of assets. AVOCADO_TIMEOUT_EXPECTED -~~~~~~~~~~~~~~~~~~~~~~~~ +^^^^^^^^^^^^^^^^^^^^^^^^ The Avocado framework has a timeout mechanism which interrupts tests to avoid the test suite of getting stuck. The timeout value can be set via test parameter or property defined in the test class, for further details:: @@ -1192,7 +1179,7 @@ compiled with debug flags. Therefore, the ``AVOCADO_TIMEOUT_EXPECTED`` variable has been used to determine whether those tests should run or not. GITLAB_CI -~~~~~~~~~ +^^^^^^^^^ A number of tests are flagged to not run on the GitLab CI. Usually because they proved to the flaky or there are constraints on the CI environment which would make them fail. If you encounter a similar situation then use that @@ -1205,7 +1192,7 @@ variable as shown on the code snippet below to skip the test: do_something() Uninstalling Avocado --------------------- +~~~~~~~~~~~~~~~~~~~~ If you've followed the manual installation instructions above, you can easily uninstall Avocado. Start by listing the packages you have @@ -1223,7 +1210,7 @@ Avocado is installed will be cleaned up as part of ``make check-clean``. .. _checktcg-ref: Testing with "make check-tcg" -============================= +----------------------------- The check-tcg tests are intended for simple smoke tests of both linux-user and softmmu TCG functionality. However to build test @@ -1256,7 +1243,7 @@ itself. See :ref:`container-ref` for more details. Running subset of tests ------------------------ +~~~~~~~~~~~~~~~~~~~~~~~ You can build the tests for one architecture:: @@ -1270,7 +1257,7 @@ Adding ``V=1`` to the invocation will show the details of how to invoke QEMU for the test which is useful for debugging tests. TCG test dependencies ---------------------- +~~~~~~~~~~~~~~~~~~~~~ The TCG tests are deliberately very light on dependencies and are either totally bare with minimal gcc lib support (for softmmu tests) @@ -1302,3 +1289,22 @@ exercise as many corner cases as possible. It is a useful test suite to run to exercise QEMU's linux-user code:: https://linux-test-project.github.io/ + +GCC gcov support +---------------- + +``gcov`` is a GCC tool to analyze the testing coverage by +instrumenting the tested code. To use it, configure QEMU with +``--enable-gcov`` option and build. Then run the tests as usual. + +If you want to gather coverage information on a single test the ``make +clean-gcda`` target can be used to delete any existing coverage +information before running a single test. + +You can generate a HTML coverage report by executing ``make +coverage-html`` which will create +``meson-logs/coveragereport/index.html``. + +Further analysis can be conducted by running the ``gcov`` command +directly on the various .gcda output files. Please read the ``gcov`` +documentation for more information. diff --git a/docs/hyperv.txt b/docs/hyperv.txt index 000638a..5d99fd9 100644 --- a/docs/hyperv.txt +++ b/docs/hyperv.txt @@ -189,7 +189,15 @@ enabled. Requires: hv-vpindex, hv-synic, hv-time, hv-stimer -3.17. hv-no-nonarch-coresharing=on/off/auto +3.18. hv-avic (hv-apicv) +======================= +The enlightenment allows to use Hyper-V SynIC with hardware APICv/AVIC enabled. +Normally, Hyper-V SynIC disables these hardware feature and suggests the guest +to use paravirtualized AutoEOI feature. +Note: enabling this feature on old hardware (without APICv/AVIC support) may +have negative effect on guest's performace. + +3.19. hv-no-nonarch-coresharing=on/off/auto =========================================== This enlightenment tells guest OS that virtual processors will never share a physical core unless they are reported as sibling SMT threads. This information @@ -203,8 +211,25 @@ When the option is set to 'on' QEMU will always enable the feature, regardless of host setup. To keep guests secure, this can only be used in conjunction with exposing correct vCPU topology and vCPU pinning. -4. Development features -======================== +3.20. hv-version-id-{build,major,minor,spack,sbranch,snumber} +============================================================= +This changes Hyper-V version identification in CPUID 0x40000002.EAX-EDX from the +default (WS2016). +- hv-version-id-build sets 'Build Number' (32 bits) +- hv-version-id-major sets 'Major Version' (16 bits) +- hv-version-id-minor sets 'Minor Version' (16 bits) +- hv-version-id-spack sets 'Service Pack' (32 bits) +- hv-version-id-sbranch sets 'Service Branch' (8 bits) +- hv-version-id-snumber sets 'Service Number' (24 bits) + +Note: hv-version-id-* are not enlightenments and thus don't enable Hyper-V +identification when specified without any other enlightenments. + +4. Supplementary features +========================= + +4.1. hv-passthrough +=================== In some cases (e.g. during development) it may make sense to use QEMU in 'pass-through' mode and give Windows guests all enlightenments currently supported by KVM. This pass-through mode is enabled by "hv-passthrough" CPU @@ -215,8 +240,16 @@ values from KVM to QEMU. "hv-passthrough" overrides all other "hv-*" settings on the command line. Also, enabling this flag effectively prevents migration as the list of enabled enlightenments may differ between target and destination hosts. +4.2. hv-enforce-cpuid +===================== +By default, KVM allows the guest to use all currently supported Hyper-V +enlightenments when Hyper-V CPUID interface was exposed, regardless of if +some features were not announced in guest visible CPUIDs. 'hv-enforce-cpuid' +feature alters this behavior and only allows the guest to use exposed Hyper-V +enlightenments. + -4. Useful links +5. Useful links ================ Hyper-V Top Level Functional specification and other information: https://github.com/MicrosoftDocs/Virtualization-Documentation diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 1d59f0e..7170aaa 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -2815,6 +2815,7 @@ static void virt_machine_6_1_options(MachineClass *mc) virt_machine_6_2_options(mc); compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); + mc->smp_props.prefer_sockets = true; /* qemu ITS was introduced with 6.2 */ vmc->no_tcg_its = true; diff --git a/hw/core/machine.c b/hw/core/machine.c index 067f42b..3920a2f 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -746,64 +746,163 @@ void machine_set_cpu_numa_node(MachineState *machine, } } +/* + * Report information of a machine's supported CPU topology hierarchy. + * Topology members will be ordered from the largest to the smallest + * in the string. + */ +static char *cpu_hierarchy_to_string(MachineState *ms) +{ + MachineClass *mc = MACHINE_GET_CLASS(ms); + GString *s = g_string_new(NULL); + + g_string_append_printf(s, "sockets (%u)", ms->smp.sockets); + + if (mc->smp_props.dies_supported) { + g_string_append_printf(s, " * dies (%u)", ms->smp.dies); + } + + g_string_append_printf(s, " * cores (%u)", ms->smp.cores); + g_string_append_printf(s, " * threads (%u)", ms->smp.threads); + + return g_string_free(s, false); +} + +/* + * smp_parse - Generic function used to parse the given SMP configuration + * + * Any missing parameter in "cpus/maxcpus/sockets/cores/threads" will be + * automatically computed based on the provided ones. + * + * In the calculation of omitted sockets/cores/threads: we prefer sockets + * over cores over threads before 6.2, while preferring cores over sockets + * over threads since 6.2. + * + * In the calculation of cpus/maxcpus: When both maxcpus and cpus are omitted, + * maxcpus will be computed from the given parameters and cpus will be set + * equal to maxcpus. When only one of maxcpus and cpus is given then the + * omitted one will be set to its given counterpart's value. Both maxcpus and + * cpus may be specified, but maxcpus must be equal to or greater than cpus. + * + * For compatibility, apart from the parameters that will be computed, newly + * introduced topology members which are likely to be target specific should + * be directly set as 1 if they are omitted (e.g. dies for PC since 4.1). + */ static void smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp) { + MachineClass *mc = MACHINE_GET_CLASS(ms); unsigned cpus = config->has_cpus ? config->cpus : 0; unsigned sockets = config->has_sockets ? config->sockets : 0; + unsigned dies = config->has_dies ? config->dies : 0; unsigned cores = config->has_cores ? config->cores : 0; unsigned threads = config->has_threads ? config->threads : 0; + unsigned maxcpus = config->has_maxcpus ? config->maxcpus : 0; - if (config->has_dies && config->dies != 0 && config->dies != 1) { + /* + * Specified CPU topology parameters must be greater than zero, + * explicit configuration like "cpus=0" is not allowed. + */ + if ((config->has_cpus && config->cpus == 0) || + (config->has_sockets && config->sockets == 0) || + (config->has_dies && config->dies == 0) || + (config->has_cores && config->cores == 0) || + (config->has_threads && config->threads == 0) || + (config->has_maxcpus && config->maxcpus == 0)) { + warn_report("Deprecated CPU topology (considered invalid): " + "CPU topology parameters must be greater than zero"); + } + + /* + * If not supported by the machine, a topology parameter must be + * omitted or specified equal to 1. + */ + if (!mc->smp_props.dies_supported && dies > 1) { error_setg(errp, "dies not supported by this machine's CPU topology"); return; } - /* compute missing values, prefer sockets over cores over threads */ - if (cpus == 0 || sockets == 0) { + dies = dies > 0 ? dies : 1; + + /* compute missing values based on the provided ones */ + if (cpus == 0 && maxcpus == 0) { + sockets = sockets > 0 ? sockets : 1; cores = cores > 0 ? cores : 1; threads = threads > 0 ? threads : 1; - if (cpus == 0) { - sockets = sockets > 0 ? sockets : 1; - cpus = cores * threads * sockets; + } else { + maxcpus = maxcpus > 0 ? maxcpus : cpus; + + if (mc->smp_props.prefer_sockets) { + /* prefer sockets over cores before 6.2 */ + if (sockets == 0) { + cores = cores > 0 ? cores : 1; + threads = threads > 0 ? threads : 1; + sockets = maxcpus / (dies * cores * threads); + } else if (cores == 0) { + threads = threads > 0 ? threads : 1; + cores = maxcpus / (sockets * dies * threads); + } } else { - ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; - sockets = ms->smp.max_cpus / (cores * threads); + /* prefer cores over sockets since 6.2 */ + if (cores == 0) { + sockets = sockets > 0 ? sockets : 1; + threads = threads > 0 ? threads : 1; + cores = maxcpus / (sockets * dies * threads); + } else if (sockets == 0) { + threads = threads > 0 ? threads : 1; + sockets = maxcpus / (dies * cores * threads); + } + } + + /* try to calculate omitted threads at last */ + if (threads == 0) { + threads = maxcpus / (sockets * dies * cores); } - } else if (cores == 0) { - threads = threads > 0 ? threads : 1; - cores = cpus / (sockets * threads); - cores = cores > 0 ? cores : 1; - } else if (threads == 0) { - threads = cpus / (cores * sockets); - threads = threads > 0 ? threads : 1; - } else if (sockets * cores * threads < cpus) { - error_setg(errp, "cpu topology: " - "sockets (%u) * cores (%u) * threads (%u) < " - "smp_cpus (%u)", - sockets, cores, threads, cpus); - return; } - ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; + maxcpus = maxcpus > 0 ? maxcpus : sockets * dies * cores * threads; + cpus = cpus > 0 ? cpus : maxcpus; + + ms->smp.cpus = cpus; + ms->smp.sockets = sockets; + ms->smp.dies = dies; + ms->smp.cores = cores; + ms->smp.threads = threads; + ms->smp.max_cpus = maxcpus; - if (ms->smp.max_cpus < cpus) { - error_setg(errp, "maxcpus must be equal to or greater than smp"); + /* sanity-check of the computed topology */ + if (sockets * dies * cores * threads != maxcpus) { + g_autofree char *topo_msg = cpu_hierarchy_to_string(ms); + error_setg(errp, "Invalid CPU topology: " + "product of the hierarchy must match maxcpus: " + "%s != maxcpus (%u)", + topo_msg, maxcpus); return; } - if (sockets * cores * threads != ms->smp.max_cpus) { + if (maxcpus < cpus) { + g_autofree char *topo_msg = cpu_hierarchy_to_string(ms); error_setg(errp, "Invalid CPU topology: " - "sockets (%u) * cores (%u) * threads (%u) " - "!= maxcpus (%u)", - sockets, cores, threads, - ms->smp.max_cpus); + "maxcpus must be equal to or greater than smp: " + "%s == maxcpus (%u) < smp_cpus (%u)", + topo_msg, maxcpus, cpus); return; } - ms->smp.cpus = cpus; - ms->smp.cores = cores; - ms->smp.threads = threads; - ms->smp.sockets = sockets; + if (ms->smp.cpus < mc->min_cpus) { + error_setg(errp, "Invalid SMP CPUs %d. The min CPUs " + "supported by machine '%s' is %d", + ms->smp.cpus, + mc->name, mc->min_cpus); + return; + } + + if (ms->smp.max_cpus > mc->max_cpus) { + error_setg(errp, "Invalid SMP CPUs %d. The max CPUs " + "supported by machine '%s' is %d", + ms->smp.max_cpus, + mc->name, mc->max_cpus); + return; + } } static void machine_get_smp(Object *obj, Visitor *v, const char *name, @@ -811,11 +910,11 @@ static void machine_get_smp(Object *obj, Visitor *v, const char *name, { MachineState *ms = MACHINE(obj); SMPConfiguration *config = &(SMPConfiguration){ - .has_cores = true, .cores = ms->smp.cores, + .has_cpus = true, .cpus = ms->smp.cpus, .has_sockets = true, .sockets = ms->smp.sockets, .has_dies = true, .dies = ms->smp.dies, + .has_cores = true, .cores = ms->smp.cores, .has_threads = true, .threads = ms->smp.threads, - .has_cpus = true, .cpus = ms->smp.cpus, .has_maxcpus = true, .maxcpus = ms->smp.max_cpus, }; if (!visit_type_SMPConfiguration(v, name, &config, &error_abort)) { @@ -826,35 +925,14 @@ static void machine_get_smp(Object *obj, Visitor *v, const char *name, static void machine_set_smp(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { - MachineClass *mc = MACHINE_GET_CLASS(obj); MachineState *ms = MACHINE(obj); - SMPConfiguration *config; - ERRP_GUARD(); + g_autoptr(SMPConfiguration) config = NULL; if (!visit_type_SMPConfiguration(v, name, &config, errp)) { return; } - mc->smp_parse(ms, config, errp); - if (*errp) { - goto out_free; - } - - /* sanity-check smp_cpus and max_cpus against mc */ - if (ms->smp.cpus < mc->min_cpus) { - error_setg(errp, "Invalid SMP CPUs %d. The min CPUs " - "supported by machine '%s' is %d", - ms->smp.cpus, - mc->name, mc->min_cpus); - } else if (ms->smp.max_cpus > mc->max_cpus) { - error_setg(errp, "Invalid SMP CPUs %d. The max CPUs " - "supported by machine '%s' is %d", - current_machine->smp.max_cpus, - mc->name, mc->max_cpus); - } - -out_free: - qapi_free_SMPConfiguration(config); + smp_parse(ms, config, errp); } static void machine_class_init(ObjectClass *oc, void *data) @@ -864,7 +942,6 @@ static void machine_class_init(ObjectClass *oc, void *data) /* Default 128 MB as guest ram size */ mc->default_ram_size = 128 * MiB; mc->rom_file_has_mr = true; - mc->smp_parse = smp_parse; /* numa node memory size aligned on 8MB by default. * On Linux, each node's border has to be 8MB aligned @@ -1028,10 +1105,10 @@ static void machine_initfn(Object *obj) /* default to mc->default_cpus */ ms->smp.cpus = mc->default_cpus; ms->smp.max_cpus = mc->default_cpus; - ms->smp.cores = 1; + ms->smp.sockets = 1; ms->smp.dies = 1; + ms->smp.cores = 1; ms->smp.threads = 1; - ms->smp.sockets = 1; } static void machine_finalize(Object *obj) diff --git a/hw/i386/pc.c b/hw/i386/pc.c index df457ec..86223ac 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -93,7 +93,11 @@ #include "trace.h" #include CONFIG_DEVICES -GlobalProperty pc_compat_6_1[] = {}; +GlobalProperty pc_compat_6_1[] = { + { TYPE_X86_CPU, "hv-version-id-build", "0x1bbc" }, + { TYPE_X86_CPU, "hv-version-id-major", "0x0006" }, + { TYPE_X86_CPU, "hv-version-id-minor", "0x0001" }, +}; const size_t pc_compat_6_1_len = G_N_ELEMENTS(pc_compat_6_1); GlobalProperty pc_compat_6_0[] = { @@ -710,67 +714,6 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level) } } -/* - * This function is very similar to smp_parse() - * in hw/core/machine.c but includes CPU die support. - */ -static void pc_smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp) -{ - unsigned cpus = config->has_cpus ? config->cpus : 0; - unsigned sockets = config->has_sockets ? config->sockets : 0; - unsigned dies = config->has_dies ? config->dies : 1; - unsigned cores = config->has_cores ? config->cores : 0; - unsigned threads = config->has_threads ? config->threads : 0; - - /* compute missing values, prefer sockets over cores over threads */ - if (cpus == 0 || sockets == 0) { - cores = cores > 0 ? cores : 1; - threads = threads > 0 ? threads : 1; - if (cpus == 0) { - sockets = sockets > 0 ? sockets : 1; - cpus = cores * threads * dies * sockets; - } else { - ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; - sockets = ms->smp.max_cpus / (cores * threads * dies); - } - } else if (cores == 0) { - threads = threads > 0 ? threads : 1; - cores = cpus / (sockets * dies * threads); - cores = cores > 0 ? cores : 1; - } else if (threads == 0) { - threads = cpus / (cores * dies * sockets); - threads = threads > 0 ? threads : 1; - } else if (sockets * dies * cores * threads < cpus) { - error_setg(errp, "cpu topology: " - "sockets (%u) * dies (%u) * cores (%u) * threads (%u) < " - "smp_cpus (%u)", - sockets, dies, cores, threads, cpus); - return; - } - - ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; - - if (ms->smp.max_cpus < cpus) { - error_setg(errp, "maxcpus must be equal to or greater than smp"); - return; - } - - if (sockets * dies * cores * threads != ms->smp.max_cpus) { - error_setg(errp, "Invalid CPU topology deprecated: " - "sockets (%u) * dies (%u) * cores (%u) * threads (%u) " - "!= maxcpus (%u)", - sockets, dies, cores, threads, - ms->smp.max_cpus); - return; - } - - ms->smp.cpus = cpus; - ms->smp.cores = cores; - ms->smp.threads = threads; - ms->smp.sockets = sockets; - ms->smp.dies = dies; -} - static void pc_machine_done(Notifier *notifier, void *data) { @@ -1734,7 +1677,6 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) mc->auto_enable_numa_with_memdev = true; mc->has_hotpluggable_cpus = true; mc->default_boot_order = "cad"; - mc->smp_parse = pc_smp_parse; mc->block_default_type = IF_IDE; mc->max_cpus = 255; mc->reset = pc_machine_reset; @@ -1745,6 +1687,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) hc->unplug = pc_machine_device_unplug_cb; mc->default_cpu_type = TARGET_DEFAULT_CPU_TYPE; mc->nvdimm_supported = true; + mc->smp_props.dies_supported = true; mc->default_ram_id = "pc.ram"; object_class_property_add(oc, PC_MACHINE_MAX_RAM_BELOW_4G, "size", diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 6cc834a..6ad0d76 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -432,6 +432,7 @@ static void pc_i440fx_6_1_machine_options(MachineClass *m) m->is_default = false; compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len); compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len); + m->smp_props.prefer_sockets = true; } DEFINE_I440FX_MACHINE(v6_1, "pc-i440fx-6.1", NULL, diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 5481d5c..fcc6e4e 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -372,6 +372,7 @@ static void pc_q35_6_1_machine_options(MachineClass *m) m->alias = NULL; compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len); compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len); + m->smp_props.prefer_sockets = true; } DEFINE_Q35_MACHINE(v6_1, "pc-q35-6.1", NULL, diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index b7bee5f..163c903 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -4685,6 +4685,7 @@ static void spapr_machine_6_1_class_options(MachineClass *mc) spapr_machine_6_2_class_options(mc); compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); smc->pre_6_2_numa_affinity = true; + mc->smp_props.prefer_sockets = true; } DEFINE_SPAPR_MACHINE(6_1, "6.1", false); diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 61aeccb..653587e 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -814,6 +814,7 @@ static void ccw_machine_6_1_class_options(MachineClass *mc) { ccw_machine_6_2_class_options(mc); compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); + mc->smp_props.prefer_sockets = true; } DEFINE_CCW_MACHINE(6_1, "6.1", false); diff --git a/include/hw/boards.h b/include/hw/boards.h index 463a551..5adbcbb 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -109,6 +109,16 @@ typedef struct { } CPUArchIdList; /** + * SMPCompatProps: + * @prefer_sockets - whether sockets are preferred over cores in smp parsing + * @dies_supported - whether dies are supported by the machine + */ +typedef struct { + bool prefer_sockets; + bool dies_supported; +} SMPCompatProps; + +/** * MachineClass: * @deprecation_reason: If set, the machine is marked as deprecated. The * string should provide some clear information about what to use instead. @@ -169,10 +179,6 @@ typedef struct { * kvm-type may be NULL if it is not needed. * @numa_mem_supported: * true if '--numa node.mem' option is supported and false otherwise - * @smp_parse: - * The function pointer to hook different machine specific functions for - * parsing "smp-opts" from QemuOpts to MachineState::CpuTopology and more - * machine specific topology fields, such as smp_dies for PCMachine. * @hotplug_allowed: * If the hook is provided, then it'll be called for each device * hotplug to check whether the device hotplug is allowed. Return @@ -209,7 +215,6 @@ struct MachineClass { void (*reset)(MachineState *state); void (*wakeup)(MachineState *state); int (*kvm_type)(MachineState *machine, const char *arg); - void (*smp_parse)(MachineState *ms, SMPConfiguration *config, Error **errp); BlockInterfaceType block_default_type; int units_per_default_bus; @@ -247,6 +252,7 @@ struct MachineClass { bool nvdimm_supported; bool numa_mem_supported; bool auto_enable_numa; + SMPCompatProps smp_props; const char *default_ram_id; HotplugHandler *(*get_hotplug_handler)(MachineState *machine, @@ -274,17 +280,18 @@ typedef struct DeviceMemoryState { /** * CpuTopology: * @cpus: the number of present logical processors on the machine - * @cores: the number of cores in one package - * @threads: the number of threads in one core * @sockets: the number of sockets on the machine + * @dies: the number of dies in one socket + * @cores: the number of cores in one die + * @threads: the number of threads in one core * @max_cpus: the maximum number of logical processors on the machine */ typedef struct CpuTopology { unsigned int cpus; + unsigned int sockets; unsigned int dies; unsigned int cores; unsigned int threads; - unsigned int sockets; unsigned int max_cpus; } CpuTopology; diff --git a/qapi/machine.json b/qapi/machine.json index f1c4983..0e91a57 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -1393,7 +1393,7 @@ # # @dies: number of dies per socket in the CPU topology # -# @cores: number of cores per thread in the CPU topology +# @cores: number of cores per die in the CPU topology # # @threads: number of threads per core in the CPU topology # diff --git a/qemu-options.hx b/qemu-options.hx index ceca528..8ef1781 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -220,9 +220,14 @@ SRST Simulate a SMP system with '\ ``n``\ ' CPUs initially present on the machine type board. On boards supporting CPU hotplug, the optional '\ ``maxcpus``\ ' parameter can be set to enable further CPUs to be - added at runtime. If omitted the maximum number of CPUs will be - set to match the initial CPU count. Both parameters are subject to - an upper limit that is determined by the specific machine type chosen. + added at runtime. When both parameters are omitted, the maximum number + of CPUs will be calculated from the provided topology members and the + initial CPU count will match the maximum number. When only one of them + is given then the omitted one will be set to its counterpart's value. + Both parameters may be specified, but the maximum number of CPUs must + be equal to or greater than the initial CPU count. Both parameters are + subject to an upper limit that is determined by the specific machine + type chosen. To control reporting of CPU topology information, the number of sockets, dies per socket, cores per die, and threads per core can be specified. @@ -233,11 +238,14 @@ SRST of computing the CPU maximum count. Either the initial CPU count, or at least one of the topology parameters - must be specified. Values for any omitted parameters will be computed - from those which are given. Historically preference was given to the - coarsest topology parameters when computing missing values (ie sockets - preferred over cores, which were preferred over threads), however, this - behaviour is considered liable to change. + must be specified. The specified parameters must be greater than zero, + explicit configuration like "cpus=0" is not allowed. Values for any + omitted parameters will be computed from those which are given. + Historically preference was given to the coarsest topology parameters + when computing missing values (ie sockets preferred over cores, which + were preferred over threads), however, this behaviour is considered + liable to change. Prior to 6.2 the preference was sockets over cores + over threads. Since 6.2 the preference is cores over sockets over threads. ERST DEF("numa", HAS_ARG, QEMU_OPTION_numa, diff --git a/target/i386/cpu.c b/target/i386/cpu.c index cacec60..a7b1b6a 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -6258,10 +6258,6 @@ static void x86_cpu_hyperv_realize(X86CPU *cpu) cpu->hyperv_interface_id[2] = 0; cpu->hyperv_interface_id[3] = 0; - /* Hypervisor system identity */ - cpu->hyperv_version_id[0] = 0x00001bbc; - cpu->hyperv_version_id[1] = 0x00060001; - /* Hypervisor implementation limits */ cpu->hyperv_limits[0] = 64; cpu->hyperv_limits[1] = 0; @@ -6644,6 +6640,8 @@ static void x86_cpu_initfn(Object *obj) object_property_add_alias(obj, "sse4_1", obj, "sse4.1"); object_property_add_alias(obj, "sse4_2", obj, "sse4.2"); + object_property_add_alias(obj, "hv-apicv", obj, "hv-avic"); + if (xcc->model) { x86_cpu_load_model(cpu, xcc->model); } @@ -6831,9 +6829,23 @@ static Property x86_cpu_properties[] = { HYPERV_FEAT_IPI, 0), DEFINE_PROP_BIT64("hv-stimer-direct", X86CPU, hyperv_features, HYPERV_FEAT_STIMER_DIRECT, 0), + DEFINE_PROP_BIT64("hv-avic", X86CPU, hyperv_features, + HYPERV_FEAT_AVIC, 0), DEFINE_PROP_ON_OFF_AUTO("hv-no-nonarch-coresharing", X86CPU, hyperv_no_nonarch_cs, ON_OFF_AUTO_OFF), DEFINE_PROP_BOOL("hv-passthrough", X86CPU, hyperv_passthrough, false), + DEFINE_PROP_BOOL("hv-enforce-cpuid", X86CPU, hyperv_enforce_cpuid, false), + + /* WS2008R2 identify by default */ + DEFINE_PROP_UINT32("hv-version-id-build", X86CPU, hyperv_ver_id_build, + 0x3839), + DEFINE_PROP_UINT16("hv-version-id-major", X86CPU, hyperv_ver_id_major, + 0x000A), + DEFINE_PROP_UINT16("hv-version-id-minor", X86CPU, hyperv_ver_id_minor, + 0x0000), + DEFINE_PROP_UINT32("hv-version-id-spack", X86CPU, hyperv_ver_id_sp, 0), + DEFINE_PROP_UINT8("hv-version-id-sbranch", X86CPU, hyperv_ver_id_sb, 0), + DEFINE_PROP_UINT32("hv-version-id-snumber", X86CPU, hyperv_ver_id_sn, 0), DEFINE_PROP_BOOL("check", X86CPU, check_cpuid, true), DEFINE_PROP_BOOL("enforce", X86CPU, enforce_cpuid, false), @@ -6860,6 +6872,8 @@ static Property x86_cpu_properties[] = { DEFINE_PROP_BOOL("l3-cache", X86CPU, enable_l3_cache, true), DEFINE_PROP_BOOL("kvm-no-smi-migration", X86CPU, kvm_no_smi_migration, false), + DEFINE_PROP_BOOL("kvm-pv-enforce-cpuid", X86CPU, kvm_pv_enforce_cpuid, + false), DEFINE_PROP_BOOL("vmware-cpuid-freq", X86CPU, vmware_cpuid_freq, true), DEFINE_PROP_BOOL("tcg-cpuid", X86CPU, expose_tcg, true), DEFINE_PROP_BOOL("x-migrate-smi-count", X86CPU, migrate_smi_count, diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 29552dc..3edaad7 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -1056,6 +1056,7 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS]; #define HYPERV_FEAT_EVMCS 12 #define HYPERV_FEAT_IPI 13 #define HYPERV_FEAT_STIMER_DIRECT 14 +#define HYPERV_FEAT_AVIC 15 #ifndef HYPERV_SPINLOCK_NEVER_NOTIFY #define HYPERV_SPINLOCK_NEVER_NOTIFY 0xFFFFFFFF @@ -1716,9 +1717,15 @@ struct X86CPU { OnOffAuto hyperv_no_nonarch_cs; uint32_t hyperv_vendor_id[3]; uint32_t hyperv_interface_id[4]; - uint32_t hyperv_version_id[4]; uint32_t hyperv_limits[3]; uint32_t hyperv_nested[4]; + bool hyperv_enforce_cpuid; + uint32_t hyperv_ver_id_build; + uint16_t hyperv_ver_id_major; + uint16_t hyperv_ver_id_minor; + uint32_t hyperv_ver_id_sp; + uint8_t hyperv_ver_id_sb; + uint32_t hyperv_ver_id_sn; bool check_cpuid; bool enforce_cpuid; @@ -1802,6 +1809,9 @@ struct X86CPU { /* Stop SMI delivery for migration compatibility with old machines */ bool kvm_no_smi_migration; + /* Forcefully disable KVM PV features not exposed in guest CPUIDs */ + bool kvm_pv_enforce_cpuid; + /* Number of physical address bits supported */ uint32_t phys_bits; diff --git a/target/i386/kvm/hyperv-proto.h b/target/i386/kvm/hyperv-proto.h index 5fbb385..89f81af 100644 --- a/target/i386/kvm/hyperv-proto.h +++ b/target/i386/kvm/hyperv-proto.h @@ -66,6 +66,7 @@ #define HV_APIC_ACCESS_RECOMMENDED (1u << 3) #define HV_SYSTEM_RESET_RECOMMENDED (1u << 4) #define HV_RELAXED_TIMING_RECOMMENDED (1u << 5) +#define HV_DEPRECATING_AEOI_RECOMMENDED (1u << 9) #define HV_CLUSTER_IPI_RECOMMENDED (1u << 10) #define HV_EX_PROCESSOR_MASKS_RECOMMENDED (1u << 11) #define HV_ENLIGHTENED_VMCS_RECOMMENDED (1u << 14) diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 7f1b060..f25837f 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -821,9 +821,7 @@ static struct { .desc = "virtual APIC (hv-vapic)", .flags = { {.func = HV_CPUID_FEATURES, .reg = R_EAX, - .bits = HV_APIC_ACCESS_AVAILABLE}, - {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, - .bits = HV_APIC_ACCESS_RECOMMENDED} + .bits = HV_APIC_ACCESS_AVAILABLE} } }, [HYPERV_FEAT_TIME] = { @@ -926,6 +924,13 @@ static struct { }, .dependencies = BIT(HYPERV_FEAT_STIMER) }, + [HYPERV_FEAT_AVIC] = { + .desc = "AVIC/APICv support (hv-avic/hv-apicv)", + .flags = { + {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, + .bits = HV_DEPRECATING_AEOI_RECOMMENDED} + } + }, }; static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max, @@ -1253,14 +1258,18 @@ bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp) cpu->hyperv_interface_id[3] = hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EDX); - cpu->hyperv_version_id[0] = + cpu->hyperv_ver_id_build = hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EAX); - cpu->hyperv_version_id[1] = - hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EBX); - cpu->hyperv_version_id[2] = + cpu->hyperv_ver_id_major = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EBX) >> 16; + cpu->hyperv_ver_id_minor = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EBX) & 0xffff; + cpu->hyperv_ver_id_sp = hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_ECX); - cpu->hyperv_version_id[3] = - hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EDX); + cpu->hyperv_ver_id_sb = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EDX) >> 24; + cpu->hyperv_ver_id_sn = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EDX) & 0xffffff; cpu->hv_max_vps = hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_EAX); @@ -1346,10 +1355,12 @@ static int hyperv_fill_cpuids(CPUState *cs, c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_VERSION; - c->eax = cpu->hyperv_version_id[0]; - c->ebx = cpu->hyperv_version_id[1]; - c->ecx = cpu->hyperv_version_id[2]; - c->edx = cpu->hyperv_version_id[3]; + c->eax = cpu->hyperv_ver_id_build; + c->ebx = (uint32_t)cpu->hyperv_ver_id_major << 16 | + cpu->hyperv_ver_id_minor; + c->ecx = cpu->hyperv_ver_id_sp; + c->edx = (uint32_t)cpu->hyperv_ver_id_sb << 24 | + (cpu->hyperv_ver_id_sn & 0xffffff); c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_FEATURES; @@ -1366,6 +1377,7 @@ static int hyperv_fill_cpuids(CPUState *cs, c->ebx |= HV_POST_MESSAGES | HV_SIGNAL_EVENTS; } + /* Not exposed by KVM but needed to make CPU hotplug in Windows work */ c->edx |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE; @@ -1374,6 +1386,11 @@ static int hyperv_fill_cpuids(CPUState *cs, c->eax = hv_build_cpuid_leaf(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EAX); c->ebx = cpu->hyperv_spinlock_attempts; + if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VAPIC) && + !hyperv_feat_enabled(cpu, HYPERV_FEAT_AVIC)) { + c->eax |= HV_APIC_ACCESS_RECOMMENDED; + } + if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_ON) { c->eax |= HV_NO_NONARCH_CORESHARING; } else if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_AUTO) { @@ -1531,6 +1548,15 @@ static int hyperv_init_vcpu(X86CPU *cpu) cpu->hyperv_nested[0] = evmcs_version; } + if (cpu->hyperv_enforce_cpuid) { + ret = kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_ENFORCE_CPUID, 0, 1); + if (ret < 0) { + error_report("failed to enable KVM_CAP_HYPERV_ENFORCE_CPUID: %s", + strerror(-ret)); + return ret; + } + } + return 0; } @@ -1629,6 +1655,16 @@ int kvm_arch_init_vcpu(CPUState *cs) cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused); + if (cpu->kvm_pv_enforce_cpuid) { + r = kvm_vcpu_enable_cap(cs, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 0, 1); + if (r < 0) { + fprintf(stderr, + "failed to enable KVM_CAP_ENFORCE_PV_FEATURE_CPUID: %s", + strerror(-r)); + abort(); + } + } + for (i = 0; i <= limit; i++) { if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { fprintf(stderr, "unsupported level value: 0x%x\n", limit); diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c index c677cd6..90bf68a 100644 --- a/tests/qtest/numa-test.c +++ b/tests/qtest/numa-test.c @@ -42,7 +42,8 @@ static void test_def_cpu_split(const void *data) g_autofree char *s = NULL; g_autofree char *cli = NULL; - cli = make_cli(data, "-machine smp.cpus=8 -numa node,memdev=ram -numa node"); + cli = make_cli(data, "-machine smp.cpus=8,smp.sockets=8 " + "-numa node,memdev=ram -numa node"); qts = qtest_init(cli); s = qtest_hmp(qts, "info numa"); @@ -265,7 +266,8 @@ static void pc_dynamic_cpu_cfg(const void *data) QTestState *qs; g_autofree char *cli = NULL; - cli = make_cli(data, "-nodefaults --preconfig -machine smp.cpus=2"); + cli = make_cli(data, "-nodefaults --preconfig " + "-machine smp.cpus=2,smp.sockets=2"); qs = qtest_init(cli); /* create 2 numa nodes */ |