CPU profiles (2/3): CPUID definitions #54
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Bumps [r-efi](https://github.com/r-efi/r-efi) from 5.2.0 to 5.3.0. - [Release notes](https://github.com/r-efi/r-efi/releases) - [Changelog](https://github.com/r-efi/r-efi/blob/main/NEWS.md) - [Commits](r-efi/r-efi@v5.2.0...v5.3.0) --- updated-dependencies: - dependency-name: r-efi dependency-version: 5.3.0 dependency-type: indirect update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [toml_datetime](https://github.com/toml-rs/toml) from 0.6.8 to 0.6.11. - [Commits](toml-rs/toml@toml_datetime-v0.6.8...toml_datetime-v0.6.11) --- updated-dependencies: - dependency-name: toml_datetime dependency-version: 0.6.11 dependency-type: indirect update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
In case of CVM guest rsdp is set to none. Unwrapping it make the vmm crashed. Don't call configure system if the rsdb address is none. Signed-off-by: Muminul Islam <[email protected]>
Bumps [anstream](https://github.com/rust-cli/anstyle) from 0.6.15 to 0.6.19. - [Commits](rust-cli/anstyle@anstream-v0.6.15...anstream-v0.6.19) --- updated-dependencies: - dependency-name: anstream dependency-version: 0.6.19 dependency-type: indirect update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Optimize lychee workflow to check only changed files in pull requests, avoiding excessive API calls to prevent rate limits. Fixes cloud-hypervisor#7056 Signed-off-by: Shubham Chakrawar <[email protected]>
Bumps [tj-actions/changed-files](https://github.com/tj-actions/changed-files) from 40 to 46. - [Release notes](https://github.com/tj-actions/changed-files/releases) - [Changelog](https://github.com/tj-actions/changed-files/blob/main/HISTORY.md) - [Commits](tj-actions/changed-files@v40...v46) --- updated-dependencies: - dependency-name: tj-actions/changed-files dependency-version: '46' dependency-type: direct:production ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [anyhow](https://github.com/dtolnay/anyhow) from 1.0.94 to 1.0.98. - [Release notes](https://github.com/dtolnay/anyhow/releases) - [Commits](dtolnay/anyhow@1.0.94...1.0.98) --- updated-dependencies: - dependency-name: anyhow dependency-version: 1.0.98 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [async-process](https://github.com/smol-rs/async-process) from 2.3.0 to 2.4.0. - [Release notes](https://github.com/smol-rs/async-process/releases) - [Changelog](https://github.com/smol-rs/async-process/blob/master/CHANGELOG.md) - [Commits](smol-rs/async-process@v2.3.0...v2.4.0) --- updated-dependencies: - dependency-name: async-process dependency-version: 2.4.0 dependency-type: indirect update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [landlock](https://github.com/landlock-lsm/rust-landlock) from 0.4.0 to 0.4.2. - [Release notes](https://github.com/landlock-lsm/rust-landlock/releases) - [Changelog](https://github.com/landlock-lsm/rust-landlock/blob/main/CHANGELOG.md) - [Commits](landlock-lsm/rust-landlock@v0.4.0...v0.4.2) --- updated-dependencies: - dependency-name: landlock dependency-version: 0.4.2 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [rustc-demangle](https://github.com/rust-lang/rustc-demangle) from 0.1.24 to 0.1.26. - [Release notes](https://github.com/rust-lang/rustc-demangle/releases) - [Changelog](https://github.com/rust-lang/rustc-demangle/blob/main/CHANGELOG.md) - [Commits](rust-lang/rustc-demangle@0.1.24...rustc-demangle-v0.1.26) --- updated-dependencies: - dependency-name: rustc-demangle dependency-version: 0.1.26 dependency-type: indirect update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [crate-ci/typos](https://github.com/crate-ci/typos) from 1.34.0 to 1.35.1. - [Release notes](https://github.com/crate-ci/typos/releases) - [Changelog](https://github.com/crate-ci/typos/blob/master/CHANGELOG.md) - [Commits](crate-ci/typos@v1.34.0...v1.35.1) --- updated-dependencies: - dependency-name: crate-ci/typos dependency-version: 1.35.1 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [rand](https://github.com/rust-random/rand) from 0.9.1 to 0.9.2. - [Release notes](https://github.com/rust-random/rand/releases) - [Changelog](https://github.com/rust-random/rand/blob/master/CHANGELOG.md) - [Commits](rust-random/rand@rand_core-0.9.1...rand_core-0.9.2) --- updated-dependencies: - dependency-name: rand dependency-version: 0.9.2 dependency-type: indirect update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Now 'create_acpi_tables_internal()' can generate ACPI tables with different dsdt offset, so that it can be reused for generating ACPI tables for `fw_cfg`. Signed-off-by: Bo Chen <[email protected]> Signed-off-by: Alex Orozco <[email protected]>
When generating ACPI tables, we are not using "offset", instead we are using (guest physical) addresses. Signed-off-by: Bo Chen <[email protected]>
Signed-off-by: Bo Chen <[email protected]>
Fix clippy error: "error: manual implementation of `.is_multiple_of() `" from rustc 1.90.0-beta.1 (788da80fc 2025-08-04). Signed-off-by: Songqian Li <[email protected]>
rustc 1.90.0-beta.1 (788da80fc 2025-08-04) suggests using library feature `unsigned_is_multiple_of`. It is stabled in Rust 1.87.0. Update image to 20250807-0 since MSRV in Dockerfile is updated. Signed-off-by: Songqian Li <[email protected]> Signed-off-by: Bo Chen <[email protected]>
Replacing pdf link with new available link to fix the failed CI. Signed-off-by: Songqian Li <[email protected]>
Bumps [crate-ci/typos](https://github.com/crate-ci/typos) from 1.35.1 to 1.35.2. - [Release notes](https://github.com/crate-ci/typos/releases) - [Changelog](https://github.com/crate-ci/typos/blob/master/CHANGELOG.md) - [Commits](crate-ci/typos@v1.35.1...v1.35.2) --- updated-dependencies: - dependency-name: crate-ci/typos dependency-version: 1.35.2 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps redox_users from 0.5.0 to 0.5.2. --- updated-dependencies: - dependency-name: redox_users dependency-version: 0.5.2 dependency-type: indirect update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [crate-ci/typos](https://github.com/crate-ci/typos) from 1.35.2 to 1.35.3. - [Release notes](https://github.com/crate-ci/typos/releases) - [Changelog](https://github.com/crate-ci/typos/blob/master/CHANGELOG.md) - [Commits](crate-ci/typos@v1.35.2...v1.35.3) --- updated-dependencies: - dependency-name: crate-ci/typos dependency-version: 1.35.3 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps [async-trait](https://github.com/dtolnay/async-trait) from 0.1.86 to 0.1.88. - [Release notes](https://github.com/dtolnay/async-trait/releases) - [Commits](dtolnay/async-trait@0.1.86...0.1.88) --- updated-dependencies: - dependency-name: async-trait dependency-version: 0.1.88 dependency-type: indirect update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
Link checker excludes checks on local links and links with variables. Signed-off-by: Songqian Li <[email protected]>
### Errors in src/main.rs * [404] <https://github.com/cloud-hypervisor/cloud-hypervisor/issues/new /n> | Rejected status code (this depends on your "accept" configuration) : Not Found Signed-off-by: Songqian Li <[email protected]>
The option parser did not allow quoting any special characters, which means that some strings could not be passed via command-line options. Fix this by allowing double quotes to quote all the special characters, such as '@', ',', '[', and ']'. '"' can be escaped by doubling it. The implementation uses some tricks to stay modular. Signed-off-by: Demi Marie Obenour <[email protected]>
Set UEFI_START and UEFI_SIZE for riscv64 layout. Signed-off-by: Ruoqing He <[email protected]>
Provide Error definitions and load_uefi to be referenced while loading firmware. Signed-off-by: Ruoqing He <[email protected]>
uefi_flash field in memory_manager is required for uefi loading and booting, enable it for riscv64 architecture. Signed-off-by: Ruoqing He <[email protected]>
Error::UefiLoad is required for load_firmware to propagate errors encountered, define it for riscv64. Signed-off-by: Ruoqing He <[email protected]>
Implement firmware boot (UEFI boot) for riscv64 architecture. Signed-off-by: Ruoqing He <[email protected]>
As we have replaced all KVM_GET_XSAVE calls with KVM_GET_XSAVE2 we need to update the seccomp filters accordingly. Signed-Off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
Virtio PCI devices are created in a set of nested functions. In each of this function a vector is created to add created devices to, only to be appended to the vector of the higher nesting level. Those nested vectors are unnecessary as we can directly write to the member of. Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
Allocating a device ID is crucial for assigning a specific ID to a device. We need this to implement configurable PCI BDF. Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
Next to tests for `allocate_device_bdf`, we introduce a new constructor `new_without_address_manager`, only available in the test build. As there is no way to instantiate an `AddressManager` in the tests, we use this constructor to work around this. Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
Updates all config structs in order to make the new config option available to all PCI device. Additionally update the parser so the new option becomes available on the CLI. Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
We use `VecDeque` to sort devices implicitly. Devices whose config contains a fixed BDF are added to the front, while those without a BDF given are added to the back. Processing the `VecDeque` sequentially from first to last then ensures that no clashes occur when assigning BDFs to devices. Otherwise, we could end up in the case that we assigned a BDF required by one device's config to one without a BDF. Signed-off-by: Pascal Scholz <[email protected]> On-behalf-of: SAP [email protected]
TLS connections have a TLS server (the endpoint that listens for a connection) and a TLS client (the endpoint that initiates the connection). This commit adds the code for the client side, which will be the source host. On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
This is the TLS server side, which will be the live migration target. On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
Also it seems like AsRawFd should be avoided https://rust-lang.github.io/rfcs/3128-io-safety.html On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
This allows (more or less) transparent usage of TLS encrypted TCP connections. On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
For TLS we need certificates (and a key for the TLS server). This commits adds parameters for that and encrypts the connection with TLS if the necessary parameters are provided. On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
The ReadVolatile and WriteVolatile implementations of TlsStream were very slow, mainly because they allocated a large buffer on each invocation. The TlsStreamWrapper carries a buffer that it uses for ReadVolatile and WriteVolatile and that is allocated once on creation. On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
When using multiple tcp connections during live migration, the main thread spawns multiple worker threads to send data. When one of those workers encountered an error, the VMM would panic. With these changes worker threads will report errors to the main thread which can then stop the live migration without panicking. On-behalf-of: SAP [email protected] Signed-off-by: Sebastian Eydam <[email protected]>
This was missing. We tried to access the option from the parsed args but it is not yet known to clap that clap should parse these options. Follow-up of d5e345b. Signed-off-by: Philipp Schuster <[email protected]> On-behalf-of: SAP [email protected]
Rename to the same name that the argument parser uses. This is also consistent with the rest of the CLI, where underscores are unusual. Signed-off-by: Philipp Schuster <[email protected]> On-behalf-of: SAP [email protected]
Since enabling AMX tile state components affect the result returned by `Hypervisor::get_supported_cpuid` we want this enabled prior to checking CPUID compatibility between the source and destination VMs. Although this is not required today, it is necessary in order for the upcoming CPU profiles correctly, and it will also be necessary once the check_cpuid_compatibility checks are extended to take state components into account. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
Temporary workaround until we switch over to the WIP fix upstream Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
These data structures are required to define CPU profiles. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We want CPU profiles to keep a record of the hypervisor type and cpu vendor that they are intended to work with. This is made more convenient if all of these types implement common traits (used for serialization). Signed-Off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We introduce essential data structures together with basic functionality that is necessary to apply a CPU profile to a host. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We integrate the CPU profile into the various configs that ultimately get set by the user. This quickly ends up involving multiple files, luckily Rust helps us find which ones via compilation errors. Signed-Off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
If a CPU profile is configured it should result in guests seeing a restricted subset of CPUID. This is what we finally achieve in this commit. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We include CPU profiles corresponding to Intel Skylake and Sapphire rapids server that we generated using our WIP CPU profile generation tool. Signed-of-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We introduce data structures to describe values within the registers modified by the CPUID instruction. These data structures will later be used by the upcoming CPU profile generation tool. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We introduce CPUID definitions for Intel CPUs that will be utilized by the upcoming CPU Profile generation tool. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We introduce CPUID definitions defined for the KVM hypervisor. These definitions will later be utilized by the upcoming CPU profile generation tool. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
We use the Intel CPUID definitions to provide more information when CPUID compatibility checks fail (when both the source and destination VM run on Intel CPUs). Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP [email protected]
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
18 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is the second PR in the CPU profiles series.
In this PR we introduce CPUID definitions describing the values within registers modified by the CPUID instruction. We write out an (almost) complete table of such descriptions of Intel CPUs and also for the KVM hypervisor.
These tables will be utilized by the upcoming CPU profile generation tool, but we also utilize the Intel table already in this PR in order to give more detailed logs when CPUID compatibility checks fail.
This PR depends on #50. A diff view between the two can be found here: olivereanderson/cloud-hypervisor@olivereanderson:cloud-hypervisor:cpu-profiles-cpuid...cpuid-definitions
Outlook
We also want to support generating CPU profiles for AMD CPUs, but we do not have the time to do that right now.
If someone else wants to pick that up (before we do) then we suggest creating separate CPUID definitions for AMD
even though maybe 80% or more of the tables will coincide.