build: Release v38.0

Signed-off-by: Bo Chen <chen.bo@intel.com>

.github/workflows/audit.yaml

@@ -9,7 +9,7 @@ jobs:
     name: Audit
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
       - uses: actions-rs/audit-check@v1
         with:
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/build.yaml

@@ -13,13 +13,13 @@ jobs:
           - stable
           - beta
           - nightly
-          - "1.64"
+          - "1.70"
         target:
           - x86_64-unknown-linux-gnu
           - x86_64-unknown-linux-musl
     steps:
       - name: Code checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
@@ -54,6 +54,9 @@ jobs:
       - name: Build (sev_snp)
         run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "sev_snp"  -- -D warnings -D clippy::undocumented_unsafe_blocks
 
+      - name: Build (igvm)
+        run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "igvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks
+
       - name: Build (mshv + kvm)
         run: cargo rustc --locked --bin cloud-hypervisor --no-default-features --features "mshv,kvm"  -- -D warnings -D clippy::undocumented_unsafe_blocks
 

.github/workflows/dco.yaml

@@ -5,7 +5,7 @@ jobs:
   check:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Set up Python 3.x
       uses: actions/setup-python@v1
       with:

.github/workflows/docker-image.yaml

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v1

.github/workflows/fuzz-build.yaml

@@ -12,9 +12,11 @@ jobs:
           - nightly
         target:
           - x86_64-unknown-linux-gnu
+    env:
+      RUSTFLAGS: -D warnings
     steps:
       - name: Code checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: Install Rust toolchain (${{ matrix.rust }})
         uses: actions-rs/toolchain@v1
         with:
@@ -22,8 +24,8 @@ jobs:
             target: ${{ matrix.target }}
             override: true
       - name: Install Cargo fuzz
-        # Temporary fix for cargo-fuzz on latest nightly: https://github.com/rust-fuzz/cargo-fuzz/issues/276
-        #run: cargo install cargo-fuzz
-        run: cargo install --git https://github.com/rust-fuzz/cargo-fuzz --rev b4df3e58f767b5cad8d1aa6753961003f56f3609
-      - name: Cargo Fuzz Build
+        run: cargo install cargo-fuzz
+      - name: Fuzz Build
         run: cargo fuzz build
+      - name: Fuzz Check
+        run: cargo fuzz check

.github/workflows/gitlint.yaml

@@ -0,0 +1,26 @@
+name: Commit messages check
+
+on:
+  pull_request:
+
+jobs:
+  gitlint:
+    name: Check commit messages
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.event.pull_request.head.sha }}
+        fetch-depth: 0
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install --upgrade gitlint
+    - name: Lint git commit messages
+      run: |
+        gitlint --commits origin/$GITHUB_BASE_REF..

.github/workflows/hadolint.yaml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Lint Dockerfile
         uses: hadolint/hadolint-action@master

.github/workflows/openapi.yaml

@@ -0,0 +1,16 @@
+name: Cloud Hypervisor OpenAPI Validation
+
+on:
+  pull_request:
+
+jobs:
+  Validate:
+    runs-on: ubuntu-latest
+    container: openapitools/openapi-generator-cli
+    steps:
+    - uses: actions/checkout@v4
+    - name: Validate OpenAPI
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      run: |
+        /usr/local/bin/docker-entrypoint.sh validate -i vmm/src/api/openapi/cloud-hypervisor.yaml

.github/workflows/quality.yaml

@@ -34,7 +34,7 @@ jobs:
             experimental: true
     steps:
       - name: Code checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
@@ -109,6 +109,14 @@ jobs:
           command: clippy
           args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "sev_snp" -- -D warnings -D clippy::undocumented_unsafe_blocks
 
+      - name: Clippy (igvm)
+        if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: ${{ matrix.target != 'x86_64-unknown-linux-gnu' }}
+          command: clippy
+          args: --target=${{ matrix.target }} --locked --all --all-targets --no-default-features --tests --examples --features "igvm" -- -D warnings -D clippy::undocumented_unsafe_blocks
+
       - name: Clippy (kvm + tdx)
         if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
         uses: actions-rs/cargo@v1
@@ -125,6 +133,6 @@ jobs:
     name: Typos / Spellcheck
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       # Executes "typos ."
       - uses: crate-ci/typos@v1.16.11

.github/workflows/release.yaml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: Install musl-gcc
         run: sudo apt install -y musl-tools
       - name: Create release directory
@@ -16,29 +16,29 @@ jobs:
       - name: Install Rust toolchain (x86_64-unknown-linux-gnu)
         uses: actions-rs/toolchain@v1
         with:
-          toolchain: "1.67.1"
+          toolchain: "1.70"
           target: x86_64-unknown-linux-gnu
       - name: Install Rust toolchain (x86_64-unknown-linux-musl)
         uses: actions-rs/toolchain@v1
         with:
-          toolchain: "1.67.1"
+          toolchain: "1.70"
           target: x86_64-unknown-linux-musl
       - name: Build
         uses: actions-rs/cargo@v1
         with:
-          toolchain: "1.67.1"
+          toolchain: "1.70"
           command: build
           args: --all --release --features mshv --target=x86_64-unknown-linux-gnu
       - name: Static Build
         uses: actions-rs/cargo@v1
         with:
-          toolchain: "1.67.1"
+          toolchain: "1.70"
           command: build
           args: --all --release --features mshv --target=x86_64-unknown-linux-musl
       - name: Install Rust toolchain (aarch64-unknown-linux-musl)
         uses: actions-rs/toolchain@v1
         with:
-          toolchain: "1.67.1"
+          toolchain: "1.70"
           target: aarch64-unknown-linux-musl
           override: true
       - name: Create Release

.github/workflows/shlint.yaml

@@ -0,0 +1,20 @@
+name: Shell scripts check
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+jobs:
+  sh-checker:
+    name: Check shell scripts
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+    - name: Run the shell script checkers
+      uses: luizm/action-sh-checker@master
+      env:
+        SHFMT_OPTS: -i 4 -d
+        SHELLCHECK_OPTS: -x --source-path scripts

.gitignore

@@ -6,3 +6,4 @@
 **/rusty-tags.vi
 /rpm/SOURCES
 /.vscode
+/vendor

.gitlint

@@ -0,0 +1,15 @@
+[general]
+extra-path=scripts/gitlint/rules.py
+regex-style-search=true
+
+[ignore-by-author-name]
+regex=dependabot
+ignore=all
+
+# default 72
+[title-max-length]
+line-length=72
+
+# default 80
+[body-max-line-length]
+line-length=72

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cloud-hypervisor"
-version = "35.0.0"
+version = "38.0.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2021"
 default-run = "cloud-hypervisor"
@@ -15,7 +15,7 @@ homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
 # a.) A dependency requires it,
 # b.) If we want to use a new feature and that MSRV is at least 6 months old,
 # c.) There is a security issue that is addressed by the toolchain update.
-rust-version = "1.64"
+rust-version = "1.70"
 
 [profile.release]
 lto = true
@@ -29,50 +29,52 @@ strip = false
 debug = true
 
 [dependencies]
-anyhow = "1.0.75"
+anyhow = "1.0.79"
 api_client = { path = "api_client" }
-argh = "0.1.9"
-dhat = { version = "0.3.2", optional = true }
+clap = { version = "4.4.7", features = ["string"] }
+dhat = { version = "0.3.3", optional = true }
 epoll = "4.3.3"
 event_monitor = { path = "event_monitor" }
 hypervisor = { path = "hypervisor" }
-libc = "0.2.147"
-log = { version = "0.4.17", features = ["std"] }
+libc = "0.2.153"
+log = { version = "0.4.20", features = ["std"] }
 option_parser = { path = "option_parser" }
-seccompiler = "0.3.0"
-serde_json = "1.0.107"
+seccompiler = "0.4.0"
+serde_json = "1.0.109"
 signal-hook = "0.3.17"
-thiserror = "1.0.40"
+thiserror = "1.0.52"
 tpm = { path = "tpm"}
 tracer = { path = "tracer" }
 vmm = { path = "vmm" }
-vmm-sys-util = "0.11.0"
-vm-memory = "0.12.2"
+vmm-sys-util = "0.12.1"
+vm-memory = "0.14.0"
 zbus = { version = "3.11.1", optional = true }
 
 # List of patched crates
 [patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.6.0-tdx" }
-kvm-ioctls = { git = "https://github.com/rust-vmm/kvm-ioctls", branch = "main" }
-versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.7.0" }
+versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch-0.1.6" }
 
 [dev-dependencies]
 dirs = "5.0.0"
 net_util = { path = "net_util" }
-once_cell = "1.18.0"
-serde_json = "1.0.107"
+once_cell = "1.19.0"
+serde_json = "1.0.109"
 test_infra = { path = "test_infra" }
 wait-timeout = "0.2.0"
 
+# Please adjust `vmm::feature_list()` accordingly when changing the
+# feature list below
 [features]
 default = ["kvm", "io_uring"]
 dbus_api = ["zbus", "vmm/dbus_api"]
 dhat-heap = ["dhat"] # For heap profiling
 guest_debug = ["vmm/guest_debug"]
+igvm = ["vmm/igvm", "mshv"]
 io_uring = ["vmm/io_uring"]
 kvm = ["vmm/kvm"]
 mshv = ["vmm/mshv"]
-sev_snp = ["vmm/sev_snp", "mshv"]
+sev_snp = ["igvm", "vmm/sev_snp", "mshv"]
 tdx = ["vmm/tdx"]
 tracing = ["vmm/tracing", "tracer/tracing"]
 

Jenkinsfile

@@ -53,6 +53,9 @@ pipeline {
                             return runWorkers
                         }
                     }
+                    environment {
+                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
+                    }
                     stages {
                         stage('Checkout') {
                             steps {
@@ -64,11 +67,6 @@ pipeline {
                                 sh 'scripts/prepare_vdpa.sh'
                             }
                         }
-                        stage('Run OpenAPI tests') {
-                            steps {
-                                sh 'scripts/run_openapi_tests.sh'
-                            }
-                        }
                         stage('Run unit tests') {
                             steps {
                                 sh 'scripts/dev_cli.sh tests --unit'
@@ -125,6 +123,9 @@ pipeline {
                             return runWorkers
                         }
                     }
+                    environment {
+                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
+                    }
                     stages {
                         stage('Checkout') {
                             steps {
@@ -142,7 +143,7 @@ pipeline {
                             }
                             steps {
                                 sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration -- -- --skip common_parallel::test_vfio'
+                                sh 'scripts/dev_cli.sh tests --integration'
                             }
                         }
                         stage('Run live-migration integration tests') {
@@ -160,7 +161,7 @@ pipeline {
                             }
                             steps {
                                 sh 'sudo modprobe openvswitch'
-                                sh 'scripts/dev_cli.sh tests --integration --libc musl -- -- --skip common_parallel::test_vfio'
+                                sh 'scripts/dev_cli.sh tests --integration --libc musl'
                             }
                         }
                         stage('Run live-migration integration tests for musl') {
@@ -364,6 +365,9 @@ pipeline {
                             }
                         }
                     }
+                    environment {
+                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
+                    }
                     stages {
                         stage('Checkout') {
                             steps {
@@ -405,6 +409,9 @@ pipeline {
                             }
                         }
                     }
+                    environment {
+                        AUTH_DOWNLOAD_TOKEN = credentials('8a26fd74-d40e-414c-9132-ff3f867806ef')
+                    }
                     stages {
                         stage('Checkout') {
                             steps {
@@ -505,5 +512,19 @@ def boolean skipWorkerBuild() {
         return true
     }
 
+    if (sh(
+        returnStatus: true,
+        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v '^\\.'"
+    ) != 0) {
+        return true
+    }
+
+    if (sh(
+        returnStatus: true,
+        script: "git diff --name-only origin/${env.CHANGE_TARGET}... | grep -v 'gitlint'"
+    ) != 0) {
+        return true
+    }
+
     return false
 }

README.md

@@ -150,7 +150,7 @@ $ sudo setcap cap_net_admin+ep ./cloud-hypervisor
 $ ./create-cloud-init.sh
 $ ./cloud-hypervisor \
 	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw --disk path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask="
@@ -163,7 +163,7 @@ GRUB) is required then it necessary to switch to the serial console instead of
 ```shell
 $ ./cloud-hypervisor \
 	--kernel ./hypervisor-fw \
-	--disk path=focal-server-cloudimg-amd64.raw --disk path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask=" \
@@ -225,7 +225,7 @@ $ sudo setcap cap_net_admin+ep ./cloud-hypervisor
 $ ./create-cloud-init.sh
 $ ./cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
-	--disk path=focal-server-cloudimg-amd64.raw --disk path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-amd64.raw path=/tmp/ubuntu-cloudinit.img \
 	--cmdline "console=hvc0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \
@@ -239,7 +239,7 @@ $ sudo setcap cap_net_admin+ep ./cloud-hypervisor
 $ ./create-cloud-init.sh
 $ ./cloud-hypervisor \
 	--kernel ./linux-cloud-hypervisor/arch/arm64/boot/Image \
-	--disk path=focal-server-cloudimg-arm64.raw --disk path=/tmp/ubuntu-cloudinit.img \
+	--disk path=focal-server-cloudimg-arm64.raw path=/tmp/ubuntu-cloudinit.img \
 	--cmdline "console=hvc0 root=/dev/vda1 rw" \
 	--cpus boot=4 \
 	--memory size=1024M \

api_client/Cargo.toml

@@ -5,4 +5,4 @@ authors = ["The Cloud Hypervisor Authors"]
 edition = "2021"
 
 [dependencies]
-vmm-sys-util = "0.11.0"
+vmm-sys-util = "0.12.1"

arch/Cargo.toml

@@ -10,20 +10,20 @@ sev_snp = []
 tdx = []
 
 [dependencies]
-anyhow = "1.0.75"
+anyhow = "1.0.79"
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.147"
-linux-loader = { version = "0.9.1", features = ["elf", "bzimage", "pe"] }
-log = "0.4.17"
-serde = { version = "1.0.168", features = ["rc", "derive"] }
-thiserror = "1.0.40"
+libc = "0.2.153"
+linux-loader = { version = "0.11.0", features = ["elf", "bzimage", "pe"] }
+log = "0.4.20"
+serde = { version = "1.0.196", features = ["rc", "derive"] }
+thiserror = "1.0.52"
 uuid = "1.3.4"
-versionize = "0.1.10"
-versionize_derive = "0.1.4"
-vm-memory = { version = "0.12.2", features = ["backend-mmap", "backend-bitmap"] }
+versionize = "0.2.0"
+versionize_derive = "0.1.6"
+vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-bitmap"] }
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = { version = "0.11.0", features = ["with-serde"] }
+vmm-sys-util = { version = "0.12.1", features = ["with-serde"] }
 
 [target.'cfg(target_arch = "aarch64")'.dependencies]
 fdt_parser = { version = "0.1.4", package = "fdt" }

arch/src/aarch64/fdt.rs

@@ -290,10 +290,7 @@ fn create_cpu_nodes(
     fdt.property_u32("#size-cells", 0x0)?;
 
     let num_cpus = vcpu_mpidr.len();
-    let threads_per_core = vcpu_topology.unwrap_or_default().0;
-    let cores_per_package = vcpu_topology.unwrap_or_default().1;
-    let packages = vcpu_topology.unwrap_or_default().2;
-
+    let (threads_per_core, cores_per_package, packages) = vcpu_topology.unwrap_or((1, 1, 1));
     let max_cpus: u32 = (threads_per_core * cores_per_package * packages).into();
 
     // Add cache info.

arch/src/aarch64/layout.rs

@@ -111,8 +111,9 @@ pub const RAM_64BIT_START: GuestAddress = GuestAddress(0x1_0000_0000);
 pub const CMDLINE_MAX_SIZE: usize = 2048;
 
 /// FDT is at the beginning of RAM.
-/// Maximum size of the device tree blob as specified in https://www.kernel.org/doc/Documentation/arm64/booting.txt.
 pub const FDT_START: GuestAddress = RAM_START;
+/// Maximum size of the device tree blob as specified in [the kernel
+/// documentation](https://www.kernel.org/doc/Documentation/arm64/booting.txt).
 pub const FDT_MAX_SIZE: u64 = 0x20_0000;
 
 /// Put ACPI table above dtb

arch/src/aarch64/uefi.rs

@@ -1,8 +1,9 @@
 // Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
 
 use std::io::{Read, Seek, SeekFrom};
+use std::os::fd::AsFd;
 use std::result;
-use vm_memory::{Bytes, GuestAddress, GuestMemory};
+use vm_memory::{GuestAddress, GuestMemory};
 
 /// Errors thrown while loading UEFI binary
 #[derive(Debug)]
@@ -24,7 +25,7 @@ pub fn load_uefi<F, M: GuestMemory>(
     uefi_image: &mut F,
 ) -> Result<()>
 where
-    F: Read + Seek,
+    F: Read + Seek + AsFd,
 {
     let uefi_size = uefi_image
         .seek(SeekFrom::End(0))
@@ -36,6 +37,6 @@ where
     }
     uefi_image.rewind().map_err(|_| Error::SeekUefiStart)?;
     guest_mem
-        .read_exact_from(guest_addr, uefi_image, uefi_size)
+        .read_exact_volatile_from(guest_addr, &mut uefi_image.as_fd(), uefi_size)
         .map_err(|_| Error::ReadUefiImage)
 }

arch/src/lib.rs

@@ -91,8 +91,9 @@ pub mod x86_64;
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::{
     arch_memory_regions, configure_system, configure_vcpu, generate_common_cpuid,
-    get_host_cpu_phys_bits, initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE,
-    layout::CMDLINE_START, regs, CpuidFeatureEntry, EntryPoint, _NSIG,
+    generate_ram_ranges, get_host_cpu_phys_bits, initramfs_load_addr, layout,
+    layout::CMDLINE_MAX_SIZE, layout::CMDLINE_START, regs, CpuidConfig, CpuidFeatureEntry,
+    EntryPoint, _NSIG,
 };
 
 /// Safe wrapper for `sysconf(_SC_PAGESIZE)`.
@@ -108,6 +109,7 @@ pub struct NumaNode {
     pub memory_regions: Vec<Arc<GuestRegionMmap>>,
     pub hotplug_regions: Vec<Arc<GuestRegionMmap>>,
     pub cpus: Vec<u8>,
+    pub pci_segments: Vec<u16>,
     pub distances: BTreeMap<u32, u8>,
     pub memory_zones: Vec<String>,
     #[cfg(target_arch = "x86_64")]

arch/src/x86_64/mod.rs

@@ -17,14 +17,13 @@ use crate::InitramfsConfig;
 use crate::RegionType;
 use hypervisor::arch::x86::{CpuIdEntry, CPUID_FLAG_VALID_INDEX};
 use hypervisor::{CpuVendor, HypervisorCpuError, HypervisorError};
-use linux_loader::loader::bootparam::boot_params;
 use linux_loader::loader::elf::start_info::{
     hvm_memmap_table_entry, hvm_modlist_entry, hvm_start_info,
 };
 use std::collections::BTreeMap;
 use std::mem;
 use vm_memory::{
-    Address, ByteValued, Bytes, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic,
+    Address, Bytes, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic,
     GuestMemoryRegion, GuestUsize,
 };
 mod smbios;
@@ -37,6 +36,9 @@ const TSC_DEADLINE_TIMER_ECX_BIT: u8 = 24; // tsc deadline timer ecx bit.
 const HYPERVISOR_ECX_BIT: u8 = 31; // Hypervisor ecx bit.
 const MTRR_EDX_BIT: u8 = 12; // Hypervisor ecx bit.
 const INVARIANT_TSC_EDX_BIT: u8 = 8; // Invariant TSC bit on 0x8000_0007 EDX
+const AMX_BF16: u8 = 22; // AMX tile computation on bfloat16 numbers
+const AMX_TILE: u8 = 24; // AMX tile load/store instructions
+const AMX_INT8: u8 = 25; // AMX tile computation on 8-bit integers
 
 // KVM feature bits
 #[cfg(feature = "tdx")]
@@ -113,37 +115,14 @@ impl SgxEpcRegion {
     }
 }
 
-// This is a workaround to the Rust enforcement specifying that any implementation of a foreign
-// trait (in this case `DataInit`) where:
-// *    the type that is implementing the trait is foreign or
-// *    all of the parameters being passed to the trait (if there are any) are also foreign
-// is prohibited.
-#[derive(Copy, Clone, Default)]
-struct StartInfoWrapper(hvm_start_info);
-
-#[derive(Copy, Clone, Default)]
-struct MemmapTableEntryWrapper(hvm_memmap_table_entry);
-
-#[derive(Copy, Clone, Default)]
-struct ModlistEntryWrapper(hvm_modlist_entry);
-
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for StartInfoWrapper {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for MemmapTableEntryWrapper {}
-// SAFETY: data structure only contain a series of integers
-unsafe impl ByteValued for ModlistEntryWrapper {}
-
-// This is a workaround to the Rust enforcement specifying that any implementation of a foreign
-// trait (in this case `DataInit`) where:
-// *    the type that is implementing the trait is foreign or
-// *    all of the parameters being passed to the trait (if there are any) are also foreign
-// is prohibited.
-#[derive(Copy, Clone, Default)]
-struct BootParamsWrapper(boot_params);
-
-// SAFETY: BootParamsWrap is a wrapper over `boot_params` (a series of ints).
-unsafe impl ByteValued for BootParamsWrapper {}
+pub struct CpuidConfig {
+    pub sgx_epc_sections: Option<Vec<SgxEpcSection>>,
+    pub phys_bits: u8,
+    pub kvm_hyperv: bool,
+    #[cfg(feature = "tdx")]
+    pub tdx: bool,
+    pub amx: bool,
+}
 
 #[derive(Debug)]
 pub enum Error {
@@ -209,6 +188,26 @@ impl From<Error> for super::Error {
     }
 }
 
+pub fn get_x2apic_id(cpu_id: u32, topology: Option<(u8, u8, u8)>) -> u32 {
+    if let Some(t) = topology {
+        let thread_mask_width = u8::BITS - (t.0 - 1).leading_zeros();
+        let core_mask_width = u8::BITS - (t.1 - 1).leading_zeros();
+        let die_mask_width = u8::BITS - (t.2 - 1).leading_zeros();
+
+        let thread_id = cpu_id % (t.0 as u32);
+        let core_id = cpu_id / (t.0 as u32) % (t.1 as u32);
+        let die_id = cpu_id / ((t.0 * t.1) as u32) % (t.2 as u32);
+        let socket_id = cpu_id / ((t.0 * t.1 * t.2) as u32);
+
+        return thread_id
+            | (core_id << thread_mask_width)
+            | (die_id << (thread_mask_width + core_mask_width))
+            | (socket_id << (thread_mask_width + core_mask_width + die_mask_width));
+    }
+
+    cpu_id
+}
+
 #[derive(Copy, Clone, Debug)]
 pub enum CpuidReg {
     EAX,
@@ -228,6 +227,26 @@ pub struct CpuidPatch {
 }
 
 impl CpuidPatch {
+    pub fn get_cpuid_reg(
+        cpuid: &[CpuIdEntry],
+        function: u32,
+        index: Option<u32>,
+        reg: CpuidReg,
+    ) -> Option<u32> {
+        for entry in cpuid.iter() {
+            if entry.function == function && (index.is_none() || index.unwrap() == entry.index) {
+                return match reg {
+                    CpuidReg::EAX => Some(entry.eax),
+                    CpuidReg::EBX => Some(entry.ebx),
+                    CpuidReg::ECX => Some(entry.ecx),
+                    CpuidReg::EDX => Some(entry.edx),
+                };
+            }
+        }
+
+        None
+    }
+
     pub fn set_cpuid_reg(
         cpuid: &mut Vec<CpuIdEntry>,
         function: u32,
@@ -552,11 +571,7 @@ impl CpuidFeatureEntry {
 
 pub fn generate_common_cpuid(
     hypervisor: &Arc<dyn hypervisor::Hypervisor>,
-    topology: Option<(u8, u8, u8)>,
-    sgx_epc_sections: Option<Vec<SgxEpcSection>>,
-    phys_bits: u8,
-    kvm_hyperv: bool,
-    #[cfg(feature = "tdx")] tdx_enabled: bool,
+    config: &CpuidConfig,
 ) -> super::Result<Vec<CpuIdEntry>> {
     // SAFETY: cpuid called with valid leaves
     if unsafe { x86_64::__cpuid(1) }.ecx & 1 << HYPERVISOR_ECX_BIT == 1 << HYPERVISOR_ECX_BIT {
@@ -574,7 +589,10 @@ pub fn generate_common_cpuid(
         );
     }
 
-    info!("Generating guest CPUID for with physical address size: {phys_bits}");
+    info!(
+        "Generating guest CPUID for with physical address size: {}",
+        config.phys_bits
+    );
     let cpuid_patches = vec![
         // Patch tsc deadline timer bit
         CpuidPatch {
@@ -615,16 +633,12 @@ pub fn generate_common_cpuid(
 
     CpuidPatch::patch_cpuid(&mut cpuid, cpuid_patches);
 
-    if let Some(t) = topology {
-        update_cpuid_topology(&mut cpuid, t.0, t.1, t.2);
-    }
-
-    if let Some(sgx_epc_sections) = sgx_epc_sections {
+    if let Some(sgx_epc_sections) = &config.sgx_epc_sections {
         update_cpuid_sgx(&mut cpuid, sgx_epc_sections)?;
     }
 
     #[cfg(feature = "tdx")]
-    let tdx_capabilities = if tdx_enabled {
+    let tdx_capabilities = if config.tdx {
         let caps = hypervisor
             .tdx_capabilities()
             .map_err(Error::TdxCapabilities)?;
@@ -637,6 +651,12 @@ pub fn generate_common_cpuid(
     // Update some existing CPUID
     for entry in cpuid.as_mut_slice().iter_mut() {
         match entry.function {
+            // Clear AMX related bits if the AMX feature is not enabled
+            0x7 => {
+                if !config.amx && entry.index == 0 {
+                    entry.edx &= !(1 << AMX_BF16 | 1 << AMX_TILE | 1 << AMX_INT8)
+                }
+            }
             0xd =>
             {
                 #[cfg(feature = "tdx")]
@@ -672,12 +692,12 @@ pub fn generate_common_cpuid(
             }
             // Set CPU physical bits
             0x8000_0008 => {
-                entry.eax = (entry.eax & 0xffff_ff00) | (phys_bits as u32 & 0xff);
+                entry.eax = (entry.eax & 0xffff_ff00) | (config.phys_bits as u32 & 0xff);
             }
             0x4000_0001 => {
                 // These features are not supported by TDX
                 #[cfg(feature = "tdx")]
-                if tdx_enabled {
+                if config.tdx {
                     entry.eax &= !(1 << KVM_FEATURE_CLOCKSOURCE_BIT
                         | 1 << KVM_FEATURE_CLOCKSOURCE2_BIT
                         | 1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT
@@ -705,7 +725,7 @@ pub fn generate_common_cpuid(
         });
     }
 
-    if kvm_hyperv {
+    if config.kvm_hyperv {
         // Remove conflicting entries
         cpuid.retain(|c| c.function != 0x4000_0000);
         cpuid.retain(|c| c.function != 0x4000_0001);
@@ -761,19 +781,30 @@ pub fn configure_vcpu(
     boot_setup: Option<(EntryPoint, &GuestMemoryAtomic<GuestMemoryMmap>)>,
     cpuid: Vec<CpuIdEntry>,
     kvm_hyperv: bool,
+    cpu_vendor: CpuVendor,
+    topology: Option<(u8, u8, u8)>,
 ) -> super::Result<()> {
+    let x2apic_id = get_x2apic_id(id as u32, topology);
+
     // Per vCPU CPUID changes; common are handled via generate_common_cpuid()
     let mut cpuid = cpuid;
-    CpuidPatch::set_cpuid_reg(&mut cpuid, 0xb, None, CpuidReg::EDX, u32::from(id));
-    CpuidPatch::set_cpuid_reg(&mut cpuid, 0x1f, None, CpuidReg::EDX, u32::from(id));
+    CpuidPatch::set_cpuid_reg(&mut cpuid, 0xb, None, CpuidReg::EDX, x2apic_id);
+    CpuidPatch::set_cpuid_reg(&mut cpuid, 0x1f, None, CpuidReg::EDX, x2apic_id);
+    if matches!(cpu_vendor, CpuVendor::AMD) {
+        CpuidPatch::set_cpuid_reg(&mut cpuid, 0x8000_001e, Some(0), CpuidReg::EAX, x2apic_id);
+    }
 
     // Set ApicId in cpuid for each vcpu
     // SAFETY: get host cpuid when eax=1
     let mut cpu_ebx = unsafe { core::arch::x86_64::__cpuid(1) }.ebx;
     cpu_ebx &= 0xffffff;
-    cpu_ebx |= (id as u32) << 24;
+    cpu_ebx |= x2apic_id << 24;
     CpuidPatch::set_cpuid_reg(&mut cpuid, 0x1, None, CpuidReg::EBX, cpu_ebx);
 
+    if let Some(t) = topology {
+        update_cpuid_topology(&mut cpuid, t.0, t.1, t.2, cpu_vendor, id);
+    }
+
     // The TSC frequency CPUID leaf should not be included when running with HyperV emulation
     if !kvm_hyperv {
         if let Some(tsc_khz) = vcpu.tsc_khz().map_err(Error::GetTscFrequency)? {
@@ -868,6 +899,7 @@ pub fn configure_system(
     serial_number: Option<&str>,
     uuid: Option<&str>,
     oem_strings: Option<&[&str]>,
+    topology: Option<(u8, u8, u8)>,
 ) -> super::Result<()> {
     // Write EBDA address to location where ACPICA expects to find it
     guest_mem
@@ -880,7 +912,7 @@ pub fn configure_system(
     // Place the MP table after the SMIOS table aligned to 16 bytes
     let offset = GuestAddress(layout::SMBIOS_START).unchecked_add(size);
     let offset = GuestAddress((offset.0 + 16) & !0xf);
-    mptable::setup_mptable(offset, guest_mem, _num_cpus).map_err(Error::MpTableSetup)?;
+    mptable::setup_mptable(offset, guest_mem, _num_cpus, topology).map_err(Error::MpTableSetup)?;
 
     // Check that the RAM is not smaller than the RSDP start address
     if let Some(rsdp_addr) = rsdp_addr {
@@ -898,52 +930,11 @@ pub fn configure_system(
     )
 }
 
-fn configure_pvh(
-    guest_mem: &GuestMemoryMmap,
-    cmdline_addr: GuestAddress,
-    initramfs: &Option<InitramfsConfig>,
-    rsdp_addr: Option<GuestAddress>,
-    sgx_epc_region: Option<SgxEpcRegion>,
-) -> super::Result<()> {
-    const XEN_HVM_START_MAGIC_VALUE: u32 = 0x336ec578;
-
-    let mut start_info: StartInfoWrapper = StartInfoWrapper(hvm_start_info::default());
-
-    start_info.0.magic = XEN_HVM_START_MAGIC_VALUE;
-    start_info.0.version = 1; // pvh has version 1
-    start_info.0.nr_modules = 0;
-    start_info.0.cmdline_paddr = cmdline_addr.raw_value();
-    start_info.0.memmap_paddr = layout::MEMMAP_START.raw_value();
-
-    if let Some(rsdp_addr) = rsdp_addr {
-        start_info.0.rsdp_paddr = rsdp_addr.0;
-    }
-
-    if let Some(initramfs_config) = initramfs {
-        // The initramfs has been written to guest memory already, here we just need to
-        // create the module structure that describes it.
-        let ramdisk_mod: ModlistEntryWrapper = ModlistEntryWrapper(hvm_modlist_entry {
-            paddr: initramfs_config.address.raw_value(),
-            size: initramfs_config.size as u64,
-            ..Default::default()
-        });
-
-        start_info.0.nr_modules += 1;
-        start_info.0.modlist_paddr = layout::MODLIST_START.raw_value();
-
-        // Write the modlist struct to guest memory.
-        guest_mem
-            .write_obj(ramdisk_mod, layout::MODLIST_START)
-            .map_err(super::Error::ModlistSetup)?;
-    }
-
-    // Vector to hold the memory maps which needs to be written to guest memory
-    // at MEMMAP_START after all of the mappings are recorded.
-    let mut memmap: Vec<hvm_memmap_table_entry> = Vec::new();
-
-    // Create the memory map entries.
-    add_memmap_entry(&mut memmap, 0, layout::EBDA_START.raw_value(), E820_RAM);
+type RamRange = (u64, u64);
 
+/// Returns usable physical memory ranges for the guest
+/// These should be used to create e820_RAM memory maps
+pub fn generate_ram_ranges(guest_mem: &GuestMemoryMmap) -> super::Result<Vec<RamRange>> {
     // Merge continuous memory regions into one region.
     // Note: memory regions from "GuestMemory" are sorted and non-zero sized.
     let ram_regions = {
@@ -976,16 +967,12 @@ fn configure_pvh(
         ram_regions
     };
 
-    if ram_regions.len() > 2 {
-        error!(
-            "There should be up to two non-continuous regions, devidided by the
-            gap at the end of 32bit address space (e.g. between 3G and 4G)."
-        );
-        return Err(super::Error::MemmapTableSetup);
-    }
-
     // Create the memory map entry for memory region before the gap
-    {
+    let mut ram_ranges = vec![];
+
+    // Generate the first usable physical memory range before the gap. The e820 map
+    // should only report memory above 1MiB.
+    let first_ram_range = {
         let (first_region_start, first_region_end) =
             ram_regions.first().ok_or(super::Error::MemmapTableSetup)?;
         let high_ram_start = layout::HIGH_RAM_START.raw_value();
@@ -1005,39 +992,87 @@ fn configure_pvh(
         }
 
         info!(
-            "create_memmap_entry, start: 0x{:08x}, end: 0x{:08x}",
+            "first usable physical memory range, start: 0x{:08x}, end: 0x{:08x}",
             high_ram_start, first_region_end
         );
 
-        add_memmap_entry(
-            &mut memmap,
-            high_ram_start,
-            first_region_end - high_ram_start,
-            E820_RAM,
+        (high_ram_start, *first_region_end)
+    };
+    ram_ranges.push(first_ram_range);
+
+    // Generate additional usable physical memory range after the gap if any.
+    for ram_region in ram_regions.iter().skip(1) {
+        info!(
+            "found usable physical memory range, start: 0x{:08x}, end: 0x{:08x}",
+            ram_region.0, ram_region.1
         );
+
+        ram_ranges.push(*ram_region);
     }
 
-    // Create the memory map entry for memory region after the gap if any
-    if let Some((second_region_start, second_region_end)) = ram_regions.get(1) {
-        let ram_64bit_start = layout::RAM_64BIT_START.raw_value();
+    Ok(ram_ranges)
+}
 
-        if second_region_start != &ram_64bit_start {
-            error!(
-                "Unexpected second memory region layout: start: 0x{:08x}, ram_64bit_start: 0x{:08x}",
-                second_region_start, ram_64bit_start
-            );
+fn configure_pvh(
+    guest_mem: &GuestMemoryMmap,
+    cmdline_addr: GuestAddress,
+    initramfs: &Option<InitramfsConfig>,
+    rsdp_addr: Option<GuestAddress>,
+    sgx_epc_region: Option<SgxEpcRegion>,
+) -> super::Result<()> {
+    const XEN_HVM_START_MAGIC_VALUE: u32 = 0x336ec578;
 
-            return Err(super::Error::MemmapTableSetup);
-        }
+    let mut start_info = hvm_start_info {
+        magic: XEN_HVM_START_MAGIC_VALUE,
+        version: 1, // pvh has version 1
+        nr_modules: 0,
+        cmdline_paddr: cmdline_addr.raw_value(),
+        memmap_paddr: layout::MEMMAP_START.raw_value(),
+        ..Default::default()
+    };
 
+    if let Some(rsdp_addr) = rsdp_addr {
+        start_info.rsdp_paddr = rsdp_addr.0;
+    }
+
+    if let Some(initramfs_config) = initramfs {
+        // The initramfs has been written to guest memory already, here we just need to
+        // create the module structure that describes it.
+        let ramdisk_mod = hvm_modlist_entry {
+            paddr: initramfs_config.address.raw_value(),
+            size: initramfs_config.size as u64,
+            ..Default::default()
+        };
+
+        start_info.nr_modules += 1;
+        start_info.modlist_paddr = layout::MODLIST_START.raw_value();
+
+        // Write the modlist struct to guest memory.
+        guest_mem
+            .write_obj(ramdisk_mod, layout::MODLIST_START)
+            .map_err(super::Error::ModlistSetup)?;
+    }
+
+    // Vector to hold the memory maps which needs to be written to guest memory
+    // at MEMMAP_START after all of the mappings are recorded.
+    let mut memmap: Vec<hvm_memmap_table_entry> = Vec::new();
+
+    // Create the memory map entries.
+    add_memmap_entry(&mut memmap, 0, layout::EBDA_START.raw_value(), E820_RAM);
+
+    // Get usable physical memory ranges
+    let ram_ranges = generate_ram_ranges(guest_mem)?;
+
+    // Create e820 memory map entries
+    for ram_range in ram_ranges {
         info!(
             "create_memmap_entry, start: 0x{:08x}, end: 0x{:08x}",
-            ram_64bit_start, second_region_end
+            ram_range.0, ram_range.1
         );
         add_memmap_entry(
             &mut memmap,
-            ram_64bit_start,
-            second_region_end - ram_64bit_start,
+            ram_range.0,
+            ram_range.1 - ram_range.0,
             E820_RAM,
         );
     }
@@ -1058,7 +1093,7 @@ fn configure_pvh(
         );
     }
 
-    start_info.0.memmap_entries = memmap.len() as u32;
+    start_info.memmap_entries = memmap.len() as u32;
 
     // Copy the vector with the memmap table to the MEMMAP_START address
     // which is already saved in the memmap_paddr field of hvm_start_info struct.
@@ -1067,17 +1102,14 @@ fn configure_pvh(
     guest_mem
         .checked_offset(
             memmap_start_addr,
-            mem::size_of::<hvm_memmap_table_entry>() * start_info.0.memmap_entries as usize,
+            mem::size_of::<hvm_memmap_table_entry>() * start_info.memmap_entries as usize,
         )
         .ok_or(super::Error::MemmapTablePastRamEnd)?;
 
-    // For every entry in the memmap vector, create a MemmapTableEntryWrapper
-    // and write it to guest memory.
+    // For every entry in the memmap vector, write it to guest memory.
     for memmap_entry in memmap {
-        let map_entry_wrapper: MemmapTableEntryWrapper = MemmapTableEntryWrapper(memmap_entry);
-
         guest_mem
-            .write_obj(map_entry_wrapper, memmap_start_addr)
+            .write_obj(memmap_entry, memmap_start_addr)
             .map_err(|_| super::Error::MemmapTableSetup)?;
         memmap_start_addr =
             memmap_start_addr.unchecked_add(mem::size_of::<hvm_memmap_table_entry>() as u64);
@@ -1160,11 +1192,27 @@ fn update_cpuid_topology(
     threads_per_core: u8,
     cores_per_die: u8,
     dies_per_package: u8,
+    cpu_vendor: CpuVendor,
+    id: u8,
 ) {
+    let x2apic_id = get_x2apic_id(
+        id as u32,
+        Some((threads_per_core, cores_per_die, dies_per_package)),
+    );
+
     let thread_width = 8 - (threads_per_core - 1).leading_zeros();
     let core_width = (8 - (cores_per_die - 1).leading_zeros()) + thread_width;
     let die_width = (8 - (dies_per_package - 1).leading_zeros()) + core_width;
 
+    let mut cpu_ebx = CpuidPatch::get_cpuid_reg(cpuid, 0x1, None, CpuidReg::EBX).unwrap_or(0);
+    cpu_ebx |= ((dies_per_package as u32) * (cores_per_die as u32) * (threads_per_core as u32))
+        & 0xff << 16;
+    CpuidPatch::set_cpuid_reg(cpuid, 0x1, None, CpuidReg::EBX, cpu_ebx);
+
+    let mut cpu_edx = CpuidPatch::get_cpuid_reg(cpuid, 0x1, None, CpuidReg::EDX).unwrap_or(0);
+    cpu_edx |= 1 << 28;
+    CpuidPatch::set_cpuid_reg(cpuid, 0x1, None, CpuidReg::EDX, cpu_edx);
+
     // CPU Topology leaf 0xb
     CpuidPatch::set_cpuid_reg(cpuid, 0xb, Some(0), CpuidReg::EAX, thread_width);
     CpuidPatch::set_cpuid_reg(
@@ -1216,13 +1264,72 @@ fn update_cpuid_topology(
         u32::from(dies_per_package * cores_per_die * threads_per_core),
     );
     CpuidPatch::set_cpuid_reg(cpuid, 0x1f, Some(2), CpuidReg::ECX, 5 << 8);
+
+    if matches!(cpu_vendor, CpuVendor::AMD) {
+        CpuidPatch::set_cpuid_reg(
+            cpuid,
+            0x8000_001e,
+            Some(0),
+            CpuidReg::EBX,
+            ((threads_per_core as u32 - 1) << 8) | (x2apic_id & 0xff),
+        );
+        CpuidPatch::set_cpuid_reg(
+            cpuid,
+            0x8000_001e,
+            Some(0),
+            CpuidReg::ECX,
+            ((dies_per_package as u32 - 1) << 8) | (thread_width + die_width) & 0xff,
+        );
+        CpuidPatch::set_cpuid_reg(cpuid, 0x8000_001e, Some(0), CpuidReg::EDX, 0);
+        if cores_per_die * threads_per_core > 1 {
+            let ecx =
+                CpuidPatch::get_cpuid_reg(cpuid, 0x8000_0001, Some(0), CpuidReg::ECX).unwrap_or(0);
+            CpuidPatch::set_cpuid_reg(
+                cpuid,
+                0x8000_0001,
+                Some(0),
+                CpuidReg::ECX,
+                ecx | (1u32 << 1) | (1u32 << 22),
+            );
+            CpuidPatch::set_cpuid_reg(
+                cpuid,
+                0x0000_0001,
+                Some(0),
+                CpuidReg::EBX,
+                (x2apic_id << 24) | (8 << 8) | (((cores_per_die * threads_per_core) as u32) << 16),
+            );
+            let cpuid_patches = vec![
+                // Patch tsc deadline timer bit
+                CpuidPatch {
+                    function: 1,
+                    index: 0,
+                    flags_bit: None,
+                    eax_bit: None,
+                    ebx_bit: None,
+                    ecx_bit: None,
+                    edx_bit: Some(28),
+                },
+            ];
+            CpuidPatch::patch_cpuid(cpuid, cpuid_patches);
+            CpuidPatch::set_cpuid_reg(
+                cpuid,
+                0x8000_0008,
+                Some(0),
+                CpuidReg::ECX,
+                ((thread_width + core_width + die_width) << 12)
+                    | ((cores_per_die * threads_per_core) - 1) as u32,
+            );
+        } else {
+            CpuidPatch::set_cpuid_reg(cpuid, 0x8000_0008, Some(0), CpuidReg::ECX, 0u32);
+        }
+    }
 }
 
 // The goal is to update the CPUID sub-leaves to reflect the number of EPC
 // sections exposed to the guest.
 fn update_cpuid_sgx(
     cpuid: &mut Vec<CpuIdEntry>,
-    epc_sections: Vec<SgxEpcSection>,
+    epc_sections: &[SgxEpcSection],
 ) -> Result<(), Error> {
     // Something's wrong if there's no EPC section.
     if epc_sections.is_empty() {
@@ -1294,6 +1401,7 @@ mod tests {
             None,
             None,
             None,
+            None,
         );
         assert!(config_err.is_err());
 
@@ -1316,6 +1424,7 @@ mod tests {
             None,
             None,
             None,
+            None,
         )
         .unwrap();
 
@@ -1343,6 +1452,7 @@ mod tests {
             None,
             None,
             None,
+            None,
         )
         .unwrap();
 
@@ -1356,6 +1466,7 @@ mod tests {
             None,
             None,
             None,
+            None,
         )
         .unwrap();
     }
@@ -1384,4 +1495,25 @@ mod tests {
 
         assert_eq!(format!("{memmap:?}"), format!("{expected_memmap:?}"));
     }
+
+    #[test]
+    fn test_get_x2apic_id() {
+        let x2apic_id = get_x2apic_id(0, Some((2, 3, 1)));
+        assert_eq!(x2apic_id, 0);
+
+        let x2apic_id = get_x2apic_id(1, Some((2, 3, 1)));
+        assert_eq!(x2apic_id, 1);
+
+        let x2apic_id = get_x2apic_id(2, Some((2, 3, 1)));
+        assert_eq!(x2apic_id, 2);
+
+        let x2apic_id = get_x2apic_id(6, Some((2, 3, 1)));
+        assert_eq!(x2apic_id, 8);
+
+        let x2apic_id = get_x2apic_id(7, Some((2, 3, 1)));
+        assert_eq!(x2apic_id, 9);
+
+        let x2apic_id = get_x2apic_id(8, Some((2, 3, 1)));
+        assert_eq!(x2apic_id, 10);
+    }
 }

arch/src/x86_64/mptable.rs

@@ -6,10 +6,9 @@
 // found in the LICENSE-BSD-3-Clause file.
 
 use crate::layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
-use crate::x86_64::mpspec;
+use crate::x86_64::{get_x2apic_id, mpspec};
 use crate::GuestMemoryMmap;
 use libc::c_char;
-use std::io;
 use std::mem;
 use std::result;
 use std::slice;
@@ -126,9 +125,18 @@ fn compute_mp_size(num_cpus: u8) -> usize {
 }
 
 /// Performs setup of the MP table for the given `num_cpus`.
-pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8) -> Result<()> {
-    if num_cpus as u32 > MAX_SUPPORTED_CPUS {
-        return Err(Error::TooManyCpus);
+pub fn setup_mptable(
+    offset: GuestAddress,
+    mem: &GuestMemoryMmap,
+    num_cpus: u8,
+    topology: Option<(u8, u8, u8)>,
+) -> Result<()> {
+    if num_cpus > 0 {
+        let cpu_id_max = num_cpus - 1;
+        let x2apic_id_max = get_x2apic_id(cpu_id_max.into(), topology);
+        if x2apic_id_max >= MAX_SUPPORTED_CPUS {
+            return Err(Error::TooManyCpus);
+        }
     }
 
     // Used to keep track of the next base pointer into the MP table.
@@ -142,7 +150,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
     }
 
     let mut checksum: u8 = 0;
-    let ioapicid: u8 = num_cpus + 1;
+    let ioapicid: u8 = MAX_SUPPORTED_CPUS as u8 + 1;
 
     // The checked_add here ensures the all of the following base_mp.unchecked_add's will be without
     // overflow.
@@ -154,7 +162,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         return Err(Error::AddressOverflow);
     }
 
-    mem.read_exact_from(base_mp, &mut io::repeat(0), mp_size)
+    mem.read_exact_volatile_from(base_mp, &mut vec![0; mp_size].as_slice(), mp_size)
         .map_err(Error::Clear)?;
 
     {
@@ -180,7 +188,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         for cpu_id in 0..num_cpus {
             let mut mpc_cpu = MpcCpuWrapper(mpspec::mpc_cpu::default());
             mpc_cpu.0.type_ = mpspec::MP_PROCESSOR as u8;
-            mpc_cpu.0.apicid = cpu_id;
+            mpc_cpu.0.apicid = get_x2apic_id(cpu_id as u32, topology) as u8;
             mpc_cpu.0.apicver = APIC_VERSION;
             mpc_cpu.0.cpuflag = mpspec::CPU_ENABLED as u8
                 | if cpu_id == 0 {
@@ -291,7 +299,10 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
 mod tests {
     use super::*;
     use crate::layout::MPTABLE_START;
-    use vm_memory::{GuestAddress, GuestUsize};
+    use vm_memory::{
+        bitmap::BitmapSlice, GuestAddress, GuestUsize, VolatileMemoryError, VolatileSlice,
+        WriteVolatile,
+    };
 
     fn table_entry_size(type_: u8) -> usize {
         match type_ as u32 {
@@ -310,7 +321,7 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus).unwrap();
+        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap();
     }
 
     #[test]
@@ -319,7 +330,7 @@ mod tests {
         let mem = GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus) - 1)])
             .unwrap();
 
-        assert!(setup_mptable(MPTABLE_START, &mem, num_cpus).is_err());
+        assert!(setup_mptable(MPTABLE_START, &mem, num_cpus, None).is_err());
     }
 
     #[test]
@@ -328,7 +339,7 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus).unwrap();
+        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap();
 
         let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
 
@@ -344,27 +355,31 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(num_cpus))]).unwrap();
 
-        setup_mptable(MPTABLE_START, &mem, num_cpus).unwrap();
+        setup_mptable(MPTABLE_START, &mem, num_cpus, None).unwrap();
 
         let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
         let mpc_offset = GuestAddress(mpf_intel.0.physptr as GuestUsize);
         let mpc_table: MpcTableWrapper = mem.read_obj(mpc_offset).unwrap();
 
         struct Sum(u8);
-        impl io::Write for Sum {
-            fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
-                for v in buf.iter() {
+        impl WriteVolatile for Sum {
+            fn write_volatile<B: BitmapSlice>(
+                &mut self,
+                buf: &VolatileSlice<B>,
+            ) -> result::Result<usize, VolatileMemoryError> {
+                let mut tmp = vec![0u8; buf.len()];
+                tmp.write_all_volatile(buf)?;
+
+                for v in tmp.iter() {
                     self.0 = self.0.wrapping_add(*v);
                 }
+
                 Ok(buf.len())
             }
-            fn flush(&mut self) -> io::Result<()> {
-                Ok(())
-            }
         }
 
         let mut sum = Sum(0);
-        mem.write_to(mpc_offset, &mut sum, mpc_table.0.length as usize)
+        mem.write_volatile_to(mpc_offset, &mut sum, mpc_table.0.length as usize)
             .unwrap();
         assert_eq!(sum.0, 0);
     }
@@ -378,7 +393,7 @@ mod tests {
         .unwrap();
 
         for i in 0..MAX_SUPPORTED_CPUS as u8 {
-            setup_mptable(MPTABLE_START, &mem, i).unwrap();
+            setup_mptable(MPTABLE_START, &mem, i, None).unwrap();
 
             let mpf_intel: MpfIntelWrapper = mem.read_obj(MPTABLE_START).unwrap();
             let mpc_offset = GuestAddress(mpf_intel.0.physptr as GuestUsize);
@@ -411,7 +426,7 @@ mod tests {
         let mem =
             GuestMemoryMmap::from_ranges(&[(MPTABLE_START, compute_mp_size(cpus as u8))]).unwrap();
 
-        let result = setup_mptable(MPTABLE_START, &mem, cpus as u8);
+        let result = setup_mptable(MPTABLE_START, &mem, cpus as u8, None);
         assert!(result.is_err());
     }
 }

block/Cargo.toml

@@ -10,18 +10,18 @@ io_uring = ["dep:io-uring"]
 
 [dependencies]
 byteorder = "1.4.3"
-crc32c = "0.6.4"
-io-uring = { version = "0.6.1", optional = true }
-libc = "0.2.147"
-log = "0.4.17"
+crc-any = "2.4.4"
+io-uring = { version = "0.6.2", optional = true }
+libc = "0.2.153"
+log = "0.4.20"
 remain = "0.2.11"
-smallvec = "1.11.0"
-thiserror = "1.0.40"
+smallvec = "1.13.1"
+thiserror = "1.0.52"
 uuid = { version = "1.3.4", features = ["v4"] }
-versionize = "0.1.10"
-versionize_derive = "0.1.4"
+versionize = "0.2.0"
+versionize_derive = "0.1.6"
 virtio-bindings = { version = "0.2.0", features = ["virtio-v5_0_0"] }
-virtio-queue = "0.9.0"
-vm-memory = { version = "0.12.2", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+virtio-queue = "0.11.0"
+vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-virtio = { path = "../vm-virtio" }
-vmm-sys-util = "0.11.0"
+vmm-sys-util = "0.12.1"

block/src/lib.rs

@@ -24,6 +24,7 @@ pub mod qcow_sync;
 ///
 /// Enabled with the `"io_uring"` feature
 pub mod raw_async;
+pub mod raw_async_aio;
 pub mod raw_sync;
 pub mod vhd;
 pub mod vhdx;
@@ -61,6 +62,7 @@ use vm_memory::{
     GuestMemoryError, GuestMemoryLoadGuard,
 };
 use vm_virtio::{AccessPlatform, Translatable};
+use vmm_sys_util::aio;
 use vmm_sys_util::eventfd::EventFd;
 use vmm_sys_util::{ioctl_io_nr, ioctl_ioc_nr};
 
@@ -141,10 +143,14 @@ pub enum ExecuteError {
     Flush(io::Error),
     #[error("Failed to read: {0}")]
     Read(GuestMemoryError),
+    #[error("Failed to read_exact: {0}")]
+    ReadExact(io::Error),
     #[error("Failed to seek: {0}")]
     Seek(io::Error),
     #[error("Failed to write: {0}")]
     Write(GuestMemoryError),
+    #[error("Failed to write_all: {0}")]
+    WriteAll(io::Error),
     #[error("Unsupported request: {0}")]
     Unsupported(u32),
     #[error("Failed to submit io uring: {0}")]
@@ -167,8 +173,10 @@ impl ExecuteError {
             ExecuteError::BadRequest(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Flush(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Read(_) => VIRTIO_BLK_S_IOERR,
+            ExecuteError::ReadExact(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Seek(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Write(_) => VIRTIO_BLK_S_IOERR,
+            ExecuteError::WriteAll(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::Unsupported(_) => VIRTIO_BLK_S_UNSUPP,
             ExecuteError::SubmitIoUring(_) => VIRTIO_BLK_S_IOERR,
             ExecuteError::GetHostAddress(_) => VIRTIO_BLK_S_IOERR,
@@ -349,13 +357,21 @@ impl Request {
 
             match self.request_type {
                 RequestType::In => {
-                    mem.read_exact_from(*data_addr, disk, *data_len as usize)
-                        .map_err(ExecuteError::Read)?;
+                    let mut buf = vec![0u8; *data_len as usize];
+                    disk.read_exact(&mut buf).map_err(ExecuteError::ReadExact)?;
+                    mem.read_exact_volatile_from(
+                        *data_addr,
+                        &mut buf.as_slice(),
+                        *data_len as usize,
+                    )
+                    .map_err(ExecuteError::Read)?;
                     len += data_len;
                 }
                 RequestType::Out => {
-                    mem.write_all_to(*data_addr, disk, *data_len as usize)
+                    let mut buf: Vec<u8> = Vec::new();
+                    mem.write_all_volatile_to(*data_addr, &mut buf, *data_len as usize)
                         .map_err(ExecuteError::Write)?;
+                    disk.write_all(&buf).map_err(ExecuteError::WriteAll)?;
                     if !self.writeback {
                         disk.flush().map_err(ExecuteError::Flush)?;
                     }
@@ -565,6 +581,11 @@ unsafe impl ByteValued for VirtioBlockConfig {}
 // SAFETY: data structure only contain a series of integers
 unsafe impl ByteValued for VirtioBlockGeometry {}
 
+/// Check if aio can be used on the current system.
+pub fn block_aio_is_supported() -> bool {
+    aio::IoContext::new(1).is_ok()
+}
+
 /// Check if io_uring for block device can be used on the current system, as
 /// it correctly supports the expected io_uring features.
 pub fn block_io_uring_is_supported() -> bool {

block/src/qcow/vec_cache.rs

@@ -136,7 +136,7 @@ impl<T: Cacheable> CacheMap<T> {
 mod tests {
     use super::*;
 
-    struct NumCache(pub u64);
+    struct NumCache(());
     impl Cacheable for NumCache {
         fn dirty(&self) -> bool {
             true
@@ -148,28 +148,28 @@ mod tests {
         let mut cache = CacheMap::<NumCache>::new(3);
         let mut evicted = None;
         cache
-            .insert(0, NumCache(5), |index, _| {
+            .insert(0, NumCache(()), |index, _| {
                 evicted = Some(index);
                 Ok(())
             })
             .unwrap();
         assert_eq!(evicted, None);
         cache
-            .insert(1, NumCache(6), |index, _| {
+            .insert(1, NumCache(()), |index, _| {
                 evicted = Some(index);
                 Ok(())
             })
             .unwrap();
         assert_eq!(evicted, None);
         cache
-            .insert(2, NumCache(7), |index, _| {
+            .insert(2, NumCache(()), |index, _| {
                 evicted = Some(index);
                 Ok(())
             })
             .unwrap();
         assert_eq!(evicted, None);
         cache
-            .insert(3, NumCache(8), |index, _| {
+            .insert(3, NumCache(()), |index, _| {
                 evicted = Some(index);
                 Ok(())
             })

block/src/raw_async_aio.rs

@@ -0,0 +1,150 @@
+// Copyright © 2023 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
+//
+// Copyright © 2023 Crusoe Energy Systems LLC
+//
+
+use crate::async_io::{
+    AsyncIo, AsyncIoError, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult,
+};
+use crate::DiskTopology;
+use std::fs::File;
+use std::io::{Seek, SeekFrom};
+use std::os::unix::io::{AsRawFd, RawFd};
+use vmm_sys_util::aio;
+use vmm_sys_util::eventfd::EventFd;
+
+pub struct RawFileDiskAio {
+    file: File,
+}
+
+impl RawFileDiskAio {
+    pub fn new(file: File) -> Self {
+        RawFileDiskAio { file }
+    }
+}
+
+impl DiskFile for RawFileDiskAio {
+    fn size(&mut self) -> DiskFileResult<u64> {
+        self.file
+            .seek(SeekFrom::End(0))
+            .map_err(DiskFileError::Size)
+    }
+
+    fn new_async_io(&self, ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
+        Ok(Box::new(
+            RawFileAsyncAio::new(self.file.as_raw_fd(), ring_depth)
+                .map_err(DiskFileError::NewAsyncIo)?,
+        ) as Box<dyn AsyncIo>)
+    }
+
+    fn topology(&mut self) -> DiskTopology {
+        if let Ok(topology) = DiskTopology::probe(&self.file) {
+            topology
+        } else {
+            warn!("Unable to get device topology. Using default topology");
+            DiskTopology::default()
+        }
+    }
+}
+
+pub struct RawFileAsyncAio {
+    fd: RawFd,
+    ctx: aio::IoContext,
+    eventfd: EventFd,
+}
+
+impl RawFileAsyncAio {
+    pub fn new(fd: RawFd, queue_depth: u32) -> std::io::Result<Self> {
+        let eventfd = EventFd::new(libc::EFD_NONBLOCK)?;
+        let ctx = aio::IoContext::new(queue_depth)?;
+
+        Ok(RawFileAsyncAio { fd, ctx, eventfd })
+    }
+}
+
+impl AsyncIo for RawFileAsyncAio {
+    fn notifier(&self) -> &EventFd {
+        &self.eventfd
+    }
+
+    fn read_vectored(
+        &mut self,
+        offset: libc::off_t,
+        iovecs: &[libc::iovec],
+        user_data: u64,
+    ) -> AsyncIoResult<()> {
+        let iocbs = [&mut aio::IoControlBlock {
+            aio_fildes: self.fd.as_raw_fd() as u32,
+            aio_lio_opcode: aio::IOCB_CMD_PREADV as u16,
+            aio_buf: iovecs.as_ptr() as u64,
+            aio_nbytes: iovecs.len() as u64,
+            aio_offset: offset,
+            aio_data: user_data,
+            aio_flags: aio::IOCB_FLAG_RESFD,
+            aio_resfd: self.eventfd.as_raw_fd() as u32,
+            ..Default::default()
+        }];
+        let _ = self
+            .ctx
+            .submit(&iocbs[..])
+            .map_err(AsyncIoError::ReadVectored)?;
+
+        Ok(())
+    }
+
+    fn write_vectored(
+        &mut self,
+        offset: libc::off_t,
+        iovecs: &[libc::iovec],
+        user_data: u64,
+    ) -> AsyncIoResult<()> {
+        let iocbs = [&mut aio::IoControlBlock {
+            aio_fildes: self.fd.as_raw_fd() as u32,
+            aio_lio_opcode: aio::IOCB_CMD_PWRITEV as u16,
+            aio_buf: iovecs.as_ptr() as u64,
+            aio_nbytes: iovecs.len() as u64,
+            aio_offset: offset,
+            aio_data: user_data,
+            aio_flags: aio::IOCB_FLAG_RESFD,
+            aio_resfd: self.eventfd.as_raw_fd() as u32,
+            ..Default::default()
+        }];
+        let _ = self
+            .ctx
+            .submit(&iocbs[..])
+            .map_err(AsyncIoError::WriteVectored)?;
+
+        Ok(())
+    }
+
+    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
+        if let Some(user_data) = user_data {
+            let iocbs = [&mut aio::IoControlBlock {
+                aio_fildes: self.fd.as_raw_fd() as u32,
+                aio_lio_opcode: aio::IOCB_CMD_FSYNC as u16,
+                aio_data: user_data,
+                aio_flags: aio::IOCB_FLAG_RESFD,
+                aio_resfd: self.eventfd.as_raw_fd() as u32,
+                ..Default::default()
+            }];
+            let _ = self.ctx.submit(&iocbs[..]).map_err(AsyncIoError::Fsync)?;
+        } else {
+            // SAFETY: FFI call with a valid fd
+            unsafe { libc::fsync(self.fd) };
+        }
+
+        Ok(())
+    }
+
+    fn next_completed_request(&mut self) -> Option<(u64, i32)> {
+        let mut events: [aio::IoEvent; 1] = [aio::IoEvent::default()];
+        let rc = self.ctx.get_events(0, &mut events, None).unwrap();
+        if rc == 0 {
+            None
+        } else {
+            Some((events[0].data, events[0].res as i32))
+        }
+    }
+}

block/src/vhdx/vhdx_header.rs

@@ -192,7 +192,9 @@ impl Header {
         };
 
         new_header.get_header_as_buffer(&mut buffer);
-        new_header.checksum = crc32c::crc32c(&buffer);
+        let mut crc = crc_any::CRC::crc32c();
+        crc.digest(&buffer);
+        new_header.checksum = crc.get_crc() as u32;
         new_header.get_header_as_buffer(&mut buffer);
 
         f.seek(SeekFrom::Start(start))
@@ -351,12 +353,6 @@ impl RegionTableEntry {
     }
 }
 
-#[derive(Clone, Debug)]
-struct RegionEntry {
-    _start: u64,
-    _end: u64,
-}
-
 enum HeaderNo {
     First,
     Second,
@@ -480,7 +476,10 @@ pub fn calculate_checksum(buffer: &mut [u8], csum_offset: usize) -> Result<u32>
     // Zero the checksum in the buffer
     LittleEndian::write_u32(csum_buf, 0);
     // Calculate the checksum on the resulting buffer
-    let new_csum = crc32c::crc32c(buffer);
+    let mut crc = crc_any::CRC::crc32c();
+    crc.digest(&buffer);
+    let new_csum = crc.get_crc() as u32;
+
     // Put back the original checksum in the buffer
     LittleEndian::write_u32(&mut buffer[csum_offset..csum_offset + 4], orig_csum);
 

devices/Cargo.toml

@@ -6,24 +6,24 @@ edition = "2021"
 
 [dependencies]
 acpi_tables = { git = "https://github.com/rust-vmm/acpi_tables", branch = "main"  }
-anyhow = "1.0.75"
+anyhow = "1.0.79"
 arch = { path = "../arch" }
-bitflags = "2.3.3"
+bitflags = "2.4.1"
 byteorder = "1.4.3"
 event_monitor = { path = "../event_monitor" }
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.147"
-log = "0.4.17"
+libc = "0.2.153"
+log = "0.4.20"
 pci = { path = "../pci" }
-thiserror = "1.0.40"
+thiserror = "1.0.52"
 tpm = { path = "../tpm" }
-versionize = "0.1.10"
-versionize_derive = "0.1.4"
+versionize = "0.2.0"
+versionize_derive = "0.1.6"
 vm-allocator = { path = "../vm-allocator" }
 vm-device = { path = "../vm-device" }
-vm-memory = "0.12.2"
+vm-memory = "0.14.0"
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = "0.11.0"
+vmm-sys-util = "0.12.1"
 
 [target.'cfg(target_arch = "aarch64")'.dependencies]
 arch = { path = "../arch" }

devices/src/debug_console.rs

@@ -0,0 +1,64 @@
+// Copyright © 2023 Cyberus Technology
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+//! Module for [`DebugconState`].
+
+use std::io;
+use std::io::Write;
+use std::sync::{Arc, Barrier};
+use vm_device::BusDevice;
+use vm_migration::{Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable};
+
+/// I/O-port.
+pub const DEFAULT_PORT: u64 = 0xe9;
+
+#[derive(Default)]
+pub struct DebugconState {}
+
+/// Emulates a debug console similar to the QEMU debugcon device. This device
+/// is stateless and only prints the bytes (usually text) that are written to
+/// it.
+///
+/// This device is only available on x86.
+///
+/// Reference:
+/// - https://github.com/qemu/qemu/blob/master/hw/char/debugcon.c
+/// - https://phip1611.de/blog/how-to-use-qemus-debugcon-feature-and-write-to-a-file/
+pub struct DebugConsole {
+    id: String,
+    out: Box<dyn io::Write + Send>,
+}
+
+impl DebugConsole {
+    pub fn new(id: String, out: Box<dyn io::Write + Send>) -> Self {
+        Self { id, out }
+    }
+}
+
+impl BusDevice for DebugConsole {
+    fn read(&mut self, _base: u64, _offset: u64, _data: &mut [u8]) {}
+
+    fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+        if let Err(e) = self.out.write_all(data) {
+            // unlikely
+            error!("debug-console: failed writing data: {e:?}");
+        }
+        None
+    }
+}
+
+impl Snapshottable for DebugConsole {
+    fn id(&self) -> String {
+        self.id.clone()
+    }
+
+    fn snapshot(&mut self) -> Result<Snapshot, MigratableError> {
+        Snapshot::new_from_state(&())
+    }
+}
+
+impl Pausable for DebugConsole {}
+impl Transportable for DebugConsole {}
+impl Migratable for DebugConsole {}

devices/src/legacy/serial.rs

@@ -166,8 +166,8 @@ impl Serial {
         Self::new(id, interrupt, None, state)
     }
 
-    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
-        self.out = Some(out);
+    pub fn set_out(&mut self, out: Option<Box<dyn io::Write + Send>>) {
+        self.out = out;
     }
 
     /// Queues raw bytes for the guest to read and signals the interrupt if the line status would

devices/src/legacy/uart_pl011.rs

@@ -201,8 +201,8 @@ impl Pl011 {
         }
     }
 
-    pub fn set_out(&mut self, out: Box<dyn io::Write + Send>) {
-        self.out = Some(out);
+    pub fn set_out(&mut self, out: Option<Box<dyn io::Write + Send>>) {
+        self.out = out;
     }
 
     fn state(&self) -> Pl011State {

devices/src/lib.rs

@@ -15,6 +15,8 @@ extern crate event_monitor;
 extern crate log;
 
 pub mod acpi;
+#[cfg(target_arch = "x86_64")]
+pub mod debug_console;
 #[cfg(target_arch = "aarch64")]
 pub mod gic;
 pub mod interrupt_controller;

devices/src/pvpanic.rs

@@ -26,6 +26,7 @@ const PVPANIC_VENDOR_ID: u16 = 0x1b36;
 const PVPANIC_DEVICE_ID: u16 = 0x0011;
 
 pub const PVPANIC_DEVICE_MMIO_SIZE: u64 = 0x2;
+pub const PVPANIC_DEVICE_MMIO_ALIGNMENT: u64 = 0x10;
 
 const PVPANIC_PANICKED: u8 = 1 << 0;
 const PVPANIC_CRASH_LOADED: u8 = 1 << 1;
@@ -180,8 +181,9 @@ impl PciDevice for PvPanicDevice {
 
     fn allocate_bars(
         &mut self,
-        allocator: &Arc<Mutex<SystemAllocator>>,
-        _mmio_allocator: &mut AddressAllocator,
+        _allocator: &Arc<Mutex<SystemAllocator>>,
+        mmio32_allocator: &mut AddressAllocator,
+        _mmio64_allocator: &mut AddressAllocator,
         resources: Option<Vec<Resource>>,
     ) -> std::result::Result<Vec<PciBarConfiguration>, PciDeviceError> {
         let mut bars = Vec::new();
@@ -189,10 +191,8 @@ impl PciDevice for PvPanicDevice {
         let bar_id = 0;
         let region_size = PVPANIC_DEVICE_MMIO_SIZE;
         let restoring = resources.is_some();
-        let bar_addr = allocator
-            .lock()
-            .unwrap()
-            .allocate_mmio_hole_addresses(None, region_size, None)
+        let bar_addr = mmio32_allocator
+            .allocate(None, region_size, Some(PVPANIC_DEVICE_MMIO_ALIGNMENT))
             .ok_or(PciDeviceError::IoAllocationFailed(region_size))?;
 
         let bar = PciBarConfiguration::default()
@@ -217,11 +217,12 @@ impl PciDevice for PvPanicDevice {
 
     fn free_bars(
         &mut self,
-        allocator: &mut SystemAllocator,
-        _mmio_allocator: &mut AddressAllocator,
+        _allocator: &mut SystemAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        _mmio64_allocator: &mut AddressAllocator,
     ) -> std::result::Result<(), PciDeviceError> {
         for bar in self.bar_regions.drain(..) {
-            allocator.free_mmio_hole_addresses(GuestAddress(bar.addr()), bar.size());
+            mmio32_allocator.free(GuestAddress(bar.addr()), bar.size());
         }
 
         Ok(())

docs/amd_sev_snp.md

@@ -36,3 +36,5 @@ You can run a SEV-SNP VM using the following command:
      --memory size=1G \
      --disk path=ubuntu.img
 ```
+
+For more information related to Microsoft Hypervisor please see [mshv.md](mshv.md)

docs/api.md

@@ -147,7 +147,7 @@ We want to create a virtual machine with the following characteristics:
   `/opt/clh/images/focal-server-cloudimg-amd64.raw`
 
 ```shell
-#!/bin/bash
+#!/usr/bin/env bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i \
      -X PUT 'http://localhost/api/v1/vm.create'  \
@@ -167,7 +167,7 @@ curl --unix-socket /tmp/cloud-hypervisor.sock -i \
 Once the VM is created, we can boot it:
 
 ```shell
-#!/bin/bash
+#!/usr/bin/env bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1/vm.boot'
 ```
@@ -177,7 +177,7 @@ curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1
 We can fetch information about any VM, as soon as it's created:
 
 ```shell
-#!/bin/bash
+#!/usr/bin/env bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i \
      -X GET 'http://localhost/api/v1/vm.info' \
@@ -189,7 +189,7 @@ curl --unix-socket /tmp/cloud-hypervisor.sock -i \
 We can reboot a VM that's already booted:
 
 ```shell
-#!/bin/bash
+#!/usr/bin/env bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1/vm.reboot'
 ```
@@ -199,7 +199,7 @@ curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1
 Once booted, we can shut a VM down from the REST API:
 
 ```shell
-#!/bin/bash
+#!/usr/bin/env bash
 
 curl --unix-socket /tmp/cloud-hypervisor.sock -i -X PUT 'http://localhost/api/v1/vm.shutdown'
 ```
@@ -295,7 +295,7 @@ From the CLI, one can:
 The REST API, D-Bus API and the CLI all rely on a common, [internal API](#internal-api).
 
 The CLI options are parsed by the
-[argh crate](https://docs.rs/argh/latest/argh/) and then translated into
+[clap crate](https://docs.rs/clap/4.3.11/clap/) and then translated into
 [internal API](#internal-api) commands.
 
 The REST API is processed by an HTTP thread using the
@@ -327,7 +327,7 @@ As a summary, the REST API, the D-Bus API and the CLI are essentially frontends
                        |                                      |      +------------------------+
                        |            +----------+              |                 VMM
                        |     CLI    |          |              |
-                       +----------->+   argh   +--------------+
+                       +----------->+   clap   +--------------+
                                     |          |
                                     +----------+
 
@@ -385,7 +385,7 @@ APIs work together, let's look at a complete VM creation flow, from the
    [REST API](#rest-api) in order to creates a virtual machine:
    ```
    shell
-   #!/bin/bash
+   #!/usr/bin/env bash
 
 	curl --unix-socket /tmp/cloud-hypervisor.sock -i \
 		-X PUT 'http://localhost/api/v1/vm.create'  \

docs/balloon.md

@@ -54,7 +54,7 @@ Value is a boolean set to `off` by default.
 _Example_
 
 ```
---ballloon size=2G,deflate_on_oom=on
+--balloon size=2G,deflate_on_oom=on
 ```
 
 ### `free_page_reporting`
@@ -72,5 +72,5 @@ Value is a boolean set to `off` by default.
 _Example_
 
 ```
---ballloon size=0,free_page_reporting=on
+--balloon size=0,free_page_reporting=on
 ```

docs/coverage.md

@@ -0,0 +1,81 @@
+# Code coverage
+
+LLVM provides a set of tools to collect code coverage data and present the data
+in human-consumable forms.
+
+## Building a suitable binary
+
+The compiler flag to generate code coverage data has been stabilized since Rust
+1.60.
+
+An instrumented binary can be built with the following command:
+
+```shell
+cargo clean && RUSTFLAGS='-C instrument-coverage' cargo build
+```
+
+Using either `debug` or `release` profile is fine. You will need to adjust
+the path for some commands.
+
+## Running the binary
+
+Run the binary as you normally would. When the process exits, you will see
+files with the prefix `profraw`.
+
+Multiple runs of the same binary will produce multiple `profraw` files.
+
+The more diverse the runs are, the better. Try to exercise different features
+as much as possible.
+
+## Combining raw data
+
+Raw data files can be combined with `llvm-profdata`.
+
+```shell
+rustup component add llvm-tools-preview
+# Assuming profraw files reside in the current directory and its children directories
+find . -name '*.profraw' -exec llvm-profdata merge -sparse {} -o coverage.profdata \;
+```
+
+A file named `coverage.profdata` will be generated.
+
+## Generating HTML files for human consumption
+
+This can be done either with LLVM or `grcov`.
+
+Here is an example using grcov.
+
+```shell
+cargo install grcov
+# Assuming the profdata file is in the top level directory of the Cloud Hypervisor repository
+grcov . --binary-path ./target/x86_64-unknown-linux-gnu/release -s . -t html --branch --ignore-not-existing -o coverage-html-output/
+```
+
+You can then open the `index.html` file under coverage-html-output to see the
+results.
+
+## Notes on running the in-tree integration tests and unit tests
+
+Please set RUSTFLAGS the same way while invoking `dev_cli.sh`. The script will
+pass RUSTFLAGS to the container.
+
+Since the `profraw` files are generated from within the container, the file
+paths embedded in the data files are going to be different. It is easier to do
+the data processing from within the container if you don't want to fight the
+tool chain.
+
+```shell
+# Get a shell
+./scripts/dev_cli.sh shell
+
+# Install llvm-tools-preview for llvm-profdata
+rustup component add llvm-tools-preview
+# Merge data files by using the following command
+find . -name '*.profraw' -exec `rustc --print sysroot`/lib/rustlib/x86_64-unknown-linux-gnu/bin/llvm-profdata merge -sparse {} -o coverage.profdata \;
+
+# As of writing, the container has Rust 1.67.1. It is too old for grcov.
+rustup install stable
+cargo +stable install grcov
+# Run grcov as usual
+grcov . --binary-path ./target/x86_64-unknown-linux-gnu/release -s . -t html --branch --ignore-not-existing -o coverage-html-output/
+```

docs/debug-port.md

@@ -1,7 +1,16 @@
-# `cloud-hypervisor` debug IO port
+# `cloud-hypervisor` debug IO ports
 
-`cloud-hypervisor` uses the [`0x80`](https://www.intel.com/content/www/us/en/support/articles/000005500/boards-and-kits.html)
-I/O port to trace user defined guest events.
+When running x86 guests, `cloud-hypervisor` provides different kinds of debug ports:
+- [`0x80` debug port](https://www.intel.com/content/www/us/en/support/articles/000005500/boards-and-kits.html) 
+- Debug console (by default at `0xe9`). 
+- Firmware debug port at `0x402`.
+
+All of them can be used to trace user-defined guest events and all of them can
+be used simultaneously.
+
+## Debug Ports Overview
+
+### `0x80` I/O port
 
 Whenever the guest write one byte between `0x0` and `0xF` on this particular
 I/O port, `cloud-hypervisor` will log and timestamp that event at the `debug`
@@ -30,13 +39,13 @@ guest will have `cloud-hypervisor` generate timestamped logs of all those steps.
 That provides a basic but convenient way of measuring not only the overall guest
 boot time but all intermediate steps as well.
 
-## Logging
+#### Logging
 
 Assuming parts of the guest software stack have been instrumented to use the
 `cloud-hypervisor` debug I/O port, we may want to gather the related logs.
 
 To do so we need to start `cloud-hypervisor` with the right debug level
-(`-v -v -v`). It is also recommended to have it log into a dedicated file in order
+(`-vvv`). It is also recommended to have it log into a dedicated file in order
 to easily grep for the tracing logs (e.g.
 `--log-file /tmp/cloud-hypervisor.log`):
 
@@ -48,7 +57,7 @@ to easily grep for the tracing logs (e.g.
     --memory size=1024M \
     --rng \
     --log-file /tmp/ch-fw.log \
-    -v -v -v
+    -vvv
 ```
 
 After booting the guest, we then have to grep for the debug I/O port traces in
@@ -59,3 +68,29 @@ $ grep "Debug I/O port" /tmp/ch-fw.log
 cloud-hypervisor: 19.762449ms: DEBUG:vmm/src/vm.rs:510 -- [Debug I/O port: Firmware code 0x0] 0.019004 seconds
 cloud-hypervisor: 403.499628ms: DEBUG:vmm/src/vm.rs:510 -- [Debug I/O port: Firmware code 0x1] 0.402744 seconds
 ```
+
+### Debug console port
+
+The debug console is inspired by QEMU and Bochs, which have a similar feature. 
+By default, the I/O port `0xe9` is used. This port can be configured like a 
+console. Thus, it can print to a tty, a file, or a pty, for example.
+
+### Firmware debug port
+
+The firmware debug port is also a simple port that prints all bytes written to
+it. The firmware debug port only prints to stdout.
+
+## When do I need these ports?
+
+The ports are on the one hand interesting for firmware or kernel developers, as
+they provide an easy way to print debug information from within a guest. 
+Furthermore, you can patch "normal" software to measure certain events, such as
+the boot time of a guest.
+
+## Which port should I choose?
+
+The `0x80` debug port and the port of the firmware debug device are always
+available. The debug console must be activated via the command line, but
+provides more configuration options. 
+
+You can use different ports for different aspect of your logging messages. 

docs/gdb.md

@@ -8,7 +8,7 @@ To enable debugging with GDB, build with the `guest_debug` feature enabled:
 cargo build --features guest_debug
 ```
 
-To use the `--gdb` option, specify the Unix Domain Socket with `path` that Cloud Hypervisor will use to communicate with the host's GDB:
+To use the `--gdb` option, specify the Unix Domain Socket with `--path` that Cloud Hypervisor will use to communicate with the host's GDB:
 
 ```bash
 ./cloud-hypervisor \

docs/hotplug.md

@@ -27,16 +27,16 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask=" \
 	--rng \
-	--api-socket /tmp/ch-socket
+	--api-socket=/tmp/ch-socket
 $ popd
 ```
 
-Notice the addition of `--api-socket /tmp/ch-socket` and a `max` parameter on `--cpus boot=4,max=8`.
+Notice the addition of `--api-socket=/tmp/ch-socket` and a `max` parameter on `--cpus boot=4,max=8`.
 
 To ask the VMM to add additional vCPUs then use the resize API:
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket resize --cpus 8
+./ch-remote --api-socket=/tmp/ch-socket resize --cpus 8
 ```
 
 The extra vCPU threads will be created and advertised to the running kernel. The kernel does not bring up the CPUs immediately and instead the user must "online" them from inside the VM:
@@ -56,7 +56,7 @@ After a reboot the added CPUs will remain.
 Removing CPUs works similarly by reducing the number in the "desired_vcpus" field of the reisze API. The CPUs will be automatically offlined inside the guest so there is no need to run any commands inside the guest:
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket resize --cpus 2
+./ch-remote --api-socket=/tmp/ch-socket resize --cpus 2
 ```
 
 As per adding CPUs to the guest, after a reboot the VM will be running with the reduced number of vCPUs.
@@ -85,7 +85,7 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--memory size=1024M,hotplug_size=8192M \
 	--net "tap=,mac=,ip=,mask=" \
 	--rng \
-	--api-socket /tmp/ch-socket
+	--api-socket=/tmp/ch-socket
 $ popd
 ```
 
@@ -98,7 +98,7 @@ root@ch-guest ~ # echo online | sudo tee /sys/devices/system/memory/auto_online_
 To ask the VMM to expand the RAM for the VM:
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket resize --memory 3G
+./ch-remote --api-socket=/tmp/ch-socket resize --memory 3G
 ```
 
 The new memory is now available to use inside the VM:
@@ -134,14 +134,14 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--disk path=focal-server-cloudimg-amd64.raw \
 	--memory size=1024M,hotplug_size=8192M,hotplug_method=virtio-mem \
 	--net "tap=,mac=,ip=,mask=" \
-	--api-socket /tmp/ch-socket
+	--api-socket=/tmp/ch-socket
 $ popd
 ```
 
 To ask the VMM to expand the RAM for the VM (request is in bytes):
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket resize --memory 3G
+./ch-remote --api-socket=/tmp/ch-socket resize --memory 3G
 ```
 
 The new memory is now available to use inside the VM:
@@ -172,17 +172,17 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 	--cpus boot=4 \
 	--memory size=1024M \
 	--net "tap=,mac=,ip=,mask=" \
-	--api-socket /tmp/ch-socket
+	--api-socket=/tmp/ch-socket
 ```
 
-Notice the addition of `--api-socket /tmp/ch-socket`.
+Notice the addition of `--api-socket=/tmp/ch-socket`.
 
 ### Add VFIO Device
 
 To ask the VMM to add additional VFIO device then use the `add-device` API.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket add-device path=/sys/bus/pci/devices/0000:01:00.0/
+./ch-remote --api-socket=/tmp/ch-socket add-device path=/sys/bus/pci/devices/0000:01:00.0/
 ```
 
 ### Add Disk Device
@@ -190,7 +190,7 @@ To ask the VMM to add additional VFIO device then use the `add-device` API.
 To ask the VMM to add additional disk device then use the `add-disk` API.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket add-disk path=/foo/bar/cloud.img
+./ch-remote --api-socket=/tmp/ch-socket add-disk path=/foo/bar/cloud.img
 ```
 
 ### Add Fs Device
@@ -198,7 +198,7 @@ To ask the VMM to add additional disk device then use the `add-disk` API.
 To ask the VMM to add additional fs device then use the `add-fs` API.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket add-fs tag=myfs,socket=/foo/bar/virtiofs.sock
+./ch-remote --api-socket=/tmp/ch-socket add-fs tag=myfs,socket=/foo/bar/virtiofs.sock
 ```
 
 ### Add Net Device
@@ -206,7 +206,7 @@ To ask the VMM to add additional fs device then use the `add-fs` API.
 To ask the VMM to add additional network device then use the `add-net` API.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket add-net tap=chtap0
+./ch-remote --api-socket=/tmp/ch-socket add-net tap=chtap0
 ```
 
 ### Add Pmem Device
@@ -214,7 +214,7 @@ To ask the VMM to add additional network device then use the `add-net` API.
 To ask the VMM to add additional PMEM device then use the `add-pmem` API.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket add-pmem file=/foo/bar.cloud.img
+./ch-remote --api-socket=/tmp/ch-socket add-pmem file=/foo/bar.cloud.img
 ```
 
 ### Add Vsock Device
@@ -222,7 +222,7 @@ To ask the VMM to add additional PMEM device then use the `add-pmem` API.
 To ask the VMM to add additional vsock device then use the `add-vsock` API.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket add-vsock cid=3,socket=/foo/bar/vsock.sock
+./ch-remote --api-socket=/tmp/ch-socket add-vsock cid=3,socket=/foo/bar/vsock.sock
 ```
 
 ### Common Across All PCI Devices
@@ -244,7 +244,7 @@ After a reboot the added PCI device will remain.
 Removing a PCI device works the same way for all kind of PCI devices. The unique identifier related to the device must be provided. This identifier can be provided by the user when adding the new device, or by default Cloud Hypervisor will assign one.
 
 ```shell
-./ch-remote --api-socket /tmp/ch-socket remove-device _disk0
+./ch-remote --api-socket=/tmp/ch-socket remove-device _disk0
 ```
 
 As per adding a PCI device to the guest, after a reboot the VM will be running without the removed PCI device.

docs/intel_tdx.md

@@ -103,7 +103,7 @@ firmware:
 ### TDShim
 
 > **Note**
-> The latest version of TDShim being tested is [_66bb334_](https://github.com/confidential-containers/td-shim/tree/66bb33451befbf1291abe3cfea7ee9e99d922b0d).
+> The latest version of TDShim being tested is [_v0.8.0_](https://github.com/confidential-containers/td-shim/releases/tag/v0.8.0).
 
 This is a lightweight version of the TDVF, written in Rust and designed for
 direct kernel boot, which is useful for containers use cases.
@@ -113,7 +113,7 @@ and `LLVM` first. The TDshim can be build as follows:
 ```bash
 git clone https://github.com/confidential-containers/td-shim
 cd td-shim
-git checkout 66bb33451befbf1291abe3cfea7ee9e99d922b0d
+git checkout v0.8.0
 cargo install cargo-xbuild
 export CC=clang
 export AR=llvm-ar
@@ -121,15 +121,13 @@ export CC_x86_64_unknown_none=clang
 export AR_x86_64_unknown_none=llvm-ar
 git submodule update --init --recursive
 ./sh_script/preparation.sh
-cargo xbuild -p td-shim --target x86_64-unknown-none --release --features=main,tdx
-cargo run -p td-shim-tools --bin td-shim-ld --features=linker -- target/x86_64-unknown-none/release/ResetVector.bin target/x86_64-unknown-none/release/td-shim -o target/release/final.bin
+cargo image --release
 ```
 
 If debug logs from the TDShim is needed, here are the alternative
 commands:
 ```bash
-cargo xbuild -p td-shim --target x86_64-unknown-none --features=main,tdx
-cargo run -p td-shim-tools --bin td-shim-ld --features=linker -- target/x86_64-unknown-none/debug/ResetVector.bin target/x86_64-unknown-none/debug/td-shim -o target/debug/final.bin
+cargo image
 ```
 
 And run a TDX VM by providing the firmware previously built, along with a guest

docs/io_throttling.md

@@ -42,3 +42,14 @@ actual rate limit users get can be as low as
 generally advisable to keep `bw/ops_refill_time` larger than `100 ms`
 (`cool_down_time`) to make sure the actual rate limit is close to users'
 expectation ("refill-rate").
+
+## Rate Limit Groups
+It is possible to throttle the aggregate bandwidth or operations
+of multiple virtio-blk devices using a `rate_limit_group`. virtio-blk devices may be
+dynamically added and removed from a `rate_limit_group`. The following example
+demonstrates how to throttle the aggregate bandwidth of two disks to 10 MiB/s.
+```
+--disk path=disk0.raw,rate_limit_group=group0 \
+       path=disk1.raw,rate_limit_group=group0 \
+--rate-limit-group bw_size=1048576,bw_refill_time,bw_refill_time=100
+```

docs/iommu.md

@@ -60,10 +60,7 @@ implement a full emulation of a physical IOMMU.
 
 ### Kernel
 
-Since virtio-iommu has landed partially into the version 5.3 of the Linux
-kernel, a special branch is needed to get things working with Cloud Hypervisor.
-By partially, we are talking about x86 specifically, as it is already fully
-functional for ARM architectures.
+As of Kernel 5.14, virtio-iommu is available for both X86-64 and Aarch64.
 
 ## Usage
 
@@ -245,7 +242,7 @@ e.g.
 
 ```bash
 ./cloud-hypervisor \
-    --api-socket /tmp/api \
+    --api-socket=/tmp/api \
     --cpus boot=1 \
     --memory size=4G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
@@ -260,7 +257,7 @@ requiring the IOMMU then may be hotplugged:
 e.g.
 
 ```bash
-./ch-remote --api-socket /tmp/api add-device path=/sys/bus/pci/devices/0000:00:04.0,iommu=on,pci_segment=1
+./ch-remote --api-socket=/tmp/api add-device path=/sys/bus/pci/devices/0000:00:04.0,iommu=on,pci_segment=1
 ```
 
 Devices that cannot be placed behind an IOMMU (e.g. lacking an `iommu=` option)

docs/live_migration.md

@@ -16,22 +16,22 @@ $ target/release/cloud-hypervisor
     --disk path=~/workloads/focal.raw \
     --cpus boot=1 --memory size=1G,shared=on \
     --cmdline "root=/dev/vda1 console=ttyS0"  \
-    --serial tty --console off --api-socket /tmp/api1
+    --serial tty --console off --api-socket=/tmp/api1
 ```
 
 Launch the destination VM from the same directory (on the host machine):
 ```bash
-$ target/release/cloud-hypervisor --api-socket /tmp/api2
+$ target/release/cloud-hypervisor --api-socket=/tmp/api2
 ```
 
 Get ready for receiving migration for the destination VM (on the host machine):
 ```bash
-$ target/release/ch-remote --api-socket /tmp/api2 receive-migration unix:/tmp/sock
+$ target/release/ch-remote --api-socket=/tmp/api2 receive-migration unix:/tmp/sock
 ```
 
 Start to send migration for the source VM (on the host machine):
 ```bash
-$ target/release/ch-remote --api-socket /tmp/api1 send-migration --local unix:/tmp/sock
+$ target/release/ch-remote --api-socket=/tmp/api1 send-migration --local unix:/tmp/sock
 ```
 
 When the above commands completed, the source VM should be successfully
@@ -51,7 +51,7 @@ $ sudo /target/release/cloud-hypervisor \
         --cpus boot=1 --memory size=512M \
         --kernel vmlinux \
         --cmdline "root=/dev/vda1 console=ttyS0"  \
-        --disk path=focal-1.raw path=focal-nested.raw --disk path=tmp.img\
+        --disk path=focal-1.raw path=focal-nested.raw path=tmp.img\
         --net ip=192.168.101.1
 ```
 
@@ -63,7 +63,7 @@ $ sudo /target/release/cloud-hypervisor \
         --cpus boot=1 --memory size=512M \
         --kernel vmlinux \
         --cmdline "root=/dev/vda1 console=ttyS0"  \
-        --disk path=focal-2.raw path=focal-nested.raw --disk path=tmp.img\
+        --disk path=focal-2.raw path=focal-nested.raw path=tmp.img\
         --net ip=192.168.102.1
 ```
 
@@ -74,8 +74,8 @@ vm-1:~$ sudo ./cloud-hypervisor \
         --memory size=128M \
         --kernel vmlinux \
         --cmdline "console=ttyS0 root=/dev/vda1" \
-        --disk path=/dev/vdb --disk path=/dev/vdc \
-        --api-socket /tmp/api1 \
+        --disk path=/dev/vdb path=/dev/vdc \
+        --api-socket=/tmp/api1 \
         --net ip=192.168.100.1
 vm-1:~$ # setup the guest network if needed
 vm-1:~$ sudo ip addr add 192.168.101.2/24 dev ens4
@@ -108,7 +108,7 @@ echo "tmp = $tmp"
 
 Launch the nested destination VM (inside the guest OS of the VM 2):
 ```bash
-vm-2:~$ sudo ./cloud-hypervisor --api-socket /tmp/api2
+vm-2:~$ sudo ./cloud-hypervisor --api-socket=/tmp/api2
 vm-2:~$ # setup the guest network with the following commands if needed
 vm-2:~$ sudo ip addr add 192.168.102.2/24 dev ens4
 vm-2:~$ sudo ip link set up dev ens4
@@ -122,7 +122,7 @@ vm-2:~$ ping 192.168.101.2 # This should succeed
 Get ready for receiving migration for the nested destination VM (inside
 the guest OS of the VM 2):
 ```bash
-vm-2:~$ sudo ./ch-remote --api-socket /tmp/api2 receive-migration unix:/tmp/sock2
+vm-2:~$ sudo ./ch-remote --api-socket=/tmp/api2 receive-migration unix:/tmp/sock2
 vm-2:~$ sudo socat TCP-LISTEN:6000,reuseaddr UNIX-CLIENT:/tmp/sock2
 ```
 
@@ -130,7 +130,7 @@ Start to send migration for the nested source VM (inside the guest OS of
 the VM 1):
 ```bash
 vm-1:~$ sudo socat UNIX-LISTEN:/tmp/sock1,reuseaddr TCP:192.168.102.2:6000
-vm-1:~$ sudo ./ch-remote --api-socket /tmp/api1 send-migration unix:/tmp/sock1
+vm-1:~$ sudo ./ch-remote --api-socket=/tmp/api1 send-migration unix:/tmp/sock1
 ```
 
 When the above commands completed, the source VM should be successfully

docs/logging.md

@@ -38,6 +38,6 @@ This level is for the benefit of developers. It should be used for sporadic and
 
 ### `debug!()`
 
-Use `-v -v` to enable.
+Use `-vv` to enable.
 
-For the most verbose of logging messages. It is acceptable to "spam" the log with repeated invocations of the same message. This level of logging would be combined with `--log-file`.
+For the most verbose of logging messages. It is acceptable to "spam" the log with repeated invocations of the same message. This level of logging would be combined with `--log-file`.

docs/memory.md

@@ -516,7 +516,7 @@ different distances, it can be described with the following example.
 _Example_
 
 ```
---numa guest_numa_id=0,distances=[1@15,2@25] --numa guest_numa_id=1,distances=[0@15,2@20] guest_numa_id=2,distances=[0@25,1@20]
+--numa guest_numa_id=0,distances=[1@15,2@25] guest_numa_id=1,distances=[0@15,2@20] guest_numa_id=2,distances=[0@25,1@20]
 ```
 
 ### `memory_zones`
@@ -540,14 +540,14 @@ demarcate the list.
 
 Note that a memory zone must belong to a single NUMA node. The following
 configuration is incorrect, therefore not allowed:
-`--numa guest_numa_id=0,memory_zones=mem0 --numa guest_numa_id=1,memory_zones=mem0`
+`--numa guest_numa_id=0,memory_zones=mem0 guest_numa_id=1,memory_zones=mem0`
 
 _Example_
 
 ```
 --memory size=0
---memory-zone id=mem0,size=1G id=mem1,size=1G --memory-zone id=mem2,size=1G
---numa guest_numa_id=0,memory_zones=[mem0,mem2] --numa guest_numa_id=1,memory_zones=mem1
+--memory-zone id=mem0,size=1G id=mem1,size=1G id=mem2,size=1G
+--numa guest_numa_id=0,memory_zones=[mem0,mem2] guest_numa_id=1,memory_zones=mem1
 ```
 
 ### `sgx_epc_sections`
@@ -567,12 +567,21 @@ _Example_
 
 ```
 --sgx-epc id=epc0,size=32M id=epc1,size=64M id=epc2,size=32M
---numa guest_numa_id=0,sgx_epc_sections=epc1 --numa guest_numa_id=1,sgx_epc_sections=[epc0,epc2]
+--numa guest_numa_id=0,sgx_epc_sections=epc1 guest_numa_id=1,sgx_epc_sections=[epc0,epc2]
 ```
 
 ### PCI bus
 
-Cloud Hypervisor supports only one PCI bus, which is why it has been tied to
-the NUMA node 0 by default. It is the user responsibility to organize the NUMA
-nodes correctly so that vCPUs and guest RAM which should be located on the same
-NUMA node as the PCI bus end up on the NUMA node 0.
+Cloud Hypervisor supports guests with one or more PCI segments. The default PCI segment always
+has affinity to NUMA node 0. Be default, all other PCI segments have afffinity to NUMA node 0.
+The user may configure the NUMA affinity for any additional PCI segments.
+
+_Example_
+
+```
+--platform num_pci_segments=2
+--memory-zone size=16G,host_numa_node=0,id=mem0
+--memory-zone size=16G,host_numa_node=1,id=mem1
+--numa guest_numa_id=0,memory_zones=mem0,pci_segments=[0]
+--numa guest_numa_id=1,memory_zones=mem1,pci_segments=[1]
+```

docs/mshv.md

@@ -0,0 +1,48 @@
+# Microsoft Hypervisor
+
+The Microsoft Hypervisor is a Type 1 hypervisor which runs on x64 and ARM64 architectures. As the foundation of the Hyper-V virtualization stack, it runs millions of Linux and Windows guests in Azure and on-premises deployments. It supports nested virtualization, and security features like AMD's SEV-SNP. It also supports various features in Windows such as [Device guard and confidential guard](https://techcommunity.microsoft.com/t5/iis-support-blog/windows-10-device-guard-and-credential-guard-demystified/ba-p/376419), and [WSL2](https://docs.microsoft.com/en-us/windows/wsl/wsl2-faq)
+
+Since 2020, Microsoft has been releasing open-source components to support Linux running as root partition on the Microsoft Hypervisor.
+
+    1. Kernel patches to support Linux booting as root partition
+    2. A Linux kernel driver exposing an IOCTL interface for managing guest partitions, via a device node - /dev/mshv
+    3. Rust bindings and IOCTL wrappers
+    4. IGVM related crates
+
+## Components
+
+The following components are related to MSHV support with Cloud-Hypervisor:
+
+* [igvm-crates](https://github.com/microsoft/igvm) : Parsing IGVM file
+
+* [mshv-crates](https://github.com/rust-vmm/mshv) : Rust crates to interact with kernel module (/dev/mshv)
+
+* [igvm-tooling](https://github.com/microsoft/igvm-tooling) : Tool to generate IGVM file
+
+## IGVM
+
+Independent Guest Virtual Machine (IGVM) file format.The format specification can be found in the igvm_defs crate, with a Rust implementation of the binary format in the igvm crate.
+
+The IGVM file format is designed to encapsulate all information required to launch a virtual machine on any given virtualization stack, with support for different isolation technologies such as AMD SEV-SNP and Intel TDX.
+
+At a conceptual level, this file format is a set of commands created by the tool that generated the file, used by the loader to construct the initial guest state. The file format also contains measurement information that the underlying platform will use to confirm that the file was loaded correctly and signed by the appropriate authorities.
+
+Cloud Hypervisor can be built using igvm feature flag along with mshv and/or sev-snp. IGVM only works with MSHV.
+
+## SEV-SNP
+
+AMD's [Secure Encrypted Virtualization (SEV)](https://www.amd.com/en/developer/sev.html) and extensions such as Secure Nested Paging (SEV-SNP) encrypt memory and restrict access to a guest VM's memory and registers, securing it against a compromised hypervisor or VMM. They utilize the Platform Security Processor (PSP) to store keys and encrypt/decrypt the data. Microsoft has been continuously adding/improving support for SEV-SNP on Microsoft Hyper-V. Cloud-Hypervisor can be built with the sev_snp feature including mshv and igvm feature.
+
+## Use Cases
+
+Cloud Hypervisor can be built to run on an MSHV root partition by enabling the mshv feature, e.g.:
+
+```cargo build --locked --all --all-targets --no-default-features --tests --examples --features mshv```
+
+Cloud Hypervisor on MSHV can boot Linux guests using an IGVM file. IGVM feature depends on mshv for running legacy VMs.e.g.:
+
+```cargo build --locked --all --all-targets --no-default-features --tests --examples --features igvm```
+
+For running confidential VMs on mshv, you will only need to enable sev_snp, it requires and enables mshv and igvm automatically, eg.:
+
+```cargo build --locked --all --all-targets --no-default-features --tests --examples --features sev_snp```

docs/profiling.md

@@ -25,7 +25,7 @@ $ perf record -g target/profiling/cloud-hypervisor \
         --cpus boot=1 --memory size=1G \
         --cmdline "root=/dev/pmem0p1 console=ttyS0" \
         --serial tty --console off \
-        --api-socket /tmp/api1
+        --api-socket=/tmp/api1
 ```
 
 For analysing the samples:
@@ -52,5 +52,5 @@ $ perf record --call-graph lbr --all-user --user-callchains -g target/release/cl
         --cpus boot=1 --memory size=1G \
         --cmdline "root=/dev/pmem0p1 console=ttyS0" \
         --serial tty --console off \
-        --api-socket /tmp/api1
+        --api-socket=/tmp/api1
 ```

docs/snapshot_restore.md

@@ -25,14 +25,14 @@ First thing, we must run a Cloud Hypervisor VM:
 At any point in time when the VM is running, one might choose to pause it:
 
 ```bash
-./ch-remote --api-socket /tmp/cloud-hypervisor.sock pause
+./ch-remote --api-socket=/tmp/cloud-hypervisor.sock pause
 ```
 
 Once paused, the VM can be safely snapshot into the specified directory and
 using the following command:
 
 ```bash
-./ch-remote --api-socket /tmp/cloud-hypervisor.sock snapshot file:///home/foo/snapshot
+./ch-remote --api-socket=/tmp/cloud-hypervisor.sock snapshot file:///home/foo/snapshot
 ```
 
 Given the directory was present on the system, the snapshot will succeed and
@@ -79,7 +79,7 @@ Or using two different commands from two terminals:
 ./cloud-hypervisor --api-socket /tmp/cloud-hypervisor.sock
 
 # Second terminal
-./ch-remote --api-socket /tmp/cloud-hypervisor.sock restore source_url=file:///home/foo/snapshot
+./ch-remote --api-socket=/tmp/cloud-hypervisor.sock restore source_url=file:///home/foo/snapshot
 ```
 
 Remember the VM is restored in a `paused` state, which was the VM's state when
@@ -87,7 +87,7 @@ it was snapshot. For this reason, one must explicitly `resume` the VM before to
 start using it.
 
 ```bash
-./ch-remote --api-socket /tmp/cloud-hypervisor.sock resume
+./ch-remote --api-socket=/tmp/cloud-hypervisor.sock resume
 ```
 
 At this point, the VM is fully restored and is identical to the VM which was

docs/vhost-user-blk-testing.md

@@ -94,7 +94,7 @@ VMs run in client mode. They connect to the socket created by the `dpdkvhostuser
         --memory size=1024M,hugepages=on,shared=true \
         --kernel linux/arch/x86/boot/compressed/vmlinux.bin \
         --cmdline "console=ttyS0 root=/dev/vda1 rw iommu=off" \
-        --disk path=images/focal-server-cloudimg-amd64.raw --disk vhost_user=true,socket=/var/tmp/vhost.1,num_queues=4,queue_size=128 \
+        --disk path=images/focal-server-cloudimg-amd64.raw vhost_user=true,socket=/var/tmp/vhost.1,num_queues=4,queue_size=128 \
         --console off \
         --serial tty \
         --rng

docs/vhost-user-net-testing.md

@@ -2,8 +2,8 @@
 
 The purpose of this document is to illustrate how to test vhost-user-net
 in cloud-hypervisor with OVS/DPDK as the backend. This document was
-tested with Open vSwitch v2.13.1, DPDK v19.11.3, and Cloud Hypervisor
-v15.0 on Ubuntu 20.04.1 (host kernel v5.4.0).
+tested with Open vSwitch v2.17.8, DPDK v21.11.4, and Cloud Hypervisor
+v37.0 on Ubuntu 22.04.3 (host kernel v5.15.0).
 
 ## Framework
 
@@ -74,8 +74,8 @@ Here is an example how to create a bridge and add two DPDK ports to it
 # create a bridge
 ovs-vsctl add-br ovsbr0 -- set bridge ovsbr0 datapath_type=netdev
 # create two DPDK ports and add them to the bridge
-ovs-vsctl add-port ovsbr0 vhost-user1 -- set Interface vhost-user1 type=dpdkvhostuser
-ovs-vsctl add-port ovsbr0 vhost-user2 -- set Interface vhost-user2 type=dpdkvhostuser
+ovs-vsctl add-port ovsbr0 vhost-user1 -- set Interface vhost-user1 type=dpdkvhostuserclient options:vhost-server-path=/tmp/vhost-user1
+ovs-vsctl add-port ovsbr0 vhost-user2 -- set Interface vhost-user2 type=dpdkvhostuserclient options:vhost-server-path=/tmp/vhost-user2
 # set the number of rx queues
 ovs-vsctl set Interface vhost-user1 options:n_rxq=2
 ovs-vsctl set Interface vhost-user2 options:n_rxq=2
@@ -92,7 +92,7 @@ VMs run in client mode. They connect to the socket created by the `dpdkvhostuser
         --kernel vmlinux \
         --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
         --disk path=focal-server-cloudimg-amd64.raw   \
-        --net mac=52:54:00:02:d9:01,vhost_user=true,socket=/var/run/openvswitch/vhost-user1,num_queues=4
+        --net mac=52:54:00:02:d9:01,vhost_user=true,socket=/tmp/vhost-user1,num_queues=4,vhost_mode=server
 
 # From another terminal. We need to give the cloud-hypervisor binary the NET_ADMIN capabilities for it to set TAP interfaces up on the host.
 ./cloud-hypervisor \
@@ -101,21 +101,21 @@ VMs run in client mode. They connect to the socket created by the `dpdkvhostuser
         --kernel vmlinux \
         --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
         --disk path=focal-server-cloudimg-amd64.raw   \
-        --net mac=52:54:20:11:C5:02,vhost_user=true,socket=/var/run/openvswitch/vhost-user2,num_queues=4
+        --net mac=52:54:20:11:C5:02,vhost_user=true,socket=/tmp/vhost-user2,num_queues=4,vhost_mode=server
 ```
 
 _Setup VM1_
 ```bash
 # From inside the guest
-sudo ip addr add 172.100.0.1/24 dev ens2
-sudo ip link set up dev ens2
+sudo ip addr add 172.100.0.1/24 dev ens3
+sudo ip link set up dev ens3
 ```
 
 _Setup VM2_
 ```bash
 # From inside the guest
-sudo ip addr add 172.100.0.2/24 dev ens2
-sudo ip link set up dev ens2
+sudo ip addr add 172.100.0.2/24 dev ens3
+sudo ip link set up dev ens3
 ```
 
 _Ping VM1 from VM2_

docs/vsock.md

@@ -50,14 +50,14 @@ The examples use __socat__ `>=1.7.4` to illustrate the VSOCK functionality. Howe
 
 ### Connecting from Host to Guest
 
-The host starts to listen on the defined port:
+The guest starts to listen on the defined port:
 
 `$ socat - VSOCK-LISTEN:1234`
 
-Once the host is listening, the guest can send data:
+Once the guest is listening, the host can send data:
 
 `echo -e "CONNECT 1234\\nHello from host!" | socat - UNIX-CONNECT:/tmp/ch.vsock
- 
+
 Note the string `CONNECT <port>` prepended to the actual data. It is possible for the guest to start listening on different ports, thus the specific command is needed to instruct VSOCK to which listener the host wants to connect. It needs to be sent once per connection. Once the connection established, data transfers can take place directly.
 
 ### Connecting from Guest to Host

docs/windows.md

@@ -49,7 +49,7 @@ qemu-system-x86_64 \
 	-m 4G \
 	-bios ./$OVMF_DIR/OVMF_CODE.fd \
 	-cdrom ./$WIN_ISO_FILE \
-	-drive file=./$VIRTIO_ISO_FILE,index=0,media=cdrom
+	-drive file=./$VIRTIO_ISO_FILE,index=0,media=cdrom \
 	-drive if=none,id=root,file=./$IMG_FILE \
 	-device virtio-blk-pci,drive=root,disable-legacy=on \
 	-device virtio-net-pci,netdev=mynet0,disable-legacy=on \

event_monitor/Cargo.toml

@@ -6,7 +6,7 @@ edition = "2021"
 
 [dependencies]
 flume = "0.10.14"
-libc = "0.2.147"
-once_cell = "1.18.0"
-serde = { version = "1.0.168", features = ["rc", "derive"] }
-serde_json = "1.0.107"
+libc = "0.2.153"
+once_cell = "1.19.0"
+serde = { version = "1.0.196", features = ["rc", "derive"] }
+serde_json = "1.0.109"

fuzz/Cargo.lock

@@ -5,16 +5,64 @@ version = 3
 [[package]]
 name = "acpi_tables"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/acpi_tables?branch=main#1029d22777f07b04849234bbe756da34a6df2913"
+source = "git+https://github.com/rust-vmm/acpi_tables?branch=main#1a733bf690ccc10bdfeacad33e3c9f6cce0008fd"
 dependencies = [
  "zerocopy",
 ]
 
 [[package]]
-name = "anyhow"
-version = "1.0.75"
+name = "anstream"
+version = "0.6.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4668cab20f66d8d020e1fbc0ebe47217433c1b6c8f2040faf858554e394ace6"
+checksum = "6e2e1ebcb11de5c03c67de28a7df593d32191b44939c482e97702baaaa6ab6a5"
+dependencies = [
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8901269c6307e8d93993578286ac0edf7f195079ffff5ebdeea6a59ffb7e36bc"
+
+[[package]]
+name = "anstyle-parse"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c75ac65da39e5fe5ab759307499ddad880d724eed2f6ce5b5e8a26f4f387928c"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e28923312444cdd728e4738b3f9c9cac739500909bb3d3c94b43551b16517648"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "3.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1cd54b81ec8d6180e24654d0b371ad22fc3dd083b6ff8ba325b72e00c87660a7"
+dependencies = [
+ "anstyle",
+ "windows-sys",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.79"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "080e9890a082662b09c1ad45f567faeeb47f22b5fb23895fbe1e651e718e25ca"
 
 [[package]]
 name = "api_client"
@@ -25,9 +73,9 @@ dependencies = [
 
 [[package]]
 name = "arbitrary"
-version = "1.3.0"
+version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e2d098ff73c1ca148721f37baad5ea6a465a13f9573aba8641fbbbae8164a54e"
+checksum = "7d5a26814d8dcb93b0e5a0ff3c6d80a8843bafb21b39e8e18a6f05471870e110"
 
 [[package]]
 name = "arc-swap"
@@ -57,37 +105,6 @@ dependencies = [
  "vmm-sys-util",
 ]
 
-[[package]]
-name = "argh"
-version = "0.1.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7af5ba06967ff7214ce4c7419c7d185be7ecd6cc4965a8f6e1d8ce0398aad219"
-dependencies = [
- "argh_derive",
- "argh_shared",
-]
-
-[[package]]
-name = "argh_derive"
-version = "0.1.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "56df0aeedf6b7a2fc67d06db35b09684c3e8da0c95f8f27685cb17e08413d87a"
-dependencies = [
- "argh_shared",
- "proc-macro2",
- "quote",
- "syn 2.0.23",
-]
-
-[[package]]
-name = "argh_shared"
-version = "0.1.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5693f39141bda5760ecc4111ab08da40565d1771038c4a0250f03457ec707531"
-dependencies = [
- "serde",
-]
-
 [[package]]
 name = "autocfg"
 version = "1.1.0"
@@ -111,16 +128,16 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "bitflags"
-version = "2.3.3"
+version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "630be753d4e58660abd17930c71b647fe46c27ea6b63cc59e1e3851406972e42"
+checksum = "327762f6e5a765692301e5bb513e0d9fef63be86bbc14528052b1cd3e6f03e07"
 
 [[package]]
 name = "block"
 version = "0.1.0"
 dependencies = [
  "byteorder",
- "crc32c",
+ "crc-any",
  "io-uring",
  "libc",
  "log",
@@ -139,15 +156,15 @@ dependencies = [
 
 [[package]]
 name = "bumpalo"
-version = "3.13.0"
+version = "3.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a3e2c3daef883ecc1b5d58c15adae93470a91d425f3532ba1695849656af3fc1"
+checksum = "7f30e7476521f6f8af1a1c4c0b8cc94f0bee37d91763d0ca2665f299b6cd8aec"
 
 [[package]]
 name = "byteorder"
-version = "1.4.3"
+version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
+checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
 
 [[package]]
 name = "cc"
@@ -165,13 +182,40 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
+[[package]]
+name = "clap"
+version = "4.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "80c21025abd42669a92efc996ef13cfb2c5c627858421ea58d5c3b331a6c134f"
+dependencies = [
+ "clap_builder",
+]
+
+[[package]]
+name = "clap_builder"
+version = "4.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "458bf1f341769dfcf849846f65dffdf9146daa56bcd2a47cb4e1de9915567c99"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "clap_lex",
+ "strsim 0.11.0",
+]
+
+[[package]]
+name = "clap_lex"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "98cc8fbded0c607b7ba9dd60cd98df59af97e84d24e49c8557331cfc26d301ce"
+
 [[package]]
 name = "cloud-hypervisor"
-version = "34.0.0"
+version = "37.0.0"
 dependencies = [
  "anyhow",
  "api_client",
- "argh",
+ "clap",
  "epoll",
  "event_monitor",
  "hypervisor",
@@ -208,31 +252,38 @@ dependencies = [
  "virtio-queue",
  "vm-device",
  "vm-memory",
+ "vm-migration",
  "vm-virtio",
  "vmm",
  "vmm-sys-util",
 ]
 
 [[package]]
-name = "crc32c"
-version = "0.6.4"
+name = "colorchoice"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d8f48d60e5b4d2c53d5c2b1d8a58c849a70ae5e5509b08a48d047e3b65714a74"
+checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
+
+[[package]]
+name = "crc-any"
+version = "2.4.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c01a5e1f881f6fb6099a7bdf949e946719fd4f1fefa56264890574febf0eb6d0"
 dependencies = [
- "rustc_version",
+ "debug-helper",
 ]
 
 [[package]]
 name = "crc64"
-version = "1.0.0"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55626594feae15d266d52440b26ff77de0e22230cf0c113abe619084c1ddc910"
+checksum = "2707e3afba5e19b75d582d88bc79237418f2a2a2d673d01cf9b03633b46e98f3"
 
 [[package]]
 name = "darling"
-version = "0.20.3"
+version = "0.20.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0209d94da627ab5605dcccf08bb18afa5009cfbef48d8a8b7d7bdbc79be25c5e"
+checksum = "fc5d6b04b3fd0ba9926f945895de7d806260a2d7431ba82e7edaecb043c4c6b8"
 dependencies = [
  "darling_core",
  "darling_macro",
@@ -240,29 +291,35 @@ dependencies = [
 
 [[package]]
 name = "darling_core"
-version = "0.20.3"
+version = "0.20.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "177e3443818124b357d8e76f53be906d60937f0d3a90773a664fa63fa253e621"
+checksum = "04e48a959bcd5c761246f5d090ebc2fbf7b9cd527a492b07a67510c108f1e7e3"
 dependencies = [
  "fnv",
  "ident_case",
  "proc-macro2",
  "quote",
- "strsim",
- "syn 2.0.23",
+ "strsim 0.10.0",
+ "syn 2.0.47",
 ]
 
 [[package]]
 name = "darling_macro"
-version = "0.20.3"
+version = "0.20.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "836a9bbc7ad63342d6d6e7b815ccab164bc77a2d95d84bc3117a8c0d5c98e2d5"
+checksum = "1d1545d67a2149e1d93b7e5c7752dce5a7426eb5d1357ddcfd89336b94444f77"
 dependencies = [
  "darling_core",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
 ]
 
+[[package]]
+name = "debug-helper"
+version = "0.3.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f578e8e2c440e7297e008bb5486a3a8a194775224bbc23729b0dbdfaeebf162e"
+
 [[package]]
 name = "devices"
 version = "0.1.0"
@@ -270,7 +327,7 @@ dependencies = [
  "acpi_tables",
  "anyhow",
  "arch",
- "bitflags 2.3.3",
+ "bitflags 2.4.1",
  "byteorder",
  "event_monitor",
  "hypervisor",
@@ -294,7 +351,7 @@ version = "4.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "74351c3392ea1ff6cd2628e0042d268ac2371cb613252ff383b6dfa50d22fa79"
 dependencies = [
- "bitflags 2.3.3",
+ "bitflags 2.4.1",
  "libc",
 ]
 
@@ -336,21 +393,21 @@ checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
 [[package]]
 name = "futures-core"
-version = "0.3.28"
+version = "0.3.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4bca583b7e26f571124fe5b7561d49cb2868d79116cfa0eefce955557c6fee8c"
+checksum = "dfc6580bb841c5a68e9ef15c77ccc837b40a7504914d52e47b8b0e9bbda25a1d"
 
 [[package]]
 name = "futures-sink"
-version = "0.3.28"
+version = "0.3.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f43be4fe21a13b9781a69afa4985b0f6ee0e1afab2c6f454a8cf30e2b2237b6e"
+checksum = "9fb8e00e87438d937621c1c6269e53f536c14d3fbd6a042bb24879e57d474fb5"
 
 [[package]]
 name = "getrandom"
-version = "0.2.10"
+version = "0.2.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "be4136b2a15dd319360be1c07d9933517ccf0be8f16bf62a3bee4f0d618df427"
+checksum = "190092ea657667030ac6a35e305e62fc4dd69fd98ac98631e5d3a2b1575a12b5"
 dependencies = [
  "cfg-if",
  "js-sys",
@@ -385,9 +442,9 @@ checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
 
 [[package]]
 name = "io-uring"
-version = "0.6.2"
+version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "460648e47a07a43110fbfa2e0b14afb2be920093c31e5dccc50e49568e099762"
+checksum = "a9febecd4aebbe9c7c23c8e536e966805fdf09944c8a915e7991ee51acb67087"
 dependencies = [
  "bitflags 1.3.2",
  "libc",
@@ -395,32 +452,32 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.9"
+version = "1.0.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
+checksum = "b1a46d1a171d865aa5f83f92695765caa047a9b4cbae2cbf37dbd613a793fd4c"
 
 [[package]]
 name = "jobserver"
-version = "0.1.26"
+version = "0.1.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "936cfd212a0155903bcbc060e316fb6cc7cbf2e1907329391ebadc1fe0ce77c2"
+checksum = "ab46a6e9526ddef3ae7f787c06f0f2600639ba80ea3eade3d8e670a2230f51d6"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "js-sys"
-version = "0.3.64"
+version = "0.3.68"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c5f195fe497f702db0f318b07fdd68edb16955aed830df8363d837542f8f935a"
+checksum = "406cda4b368d531c842222cf9d2600a9a4acce8d29423695379c6868a143a9ee"
 dependencies = [
  "wasm-bindgen",
 ]
 
 [[package]]
 name = "kvm-bindings"
-version = "0.6.0"
-source = "git+https://github.com/cloud-hypervisor/kvm-bindings?branch=ch-v0.6.0-tdx#7d9ffb47e5b9b1989577258800a0f57c93f1445f"
+version = "0.7.0"
+source = "git+https://github.com/cloud-hypervisor/kvm-bindings?branch=ch-v0.7.0#2dcf85d4f8aa55befcaa996b699ddb18ec9ed059"
 dependencies = [
  "serde",
  "serde_derive",
@@ -429,10 +486,11 @@ dependencies = [
 
 [[package]]
 name = "kvm-ioctls"
-version = "0.13.0"
+version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b8f8dc9c1896e5f144ec5d07169bc29f39a047686d29585a91f30489abfaeb6b"
+checksum = "9002dff009755414f22b962ec6ae6980b07d6d8b06e5297b1062019d72bd6a8c"
 dependencies = [
+ "bitflags 2.4.1",
  "kvm-bindings",
  "libc",
  "vmm-sys-util",
@@ -440,9 +498,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.148"
+version = "0.2.153"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9cdc71e17332e86d2e1d38c1f99edcb6288ee11b815fb1a4b049eaa2114d369b"
+checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
 
 [[package]]
 name = "libfuzzer-sys"
@@ -457,18 +515,18 @@ dependencies = [
 
 [[package]]
 name = "linux-loader"
-version = "0.9.1"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1db6a725c8000971f83fa93ed7ee1b600e55a1471a2a653379d3c84f72effdcf"
+checksum = "eb68dd3452f25a8defaf0ae593509cff0c777683e4d8924f59ac7c5f89267a83"
 dependencies = [
  "vm-memory",
 ]
 
 [[package]]
 name = "lock_api"
-version = "0.4.10"
+version = "0.4.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c1cc9717a20b1bb222f333e6a92fd32f7d8a18ddc5a3191a11af45dcbf4dcd16"
+checksum = "3c168f8615b12bc01f9c17e2eb0cc07dcae1940121185446edc3744920e8ef45"
 dependencies = [
  "autocfg",
  "scopeguard",
@@ -483,7 +541,7 @@ checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
 [[package]]
 name = "micro_http"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#0d0fdcd50ea10c1b4777f9a958873fc848a5b7bb"
+source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#e75dfa1eeea23b69caa7407bc2c3a76d7b7262fb"
 dependencies = [
  "libc",
  "vmm-sys-util",
@@ -528,9 +586,9 @@ dependencies = [
 
 [[package]]
 name = "once_cell"
-version = "1.18.0"
+version = "1.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dd8b5dd2ae5ed71462c540258bedcb51965123ad7e7ccf4b9a8cafaa4a63576d"
+checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
 
 [[package]]
 name = "option_parser"
@@ -561,38 +619,38 @@ dependencies = [
 
 [[package]]
 name = "pin-project"
-version = "1.1.3"
+version = "1.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fda4ed1c6c173e3fc7a83629421152e01d7b1f9b7f65fb301e490e8cfc656422"
+checksum = "0302c4a0442c456bd56f841aee5c3bfd17967563f6fadc9ceb9f9c23cf3807e0"
 dependencies = [
  "pin-project-internal",
 ]
 
 [[package]]
 name = "pin-project-internal"
-version = "1.1.3"
+version = "1.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4359fd9c9171ec6e8c62926d6faaf553a8dc3f64e1507e76da7911b4f6a04405"
+checksum = "266c042b60c9c76b8d53061e52b2e0d1116abc57cefc8c5cd671619a56ac3690"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
 ]
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.66"
+version = "1.0.78"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "18fb31db3f9bddb2ea821cde30a9f70117e3f119938b5ee630b7403aa6e2ead9"
+checksum = "e2422ad645d89c99f8f3e6b88a9fdeca7fabeac836b1002371c4367c8f984aae"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.33"
+version = "1.0.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5267fca4496028628a95160fc423a33e8b2e6af8a5302579e322e4b520293cae"
+checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
 dependencies = [
  "proc-macro2",
 ]
@@ -601,36 +659,29 @@ dependencies = [
 name = "rate_limiter"
 version = "0.1.0"
 dependencies = [
+ "epoll",
  "libc",
  "log",
+ "thiserror",
  "vmm-sys-util",
 ]
 
 [[package]]
 name = "remain"
-version = "0.2.11"
+version = "0.2.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bce3a7139d2ee67d07538ee5dba997364fbc243e7e7143e96eb830c74bfaa082"
+checksum = "1ad5e011230cad274d0532460c5ab69828ea47ae75681b42a841663efffaf794"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.23",
-]
-
-[[package]]
-name = "rustc_version"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
-dependencies = [
- "semver",
+ "syn 2.0.47",
 ]
 
 [[package]]
 name = "ryu"
-version = "1.0.15"
+version = "1.0.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ad4cc8da4ef723ed60bced201181d83791ad433213d8c24efffda1eec85d741"
+checksum = "f98d2aa92eebf49b69786be48e4477826b256916e84a57ff2a4f21923b48eb4c"
 
 [[package]]
 name = "scopeguard"
@@ -640,44 +691,38 @@ checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
 [[package]]
 name = "seccompiler"
-version = "0.3.0"
+version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f6575e3c2b3a0fe2ef3e53855b6a8dead7c29f783da5e123d378c8c6a89017e"
+checksum = "345a3e4dddf721a478089d4697b83c6c0a8f5bf16086f6c13397e4534eb6e2e5"
 dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "semver"
-version = "1.0.18"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b0293b4b29daaf487284529cc2f5675b8e57c61f70167ba415a463651fd6a918"
-
 [[package]]
 name = "serde"
-version = "1.0.168"
+version = "1.0.196"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d614f89548720367ded108b3c843be93f3a341e22d5674ca0dd5cd57f34926af"
+checksum = "870026e60fa08c69f064aa766c10f10b1d62db9ccd4d0abb206472bee0ce3b32"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.168"
+version = "1.0.196"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d4fe589678c688e44177da4f27152ee2d190757271dc7f1d5b6b9f68d869d641"
+checksum = "33c85360c95e7d137454dc81d9a4ed2b8efd8fbe19cee57357b32b9771fccb67"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.107"
+version = "1.0.113"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b420ce6e3d8bd882e9b243c6eed35dbc9a6110c9769e74b584e0d68d1f20c65"
+checksum = "69801b70b1c3dac963ecb03a364ba0ceda9cf60c71cfe475e99864759c8b8a79"
 dependencies = [
  "itoa",
  "ryu",
@@ -686,9 +731,9 @@ dependencies = [
 
 [[package]]
 name = "serde_with"
-version = "3.3.0"
+version = "3.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ca3b16a3d82c4088f343b7480a93550b3eabe1a358569c2dfe38bbcead07237"
+checksum = "64cd236ccc1b7a29e7e2739f27c0b2dd199804abc4290e32f59f3b68d6405c23"
 dependencies = [
  "serde",
  "serde_with_macros",
@@ -696,14 +741,14 @@ dependencies = [
 
 [[package]]
 name = "serde_with_macros"
-version = "3.3.0"
+version = "3.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2e6be15c453eb305019bfa438b1593c731f36a289a7853f7707ee29e870b3b3c"
+checksum = "93634eb5f75a2323b16de4748022ac4297f9e76b6dced2be287a099f41b5e788"
 dependencies = [
  "darling",
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
 ]
 
 [[package]]
@@ -731,9 +776,9 @@ dependencies = [
 
 [[package]]
 name = "smallvec"
-version = "1.11.1"
+version = "1.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "942b4a808e05215192e39f4ab80813e599068285906cc91aa64f923db842bd5a"
+checksum = "e6ecd384b10a64542d77071bd64bd7b231f4ed5940fba55e98c3de13824cf3d7"
 
 [[package]]
 name = "spin"
@@ -750,6 +795,12 @@ version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
 
+[[package]]
+name = "strsim"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ee073c9e4cd00e28217186dbe12796d692868f432bf2e97ee73bed0c56dfa01"
+
 [[package]]
 name = "syn"
 version = "1.0.109"
@@ -763,9 +814,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.23"
+version = "2.0.47"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59fb7d6d8281a51045d62b8eb3a7d1ce347b76f312af50cd3dc0af39c87c1737"
+checksum = "1726efe18f42ae774cc644f330953a5e7b3c3003d3edcecf18850fe9d4dd9afb"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -774,22 +825,22 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "1.0.48"
+version = "1.0.56"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9d6d7a740b8a666a7e828dd00da9c0dc290dff53154ea77ac109281de90589b7"
+checksum = "d54378c645627613241d077a3a79db965db602882668f9136ac42af9ecb730ad"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.48"
+version = "1.0.56"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49922ecae66cc8a249b77e68d1d0623c1b2c514f0060c27cdc68bd62a1219d35"
+checksum = "fa0faa943b50f3db30a20aa7e265dbc66076993efed8463e8de414e5d06d3471"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
 ]
 
 [[package]]
@@ -823,19 +874,25 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
 
 [[package]]
-name = "uuid"
-version = "1.4.1"
+name = "utf8parse"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "79daa5ed5740825c40b389c5e50312b9c86df53fccd33f281df655642b43869d"
+checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
+
+[[package]]
+name = "uuid"
+version = "1.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f00cc9702ca12d3c81455259621e676d0f7251cec66a21e98fe2e9a37db93b2a"
 dependencies = [
  "getrandom",
 ]
 
 [[package]]
 name = "versionize"
-version = "0.1.10"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dca4b7062e7e6d685901e815c35f9671e059de97c1c0905eeff8592f3fff442f"
+checksum = "62929d59c7f6730b7298fcb363760550f4db6e353fbac4076d447d0e82799d6d"
 dependencies = [
  "bincode",
  "crc64",
@@ -850,8 +907,8 @@ dependencies = [
 
 [[package]]
 name = "versionize_derive"
-version = "0.1.4"
-source = "git+https://github.com/cloud-hypervisor/versionize_derive?branch=ch#e502b1d4aabab342386f0c53780d49f21a6a1df6"
+version = "0.1.6"
+source = "git+https://github.com/cloud-hypervisor/versionize_derive?branch=ch-0.1.6#7906da996152e2d0ab08f5526440683bf3ca7834"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -861,7 +918,7 @@ dependencies = [
 [[package]]
 name = "vfio-bindings"
 version = "0.4.0"
-source = "git+https://github.com/rust-vmm/vfio?branch=main#847b0aa504ac6367efe42ba7e96a2d050737d4f0"
+source = "git+https://github.com/rust-vmm/vfio?branch=main#0daff4d4c159e842cf18b8b90457a45032b2df5a"
 dependencies = [
  "vmm-sys-util",
 ]
@@ -869,7 +926,7 @@ dependencies = [
 [[package]]
 name = "vfio-ioctls"
 version = "0.2.0"
-source = "git+https://github.com/rust-vmm/vfio?branch=main#847b0aa504ac6367efe42ba7e96a2d050737d4f0"
+source = "git+https://github.com/rust-vmm/vfio?branch=main#0daff4d4c159e842cf18b8b90457a45032b2df5a"
 dependencies = [
  "byteorder",
  "kvm-bindings",
@@ -885,7 +942,7 @@ dependencies = [
 [[package]]
 name = "vfio_user"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vfio-user?branch=main#2d96b90a7279547356ad8f83aaa3115ad5497302"
+source = "git+https://github.com/rust-vmm/vfio-user?branch=main#a1f6e52829e069b6d698b2cfeecac742e4653186"
 dependencies = [
  "bitflags 1.3.2",
  "libc",
@@ -901,11 +958,11 @@ dependencies = [
 
 [[package]]
 name = "vhost"
-version = "0.8.1"
+version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61957aeb36daf0b00b87fff9c10dd28a161bd35ab157553d340d183b3d8756e6"
+checksum = "2b64e816d0d49769fbfaa1494eb77cc2a3ddc526ead05c7f922cb7d64106286f"
 dependencies = [
- "bitflags 1.3.2",
+ "bitflags 2.4.1",
  "libc",
  "vm-memory",
  "vmm-sys-util",
@@ -913,9 +970,9 @@ dependencies = [
 
 [[package]]
 name = "virtio-bindings"
-version = "0.2.1"
+version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c18d7b74098a946470ea265b5bacbbf877abc3373021388454de0d47735a5b98"
+checksum = "878bcb1b2812a10c30d53b0ed054999de3d98f25ece91fc173973f9c57aaae86"
 
 [[package]]
 name = "virtio-devices"
@@ -953,9 +1010,9 @@ dependencies = [
 
 [[package]]
 name = "virtio-queue"
-version = "0.9.0"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35aca00da06841bd99162c381ec65893cace23ca0fb89254302cfe4bec4c300f"
+checksum = "e3f69a13d6610db9312acbb438b0390362af905d37634a2106be70c0f734986d"
 dependencies = [
  "log",
  "virtio-bindings",
@@ -992,9 +1049,9 @@ source = "git+https://github.com/rust-vmm/vm-fdt?branch=main#c5a99ab71b130435927
 
 [[package]]
 name = "vm-memory"
-version = "0.12.2"
+version = "0.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9dc276f0d00c17b9aeb584da0f1e1c673df0d183cc2539e3636ec8cbc5eae99b"
+checksum = "74ffc42216c32c35f858fa4bfdcd9b61017dfd691e0240268fdc85dbf59e5459"
 dependencies = [
  "arc-swap",
  "libc",
@@ -1032,9 +1089,10 @@ dependencies = [
  "anyhow",
  "arc-swap",
  "arch",
- "bitflags 2.3.3",
+ "bitflags 2.4.1",
  "block",
  "cfg-if",
+ "clap",
  "devices",
  "epoll",
  "event_monitor",
@@ -1048,6 +1106,7 @@ dependencies = [
  "once_cell",
  "option_parser",
  "pci",
+ "rate_limiter",
  "seccompiler",
  "serde",
  "serde_json",
@@ -1073,9 +1132,9 @@ dependencies = [
 
 [[package]]
 name = "vmm-sys-util"
-version = "0.11.2"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48b7b084231214f7427041e4220d77dfe726897a6d41fddee450696e66ff2a29"
+checksum = "1d1435039746e20da4f8d507a72ee1b916f7b4b05af7a91c093d2c6561934ede"
 dependencies = [
  "bitflags 1.3.2",
  "libc",
@@ -1091,9 +1150,9 @@ checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.87"
+version = "0.2.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7706a72ab36d8cb1f80ffbf0e071533974a60d0a308d01a5d0375bf60499a342"
+checksum = "c1e124130aee3fb58c5bdd6b639a0509486b0338acaaae0c84a5124b0f588b7f"
 dependencies = [
  "cfg-if",
  "wasm-bindgen-macro",
@@ -1101,24 +1160,24 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-backend"
-version = "0.2.87"
+version = "0.2.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ef2b6d3c510e9625e5fe6f509ab07d66a760f0885d858736483c32ed7809abd"
+checksum = "c9e7e1900c352b609c8488ad12639a311045f40a35491fb69ba8c12f758af70b"
 dependencies = [
  "bumpalo",
  "log",
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.87"
+version = "0.2.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dee495e55982a3bd48105a7b947fd2a9b4a8ae3010041b9e0faab3f9cd028f1d"
+checksum = "b30af9e2d358182b5c7449424f017eba305ed32a7010509ede96cdc4696c46ed"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -1126,22 +1185,22 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.87"
+version = "0.2.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "54681b18a46765f095758388f2d0cf16eb8d4169b639ab575a8f5693af210c7b"
+checksum = "642f325be6301eb8107a83d12a8ac6c1e1c54345a7ef1a9261962dfefda09e66"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.87"
+version = "0.2.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ca6ad05a4870b2bf5fe995117d3728437bd27d7cd5f06f13c17443ef369775a1"
+checksum = "4f186bd2dcf04330886ce82d6f33dd75a7bfcf69ecf5763b89fcde53b6ac9838"
 
 [[package]]
 name = "winapi"
@@ -1166,10 +1225,76 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
 [[package]]
-name = "zerocopy"
-version = "0.6.4"
+name = "windows-sys"
+version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "20707b61725734c595e840fb3704378a0cd2b9c74cc9e6e20724838fc6a1e2f9"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a18201040b24831fbb9e4eb208f8892e1f50a37feb53cc7ff887feb8f50e7cd"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cb7764e35d4db8a7921e09562a0304bf2f93e0a51bfccee0bd0bb0b666b015ea"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbaa0368d4f1d2aaefc55b6fcfee13f41544ddf36801e793edbbfd7d7df075ef"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a28637cb1fa3560a16915793afb20081aba2c92ee8af57b4d5f28e4b3e7df313"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ffe5e8e31046ce6230cc7215707b816e339ff4d4d67c65dffa206fd0f7aa7b9a"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d6fa32db2bc4a2f5abeacf2b69f7992cd09dca97498da74a151a3132c26befd"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a657e1e9d3f514745a572a6846d3c7aa7dbe1658c056ed9c3344c4109a6949e"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dff9641d1cd4be8d1a070daf9e3773c5f67e78b4d9d42263020c057706765c04"
+
+[[package]]
+name = "zerocopy"
+version = "0.7.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74d4d3961e53fa4c9a25a8637fc2bfaf2595b3d3ae34875568a5cf64787716be"
 dependencies = [
  "byteorder",
  "zerocopy-derive",
@@ -1177,11 +1302,11 @@ dependencies = [
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.6.4"
+version = "0.7.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "56097d5b91d711293a42be9289403896b68654625021732067eac7a4ca388a1f"
+checksum = "9ce1b18ccd8e73a9321186f97e46f9f04b778851177567b1975109d26a08d2a6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.23",
+ "syn 2.0.47",
 ]

fuzz/Cargo.toml

@@ -8,22 +8,26 @@ edition = "2021"
 [package.metadata]
 cargo-fuzz = true
 
+[features]
+igvm = []
+
 [dependencies]
 block = { path = "../block" }
 devices = { path = "../devices" }
 epoll = "4.3.1"
-libc = "0.2.148"
+libc = "0.2.152"
 libfuzzer-sys = "0.4.7"
-linux-loader = { version = "0.9.1", features = ["elf", "bzimage", "pe"] }
+linux-loader = { version = "0.11.0", features = ["elf", "bzimage", "pe"] }
 micro_http = { git = "https://github.com/firecracker-microvm/micro-http", branch = "main" }
 net_util = { path = "../net_util" }
-once_cell = "1.18.0"
-seccompiler = "0.3.0"
+once_cell = "1.19.0"
+seccompiler = "0.4.0"
 virtio-devices = { path = "../virtio-devices" }
-virtio-queue = "0.9.0"
+virtio-queue = "0.11.0"
 vmm = { path = "../vmm" }
-vmm-sys-util = "0.11.2"
-vm-memory = "0.12.2"
+vmm-sys-util = "0.12.1"
+vm-memory = "0.14.0"
+vm-migration = { path = "../vm-migration" }
 vm-device = { path = "../vm-device" }
 vm-virtio = { path = "../vm-virtio" }
 
@@ -31,8 +35,8 @@ vm-virtio = { path = "../vm-virtio" }
 path = ".."
 
 [patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.6.0-tdx" }
-versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.7.0" }
+versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch-0.1.6" }
 
 # Prevent this from interfering with workspaces
 [workspace]

fuzz/fuzz_targets/block.rs

@@ -21,6 +21,7 @@ use virtio_devices::{Block, VirtioDevice, VirtioInterrupt, VirtioInterruptType};
 use virtio_queue::{Queue, QueueT};
 use vm_memory::{bitmap::AtomicBitmap, Bytes, GuestAddress, GuestMemoryAtomic};
 use vmm_sys_util::eventfd::{EventFd, EFD_NONBLOCK};
+use std::collections::BTreeMap;
 
 type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
 
@@ -49,6 +50,7 @@ fuzz_target!(|bytes| {
     let shm = memfd_create(&ffi::CString::new("fuzz").unwrap(), 0).unwrap();
     let disk_file: File = unsafe { File::from_raw_fd(shm) };
     let qcow_disk = Box::new(RawFileDiskSync::new(disk_file)) as Box<dyn DiskFile>;
+    let queue_affinity = BTreeMap::new();
     let mut block = Block::new(
         "tmp".to_owned(),
         qcow_disk,
@@ -62,6 +64,7 @@ fuzz_target!(|bytes| {
         None,
         EventFd::new(EFD_NONBLOCK).unwrap(),
         None,
+        queue_affinity,
     )
     .unwrap();
 

fuzz/fuzz_targets/cmos.rs

@@ -6,8 +6,6 @@
 use devices::legacy::Cmos;
 use libc::EFD_NONBLOCK;
 use libfuzzer_sys::fuzz_target;
-use std::sync::atomic::AtomicBool;
-use std::sync::Arc;
 use vm_device::BusDevice;
 use vmm_sys_util::eventfd::EventFd;
 

fuzz/fuzz_targets/http_api.rs

@@ -7,9 +7,18 @@ use libfuzzer_sys::fuzz_target;
 use micro_http::Request;
 use once_cell::sync::Lazy;
 use std::os::unix::io::AsRawFd;
+use std::path::PathBuf;
 use std::sync::mpsc::{channel, Receiver};
+use std::sync::{Arc, Mutex};
 use std::thread;
-use vmm::api::{http::*, ApiRequest, ApiResponsePayload};
+use vm_migration::MigratableError;
+use vmm::api::{
+    http::*, ApiRequest, RequestHandler, VmInfoResponse, VmReceiveMigrationData,
+    VmSendMigrationData, VmmPingResponse,
+};
+use vmm::config::RestoreConfig;
+use vmm::vm::{Error as VmError, VmState};
+use vmm::vm_config::*;
 use vmm::{EpollContext, EpollDispatch};
 use vmm_sys_util::eventfd::EventFd;
 
@@ -69,6 +78,203 @@ fn generate_request(bytes: &[u8]) -> Option<Request> {
     Request::try_from(&request, None).ok()
 }
 
+struct StubApiRequestHandler;
+
+impl RequestHandler for StubApiRequestHandler {
+    fn vm_create(&mut self, _: Arc<Mutex<VmConfig>>) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_boot(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_pause(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_resume(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_snapshot(&mut self, _: &str) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_restore(&mut self, _: RestoreConfig) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    #[cfg(all(target_arch = "x86_64", feature = "guest_debug"))]
+    fn vm_coredump(&mut self, _: &str) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_shutdown(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_reboot(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_info(&self) -> Result<VmInfoResponse, VmError> {
+        Ok(VmInfoResponse {
+            config: Arc::new(Mutex::new(VmConfig {
+                cpus: CpusConfig {
+                    boot_vcpus: 1,
+                    max_vcpus: 1,
+                    topology: None,
+                    kvm_hyperv: false,
+                    max_phys_bits: 46,
+                    affinity: None,
+                    features: CpuFeatures::default(),
+                },
+                memory: MemoryConfig {
+                    size: 536_870_912,
+                    mergeable: false,
+                    hotplug_method: HotplugMethod::Acpi,
+                    hotplug_size: None,
+                    hotplugged_size: None,
+                    shared: false,
+                    hugepages: false,
+                    hugepage_size: None,
+                    prefault: false,
+                    zones: None,
+                    thp: true,
+                },
+                payload: Some(PayloadConfig {
+                    kernel: Some(PathBuf::from("/path/to/kernel")),
+                    firmware: None,
+                    cmdline: None,
+                    initramfs: None,
+                    #[cfg(feature = "igvm")]
+                    igvm: None,
+                }),
+                rate_limit_groups: None,
+                disks: None,
+                net: None,
+                rng: RngConfig {
+                    src: PathBuf::from("/dev/urandom"),
+                    iommu: false,
+                },
+                balloon: None,
+                fs: None,
+                pmem: None,
+                serial: ConsoleConfig {
+                    file: None,
+                    mode: ConsoleOutputMode::Null,
+                    iommu: false,
+                    socket: None,
+                },
+                console: ConsoleConfig {
+                    file: None,
+                    mode: ConsoleOutputMode::Tty,
+                    iommu: false,
+                    socket: None,
+                },
+                #[cfg(target_arch = "x86_64")]
+                debug_console: DebugConsoleConfig::default(),
+                devices: None,
+                user_devices: None,
+                vdpa: None,
+                vsock: None,
+                pvpanic: false,
+                iommu: false,
+                #[cfg(target_arch = "x86_64")]
+                sgx_epc: None,
+                numa: None,
+                watchdog: false,
+                #[cfg(feature = "guest_debug")]
+                gdb: false,
+                platform: None,
+                tpm: None,
+                preserved_fds: None,
+            })),
+            state: VmState::Running,
+            memory_actual_size: 0,
+            device_tree: None,
+        })
+    }
+
+    fn vmm_ping(&self) -> VmmPingResponse {
+        VmmPingResponse {
+            build_version: String::new(),
+            version: String::new(),
+            pid: 0,
+            features: Vec::new(),
+        }
+    }
+
+    fn vm_delete(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vmm_shutdown(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_resize(&mut self, _: Option<u8>, _: Option<u64>, _: Option<u64>) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_resize_zone(&mut self, _: String, _: u64) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_add_device(&mut self, _: DeviceConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_add_user_device(&mut self, _: UserDeviceConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_remove_device(&mut self, _: String) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_add_disk(&mut self, _: DiskConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_add_fs(&mut self, _: FsConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_add_pmem(&mut self, _: PmemConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_add_net(&mut self, _: NetConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_add_vdpa(&mut self, _: VdpaConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_add_vsock(&mut self, _: VsockConfig) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_counters(&mut self) -> Result<Option<Vec<u8>>, VmError> {
+        Ok(None)
+    }
+
+    fn vm_power_button(&mut self) -> Result<(), VmError> {
+        Ok(())
+    }
+
+    fn vm_receive_migration(&mut self, _: VmReceiveMigrationData) -> Result<(), MigratableError> {
+        Ok(())
+    }
+
+    fn vm_send_migration(&mut self, _: VmSendMigrationData) -> Result<(), MigratableError> {
+        Ok(())
+    }
+}
+
 fn http_receiver_stub(exit_evt: EventFd, api_evt: EventFd, api_receiver: Receiver<ApiRequest>) {
     let mut epoll = EpollContext::new().unwrap();
     epoll.add_event(&exit_evt, EpollDispatch::Exit).unwrap();
@@ -98,89 +304,7 @@ fn http_receiver_stub(exit_evt: EventFd, api_evt: EventFd, api_receiver: Receive
             EpollDispatch::Api => {
                 for _ in 0..api_evt.read().unwrap() {
                     let api_request = api_receiver.recv().unwrap();
-                    match api_request {
-                        ApiRequest::VmCreate(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmDelete(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmBoot(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmShutdown(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmReboot(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmInfo(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmmPing(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmPause(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmResume(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmSnapshot(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmRestore(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmmShutdown(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmResize(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmResizeZone(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddDevice(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddUserDevice(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmRemoveDevice(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddDisk(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddFs(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddPmem(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddNet(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddVdpa(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmAddVsock(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmCounters(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmReceiveMigration(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmSendMigration(_, sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                        ApiRequest::VmPowerButton(sender) => {
-                            sender.send(Ok(ApiResponsePayload::Empty)).unwrap();
-                        }
-                    }
+                    api_request(&mut StubApiRequestHandler).unwrap();
                 }
             }
             _ => {

fuzz/fuzz_targets/linux_loader_cmdline.rs

@@ -23,6 +23,8 @@ fuzz_target!(|bytes| {
         kernel: None,
         cmdline: Some(String::from_utf8_lossy(&bytes).to_string()),
         initramfs: None,
+        #[cfg(feature = "igvm")]
+        igvm: None,
     };
     let kernel_cmdline = match vmm::vm::Vm::generate_cmdline(&payload_config) {
         Ok(cmdline) => cmdline,

hypervisor/Cargo.toml

@@ -8,30 +8,32 @@ license = "Apache-2.0 OR BSD-3-Clause"
 [features]
 kvm = ["kvm-ioctls", "kvm-bindings", "vfio-ioctls/kvm"]
 mshv = ["mshv-ioctls", "mshv-bindings", "vfio-ioctls/mshv", "iced-x86"]
-sev_snp = []
+sev_snp = ["igvm_parser", "igvm_defs"]
 tdx = []
 
 [dependencies]
-anyhow = "1.0.75"
+anyhow = "1.0.79"
 byteorder = "1.4.3"
-thiserror = "1.0.40"
-libc = "0.2.147"
-log = "0.4.17"
-kvm-ioctls = { version = "0.13.0", optional = true }
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.6.0-tdx", features = ["with-serde", "fam-wrappers"], optional  = true }
+igvm_defs = { git = "https://github.com/microsoft/igvm", branch = "main", package = "igvm_defs", optional  = true }
+igvm_parser = { git = "https://github.com/microsoft/igvm", branch = "main", package = "igvm", optional  = true }
+libc = "0.2.153"
+log = "0.4.20"
+kvm-ioctls = { version = "0.16.0", optional = true }
+kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.7.0", features = ["with-serde", "fam-wrappers"], optional  = true }
 mshv-bindings = { git = "https://github.com/rust-vmm/mshv", branch = "main", features = ["with-serde", "fam-wrappers"], optional  = true }
 mshv-ioctls = { git = "https://github.com/rust-vmm/mshv", branch = "main", optional  = true}
-serde = { version = "1.0.168", features = ["rc", "derive"] }
-serde_with = { version = "3.0.0", default-features = false, features = ["macros"] }
+serde = { version = "1.0.196", features = ["rc", "derive"] }
+serde_with = { version = "3.4.0", default-features = false, features = ["macros"] }
 vfio-ioctls = { git = "https://github.com/rust-vmm/vfio", branch = "main", default-features = false }
-vm-memory = { version = "0.12.2", features = ["backend-mmap", "backend-atomic"] }
-vmm-sys-util = { version = "0.11.0", features = ["with-serde"] }
+vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-atomic"] }
+vmm-sys-util = { version = "0.12.1", features = ["with-serde"] }
+thiserror = "1.0.52"
 
 [target.'cfg(target_arch = "x86_64")'.dependencies.iced-x86]
 optional = true
-version = "1.19.0"
+version = "1.20.0"
 default-features = false
 features = ["std", "decoder", "op_code_info", "instr_info", "fast_fmt"]
 
 [dev-dependencies]
-env_logger = "0.10.0"
+env_logger = "0.10.1"

hypervisor/src/arch/x86/mod.rs

@@ -311,3 +311,17 @@ pub struct MsrEntry {
     pub index: u32,
     pub data: u64,
 }
+
+#[serde_with::serde_as]
+#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
+pub struct XsaveState {
+    #[serde_as(as = "[_; 1024usize]")]
+    pub region: [u32; 1024usize],
+}
+
+impl Default for XsaveState {
+    fn default() -> Self {
+        // SAFETY: this is plain old data structure
+        unsafe { ::std::mem::zeroed() }
+    }
+}

hypervisor/src/cpu.rs

@@ -95,12 +95,12 @@ pub enum HypervisorCpuError {
     #[error("Failed to get Msr entries: {0}")]
     GetMsrEntries(#[source] anyhow::Error),
     ///
-    /// Setting MSR entries error
+    /// Setting multi-processing  state error
     ///
     #[error("Failed to set MP state: {0}")]
     SetMpState(#[source] anyhow::Error),
     ///
-    /// Getting Msr entries error
+    /// Getting multi-processing  state error
     ///
     #[error("Failed to get MP state: {0}")]
     GetMpState(#[source] anyhow::Error),
@@ -257,6 +257,27 @@ pub enum HypervisorCpuError {
     ///
     #[error("Failed to set TSC frequency: {0}")]
     SetTscKhz(#[source] anyhow::Error),
+    ///
+    /// Error reading value at given GPA
+    ///
+    #[error("Failed to read from GPA: {0}")]
+    GpaRead(#[source] anyhow::Error),
+    ///
+    /// Error writing value at given GPA
+    ///
+    #[error("Failed to write to GPA: {0}")]
+    GpaWrite(#[source] anyhow::Error),
+    ///
+    /// Error getting CPUID leaf
+    ///
+    #[error("Failed to get CPUID entries: {0}")]
+    GetCpuidVales(#[source] anyhow::Error),
+    ///
+    /// Setting SEV control register error
+    ///
+    #[cfg(feature = "sev_snp")]
+    #[error("Failed to set sev control register: {0}")]
+    SetSevControlRegister(#[source] anyhow::Error),
 }
 
 #[derive(Debug)]
@@ -467,4 +488,21 @@ pub trait Vcpu: Send + Sync {
     fn set_tsc_khz(&self, _freq: u32) -> Result<()> {
         Ok(())
     }
+    #[cfg(target_arch = "x86_64")]
+    ///
+    /// X86 specific call to retrieve cpuid leaf
+    ///
+    fn get_cpuid_values(
+        &self,
+        _function: u32,
+        _index: u32,
+        _xfem: u64,
+        _xss: u64,
+    ) -> Result<[u32; 4]> {
+        unimplemented!()
+    }
+    #[cfg(feature = "mshv")]
+    fn set_sev_control_register(&self, _reg: u64) -> Result<()> {
+        unimplemented!()
+    }
 }

hypervisor/src/kvm/mod.rs

@@ -47,7 +47,7 @@ use vmm_sys_util::eventfd::EventFd;
 pub mod x86_64;
 #[cfg(target_arch = "x86_64")]
 use crate::arch::x86::{
-    CpuIdEntry, FpuState, LapicState, MsrEntry, SpecialRegisters, StandardRegisters,
+    CpuIdEntry, FpuState, LapicState, MsrEntry, SpecialRegisters, StandardRegisters, XsaveState,
     NUM_IOAPIC_PINS,
 };
 #[cfg(target_arch = "x86_64")]
@@ -66,13 +66,11 @@ use kvm_bindings::{
 #[cfg(target_arch = "x86_64")]
 use x86_64::check_required_kvm_extensions;
 #[cfg(target_arch = "x86_64")]
-pub use x86_64::{CpuId, ExtendedControlRegisters, MsrEntries, VcpuKvmState, Xsave};
+pub use x86_64::{CpuId, ExtendedControlRegisters, MsrEntries, VcpuKvmState};
 // aarch64 dependencies
 #[cfg(target_arch = "aarch64")]
 pub mod aarch64;
 pub use kvm_bindings;
-#[cfg(feature = "tdx")]
-use kvm_bindings::KVMIO;
 pub use kvm_bindings::{
     kvm_clock_data, kvm_create_device, kvm_device_type_KVM_DEV_TYPE_VFIO, kvm_guest_debug,
     kvm_irq_routing, kvm_irq_routing_entry, kvm_mp_state, kvm_userspace_memory_region,
@@ -86,6 +84,8 @@ use kvm_bindings::{
     KVM_REG_ARM64_SYSREG_OP0_MASK, KVM_REG_ARM64_SYSREG_OP1_MASK, KVM_REG_ARM64_SYSREG_OP2_MASK,
     KVM_REG_ARM_CORE, KVM_REG_SIZE_U128, KVM_REG_SIZE_U32, KVM_REG_SIZE_U64,
 };
+#[cfg(feature = "tdx")]
+use kvm_bindings::{kvm_run__bindgen_ty_1, KVMIO};
 pub use kvm_ioctls;
 pub use kvm_ioctls::{Cap, Kvm};
 #[cfg(target_arch = "aarch64")]
@@ -169,6 +169,52 @@ pub struct TdxCapabilities {
     pub cpuid_configs: [TdxCpuidConfig; TDX_MAX_NR_CPUID_CONFIGS],
 }
 
+#[cfg(feature = "tdx")]
+#[derive(Copy, Clone)]
+pub struct KvmTdxExit {
+    pub type_: u32,
+    pub pad: u32,
+    pub u: KvmTdxExitU,
+}
+
+#[cfg(feature = "tdx")]
+#[repr(C)]
+#[derive(Copy, Clone)]
+pub union KvmTdxExitU {
+    pub vmcall: KvmTdxExitVmcall,
+}
+
+#[cfg(feature = "tdx")]
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone, PartialEq)]
+pub struct KvmTdxExitVmcall {
+    pub type_: u64,
+    pub subfunction: u64,
+    pub reg_mask: u64,
+    pub in_r12: u64,
+    pub in_r13: u64,
+    pub in_r14: u64,
+    pub in_r15: u64,
+    pub in_rbx: u64,
+    pub in_rdi: u64,
+    pub in_rsi: u64,
+    pub in_r8: u64,
+    pub in_r9: u64,
+    pub in_rdx: u64,
+    pub status_code: u64,
+    pub out_r11: u64,
+    pub out_r12: u64,
+    pub out_r13: u64,
+    pub out_r14: u64,
+    pub out_r15: u64,
+    pub out_rbx: u64,
+    pub out_rdi: u64,
+    pub out_rsi: u64,
+    pub out_r8: u64,
+    pub out_r9: u64,
+    pub out_rdx: u64,
+}
+
 impl From<kvm_userspace_memory_region> for UserMemoryRegion {
     fn from(region: kvm_userspace_memory_region) -> Self {
         let mut flags = USER_MEMORY_REGION_READ;
@@ -356,6 +402,7 @@ impl vm::Vm for KvmVm {
             .set_identity_map_address(address)
             .map_err(|e| vm::HypervisorVmError::SetIdentityMapAddress(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the address of the three-page region in the VM's address space.
@@ -365,6 +412,7 @@ impl vm::Vm for KvmVm {
             .set_tss_address(offset)
             .map_err(|e| vm::HypervisorVmError::SetTssAddress(e.into()))
     }
+
     ///
     /// Creates an in-kernel interrupt controller.
     ///
@@ -373,6 +421,7 @@ impl vm::Vm for KvmVm {
             .create_irq_chip()
             .map_err(|e| vm::HypervisorVmError::CreateIrq(e.into()))
     }
+
     ///
     /// Registers an event that will, when signaled, trigger the `gsi` IRQ.
     ///
@@ -381,6 +430,7 @@ impl vm::Vm for KvmVm {
             .register_irqfd(fd, gsi)
             .map_err(|e| vm::HypervisorVmError::RegisterIrqFd(e.into()))
     }
+
     ///
     /// Unregisters an event that will, when signaled, trigger the `gsi` IRQ.
     ///
@@ -389,6 +439,7 @@ impl vm::Vm for KvmVm {
             .unregister_irqfd(fd, gsi)
             .map_err(|e| vm::HypervisorVmError::UnregisterIrqFd(e.into()))
     }
+
     ///
     /// Creates a VcpuFd object from a vcpu RawFd.
     ///
@@ -411,6 +462,7 @@ impl vm::Vm for KvmVm {
         };
         Ok(Arc::new(vcpu))
     }
+
     #[cfg(target_arch = "aarch64")]
     ///
     /// Creates a virtual GIC device.
@@ -420,6 +472,7 @@ impl vm::Vm for KvmVm {
             .map_err(|e| vm::HypervisorVmError::CreateVgic(anyhow!("Vgic error {:?}", e)))?;
         Ok(Arc::new(Mutex::new(gic_device)))
     }
+
     ///
     /// Registers an event to be signaled whenever a certain address is written to.
     ///
@@ -447,6 +500,7 @@ impl vm::Vm for KvmVm {
                 .map_err(|e| vm::HypervisorVmError::RegisterIoEvent(e.into()))
         }
     }
+
     ///
     /// Unregisters an event from a certain address it has been previously registered to.
     ///
@@ -541,6 +595,7 @@ impl vm::Vm for KvmVm {
             .set_gsi_routing(&irq_routing[0])
             .map_err(|e| vm::HypervisorVmError::SetGsiRouting(e.into()))
     }
+
     ///
     /// Creates a memory region structure that can be used with {create/remove}_user_memory_region
     ///
@@ -567,6 +622,7 @@ impl vm::Vm for KvmVm {
         }
         .into()
     }
+
     ///
     /// Creates a guest physical memory region.
     ///
@@ -603,6 +659,7 @@ impl vm::Vm for KvmVm {
                 .map_err(|e| vm::HypervisorVmError::CreateUserMemory(e.into()))
         }
     }
+
     ///
     /// Removes a guest physical memory region.
     ///
@@ -621,6 +678,7 @@ impl vm::Vm for KvmVm {
                 .map_err(|e| vm::HypervisorVmError::RemoveUserMemory(e.into()))
         }
     }
+
     ///
     /// Returns the preferred CPU target type which can be emulated by KVM on underlying host.
     ///
@@ -630,6 +688,7 @@ impl vm::Vm for KvmVm {
             .get_preferred_target(kvi)
             .map_err(|e| vm::HypervisorVmError::GetPreferredTarget(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     fn enable_split_irq(&self) -> vm::Result<()> {
         // Create split irqchip
@@ -645,6 +704,7 @@ impl vm::Vm for KvmVm {
             .map_err(|e| vm::HypervisorVmError::EnableSplitIrq(e.into()))?;
         Ok(())
     }
+
     #[cfg(target_arch = "x86_64")]
     fn enable_sgx_attribute(&self, file: File) -> vm::Result<()> {
         let mut cap = kvm_enable_cap {
@@ -657,6 +717,7 @@ impl vm::Vm for KvmVm {
             .map_err(|e| vm::HypervisorVmError::EnableSgxAttribute(e.into()))?;
         Ok(())
     }
+
     /// Retrieve guest clock.
     #[cfg(target_arch = "x86_64")]
     fn get_clock(&self) -> vm::Result<ClockData> {
@@ -666,6 +727,7 @@ impl vm::Vm for KvmVm {
             .map_err(|e| vm::HypervisorVmError::GetClock(e.into()))?
             .into())
     }
+
     /// Set guest clock.
     #[cfg(target_arch = "x86_64")]
     fn set_clock(&self, data: &ClockData) -> vm::Result<()> {
@@ -674,6 +736,7 @@ impl vm::Vm for KvmVm {
             .set_clock(&data)
             .map_err(|e| vm::HypervisorVmError::SetClock(e.into()))
     }
+
     /// Create a device that is used for passthrough
     fn create_passthrough_device(&self) -> vm::Result<VfioDeviceFd> {
         let mut vfio_dev = kvm_create_device {
@@ -685,6 +748,7 @@ impl vm::Vm for KvmVm {
         self.create_device(&mut vfio_dev)
             .map_err(|e| vm::HypervisorVmError::CreatePassthroughDevice(e.into()))
     }
+
     ///
     /// Start logging dirty pages
     ///
@@ -826,6 +890,7 @@ impl vm::Vm for KvmVm {
         )
         .map_err(vm::HypervisorVmError::InitMemRegionTdx)
     }
+
     /// Downcast to the underlying KvmVm type
     fn as_any(&self) -> &dyn Any {
         self
@@ -892,7 +957,9 @@ pub enum KvmError {
     #[error("Capability missing: {0:?}")]
     CapabilityMissing(Cap),
 }
+
 pub type KvmResult<T> = result::Result<T, KvmError>;
+
 impl KvmHypervisor {
     /// Create a hypervisor based on Kvm
     #[allow(clippy::new_ret_no_self)]
@@ -906,6 +973,7 @@ impl KvmHypervisor {
 
         Ok(Arc::new(KvmHypervisor { kvm: kvm_obj }))
     }
+
     /// Check if the hypervisor is available
     pub fn is_available() -> hypervisor::Result<bool> {
         match std::fs::metadata("/dev/kvm") {
@@ -917,6 +985,7 @@ impl KvmHypervisor {
         }
     }
 }
+
 /// Implementation of Hypervisor trait for KVM
 ///
 /// # Examples
@@ -935,6 +1004,7 @@ impl hypervisor::Hypervisor for KvmHypervisor {
     fn hypervisor_type(&self) -> HypervisorType {
         HypervisorType::Kvm
     }
+
     /// Create a KVM vm object of a specific VM type and return the object as Vm trait object
     ///
     /// # Examples
@@ -1090,6 +1160,7 @@ impl hypervisor::Hypervisor for KvmHypervisor {
         self.kvm.get_max_vcpus().min(u32::MAX as usize) as u32
     }
 }
+
 /// Vcpu struct for KVM
 pub struct KvmVcpu {
     fd: VcpuFd,
@@ -1099,6 +1170,7 @@ pub struct KvmVcpu {
     #[cfg(target_arch = "x86_64")]
     hyperv_synic: AtomicBool,
 }
+
 /// Implementation of Vcpu trait for KVM
 ///
 /// # Examples
@@ -1123,6 +1195,7 @@ impl cpu::Vcpu for KvmVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetStandardRegs(e.into()))?
             .into())
     }
+
     ///
     /// Returns the vCPU general purpose registers.
     /// The `KVM_GET_REGS` ioctl is not available on AArch64, `KVM_GET_ONE_REG`
@@ -1137,71 +1210,64 @@ impl cpu::Vcpu for KvmVcpu {
         // These actually are the general-purpose registers of the Armv8-a
         // architecture (i.e x0-x30 if used as a 64bit register or w0-30 when used as a 32bit register).
         for i in 0..31 {
-            state.regs.regs[i] = self
-                .fd
-                .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-                .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-                .try_into()
-                .unwrap();
+            let mut bytes = [0_u8; 8];
+            self.fd
+                .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+                .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+            state.regs.regs[i] = u64::from_le_bytes(bytes);
             off += std::mem::size_of::<u64>();
         }
 
         // We are now entering the "Other register" section of the ARMv8-a architecture.
         // First one, stack pointer.
         let off = offset_of!(user_pt_regs, sp);
-        state.regs.sp = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 8];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.regs.sp = u64::from_le_bytes(bytes);
 
         // Second one, the program counter.
         let off = offset_of!(user_pt_regs, pc);
-        state.regs.pc = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 8];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.regs.pc = u64::from_le_bytes(bytes);
 
         // Next is the processor state.
         let off = offset_of!(user_pt_regs, pstate);
-        state.regs.pstate = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 8];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.regs.pstate = u64::from_le_bytes(bytes);
 
         // The stack pointer associated with EL1
         let off = offset_of!(kvm_regs, sp_el1);
-        state.sp_el1 = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 8];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.sp_el1 = u64::from_le_bytes(bytes);
 
         // Exception Link Register for EL1, when taking an exception to EL1, this register
         // holds the address to which to return afterwards.
         let off = offset_of!(kvm_regs, elr_el1);
-        state.elr_el1 = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 8];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.elr_el1 = u64::from_le_bytes(bytes);
 
         // Saved Program Status Registers, there are 5 of them used in the kernel.
         let mut off = offset_of!(kvm_regs, spsr);
         for i in 0..KVM_NR_SPSR as usize {
-            state.spsr[i] = self
-                .fd
-                .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off))
-                .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-                .try_into()
-                .unwrap();
+            let mut bytes = [0_u8; 8];
+            self.fd
+                .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, off), &mut bytes)
+                .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+            state.spsr[i] = u64::from_le_bytes(bytes);
             off += std::mem::size_of::<u64>();
         }
 
@@ -1209,32 +1275,32 @@ impl cpu::Vcpu for KvmVcpu {
         // https://elixir.free-electrons.com/linux/v4.9.62/source/arch/arm64/include/uapi/asm/kvm.h#L53
         let mut off = offset_of!(kvm_regs, fp_regs) + offset_of!(user_fpsimd_state, vregs);
         for i in 0..32 {
-            state.fp_regs.vregs[i] = self
-                .fd
-                .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U128, off))
+            let mut bytes = [0_u8; 16];
+            self.fd
+                .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U128, off), &mut bytes)
                 .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+            state.fp_regs.vregs[i] = u128::from_le_bytes(bytes);
             off += mem::size_of::<u128>();
         }
 
         // Floating-point Status Register
         let off = offset_of!(kvm_regs, fp_regs) + offset_of!(user_fpsimd_state, fpsr);
-        state.fp_regs.fpsr = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U32, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 4];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U32, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.fp_regs.fpsr = u32::from_le_bytes(bytes);
 
         // Floating-point Control Register
         let off = offset_of!(kvm_regs, fp_regs) + offset_of!(user_fpsimd_state, fpcr);
-        state.fp_regs.fpcr = self
-            .fd
-            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U32, off))
-            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?
-            .try_into()
-            .unwrap();
+        let mut bytes = [0_u8; 4];
+        self.fd
+            .get_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U32, off), &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetCoreRegister(e.into()))?;
+        state.fp_regs.fpcr = u32::from_le_bytes(bytes);
         Ok(state)
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the vCPU general purpose registers using the `KVM_SET_REGS` ioctl.
@@ -1260,7 +1326,7 @@ impl cpu::Vcpu for KvmVcpu {
             self.fd
                 .set_one_reg(
                     arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                    state.regs.regs[i].into(),
+                    &state.regs.regs[i].to_le_bytes(),
                 )
                 .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
             off += std::mem::size_of::<u64>();
@@ -1270,7 +1336,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                state.regs.sp.into(),
+                &state.regs.sp.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1278,7 +1344,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                state.regs.pc.into(),
+                &state.regs.pc.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1286,7 +1352,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                state.regs.pstate.into(),
+                &state.regs.pstate.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1294,7 +1360,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                state.sp_el1.into(),
+                &state.sp_el1.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1302,7 +1368,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                state.elr_el1.into(),
+                &state.elr_el1.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1311,7 +1377,7 @@ impl cpu::Vcpu for KvmVcpu {
             self.fd
                 .set_one_reg(
                     arm64_core_reg_id!(KVM_REG_SIZE_U64, off),
-                    state.spsr[i].into(),
+                    &state.spsr[i].to_le_bytes(),
                 )
                 .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
             off += std::mem::size_of::<u64>();
@@ -1322,7 +1388,7 @@ impl cpu::Vcpu for KvmVcpu {
             self.fd
                 .set_one_reg(
                     arm64_core_reg_id!(KVM_REG_SIZE_U128, off),
-                    state.fp_regs.vregs[i],
+                    &state.fp_regs.vregs[i].to_le_bytes(),
                 )
                 .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
             off += mem::size_of::<u128>();
@@ -1332,7 +1398,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U32, off),
-                state.fp_regs.fpsr.into(),
+                &state.fp_regs.fpsr.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1340,7 +1406,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U32, off),
-                state.fp_regs.fpcr.into(),
+                &state.fp_regs.fpcr.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
         Ok(())
@@ -1357,6 +1423,7 @@ impl cpu::Vcpu for KvmVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetSpecialRegs(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the vCPU special registers using the `KVM_SET_SREGS` ioctl.
@@ -1367,6 +1434,7 @@ impl cpu::Vcpu for KvmVcpu {
             .set_sregs(&sregs)
             .map_err(|e| cpu::HypervisorCpuError::SetSpecialRegs(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns the floating point state (FPU) from the vCPU.
@@ -1378,6 +1446,7 @@ impl cpu::Vcpu for KvmVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetFloatingPointRegs(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Set the floating point state (FPU) of a vCPU using the `KVM_SET_FPU` ioct.
@@ -1388,6 +1457,7 @@ impl cpu::Vcpu for KvmVcpu {
             .set_fpu(&fpu)
             .map_err(|e| cpu::HypervisorCpuError::SetFloatingPointRegs(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call to setup the CPUID registers.
@@ -1402,6 +1472,7 @@ impl cpu::Vcpu for KvmVcpu {
             .set_cpuid2(&kvm_cpuid)
             .map_err(|e| cpu::HypervisorCpuError::SetCpuid(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call to enable HyperV SynIC
@@ -1419,6 +1490,7 @@ impl cpu::Vcpu for KvmVcpu {
             .enable_cap(&cap)
             .map_err(|e| cpu::HypervisorCpuError::EnableHyperVSyncIc(e.into()))
     }
+
     ///
     /// X86 specific call to retrieve the CPUID registers.
     ///
@@ -1433,6 +1505,7 @@ impl cpu::Vcpu for KvmVcpu {
 
         Ok(v)
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns the state of the LAPIC (Local Advanced Programmable Interrupt Controller).
@@ -1444,6 +1517,7 @@ impl cpu::Vcpu for KvmVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetlapicState(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the state of the LAPIC (Local Advanced Programmable Interrupt Controller).
@@ -1454,6 +1528,7 @@ impl cpu::Vcpu for KvmVcpu {
             .set_lapic(&klapic)
             .map_err(|e| cpu::HypervisorCpuError::SetLapicState(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns the model-specific registers (MSR) for this vCPU.
@@ -1475,6 +1550,7 @@ impl cpu::Vcpu for KvmVcpu {
 
         Ok(succ)
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Setup the model-specific registers (MSR) for this vCPU.
@@ -1487,6 +1563,7 @@ impl cpu::Vcpu for KvmVcpu {
             .set_msrs(&kvm_msrs)
             .map_err(|e| cpu::HypervisorCpuError::SetMsrEntries(e.into()))
     }
+
     ///
     /// Returns the vcpu's current "multiprocessing state".
     ///
@@ -1497,6 +1574,7 @@ impl cpu::Vcpu for KvmVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetMpState(e.into()))?
             .into())
     }
+
     ///
     /// Sets the vcpu's current "multiprocessing state".
     ///
@@ -1505,6 +1583,7 @@ impl cpu::Vcpu for KvmVcpu {
             .set_mp_state(mp_state.into())
             .map_err(|e| cpu::HypervisorCpuError::SetMpState(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Translates guest virtual address to guest physical address using the `KVM_TRANSLATE` ioctl.
@@ -1523,6 +1602,7 @@ impl cpu::Vcpu for KvmVcpu {
             _ => Ok((tr.physical_address, 0)),
         }
     }
+
     ///
     /// Triggers the running of the current virtual CPU returning an exit reason.
     ///
@@ -1567,7 +1647,7 @@ impl cpu::Vcpu for KvmVcpu {
                         Ok(cpu::VmExit::Shutdown)
                     } else {
                         Err(cpu::HypervisorCpuError::RunVcpu(anyhow!(
-                            "Unexpected system event with type 0x{:x}, flags 0x{:x}",
+                            "Unexpected system event with type 0x{:x}, flags 0x{:x?}",
                             event_type,
                             flags
                         )))
@@ -1614,6 +1694,7 @@ impl cpu::Vcpu for KvmVcpu {
             },
         }
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Let the guest know that it has been paused, which prevents from
@@ -1631,6 +1712,7 @@ impl cpu::Vcpu for KvmVcpu {
 
         Ok(())
     }
+
     ///
     /// Sets debug registers to set hardware breakpoints and/or enable single step.
     ///
@@ -1684,12 +1766,14 @@ impl cpu::Vcpu for KvmVcpu {
             .set_guest_debug(&dbg)
             .map_err(|e| cpu::HypervisorCpuError::SetDebugRegs(e.into()))
     }
+
     #[cfg(target_arch = "aarch64")]
     fn vcpu_init(&self, kvi: &VcpuInit) -> cpu::Result<()> {
         self.fd
             .vcpu_init(kvi)
             .map_err(|e| cpu::HypervisorCpuError::VcpuInit(e.into()))
     }
+
     ///
     /// Gets a list of the guest registers that are supported for the
     /// KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
@@ -1700,6 +1784,7 @@ impl cpu::Vcpu for KvmVcpu {
             .get_reg_list(reg_list)
             .map_err(|e| cpu::HypervisorCpuError::GetRegList(e.into()))
     }
+
     ///
     /// Gets the value of a system register
     ///
@@ -1726,13 +1811,13 @@ impl cpu::Vcpu for KvmVcpu {
                     | KVM_REG_ARM64_SYSREG_CRN_MASK
                     | KVM_REG_ARM64_SYSREG_CRM_MASK
                     | KVM_REG_ARM64_SYSREG_OP2_MASK)) as u64);
-        Ok(self
-            .fd
-            .get_one_reg(id)
-            .map_err(|e| cpu::HypervisorCpuError::GetSysRegister(e.into()))?
-            .try_into()
-            .unwrap())
+        let mut bytes = [0_u8; 8];
+        self.fd
+            .get_one_reg(id, &mut bytes)
+            .map_err(|e| cpu::HypervisorCpuError::GetSysRegister(e.into()))?;
+        Ok(u64::from_le_bytes(bytes))
     }
+
     ///
     /// Configure core registers for a given CPU.
     ///
@@ -1757,7 +1842,7 @@ impl cpu::Vcpu for KvmVcpu {
         self.fd
             .set_one_reg(
                 arm64_core_reg_id!(KVM_REG_SIZE_U64, pstate),
-                PSTATE_FAULT_BITS_64.into(),
+                &PSTATE_FAULT_BITS_64.to_le_bytes(),
             )
             .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
@@ -1766,7 +1851,10 @@ impl cpu::Vcpu for KvmVcpu {
             // Setting the PC (Processor Counter) to the current program address (kernel address).
             let pc = offset_of!(user_pt_regs, pc) + kreg_off;
             self.fd
-                .set_one_reg(arm64_core_reg_id!(KVM_REG_SIZE_U64, pc), boot_ip.into())
+                .set_one_reg(
+                    arm64_core_reg_id!(KVM_REG_SIZE_U64, pc),
+                    &boot_ip.to_le_bytes(),
+                )
                 .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
 
             // Last mandatory thing to set -> the address pointing to the FDT (also called DTB).
@@ -1777,7 +1865,7 @@ impl cpu::Vcpu for KvmVcpu {
             self.fd
                 .set_one_reg(
                     arm64_core_reg_id!(KVM_REG_SIZE_U64, regs0),
-                    fdt_start.into(),
+                    &fdt_start.to_le_bytes(),
                 )
                 .map_err(|e| cpu::HypervisorCpuError::SetCoreRegister(e.into()))?;
         }
@@ -1907,6 +1995,7 @@ impl cpu::Vcpu for KvmVcpu {
         }
         .into())
     }
+
     ///
     /// Get the current AArch64 CPU state
     ///
@@ -1941,14 +2030,13 @@ impl cpu::Vcpu for KvmVcpu {
         // register list, we are simply calling KVM_GET_ONE_REG.
         let indices = reg_list.as_slice();
         for index in indices.iter() {
+            let mut bytes = [0_u8; 8];
+            self.fd
+                .get_one_reg(*index, &mut bytes)
+                .map_err(|e| cpu::HypervisorCpuError::GetSysRegister(e.into()))?;
             sys_regs.push(kvm_bindings::kvm_one_reg {
                 id: *index,
-                addr: self
-                    .fd
-                    .get_one_reg(*index)
-                    .map_err(|e| cpu::HypervisorCpuError::GetSysRegister(e.into()))?
-                    .try_into()
-                    .unwrap(),
+                addr: u64::from_le_bytes(bytes),
             });
         }
 
@@ -1956,6 +2044,7 @@ impl cpu::Vcpu for KvmVcpu {
 
         Ok(state.into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Restore the previously saved CPU state
@@ -2045,6 +2134,7 @@ impl cpu::Vcpu for KvmVcpu {
 
         Ok(())
     }
+
     ///
     /// Restore the previously saved AArch64 CPU state
     ///
@@ -2056,7 +2146,7 @@ impl cpu::Vcpu for KvmVcpu {
         // Set system registers
         for reg in &state.sys_regs {
             self.fd
-                .set_one_reg(reg.id, reg.addr.into())
+                .set_one_reg(reg.id, &reg.addr.to_le_bytes())
                 .map_err(|e| cpu::HypervisorCpuError::SetSysRegister(e.into()))?;
         }
 
@@ -2088,7 +2178,12 @@ impl cpu::Vcpu for KvmVcpu {
     fn get_tdx_exit_details(&mut self) -> cpu::Result<TdxExitDetails> {
         let kvm_run = self.fd.get_kvm_run();
         // SAFETY: accessing a union field in a valid structure
-        let tdx_vmcall = unsafe { &mut kvm_run.__bindgen_anon_1.tdx.u.vmcall };
+        let tdx_vmcall = unsafe {
+            &mut (*((&mut kvm_run.__bindgen_anon_1) as *mut kvm_run__bindgen_ty_1
+                as *mut KvmTdxExit))
+                .u
+                .vmcall
+        };
 
         tdx_vmcall.status_code = TDG_VP_VMCALL_INVALID_OPERAND;
 
@@ -2112,13 +2207,19 @@ impl cpu::Vcpu for KvmVcpu {
     fn set_tdx_status(&mut self, status: TdxExitStatus) {
         let kvm_run = self.fd.get_kvm_run();
         // SAFETY: accessing a union field in a valid structure
-        let tdx_vmcall = unsafe { &mut kvm_run.__bindgen_anon_1.tdx.u.vmcall };
+        let tdx_vmcall = unsafe {
+            &mut (*((&mut kvm_run.__bindgen_anon_1) as *mut kvm_run__bindgen_ty_1
+                as *mut KvmTdxExit))
+                .u
+                .vmcall
+        };
 
         tdx_vmcall.status_code = match status {
             TdxExitStatus::Success => TDG_VP_VMCALL_SUCCESS,
             TdxExitStatus::InvalidOperand => TDG_VP_VMCALL_INVALID_OPERAND,
         };
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Return the list of initial MSR entries for a VCPU
@@ -2144,6 +2245,7 @@ impl cpu::Vcpu for KvmVcpu {
         ]
         .to_vec()
     }
+
     #[cfg(target_arch = "aarch64")]
     fn has_pmu_support(&self) -> bool {
         let cpu_attr = kvm_bindings::kvm_device_attr {
@@ -2154,6 +2256,7 @@ impl cpu::Vcpu for KvmVcpu {
         };
         self.fd.has_device_attr(&cpu_attr).is_ok()
     }
+
     #[cfg(target_arch = "aarch64")]
     fn init_pmu(&self, irq: u32) -> cpu::Result<()> {
         let cpu_attr = kvm_bindings::kvm_device_attr {
@@ -2216,20 +2319,25 @@ impl KvmVcpu {
     ///
     /// X86 specific call that returns the vcpu's current "xsave struct".
     ///
-    fn get_xsave(&self) -> cpu::Result<Xsave> {
-        self.fd
+    fn get_xsave(&self) -> cpu::Result<XsaveState> {
+        Ok(self
+            .fd
             .get_xsave()
-            .map_err(|e| cpu::HypervisorCpuError::GetXsaveState(e.into()))
+            .map_err(|e| cpu::HypervisorCpuError::GetXsaveState(e.into()))?
+            .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call that sets the vcpu's current "xsave struct".
     ///
-    fn set_xsave(&self, xsave: &Xsave) -> cpu::Result<()> {
+    fn set_xsave(&self, xsave: &XsaveState) -> cpu::Result<()> {
+        let xsave: kvm_bindings::kvm_xsave = (*xsave).clone().into();
         self.fd
-            .set_xsave(xsave)
+            .set_xsave(&xsave)
             .map_err(|e| cpu::HypervisorCpuError::SetXsaveState(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call that returns the vcpu's current "xcrs".
@@ -2239,6 +2347,7 @@ impl KvmVcpu {
             .get_xcrs()
             .map_err(|e| cpu::HypervisorCpuError::GetXcsr(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call that sets the vcpu's current "xcrs".
@@ -2248,6 +2357,7 @@ impl KvmVcpu {
             .set_xcrs(xcrs)
             .map_err(|e| cpu::HypervisorCpuError::SetXcsr(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns currently pending exceptions, interrupts, and NMIs as well as related
@@ -2258,6 +2368,7 @@ impl KvmVcpu {
             .get_vcpu_events()
             .map_err(|e| cpu::HypervisorCpuError::GetVcpuEvents(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets pending exceptions, interrupts, and NMIs as well as related states

hypervisor/src/kvm/x86_64/mod.rs

@@ -10,7 +10,7 @@
 
 use crate::arch::x86::{
     CpuIdEntry, DescriptorTable, FpuState, LapicState, MsrEntry, SegmentRegister, SpecialRegisters,
-    StandardRegisters, CPUID_FLAG_VALID_INDEX,
+    StandardRegisters, XsaveState, CPUID_FLAG_VALID_INDEX,
 };
 use crate::kvm::{Cap, Kvm, KvmError, KvmResult};
 use serde::{Deserialize, Serialize};
@@ -23,7 +23,7 @@ pub use {
     kvm_bindings::kvm_lapic_state, kvm_bindings::kvm_mp_state as MpState,
     kvm_bindings::kvm_msr_entry, kvm_bindings::kvm_regs, kvm_bindings::kvm_segment,
     kvm_bindings::kvm_sregs, kvm_bindings::kvm_vcpu_events as VcpuEvents,
-    kvm_bindings::kvm_xcrs as ExtendedControlRegisters, kvm_bindings::kvm_xsave as Xsave,
+    kvm_bindings::kvm_xcrs as ExtendedControlRegisters, kvm_bindings::kvm_xsave,
     kvm_bindings::CpuId, kvm_bindings::MsrList, kvm_bindings::Msrs as MsrEntries,
     kvm_bindings::KVM_CPUID_FLAG_SIGNIFCANT_INDEX,
 };
@@ -64,7 +64,7 @@ pub struct VcpuKvmState {
     pub sregs: kvm_sregs,
     pub fpu: FpuState,
     pub lapic_state: LapicState,
-    pub xsave: Xsave,
+    pub xsave: XsaveState,
     pub xcrs: ExtendedControlRegisters,
     pub mp_state: MpState,
     pub tsc_khz: Option<u32>,
@@ -330,3 +330,18 @@ impl From<MsrEntry> for kvm_msr_entry {
         }
     }
 }
+
+impl From<kvm_xsave> for XsaveState {
+    fn from(s: kvm_xsave) -> Self {
+        Self { region: s.region }
+    }
+}
+
+impl From<XsaveState> for kvm_xsave {
+    fn from(s: XsaveState) -> Self {
+        Self {
+            region: s.region,
+            extra: Default::default(),
+        }
+    }
+}

hypervisor/src/lib.rs

@@ -134,6 +134,7 @@ pub const USER_MEMORY_REGION_READ: u32 = 1;
 pub const USER_MEMORY_REGION_WRITE: u32 = 1 << 1;
 pub const USER_MEMORY_REGION_EXECUTE: u32 = 1 << 2;
 pub const USER_MEMORY_REGION_LOG_DIRTY: u32 = 1 << 3;
+pub const USER_MEMORY_REGION_ADJUSTABLE: u32 = 1 << 4;
 
 #[derive(Debug)]
 pub enum MpState {

hypervisor/src/mshv/mod.rs

@@ -20,13 +20,22 @@ use std::collections::HashMap;
 use std::sync::{Arc, RwLock};
 use vfio_ioctls::VfioDeviceFd;
 use vm::DataMatch;
+
+#[cfg(feature = "sev_snp")]
+mod snp_constants;
 // x86_64 dependencies
 #[cfg(target_arch = "x86_64")]
 pub mod x86_64;
+#[cfg(feature = "sev_snp")]
+use snp_constants::*;
+
 use crate::{
     ClockData, CpuState, IoEventAddress, IrqRoutingEntry, MpState, UserMemoryRegion,
-    USER_MEMORY_REGION_EXECUTE, USER_MEMORY_REGION_READ, USER_MEMORY_REGION_WRITE,
+    USER_MEMORY_REGION_ADJUSTABLE, USER_MEMORY_REGION_EXECUTE, USER_MEMORY_REGION_READ,
+    USER_MEMORY_REGION_WRITE,
 };
+#[cfg(feature = "sev_snp")]
+use igvm_defs::IGVM_VHS_SNP_ID_BLOCK;
 use vmm_sys_util::eventfd::EventFd;
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::VcpuMshvState;
@@ -65,6 +74,9 @@ impl From<mshv_user_mem_region> for UserMemoryRegion {
         if region.flags & HV_MAP_GPA_EXECUTABLE != 0 {
             flags |= USER_MEMORY_REGION_EXECUTE;
         }
+        if region.flags & HV_MAP_GPA_ADJUSTABLE != 0 {
+            flags |= USER_MEMORY_REGION_ADJUSTABLE;
+        }
 
         UserMemoryRegion {
             guest_phys_addr: (region.guest_pfn << PAGE_SHIFT as u64)
@@ -89,6 +101,9 @@ impl From<UserMemoryRegion> for mshv_user_mem_region {
         if region.flags & USER_MEMORY_REGION_EXECUTE != 0 {
             flags |= HV_MAP_GPA_EXECUTABLE;
         }
+        if region.flags & USER_MEMORY_REGION_ADJUSTABLE != 0 {
+            flags |= HV_MAP_GPA_ADJUSTABLE;
+        }
 
         mshv_user_mem_region {
             guest_pfn: region.guest_phys_addr >> PAGE_SHIFT,
@@ -192,6 +207,7 @@ impl MshvHypervisor {
         }
     }
 }
+
 /// Implementation of Hypervisor trait for Mshv
 ///
 /// # Examples
@@ -234,6 +250,33 @@ impl hypervisor::Hypervisor for MshvHypervisor {
             break;
         }
 
+        // Set additional partition property for SEV-SNP partition.
+        if mshv_vm_type == VmType::Snp {
+            let snp_policy = snp::get_default_snp_guest_policy();
+            let vmgexit_offloads = snp::get_default_vmgexit_offload_features();
+            // SAFETY: access union fields
+            unsafe {
+                debug!(
+                    "Setting the partition isolation policy as: 0x{:x}",
+                    snp_policy.as_uint64
+                );
+                fd.set_partition_property(
+                    hv_partition_property_code_HV_PARTITION_PROPERTY_ISOLATION_POLICY,
+                    snp_policy.as_uint64,
+                )
+                .map_err(|e| hypervisor::HypervisorError::SetPartitionProperty(e.into()))?;
+                debug!(
+                    "Setting the partition property to enable VMGEXIT offloads as : 0x{:x}",
+                    vmgexit_offloads.as_uint64
+                );
+                fd.set_partition_property(
+                    hv_partition_property_code_HV_PARTITION_PROPERTY_SEV_VMGEXIT_OFFLOADS,
+                    vmgexit_offloads.as_uint64,
+                )
+                .map_err(|e| hypervisor::HypervisorError::SetPartitionProperty(e.into()))?;
+            }
+        }
+
         // Default Microsoft Hypervisor behavior for unimplemented MSR is to
         // send a fault to the guest if it tries to access it. It is possible
         // to override this behavior with a more suitable option i.e., ignore
@@ -263,6 +306,8 @@ impl hypervisor::Hypervisor for MshvHypervisor {
             fd: vm_fd,
             msrs,
             dirty_log_slots: Arc::new(RwLock::new(HashMap::new())),
+            #[cfg(feature = "sev_snp")]
+            sev_snp_enabled: mshv_vm_type == VmType::Snp,
         }))
     }
 
@@ -303,6 +348,8 @@ pub struct MshvVcpu {
     cpuid: Vec<CpuIdEntry>,
     msrs: Vec<MsrEntry>,
     vm_ops: Option<Arc<dyn vm::VmOps>>,
+    #[cfg(feature = "sev_snp")]
+    vm_fd: Arc<VmFd>,
 }
 
 /// Implementation of Vcpu trait for Microsoft Hypervisor
@@ -329,6 +376,7 @@ impl cpu::Vcpu for MshvVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetStandardRegs(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the vCPU general purpose registers.
@@ -339,6 +387,7 @@ impl cpu::Vcpu for MshvVcpu {
             .set_regs(&regs)
             .map_err(|e| cpu::HypervisorCpuError::SetStandardRegs(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns the vCPU special registers.
@@ -350,6 +399,7 @@ impl cpu::Vcpu for MshvVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetSpecialRegs(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the vCPU special registers.
@@ -360,6 +410,7 @@ impl cpu::Vcpu for MshvVcpu {
             .set_sregs(&sregs)
             .map_err(|e| cpu::HypervisorCpuError::SetSpecialRegs(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns the floating point state (FPU) from the vCPU.
@@ -371,6 +422,7 @@ impl cpu::Vcpu for MshvVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetFloatingPointRegs(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Set the floating point state (FPU) of a vCPU.
@@ -403,6 +455,7 @@ impl cpu::Vcpu for MshvVcpu {
 
         Ok(succ)
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Setup the model-specific registers (MSR) for this vCPU.
@@ -424,6 +477,7 @@ impl cpu::Vcpu for MshvVcpu {
         /* We always have SynIC enabled on MSHV */
         Ok(())
     }
+
     #[allow(non_upper_case_globals)]
     fn run(&self) -> std::result::Result<cpu::VmExit, cpu::HypervisorCpuError> {
         let hv_message: hv_message = hv_message::default();
@@ -552,6 +606,17 @@ impl cpu::Vcpu for MshvVcpu {
 
                     Ok(cpu::VmExit::Ignore)
                 }
+                hv_message_type_HVMSG_UNACCEPTED_GPA => {
+                    let info = x.to_memory_info().unwrap();
+                    let gva = info.guest_virtual_address;
+                    let gpa = info.guest_physical_address;
+
+                    Err(cpu::HypervisorCpuError::RunVcpu(anyhow!(
+                        "Unhandled VCPU exit: Unaccepted GPA({:x}) found at GVA({:x})",
+                        gpa,
+                        gva,
+                    )))
+                }
                 hv_message_type_HVMSG_X64_CPUID_INTERCEPT => {
                     let info = x.to_cpuid_info().unwrap();
                     debug!("cpuid eax: {:x}", { info.rax });
@@ -584,6 +649,427 @@ impl cpu::Vcpu for MshvVcpu {
                         info.interrupt_vector.try_into().unwrap(),
                     ))
                 }
+                #[cfg(feature = "sev_snp")]
+                hv_message_type_HVMSG_X64_SEV_VMGEXIT_INTERCEPT => {
+                    let info = x.to_vmg_intercept_info().unwrap();
+                    let ghcb_data = info.ghcb_msr >> GHCB_INFO_BIT_WIDTH;
+                    let ghcb_msr = svm_ghcb_msr {
+                        as_uint64: info.ghcb_msr,
+                    };
+                    // SAFETY: Accessing a union element from bindgen generated bindings.
+                    let ghcb_op = unsafe { ghcb_msr.__bindgen_anon_2.ghcb_info() as u32 };
+                    // Sanity check on the header fields before handling other operations.
+                    assert!(info.header.intercept_access_type == HV_INTERCEPT_ACCESS_EXECUTE as u8);
+
+                    match ghcb_op {
+                        GHCB_INFO_HYP_FEATURE_REQUEST => {
+                            // Pre-condition: GHCB data must be zero
+                            assert!(ghcb_data == 0);
+                            let mut ghcb_response = GHCB_INFO_HYP_FEATURE_RESPONSE as u64;
+                            // Indicate support for basic SEV-SNP features
+                            ghcb_response |=
+                                (GHCB_HYP_FEATURE_SEV_SNP << GHCB_INFO_BIT_WIDTH) as u64;
+                            // Indicate support for SEV-SNP AP creation
+                            ghcb_response |= (GHCB_HYP_FEATURE_SEV_SNP_AP_CREATION
+                                << GHCB_INFO_BIT_WIDTH)
+                                as u64;
+                            debug!(
+                                "GHCB_INFO_HYP_FEATURE_REQUEST: Supported features: {:0x}",
+                                ghcb_response
+                            );
+                            let arr_reg_name_value =
+                                [(hv_register_name_HV_X64_REGISTER_GHCB, ghcb_response)];
+                            set_registers_64!(self.fd, arr_reg_name_value)
+                                .map_err(|e| cpu::HypervisorCpuError::SetRegister(e.into()))?;
+                        }
+                        GHCB_INFO_REGISTER_REQUEST => {
+                            let mut ghcb_gpa = hv_x64_register_sev_ghcb::default();
+                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                            unsafe {
+                                ghcb_gpa.__bindgen_anon_1.set_enabled(1);
+                                ghcb_gpa
+                                    .__bindgen_anon_1
+                                    .set_page_number(ghcb_msr.__bindgen_anon_2.gpa_page_number());
+                            }
+                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                            let reg_name_value = unsafe {
+                                [(
+                                    hv_register_name_HV_X64_REGISTER_SEV_GHCB_GPA,
+                                    ghcb_gpa.as_uint64,
+                                )]
+                            };
+
+                            set_registers_64!(self.fd, reg_name_value)
+                                .map_err(|e| cpu::HypervisorCpuError::SetRegister(e.into()))?;
+
+                            let mut resp_ghcb_msr = svm_ghcb_msr::default();
+                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                            unsafe {
+                                resp_ghcb_msr
+                                    .__bindgen_anon_2
+                                    .set_ghcb_info(GHCB_INFO_REGISTER_RESPONSE as u64);
+                                resp_ghcb_msr.__bindgen_anon_2.set_gpa_page_number(
+                                    ghcb_msr.__bindgen_anon_2.gpa_page_number(),
+                                );
+                            }
+                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                            let reg_name_value = unsafe {
+                                [(
+                                    hv_register_name_HV_X64_REGISTER_GHCB,
+                                    resp_ghcb_msr.as_uint64,
+                                )]
+                            };
+
+                            set_registers_64!(self.fd, reg_name_value)
+                                .map_err(|e| cpu::HypervisorCpuError::SetRegister(e.into()))?;
+                        }
+                        GHCB_INFO_SEV_INFO_REQUEST => {
+                            let sev_cpuid_function = 0x8000_001F;
+                            let cpu_leaf = self
+                                .fd
+                                .get_cpuid_values(sev_cpuid_function, 0, 0, 0)
+                                .unwrap();
+                            let ebx = cpu_leaf[1];
+                            // First 6-byte of EBX represents page table encryption bit number
+                            let pbit_encryption = (ebx & 0x3f) as u8;
+                            let mut ghcb_response = GHCB_INFO_SEV_INFO_RESPONSE as u64;
+
+                            // GHCBData[63:48] specifies the maximum GHCB protocol version supported
+                            ghcb_response |= (GHCB_PROTOCOL_VERSION_MAX as u64) << 48;
+                            // GHCBData[47:32] specifies the minimum GHCB protocol version supported
+                            ghcb_response |= (GHCB_PROTOCOL_VERSION_MIN as u64) << 32;
+                            // GHCBData[31:24] specifies the SEV page table encryption bit number.
+                            ghcb_response |= (pbit_encryption as u64) << 24;
+
+                            let arr_reg_name_value =
+                                [(hv_register_name_HV_X64_REGISTER_GHCB, ghcb_response)];
+                            set_registers_64!(self.fd, arr_reg_name_value)
+                                .map_err(|e| cpu::HypervisorCpuError::SetRegister(e.into()))?;
+                        }
+                        GHCB_INFO_NORMAL => {
+                            let exit_code =
+                                info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_code as u32;
+                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                            let pfn = unsafe { ghcb_msr.__bindgen_anon_2.gpa_page_number() };
+                            let ghcb_gpa = pfn << GHCB_INFO_BIT_WIDTH;
+                            match exit_code {
+                                SVM_EXITCODE_HV_DOORBELL_PAGE => {
+                                    let exit_info1 =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info1 as u32;
+                                    match exit_info1 {
+                                        SVM_NAE_HV_DOORBELL_PAGE_GET_PREFERRED => {
+                                            // Hypervisor does not have any preference for doorbell GPA.
+                                            let preferred_doorbell_gpa: u64 = 0xFFFFFFFFFFFFFFFF;
+                                            let mut swei2_rw_gpa_arg =
+                                                mshv_bindings::mshv_read_write_gpa {
+                                                    base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                                    byte_count: std::mem::size_of::<u64>() as u32,
+                                                    ..Default::default()
+                                                };
+                                            swei2_rw_gpa_arg.data.copy_from_slice(
+                                                &preferred_doorbell_gpa.to_le_bytes(),
+                                            );
+                                            self.fd.gpa_write(&mut swei2_rw_gpa_arg).map_err(
+                                                |e| cpu::HypervisorCpuError::GpaWrite(e.into()),
+                                            )?;
+                                        }
+                                        SVM_NAE_HV_DOORBELL_PAGE_SET => {
+                                            let exit_info2 = info
+                                                .__bindgen_anon_2
+                                                .__bindgen_anon_1
+                                                .sw_exit_info2;
+                                            let mut ghcb_doorbell_gpa =
+                                                hv_x64_register_sev_hv_doorbell::default();
+                                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                                            unsafe {
+                                                ghcb_doorbell_gpa.__bindgen_anon_1.set_enabled(1);
+                                                ghcb_doorbell_gpa
+                                                    .__bindgen_anon_1
+                                                    .set_page_number(exit_info2 >> PAGE_SHIFT);
+                                            }
+                                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                                            let reg_names = unsafe {
+                                                [(
+                                                    hv_register_name_HV_X64_REGISTER_SEV_DOORBELL_GPA,
+                                                    ghcb_doorbell_gpa.as_uint64,
+                                                )]
+                                            };
+                                            set_registers_64!(self.fd, reg_names).map_err(|e| {
+                                                cpu::HypervisorCpuError::SetRegister(e.into())
+                                            })?;
+
+                                            let mut swei2_rw_gpa_arg =
+                                                mshv_bindings::mshv_read_write_gpa {
+                                                    base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                                    byte_count: std::mem::size_of::<u64>() as u32,
+                                                    ..Default::default()
+                                                };
+                                            swei2_rw_gpa_arg.data[0..8]
+                                                .copy_from_slice(&exit_info2.to_le_bytes());
+                                            self.fd.gpa_write(&mut swei2_rw_gpa_arg).map_err(
+                                                |e| cpu::HypervisorCpuError::GpaWrite(e.into()),
+                                            )?;
+
+                                            // Clear the SW_EXIT_INFO1 register to indicate no error
+                                            let mut swei1_rw_gpa_arg =
+                                                mshv_bindings::mshv_read_write_gpa {
+                                                    base_gpa: ghcb_gpa + GHCB_SW_EXITINFO1_OFFSET,
+                                                    byte_count: std::mem::size_of::<u64>() as u32,
+                                                    ..Default::default()
+                                                };
+                                            self.fd.gpa_write(&mut swei1_rw_gpa_arg).map_err(
+                                                |e| cpu::HypervisorCpuError::GpaWrite(e.into()),
+                                            )?;
+                                        }
+                                        SVM_NAE_HV_DOORBELL_PAGE_QUERY => {
+                                            let mut reg_assocs = [ hv_register_assoc {
+                                                name: hv_register_name_HV_X64_REGISTER_SEV_DOORBELL_GPA,
+                                                ..Default::default()
+                                            } ];
+                                            self.fd.get_reg(&mut reg_assocs).unwrap();
+                                            // SAFETY: Accessing a union element from bindgen generated bindings.
+                                            let doorbell_gpa = unsafe { reg_assocs[0].value.reg64 };
+                                            let mut swei2_rw_gpa_arg =
+                                                mshv_bindings::mshv_read_write_gpa {
+                                                    base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                                    byte_count: std::mem::size_of::<u64>() as u32,
+                                                    ..Default::default()
+                                                };
+                                            swei2_rw_gpa_arg
+                                                .data
+                                                .copy_from_slice(&doorbell_gpa.to_le_bytes());
+                                            self.fd.gpa_write(&mut swei2_rw_gpa_arg).map_err(
+                                                |e| cpu::HypervisorCpuError::GpaWrite(e.into()),
+                                            )?;
+                                        }
+                                        SVM_NAE_HV_DOORBELL_PAGE_CLEAR => {
+                                            let mut swei2_rw_gpa_arg =
+                                                mshv_bindings::mshv_read_write_gpa {
+                                                    base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                                    byte_count: std::mem::size_of::<u64>() as u32,
+                                                    ..Default::default()
+                                                };
+                                            self.fd.gpa_write(&mut swei2_rw_gpa_arg).map_err(
+                                                |e| cpu::HypervisorCpuError::GpaWrite(e.into()),
+                                            )?;
+                                        }
+                                        _ => {
+                                            panic!(
+                                                "SVM_EXITCODE_HV_DOORBELL_PAGE: Unhandled exit code: {:0x}",
+                                                exit_info1
+                                            );
+                                        }
+                                    }
+                                }
+                                SVM_EXITCODE_SNP_EXTENDED_GUEST_REQUEST => {
+                                    warn!("Fetching extended guest request is not supported");
+                                    // Extended guest request is not supported by the Hypervisor
+                                    // Returning the error to the guest
+                                    // 0x6 means `The NAE event was not valid`
+                                    // Reference: GHCB Spec, page 42
+                                    let value: u64 = 0x6;
+                                    let mut swei2_rw_gpa_arg = mshv_bindings::mshv_read_write_gpa {
+                                        base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                        byte_count: std::mem::size_of::<u64>() as u32,
+                                        ..Default::default()
+                                    };
+                                    swei2_rw_gpa_arg.data.copy_from_slice(&value.to_le_bytes());
+                                    self.fd
+                                        .gpa_write(&mut swei2_rw_gpa_arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaWrite(e.into()))?;
+                                }
+                                SVM_EXITCODE_IOIO_PROT => {
+                                    let exit_info1 =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info1 as u32;
+                                    let port_info = hv_sev_vmgexit_port_info {
+                                        as_uint32: exit_info1,
+                                    };
+
+                                    let port =
+                                        // SAFETY: Accessing a union element from bindgen generated bindings.
+                                        unsafe { port_info.__bindgen_anon_1.intercepted_port() };
+                                    let mut len = 4;
+                                    // SAFETY: Accessing a union element from bindgen generated bindings.
+                                    unsafe {
+                                        if port_info.__bindgen_anon_1.operand_size_16bit() == 1 {
+                                            len = 2;
+                                        } else if port_info.__bindgen_anon_1.operand_size_8bit()
+                                            == 1
+                                        {
+                                            len = 1;
+                                        }
+                                    }
+                                    let is_write =
+                                        // SAFETY: Accessing a union element from bindgen generated bindings.
+                                        unsafe { port_info.__bindgen_anon_1.access_type() == 0 };
+                                    let mut rax_rw_gpa_arg: mshv_read_write_gpa =
+                                        mshv_bindings::mshv_read_write_gpa {
+                                            base_gpa: ghcb_gpa + GHCB_RAX_OFFSET,
+                                            byte_count: std::mem::size_of::<u64>() as u32,
+                                            ..Default::default()
+                                        };
+                                    self.fd
+                                        .gpa_read(&mut rax_rw_gpa_arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaRead(e.into()))?;
+
+                                    if is_write {
+                                        if let Some(vm_ops) = &self.vm_ops {
+                                            vm_ops
+                                                .pio_write(
+                                                    port.into(),
+                                                    &rax_rw_gpa_arg.data[0..len],
+                                                )
+                                                .map_err(|e| {
+                                                    cpu::HypervisorCpuError::RunVcpu(e.into())
+                                                })?;
+                                        }
+                                    } else {
+                                        if let Some(vm_ops) = &self.vm_ops {
+                                            vm_ops
+                                                .pio_read(
+                                                    port.into(),
+                                                    &mut rax_rw_gpa_arg.data[0..len],
+                                                )
+                                                .map_err(|e| {
+                                                    cpu::HypervisorCpuError::RunVcpu(e.into())
+                                                })?;
+                                        }
+
+                                        self.fd.gpa_write(&mut rax_rw_gpa_arg).map_err(|e| {
+                                            cpu::HypervisorCpuError::GpaWrite(e.into())
+                                        })?;
+                                    }
+
+                                    // Clear the SW_EXIT_INFO1 register to indicate no error
+                                    let mut swei1_rw_gpa_arg = mshv_bindings::mshv_read_write_gpa {
+                                        base_gpa: ghcb_gpa + GHCB_SW_EXITINFO1_OFFSET,
+                                        byte_count: std::mem::size_of::<u64>() as u32,
+                                        ..Default::default()
+                                    };
+                                    self.fd
+                                        .gpa_write(&mut swei1_rw_gpa_arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaWrite(e.into()))?;
+                                }
+                                SVM_EXITCODE_MMIO_READ => {
+                                    let src_gpa =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info1;
+                                    let dst_gpa = info.__bindgen_anon_2.__bindgen_anon_1.sw_scratch;
+                                    let data_len =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info2
+                                            as usize;
+                                    // Sanity check to make sure data len is within supported range.
+                                    assert!(data_len <= 0x8);
+
+                                    let mut data: Vec<u8> = vec![0; data_len];
+                                    if let Some(vm_ops) = &self.vm_ops {
+                                        vm_ops.mmio_read(src_gpa, &mut data[0..data_len]).map_err(
+                                            |e| cpu::HypervisorCpuError::RunVcpu(e.into()),
+                                        )?;
+                                    }
+                                    let mut arg: mshv_read_write_gpa =
+                                        mshv_bindings::mshv_read_write_gpa {
+                                            base_gpa: dst_gpa,
+                                            byte_count: data_len as u32,
+                                            ..Default::default()
+                                        };
+                                    arg.data[0..data_len].copy_from_slice(&data);
+
+                                    self.fd
+                                        .gpa_write(&mut arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaWrite(e.into()))?;
+                                }
+                                SVM_EXITCODE_MMIO_WRITE => {
+                                    let dst_gpa =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info1;
+                                    let src_gpa = info.__bindgen_anon_2.__bindgen_anon_1.sw_scratch;
+                                    let data_len =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info2
+                                            as usize;
+                                    // Sanity check to make sure data len is within supported range.
+                                    assert!(data_len <= 0x8);
+                                    let mut arg: mshv_read_write_gpa =
+                                        mshv_bindings::mshv_read_write_gpa {
+                                            base_gpa: src_gpa,
+                                            byte_count: data_len as u32,
+                                            ..Default::default()
+                                        };
+
+                                    self.fd
+                                        .gpa_read(&mut arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaRead(e.into()))?;
+
+                                    if let Some(vm_ops) = &self.vm_ops {
+                                        vm_ops
+                                            .mmio_write(dst_gpa, &arg.data[0..data_len])
+                                            .map_err(|e| {
+                                                cpu::HypervisorCpuError::RunVcpu(e.into())
+                                            })?;
+                                    }
+                                }
+                                SVM_EXITCODE_SNP_GUEST_REQUEST => {
+                                    let req_gpa =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info1;
+                                    let rsp_gpa =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info2;
+
+                                    let mshv_psp_req =
+                                        mshv_issue_psp_guest_request { req_gpa, rsp_gpa };
+                                    self.vm_fd
+                                        .psp_issue_guest_request(&mshv_psp_req)
+                                        .map_err(|e| cpu::HypervisorCpuError::RunVcpu(e.into()))?;
+
+                                    debug!(
+                                        "SNP guest request: req_gpa {:0x} rsp_gpa {:0x}",
+                                        req_gpa, rsp_gpa
+                                    );
+
+                                    let mut swei2_rw_gpa_arg = mshv_bindings::mshv_read_write_gpa {
+                                        base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                        byte_count: std::mem::size_of::<u64>() as u32,
+                                        ..Default::default()
+                                    };
+                                    self.fd
+                                        .gpa_write(&mut swei2_rw_gpa_arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaWrite(e.into()))?;
+                                }
+                                SVM_EXITCODE_SNP_AP_CREATION => {
+                                    let vmsa_gpa =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info2;
+                                    let apic_id =
+                                        info.__bindgen_anon_2.__bindgen_anon_1.sw_exit_info1 >> 32;
+                                    debug!(
+                                        "SNP AP CREATE REQUEST with VMSA GPA {:0x}, and APIC ID {:?}",
+                                        vmsa_gpa, apic_id
+                                    );
+
+                                    let mshv_ap_create_req = mshv_sev_snp_ap_create {
+                                        vp_id: apic_id,
+                                        vmsa_gpa,
+                                    };
+                                    self.vm_fd
+                                        .sev_snp_ap_create(&mshv_ap_create_req)
+                                        .map_err(|e| cpu::HypervisorCpuError::RunVcpu(e.into()))?;
+
+                                    let mut swei2_rw_gpa_arg = mshv_bindings::mshv_read_write_gpa {
+                                        base_gpa: ghcb_gpa + GHCB_SW_EXITINFO2_OFFSET,
+                                        byte_count: std::mem::size_of::<u64>() as u32,
+                                        ..Default::default()
+                                    };
+                                    self.fd
+                                        .gpa_write(&mut swei2_rw_gpa_arg)
+                                        .map_err(|e| cpu::HypervisorCpuError::GpaWrite(e.into()))?;
+                                }
+                                _ => panic!(
+                                    "GHCB_INFO_NORMAL: Unhandled exit code: {:0x}",
+                                    exit_code
+                                ),
+                            }
+                        }
+                        _ => panic!("Unsupported VMGEXIT operation: {:0x}", ghcb_op),
+                    }
+
+                    Ok(cpu::VmExit::Ignore)
+                }
                 exit => Err(cpu::HypervisorCpuError::RunVcpu(anyhow!(
                     "Unhandled VCPU exit {:?}",
                     exit
@@ -599,6 +1085,7 @@ impl cpu::Vcpu for MshvVcpu {
             },
         }
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call to setup the CPUID registers.
@@ -612,6 +1099,7 @@ impl cpu::Vcpu for MshvVcpu {
             .register_intercept_result_cpuid(&mshv_cpuid)
             .map_err(|e| cpu::HypervisorCpuError::SetCpuid(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call to retrieve the CPUID registers.
@@ -619,6 +1107,23 @@ impl cpu::Vcpu for MshvVcpu {
     fn get_cpuid2(&self, _num_entries: usize) -> cpu::Result<Vec<CpuIdEntry>> {
         Ok(self.cpuid.clone())
     }
+
+    #[cfg(target_arch = "x86_64")]
+    ///
+    /// X86 specific call to retrieve cpuid leaf
+    ///
+    fn get_cpuid_values(
+        &self,
+        function: u32,
+        index: u32,
+        xfem: u64,
+        xss: u64,
+    ) -> cpu::Result<[u32; 4]> {
+        self.fd
+            .get_cpuid_values(function, index, xfem, xss)
+            .map_err(|e| cpu::HypervisorCpuError::GetCpuidVales(e.into()))
+    }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns the state of the LAPIC (Local Advanced Programmable Interrupt Controller).
@@ -630,6 +1135,7 @@ impl cpu::Vcpu for MshvVcpu {
             .map_err(|e| cpu::HypervisorCpuError::GetlapicState(e.into()))?
             .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the state of the LAPIC (Local Advanced Programmable Interrupt Controller).
@@ -640,18 +1146,21 @@ impl cpu::Vcpu for MshvVcpu {
             .set_lapic(&lapic)
             .map_err(|e| cpu::HypervisorCpuError::SetLapicState(e.into()))
     }
+
     ///
     /// Returns the vcpu's current "multiprocessing state".
     ///
     fn get_mp_state(&self) -> cpu::Result<MpState> {
         Ok(MpState::Mshv)
     }
+
     ///
     /// Sets the vcpu's current "multiprocessing state".
     ///
     fn set_mp_state(&self, _mp_state: MpState) -> cpu::Result<()> {
         Ok(())
     }
+
     ///
     /// Set CPU state
     ///
@@ -677,6 +1186,7 @@ impl cpu::Vcpu for MshvVcpu {
             .map_err(|e| cpu::HypervisorCpuError::SetDebugRegs(e.into()))?;
         Ok(())
     }
+
     ///
     /// Get CPU State
     ///
@@ -713,6 +1223,7 @@ impl cpu::Vcpu for MshvVcpu {
         }
         .into())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Translate guest virtual address to guest physical address
@@ -729,6 +1240,7 @@ impl cpu::Vcpu for MshvVcpu {
 
         Ok((gpa, result_code))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Return the list of initial MSR entries for a VCPU
@@ -749,6 +1261,18 @@ impl cpu::Vcpu for MshvVcpu {
         ]
         .to_vec()
     }
+
+    ///
+    /// Sets the AMD specific vcpu's sev control register.
+    ///
+    #[cfg(feature = "sev_snp")]
+    fn set_sev_control_register(&self, vmsa_pfn: u64) -> cpu::Result<()> {
+        let sev_control_reg = snp::get_sev_control_register(vmsa_pfn);
+
+        self.fd
+            .set_sev_control_register(sev_control_reg)
+            .map_err(|e| cpu::HypervisorCpuError::SetSevControlRegister(e.into()))
+    }
 }
 
 impl MshvVcpu {
@@ -761,6 +1285,7 @@ impl MshvVcpu {
             .get_xsave()
             .map_err(|e| cpu::HypervisorCpuError::GetXsaveState(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call that sets the vcpu's current "xsave struct".
@@ -770,6 +1295,7 @@ impl MshvVcpu {
             .set_xsave(xsave)
             .map_err(|e| cpu::HypervisorCpuError::SetXsaveState(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call that returns the vcpu's current "xcrs".
@@ -779,6 +1305,7 @@ impl MshvVcpu {
             .get_xcrs()
             .map_err(|e| cpu::HypervisorCpuError::GetXcsr(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call that sets the vcpu's current "xcrs".
@@ -788,6 +1315,7 @@ impl MshvVcpu {
             .set_xcrs(xcrs)
             .map_err(|e| cpu::HypervisorCpuError::SetXcsr(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Returns currently pending exceptions, interrupts, and NMIs as well as related
@@ -798,6 +1326,7 @@ impl MshvVcpu {
             .get_vcpu_events()
             .map_err(|e| cpu::HypervisorCpuError::GetVcpuEvents(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets pending exceptions, interrupts, and NMIs as well as related states
@@ -940,6 +1469,8 @@ pub struct MshvVm {
     fd: Arc<VmFd>,
     msrs: Vec<MsrEntry>,
     dirty_log_slots: Arc<RwLock<HashMap<u64, MshvDirtyLogSlot>>>,
+    #[cfg(feature = "sev_snp")]
+    sev_snp_enabled: bool,
 }
 
 impl MshvVm {
@@ -977,6 +1508,7 @@ impl vm::Vm for MshvVm {
     fn set_identity_map_address(&self, _address: u64) -> vm::Result<()> {
         Ok(())
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Sets the address of the three-page region in the VM's address space.
@@ -984,12 +1516,14 @@ impl vm::Vm for MshvVm {
     fn set_tss_address(&self, _offset: usize) -> vm::Result<()> {
         Ok(())
     }
+
     ///
     /// Creates an in-kernel interrupt controller.
     ///
     fn create_irq_chip(&self) -> vm::Result<()> {
         Ok(())
     }
+
     ///
     /// Registers an event that will, when signaled, trigger the `gsi` IRQ.
     ///
@@ -1002,6 +1536,7 @@ impl vm::Vm for MshvVm {
 
         Ok(())
     }
+
     ///
     /// Unregisters an event that will, when signaled, trigger the `gsi` IRQ.
     ///
@@ -1014,6 +1549,7 @@ impl vm::Vm for MshvVm {
 
         Ok(())
     }
+
     ///
     /// Creates a VcpuFd object from a vcpu RawFd.
     ///
@@ -1032,23 +1568,33 @@ impl vm::Vm for MshvVm {
             cpuid: Vec::new(),
             msrs: self.msrs.clone(),
             vm_ops,
+            #[cfg(feature = "sev_snp")]
+            vm_fd: self.fd.clone(),
         };
         Ok(Arc::new(vcpu))
     }
+
     #[cfg(target_arch = "x86_64")]
     fn enable_split_irq(&self) -> vm::Result<()> {
         Ok(())
     }
+
     #[cfg(target_arch = "x86_64")]
     fn enable_sgx_attribute(&self, _file: File) -> vm::Result<()> {
         Ok(())
     }
+
     fn register_ioevent(
         &self,
         fd: &EventFd,
         addr: &IoEventAddress,
         datamatch: Option<DataMatch>,
     ) -> vm::Result<()> {
+        #[cfg(feature = "sev_snp")]
+        if self.sev_snp_enabled {
+            return Ok(());
+        }
+
         let addr = &mshv_ioctls::IoEventAddress::from(*addr);
         debug!(
             "register_ioevent fd {} addr {:x?} datamatch {:?}",
@@ -1073,6 +1619,7 @@ impl vm::Vm for MshvVm {
                 .map_err(|e| vm::HypervisorVmError::RegisterIoEvent(e.into()))
         }
     }
+
     /// Unregister an event from a certain address it has been previously registered to.
     fn unregister_ioevent(&self, fd: &EventFd, addr: &IoEventAddress) -> vm::Result<()> {
         let addr = &mshv_ioctls::IoEventAddress::from(*addr);
@@ -1127,7 +1674,7 @@ impl vm::Vm for MshvVm {
         readonly: bool,
         _log_dirty_pages: bool,
     ) -> UserMemoryRegion {
-        let mut flags = HV_MAP_GPA_READABLE | HV_MAP_GPA_EXECUTABLE;
+        let mut flags = HV_MAP_GPA_READABLE | HV_MAP_GPA_EXECUTABLE | HV_MAP_GPA_ADJUSTABLE;
         if !readonly {
             flags |= HV_MAP_GPA_WRITABLE;
         }
@@ -1197,6 +1744,7 @@ impl vm::Vm for MshvVm {
             .set_msi_routing(&msi_routing[0])
             .map_err(|e| vm::HypervisorVmError::SetGsiRouting(e.into()))
     }
+
     ///
     /// Start logging dirty pages
     ///
@@ -1205,6 +1753,7 @@ impl vm::Vm for MshvVm {
             .enable_dirty_page_tracking()
             .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))
     }
+
     ///
     /// Stop logging dirty pages
     ///
@@ -1223,6 +1772,7 @@ impl vm::Vm for MshvVm {
             .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))?;
         Ok(())
     }
+
     ///
     /// Get dirty pages bitmap (one bit per page)
     ///
@@ -1235,18 +1785,115 @@ impl vm::Vm for MshvVm {
             )
             .map_err(|e| vm::HypervisorVmError::GetDirtyLog(e.into()))
     }
+
     /// Retrieve guest clock.
     #[cfg(target_arch = "x86_64")]
     fn get_clock(&self) -> vm::Result<ClockData> {
         Ok(ClockData::Mshv)
     }
+
     /// Set guest clock.
     #[cfg(target_arch = "x86_64")]
     fn set_clock(&self, _data: &ClockData) -> vm::Result<()> {
         Ok(())
     }
+
     /// Downcast to the underlying MshvVm type
     fn as_any(&self) -> &dyn Any {
         self
     }
+
+    /// Initialize the SEV-SNP VM
+    #[cfg(feature = "sev_snp")]
+    fn sev_snp_init(&self) -> vm::Result<()> {
+        self.fd
+            .set_partition_property(
+                hv_partition_property_code_HV_PARTITION_PROPERTY_ISOLATION_STATE,
+                hv_partition_isolation_state_HV_PARTITION_ISOLATION_SECURE as u64,
+            )
+            .map_err(|e| vm::HypervisorVmError::InitializeSevSnp(e.into()))
+    }
+
+    ///
+    /// Importing isolated pages, these pages will be used
+    /// for the PSP(Platform Security Processor) measurement.
+    #[cfg(feature = "sev_snp")]
+    fn import_isolated_pages(
+        &self,
+        page_type: u32,
+        page_size: u32,
+        pages: &[u64],
+    ) -> vm::Result<()> {
+        if pages.is_empty() {
+            return Ok(());
+        }
+
+        let mut isolated_pages =
+            vec_with_array_field::<mshv_import_isolated_pages, u64>(pages.len());
+        isolated_pages[0].num_pages = pages.len() as u64;
+        isolated_pages[0].page_type = page_type;
+        isolated_pages[0].page_size = page_size;
+        // SAFETY: isolated_pages initialized with pages.len() and now it is being turned into
+        // pages_slice with pages.len() again. It is guaranteed to be large enough to hold
+        // everything from pages.
+        unsafe {
+            let pages_slice: &mut [u64] = isolated_pages[0].page_number.as_mut_slice(pages.len());
+            pages_slice.copy_from_slice(pages);
+        }
+        self.fd
+            .import_isolated_pages(&isolated_pages[0])
+            .map_err(|e| vm::HypervisorVmError::ImportIsolatedPages(e.into()))
+    }
+
+    ///
+    /// Complete isolated import, telling the hypervisor that
+    /// importing the pages to guest memory is complete.
+    ///
+    #[cfg(feature = "sev_snp")]
+    fn complete_isolated_import(
+        &self,
+        snp_id_block: IGVM_VHS_SNP_ID_BLOCK,
+        host_data: [u8; 32],
+        id_block_enabled: u8,
+    ) -> vm::Result<()> {
+        let mut auth_info = hv_snp_id_auth_info {
+            id_key_algorithm: snp_id_block.id_key_algorithm,
+            auth_key_algorithm: snp_id_block.author_key_algorithm,
+            ..Default::default()
+        };
+        // Each of r/s component is 576 bits long
+        auth_info.id_block_signature[..SIG_R_COMPONENT_SIZE_IN_BYTES]
+            .copy_from_slice(snp_id_block.id_key_signature.r_comp.as_ref());
+        auth_info.id_block_signature
+            [SIG_R_COMPONENT_SIZE_IN_BYTES..SIG_R_AND_S_COMPONENT_SIZE_IN_BYTES]
+            .copy_from_slice(snp_id_block.id_key_signature.s_comp.as_ref());
+        auth_info.id_key[..ECDSA_CURVE_ID_SIZE_IN_BYTES]
+            .copy_from_slice(snp_id_block.id_public_key.curve.to_le_bytes().as_ref());
+        auth_info.id_key[ECDSA_SIG_X_COMPONENT_START..ECDSA_SIG_X_COMPONENT_END]
+            .copy_from_slice(snp_id_block.id_public_key.qx.as_ref());
+        auth_info.id_key[ECDSA_SIG_Y_COMPONENT_START..ECDSA_SIG_Y_COMPONENT_END]
+            .copy_from_slice(snp_id_block.id_public_key.qy.as_ref());
+
+        let data = mshv_complete_isolated_import {
+            import_data: hv_partition_complete_isolated_import_data {
+                psp_parameters: hv_psp_launch_finish_data {
+                    id_block: hv_snp_id_block {
+                        launch_digest: snp_id_block.ld,
+                        family_id: snp_id_block.family_id,
+                        image_id: snp_id_block.image_id,
+                        version: snp_id_block.version,
+                        guest_svn: snp_id_block.guest_svn,
+                        policy: get_default_snp_guest_policy(),
+                    },
+                    id_auth_info: auth_info,
+                    host_data,
+                    id_block_enabled,
+                    author_key_enabled: 0,
+                },
+            },
+        };
+        self.fd
+            .complete_isolated_import(&data)
+            .map_err(|e| vm::HypervisorVmError::CompleteIsolatedImport(e.into()))
+    }
 }

hypervisor/src/mshv/snp_constants.rs

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause
+//
+// Copyright © 2020, Microsoft Corporation
+//
+
+// Reference: https://www.amd.com/content/dam/amd/en/documents/epyc-technical-docs/specifications/56860.pdf
+// Chapter 10
+pub const SIG_R_COMPONENT_SIZE_IN_BYTES: usize = 72;
+pub const SIG_R_AND_S_COMPONENT_SIZE_IN_BYTES: usize = 144;
+pub const ECDSA_CURVE_ID_SIZE_IN_BYTES: usize = 4;
+pub const ECDSA_SIG_X_COMPONENT_SIZE_IN_BYTES: usize = 72;
+pub const ECDSA_SIG_Y_COMPONENT_SIZE_IN_BYTES: usize = 72;
+pub const ECDSA_SIG_X_COMPONENT_START: usize = ECDSA_CURVE_ID_SIZE_IN_BYTES;
+pub const ECDSA_SIG_X_COMPONENT_END: usize =
+    ECDSA_SIG_X_COMPONENT_START + ECDSA_SIG_X_COMPONENT_SIZE_IN_BYTES;
+pub const ECDSA_SIG_Y_COMPONENT_START: usize = ECDSA_SIG_X_COMPONENT_END;
+pub const ECDSA_SIG_Y_COMPONENT_END: usize =
+    ECDSA_SIG_X_COMPONENT_END + ECDSA_SIG_Y_COMPONENT_SIZE_IN_BYTES;
+
+// These constants are derived from GHCB spec Sect. 2.6 Table 3 GHCB Layout
+// Link: https://www.amd.com/content/dam/amd/en/documents/epyc-technical-docs/specifications/56421.pdf
+pub const GHCB_RAX_OFFSET: u64 = 0x01F8;
+pub const GHCB_SW_EXITINFO1_OFFSET: u64 = 0x398;
+pub const GHCB_SW_EXITINFO2_OFFSET: u64 = 0x3A0;

hypervisor/src/vm.rs

@@ -19,6 +19,8 @@ use crate::cpu::Vcpu;
 use crate::ClockData;
 use crate::UserMemoryRegion;
 use crate::{IoEventAddress, IrqRoutingEntry};
+#[cfg(feature = "sev_snp")]
+use igvm_defs::IGVM_VHS_SNP_ID_BLOCK;
 use std::any::Any;
 #[cfg(target_arch = "x86_64")]
 use std::fs::File;
@@ -190,6 +192,13 @@ pub enum HypervisorVmError {
     #[error("Failed to assert virtual Interrupt: {0}")]
     AsserttVirtualInterrupt(#[source] anyhow::Error),
 
+    #[cfg(feature = "sev_snp")]
+    ///
+    /// Error initializing SEV-SNP on the VM
+    ///
+    #[error("Failed to initialize SEV-SNP: {0}")]
+    InitializeSevSnp(#[source] std::io::Error),
+
     #[cfg(feature = "tdx")]
     ///
     /// Error initializing TDX on the VM
@@ -213,6 +222,15 @@ pub enum HypervisorVmError {
     ///
     #[error("Failed to create Vgic: {0}")]
     CreateVgic(#[source] anyhow::Error),
+    ///
+    /// Import isolated pages error
+    ///
+    #[error("Failed to import isolated pages: {0}")]
+    ImportIsolatedPages(#[source] anyhow::Error),
+    /// Failed to complete isolated import
+    ///
+    #[error("Failed to complete isolated import: {0}")]
+    CompleteIsolatedImport(#[source] anyhow::Error),
 }
 ///
 /// Result type for returning from a function
@@ -324,6 +342,11 @@ pub trait Vm: Send + Sync + Any {
     fn stop_dirty_log(&self) -> Result<()>;
     /// Get dirty pages bitmap
     fn get_dirty_log(&self, slot: u32, base_gpa: u64, memory_size: u64) -> Result<Vec<u64>>;
+    #[cfg(feature = "sev_snp")]
+    /// Initialize SEV-SNP on this VM
+    fn sev_snp_init(&self) -> Result<()> {
+        unimplemented!()
+    }
     #[cfg(feature = "tdx")]
     /// Initialize TDX on this VM
     fn tdx_init(&self, _cpuid: &[CpuIdEntry], _max_vcpus: u32) -> Result<()> {
@@ -347,6 +370,26 @@ pub trait Vm: Send + Sync + Any {
     }
     /// Downcast to the underlying hypervisor VM type
     fn as_any(&self) -> &dyn Any;
+    /// Import the isolated pages
+    #[cfg(feature = "sev_snp")]
+    fn import_isolated_pages(
+        &self,
+        _page_type: u32,
+        _page_size: u32,
+        _pages: &[u64],
+    ) -> Result<()> {
+        unimplemented!()
+    }
+    /// Complete the isolated import
+    #[cfg(feature = "sev_snp")]
+    fn complete_isolated_import(
+        &self,
+        _snp_id_block: IGVM_VHS_SNP_ID_BLOCK,
+        _host_data: [u8; 32],
+        _id_block_enabled: u8,
+    ) -> Result<()> {
+        unimplemented!()
+    }
 }
 
 pub trait VmOps: Send + Sync {

net_gen/Cargo.toml

@@ -5,4 +5,4 @@ authors = ["The Chromium OS Authors"]
 edition = "2021"
 
 [dependencies]
-vmm-sys-util = "0.11.0"
+vmm-sys-util = "0.12.1"

net_util/Cargo.toml

@@ -6,23 +6,23 @@ edition = "2021"
 
 [dependencies]
 epoll = "4.3.3"
-getrandom = "0.2.10"
-libc = "0.2.147"
-log = "0.4.17"
+getrandom = "0.2.11"
+libc = "0.2.153"
+log = "0.4.20"
 net_gen = { path = "../net_gen" }
 rate_limiter = { path = "../rate_limiter" }
-serde = "1.0.168"
-thiserror = "1.0.40"
-versionize = "0.1.10"
-versionize_derive = "0.1.4"
+serde = "1.0.196"
+thiserror = "1.0.52"
+versionize = "0.2.0"
+versionize_derive = "0.1.6"
 virtio-bindings = "0.2.0"
-virtio-queue = "0.9.0"
-vm-memory = { version = "0.12.2", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+virtio-queue = "0.11.0"
+vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-virtio = { path = "../vm-virtio" }
-vmm-sys-util = "0.11.0"
+vmm-sys-util = "0.12.1"
 
 [dev-dependencies]
-once_cell = "1.18.0"
+once_cell = "1.19.0"
 pnet = "0.34.0"
 pnet_datalink = "0.34.0"
-serde_json = "1.0.107"
+serde_json = "1.0.109"

net_util/src/open_tap.rs

@@ -72,6 +72,10 @@ pub fn open_tap(
     let mut taps: Vec<Tap> = Vec::new();
     let mut ifname: String = String::new();
     let vnet_hdr_size = vnet_hdr_len() as i32;
+    // Check if the given interface exists before we create it.
+    let tap_existed = if_name.map_or(false, |n| {
+        Path::new(&format!("/sys/class/net/{n}")).exists()
+    });
 
     // In case the tap interface already exists, check if the number of
     // queues is appropriate. The tap might not support multiqueue while
@@ -87,11 +91,19 @@ pub fn open_tap(
                 Some(name) => Tap::open_named(name, num_rx_q, flags).map_err(Error::TapOpen)?,
                 None => Tap::new(num_rx_q).map_err(Error::TapOpen)?,
             };
-            if let Some(ip) = ip_addr {
-                tap.set_ip_addr(ip).map_err(Error::TapSetIp)?;
-            }
-            if let Some(mask) = netmask {
-                tap.set_netmask(mask).map_err(Error::TapSetNetmask)?;
+            // Don't overwrite ip configuration of existing interfaces:
+            if !tap_existed {
+                if let Some(ip) = ip_addr {
+                    tap.set_ip_addr(ip).map_err(Error::TapSetIp)?;
+                }
+                if let Some(mask) = netmask {
+                    tap.set_netmask(mask).map_err(Error::TapSetNetmask)?;
+                }
+            } else {
+                warn!(
+                    "Tap {} already exists. IP configuration will not be overwritten.",
+                    if_name.unwrap_or_default()
+                );
             }
             if let Some(mac) = host_mac {
                 tap.set_mac_addr(*mac).map_err(Error::TapSetMac)?

option_parser/src/lib.rs

@@ -290,6 +290,17 @@ impl TupleValue for Vec<u64> {
     }
 }
 
+impl TupleValue for Vec<usize> {
+    fn parse_value(input: &str) -> Result<Self, TupleError> {
+        Ok(IntegerList::from_str(input)
+            .map_err(TupleError::InvalidIntegerList)?
+            .0
+            .iter()
+            .map(|v| *v as usize)
+            .collect())
+    }
+}
+
 pub struct Tuple<S, T>(pub Vec<(S, T)>);
 
 pub enum TupleError {

pci/Cargo.toml

@@ -10,21 +10,21 @@ kvm = ["vfio-ioctls/kvm"]
 mshv = ["vfio-ioctls/mshv"]
 
 [dependencies]
-anyhow = "1.0.75"
+anyhow = "1.0.79"
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
 vfio-bindings = { git = "https://github.com/rust-vmm/vfio", branch = "main", features = ["fam-wrappers"] }
 vfio-ioctls = { git = "https://github.com/rust-vmm/vfio", branch = "main", default-features = false }
 vfio_user = { git = "https://github.com/rust-vmm/vfio-user", branch = "main" }
 
-vmm-sys-util = "0.11.0"
-libc = "0.2.147"
-log = "0.4.17"
-serde = { version = "1.0.168", features = ["derive"] }
-thiserror = "1.0.40"
-versionize = "0.1.10"
-versionize_derive = "0.1.4"
+vmm-sys-util = "0.12.1"
+libc = "0.2.153"
+log = "0.4.20"
+serde = { version = "1.0.196", features = ["derive"] }
+thiserror = "1.0.52"
+versionize = "0.2.0"
+versionize_derive = "0.1.6"
 vm-allocator = { path = "../vm-allocator" }
 vm-device = { path = "../vm-device" }
-vm-memory = { version = "0.12.2", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+vm-memory = { version = "0.14.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-migration = { path = "../vm-migration" }

pci/src/device.rs

@@ -58,7 +58,8 @@ pub trait PciDevice: BusDevice {
     fn allocate_bars(
         &mut self,
         _allocator: &Arc<Mutex<SystemAllocator>>,
-        _mmio_allocator: &mut AddressAllocator,
+        _mmio32_allocator: &mut AddressAllocator,
+        _mmio64_allocator: &mut AddressAllocator,
         _resources: Option<Vec<Resource>>,
     ) -> Result<Vec<PciBarConfiguration>> {
         Ok(Vec::new())
@@ -68,7 +69,8 @@ pub trait PciDevice: BusDevice {
     fn free_bars(
         &mut self,
         _allocator: &mut SystemAllocator,
-        _mmio_allocator: &mut AddressAllocator,
+        _mmio32_allocator: &mut AddressAllocator,
+        _mmio64_allocator: &mut AddressAllocator,
     ) -> Result<()> {
         Ok(())
     }

pci/src/vfio.rs

@@ -529,10 +529,13 @@ impl VfioCommon {
         }
     }
 
+    // The `allocator` argument is unused on `aarch64`
+    #[allow(unused_variables)]
     pub(crate) fn allocate_bars(
         &mut self,
         allocator: &Arc<Mutex<SystemAllocator>>,
-        mmio_allocator: &mut AddressAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        mmio64_allocator: &mut AddressAllocator,
         resources: Option<Vec<Resource>>,
     ) -> Result<Vec<PciBarConfiguration>, PciDeviceError> {
         let mut bars = Vec::new();
@@ -681,26 +684,23 @@ impl VfioCommon {
                 }
                 PciBarRegionType::Memory32BitRegion => {
                     // BAR allocation must be naturally aligned
-                    allocator
-                        .lock()
-                        .unwrap()
-                        .allocate_mmio_hole_addresses(
-                            restored_bar_addr,
-                            region_size,
-                            Some(region_size),
-                        )
+                    mmio32_allocator
+                        .allocate(restored_bar_addr, region_size, Some(region_size))
                         .ok_or(PciDeviceError::IoAllocationFailed(region_size))?
                 }
                 PciBarRegionType::Memory64BitRegion => {
                     // We need do some fixup to keep MMIO RW region and msix cap region page size
                     // aligned.
                     region_size = self.fixup_msix_region(bar_id, region_size);
-                    mmio_allocator
+                    mmio64_allocator
                         .allocate(
                             restored_bar_addr,
                             region_size,
-                            // SAFETY: FFI call. Trivially safe.
-                            Some(unsafe { sysconf(_SC_PAGESIZE) as GuestUsize }),
+                            Some(std::cmp::max(
+                                // SAFETY: FFI call. Trivially safe.
+                                unsafe { sysconf(_SC_PAGESIZE) as GuestUsize },
+                                region_size,
+                            )),
                         )
                         .ok_or(PciDeviceError::IoAllocationFailed(region_size))?
                 }
@@ -742,10 +742,13 @@ impl VfioCommon {
         Ok(bars)
     }
 
+    // The `allocator` argument is unused on `aarch64`
+    #[allow(unused_variables)]
     pub(crate) fn free_bars(
         &mut self,
         allocator: &mut SystemAllocator,
-        mmio_allocator: &mut AddressAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        mmio64_allocator: &mut AddressAllocator,
     ) -> Result<(), PciDeviceError> {
         for region in self.mmio_regions.iter() {
             match region.type_ {
@@ -756,10 +759,10 @@ impl VfioCommon {
                     error!("I/O region is not supported");
                 }
                 PciBarRegionType::Memory32BitRegion => {
-                    allocator.free_mmio_hole_addresses(region.start, region.length);
+                    mmio32_allocator.free(region.start, region.length);
                 }
                 PciBarRegionType::Memory64BitRegion => {
-                    mmio_allocator.free(region.start, region.length);
+                    mmio64_allocator.free(region.start, region.length);
                 }
             }
         }
@@ -1568,6 +1571,16 @@ impl VfioPciDevice {
                     self.vm
                         .create_user_memory_region(mem_region)
                         .map_err(VfioPciError::CreateUserMemoryRegion)?;
+
+                    if !self.iommu_attached {
+                        self.container
+                            .vfio_dma_map(
+                                user_memory_region.start,
+                                user_memory_region.size,
+                                user_memory_region.host_addr,
+                            )
+                            .map_err(VfioPciError::DmaMap)?;
+                    }
                 }
             }
         }
@@ -1578,6 +1591,16 @@ impl VfioPciDevice {
     pub fn unmap_mmio_regions(&mut self) {
         for region in self.common.mmio_regions.iter() {
             for user_memory_region in region.user_memory_regions.iter() {
+                // Unmap from vfio container
+                if !self.iommu_attached {
+                    if let Err(e) = self
+                        .container
+                        .vfio_dma_unmap(user_memory_region.start, user_memory_region.size)
+                    {
+                        error!("Could not unmap mmio region from vfio container: {}", e);
+                    }
+                }
+
                 // Remove region
                 let r = self.vm.make_user_memory_region(
                     user_memory_region.slot,
@@ -1694,19 +1717,22 @@ impl PciDevice for VfioPciDevice {
     fn allocate_bars(
         &mut self,
         allocator: &Arc<Mutex<SystemAllocator>>,
-        mmio_allocator: &mut AddressAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        mmio64_allocator: &mut AddressAllocator,
         resources: Option<Vec<Resource>>,
     ) -> Result<Vec<PciBarConfiguration>, PciDeviceError> {
         self.common
-            .allocate_bars(allocator, mmio_allocator, resources)
+            .allocate_bars(allocator, mmio32_allocator, mmio64_allocator, resources)
     }
 
     fn free_bars(
         &mut self,
         allocator: &mut SystemAllocator,
-        mmio_allocator: &mut AddressAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        mmio64_allocator: &mut AddressAllocator,
     ) -> Result<(), PciDeviceError> {
-        self.common.free_bars(allocator, mmio_allocator)
+        self.common
+            .free_bars(allocator, mmio32_allocator, mmio64_allocator)
     }
 
     fn write_config_register(

pci/src/vfio_user.rs

@@ -397,19 +397,22 @@ impl PciDevice for VfioUserPciDevice {
     fn allocate_bars(
         &mut self,
         allocator: &Arc<Mutex<SystemAllocator>>,
-        mmio_allocator: &mut AddressAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        mmio64_allocator: &mut AddressAllocator,
         resources: Option<Vec<Resource>>,
     ) -> Result<Vec<PciBarConfiguration>, PciDeviceError> {
         self.common
-            .allocate_bars(allocator, mmio_allocator, resources)
+            .allocate_bars(allocator, mmio32_allocator, mmio64_allocator, resources)
     }
 
     fn free_bars(
         &mut self,
         allocator: &mut SystemAllocator,
-        mmio_allocator: &mut AddressAllocator,
+        mmio32_allocator: &mut AddressAllocator,
+        mmio64_allocator: &mut AddressAllocator,
     ) -> Result<(), PciDeviceError> {
-        self.common.free_bars(allocator, mmio_allocator)
+        self.common
+            .free_bars(allocator, mmio32_allocator, mmio64_allocator)
     }
 
     fn as_any(&mut self) -> &mut dyn Any {

performance-metrics/Cargo.toml

@@ -6,10 +6,10 @@ edition = "2021"
 build = "../build.rs"
 
 [dependencies]
-argh = "0.1.9"
+clap = { version = "4.4.7", features = ["wrap_help"] }
 dirs = "5.0.0"
-serde = { version = "1.0.168", features = ["rc", "derive"] }
-serde_json = "1.0.107"
+serde = { version = "1.0.196", features = ["rc", "derive"] }
+serde_json = "1.0.109"
 test_infra = { path = "../test_infra" }
-thiserror = "1.0.40"
+thiserror = "1.0.52"
 wait-timeout = "0.2.0"

performance-metrics/src/main.rs

@@ -8,11 +8,11 @@ extern crate test_infra;
 
 mod performance_tests;
 
-use argh::FromArgs;
+use clap::{Arg, ArgAction, Command as ClapCommand};
 use performance_tests::*;
 use serde::{Deserialize, Serialize};
 use std::{
-    fmt,
+    env, fmt,
     process::Command,
     sync::{mpsc::channel, Arc},
     thread,
@@ -639,41 +639,45 @@ fn date() -> String {
     String::from_utf8_lossy(&output.stdout).trim().to_string()
 }
 
-#[derive(FromArgs)]
-/// Generate the performance metrics data for Cloud Hypervisor
-struct Options {
-    #[argh(switch, long = "list-tests")]
-    /// print the list of available metrics tests
-    list_tests: bool,
-
-    #[argh(option, long = "test-filter")]
-    /// filter metrics tests to run based on provided keywords
-    keywords: Vec<String>,
-
-    #[argh(option, long = "report-file")]
-    /// report file. Stderr is used if not specified
-    report_file: Option<String>,
-
-    #[argh(option, long = "iterations")]
-    /// override number of test iterations
-    iterations: Option<u32>,
-
-    #[argh(option, long = "timeout")]
-    /// override test timeout, Ex. --timeout 5
-    timeout: Option<u32>,
-
-    #[argh(switch, short = 'V', long = "version")]
-    /// print version information
-    version: bool,
-}
-
 fn main() {
-    let opts: Options = argh::from_env();
-
-    if opts.version {
-        println!("{} {}", env!("CARGO_BIN_NAME"), env!("BUILD_VERSION"));
-        return;
-    }
+    let cmd_arguments = ClapCommand::new("performance-metrics")
+        .version(env!("CARGO_PKG_VERSION"))
+        .author(env!("CARGO_PKG_AUTHORS"))
+        .about("Generate the performance metrics data for Cloud Hypervisor")
+        .arg(
+            Arg::new("test-filter")
+                .long("test-filter")
+                .help("Filter metrics tests to run based on provided keywords")
+                .num_args(1)
+                .required(false),
+        )
+        .arg(
+            Arg::new("list-tests")
+                .long("list-tests")
+                .help("Print the list of available metrics tests")
+                .num_args(0)
+                .action(ArgAction::SetTrue)
+                .required(false),
+        )
+        .arg(
+            Arg::new("report-file")
+                .long("report-file")
+                .help("Report file. Standard error is used if not specified")
+                .num_args(1),
+        )
+        .arg(
+            Arg::new("iterations")
+                .long("iterations")
+                .help("Override number of test iterations")
+                .num_args(1),
+        )
+        .arg(
+            Arg::new("timeout")
+                .long("timeout")
+                .help("Override test timeout, Ex. --timeout 5")
+                .num_args(1),
+        )
+        .get_matches();
 
     // It seems that the tool (ethr) used for testing the virtio-net latency
     // is not stable on AArch64, and therefore the latency test is currently
@@ -683,7 +687,7 @@ fn main() {
         .filter(|t| !(cfg!(target_arch = "aarch64") && t.name == "virtio_net_latency_us"))
         .collect();
 
-    if opts.list_tests {
+    if cmd_arguments.get_flag("list-tests") {
         for test in test_list.iter() {
             println!("\"{}\" ({})", test.name, test.control);
         }
@@ -691,7 +695,10 @@ fn main() {
         return;
     }
 
-    let test_filter = opts.keywords.iter().collect::<Vec<&String>>();
+    let test_filter = match cmd_arguments.get_many::<String>("test-filter") {
+        Some(s) => s.collect(),
+        None => Vec::new(),
+    };
 
     // Run performance tests sequentially and report results (in both readable/json format)
     let mut metrics_report: MetricsReport = Default::default();
@@ -699,8 +706,16 @@ fn main() {
     init_tests();
 
     let overrides = Arc::new(PerformanceTestOverrides {
-        test_iterations: opts.iterations,
-        test_timeout: opts.timeout,
+        test_iterations: cmd_arguments
+            .get_one::<String>("iterations")
+            .map(|s| s.parse())
+            .transpose()
+            .unwrap_or_default(),
+        test_timeout: cmd_arguments
+            .get_one::<String>("timeout")
+            .map(|s| s.parse())
+            .transpose()
+            .unwrap_or_default(),
     });
 
     for test in test_list.iter() {
@@ -719,18 +734,19 @@ fn main() {
 
     cleanup_tests();
 
-    let mut report_file: Box<dyn std::io::Write + Send> = if let Some(ref file) = opts.report_file {
-        Box::new(
-            std::fs::File::create(std::path::Path::new(file))
-                .map_err(|e| {
-                    eprintln!("Error opening report file: {file}: {e}");
-                    std::process::exit(1);
-                })
-                .unwrap(),
-        )
-    } else {
-        Box::new(std::io::stdout())
-    };
+    let mut report_file: Box<dyn std::io::Write + Send> =
+        if let Some(file) = cmd_arguments.get_one::<String>("report-file") {
+            Box::new(
+                std::fs::File::create(std::path::Path::new(file))
+                    .map_err(|e| {
+                        eprintln!("Error opening report file: {file}: {e}");
+                        std::process::exit(1);
+                    })
+                    .unwrap(),
+            )
+        } else {
+            Box::new(std::io::stdout())
+        };
 
     report_file
         .write_all(

performance-metrics/src/performance_tests.rs

@@ -19,6 +19,7 @@ pub const FOCAL_IMAGE_NAME: &str = "focal-server-cloudimg-amd64-custom-20210609-
 #[cfg(target_arch = "aarch64")]
 pub const FOCAL_IMAGE_NAME: &str = "focal-server-cloudimg-arm64-custom-20210929-0-update-tool.raw";
 
+#[allow(dead_code)]
 #[derive(Debug)]
 enum Error {
     BootTimeParse,
@@ -358,13 +359,11 @@ pub fn performance_block_io(control: &PerformanceTestControl) -> f64 {
                 guest.disk_config.disk(DiskType::OperatingSystem).unwrap()
             )
             .as_str(),
-            "--disk",
             format!(
                 "path={}",
                 guest.disk_config.disk(DiskType::CloudInit).unwrap()
             )
             .as_str(),
-            "--disk",
             format!("path={BLK_IO_TEST_IMG}").as_str(),
         ])
         .default_net()

rate_limiter/Cargo.toml

@@ -4,6 +4,8 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
-libc = "0.2.147"
-log = "0.4.17"
-vmm-sys-util = "0.11.0"
+epoll = "4.3.3"
+libc = "0.2.153"
+log = "0.4.20"
+thiserror = "1.0.40"
+vmm-sys-util = "0.12.1"

rate_limiter/src/group.rs

@@ -0,0 +1,526 @@
+// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+//
+// Copyright 2023 Crusoe Energy Systems LLC
+// SPDX-License-Identifier: Apache-2.0
+
+use crate::{RateLimiter, TokenType};
+use core::panic::AssertUnwindSafe;
+use std::fs::File;
+use std::io;
+use std::os::unix::io::{AsRawFd, FromRawFd, RawFd};
+use std::result;
+use std::sync::{Arc, Mutex};
+use std::thread;
+use thiserror::Error;
+use vmm_sys_util::eventfd::EventFd;
+
+/// Errors associated with rate-limiter group.
+#[derive(Debug, Error)]
+pub enum Error {
+    /// Cannot create thread
+    #[error("Error spawning rate-limiter thread {0}")]
+    ThreadSpawn(#[source] io::Error),
+
+    /// Cannot create epoll context.
+    #[error("Error creating epoll context: {0}")]
+    Epoll(#[source] io::Error),
+
+    /// Cannot create EventFd.
+    #[error("Error creating EventFd: {0}")]
+    EventFd(#[source] io::Error),
+
+    /// Cannot create RateLimiter.
+    #[error("Error creating RateLimiter: {0}")]
+    RateLimiter(#[source] io::Error),
+
+    /// Cannot read from EventFd.
+    #[error("Error reading from EventFd: {0}")]
+    EventFdRead(#[source] io::Error),
+
+    /// Cannot write to EventFd.
+    #[error("Error writing to EventFd: {0}")]
+    EventFdWrite(#[source] io::Error),
+}
+
+/// The RateLimiterGroupHandle is a handle to a RateLimiterGroup that may be
+/// used in exactly the same way as the RateLimiter type. When the RateLimiter
+/// within a RateLimiterGroup is unblocked, each RateLimiterGroupHandle will
+/// be notified.
+pub struct RateLimiterGroupHandle {
+    eventfd: Arc<EventFd>,
+    inner: Arc<RateLimiterGroupInner>,
+}
+
+impl RateLimiterGroupHandle {
+    fn new(inner: Arc<RateLimiterGroupInner>) -> result::Result<Self, Error> {
+        let eventfd = Arc::new(EventFd::new(0).map_err(Error::EventFd)?);
+        inner.handles.lock().unwrap().push(eventfd.clone());
+        Ok(Self { eventfd, inner })
+    }
+
+    /// Attempts to consume tokens and returns whether that is possible.
+    ///
+    /// If rate limiting is disabled on provided `token_type`, this function will always succeed.
+    pub fn consume(&self, tokens: u64, token_type: TokenType) -> bool {
+        self.inner.rate_limiter.consume(tokens, token_type)
+    }
+
+    /// Adds tokens of `token_type` to their respective bucket.
+    ///
+    /// Can be used to *manually* add tokens to a bucket. Useful for reverting a
+    /// `consume()` if needed.
+    pub fn manual_replenish(&self, tokens: u64, token_type: TokenType) {
+        self.inner.rate_limiter.manual_replenish(tokens, token_type)
+    }
+
+    /// This function needs to be called every time there is an event on the
+    /// FD provided by this object's `AsRawFd` trait implementation.
+    ///
+    /// # Errors
+    ///
+    /// If the rate limiter is disabled or is not blocked, an error is returned.
+    pub fn event_handler(&self) -> Result<(), Error> {
+        self.eventfd.read().map_err(Error::EventFdRead).map(|_| ())
+    }
+
+    /// Returns whether this rate limiter is blocked.
+    ///
+    /// The limiter 'blocks' when a `consume()` operation fails because there was not enough
+    /// budget for it.
+    /// An event will be generated on the exported FD when the limiter 'unblocks'.
+    pub fn is_blocked(&self) -> bool {
+        self.inner.rate_limiter.is_blocked()
+    }
+}
+
+impl Clone for RateLimiterGroupHandle {
+    fn clone(&self) -> Self {
+        RateLimiterGroupHandle::new(self.inner.clone()).unwrap()
+    }
+}
+
+impl AsRawFd for RateLimiterGroupHandle {
+    fn as_raw_fd(&self) -> RawFd {
+        self.eventfd.as_raw_fd()
+    }
+}
+
+impl Drop for RateLimiterGroupHandle {
+    fn drop(&mut self) {
+        let mut handles = self.inner.handles.lock().unwrap();
+        let index = handles
+            .iter()
+            .position(|handle| handle.as_raw_fd() == self.eventfd.as_raw_fd())
+            .expect("RateLimiterGroupHandle must be subscribed to RateLimiterGroup");
+        handles.remove(index);
+    }
+}
+
+struct RateLimiterGroupInner {
+    id: String,
+    rate_limiter: RateLimiter,
+    handles: Mutex<Vec<Arc<EventFd>>>,
+}
+
+/// A RateLimiterGroup is an extension of RateLimiter that enables rate-limiting
+/// the aggregate io consumption of multiple consumers.
+pub struct RateLimiterGroup {
+    inner: Arc<RateLimiterGroupInner>,
+    epoll_file: File,
+    kill_evt: EventFd,
+    epoll_thread: Option<thread::JoinHandle<()>>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+#[repr(u64)]
+enum EpollDispatch {
+    Kill = 1,
+    Unblocked = 2,
+    Unknown,
+}
+
+impl From<u64> for EpollDispatch {
+    fn from(v: u64) -> Self {
+        use EpollDispatch::*;
+        match v {
+            1 => Kill,
+            2 => Unblocked,
+            _ => Unknown,
+        }
+    }
+}
+
+impl RateLimiterGroup {
+    /// Create a new RateLimiterGroup.
+    pub fn new(
+        id: &str,
+        bytes_total_capacity: u64,
+        bytes_one_time_burst: u64,
+        bytes_complete_refill_time_ms: u64,
+        ops_total_capacity: u64,
+        ops_one_time_burst: u64,
+        ops_complete_refill_time_ms: u64,
+    ) -> result::Result<Self, Error> {
+        let rate_limiter = RateLimiter::new(
+            bytes_total_capacity,
+            bytes_one_time_burst,
+            bytes_complete_refill_time_ms,
+            ops_total_capacity,
+            ops_one_time_burst,
+            ops_complete_refill_time_ms,
+        )
+        .map_err(Error::RateLimiter)?;
+
+        let epoll_fd = epoll::create(true).map_err(Error::Epoll)?;
+        let kill_evt = EventFd::new(0).map_err(Error::EventFd)?;
+
+        epoll::ctl(
+            epoll_fd,
+            epoll::ControlOptions::EPOLL_CTL_ADD,
+            kill_evt.as_raw_fd(),
+            epoll::Event::new(epoll::Events::EPOLLIN, EpollDispatch::Kill as u64),
+        )
+        .map_err(Error::Epoll)?;
+
+        epoll::ctl(
+            epoll_fd,
+            epoll::ControlOptions::EPOLL_CTL_ADD,
+            rate_limiter.as_raw_fd(),
+            epoll::Event::new(epoll::Events::EPOLLIN, EpollDispatch::Unblocked as u64),
+        )
+        .map_err(Error::Epoll)?;
+
+        // Use 'File' to enforce closing on 'epoll_fd'
+        // SAFETY: epoll_fd is valid
+        let epoll_file = unsafe { File::from_raw_fd(epoll_fd) };
+
+        Ok(Self {
+            inner: Arc::new(RateLimiterGroupInner {
+                id: id.to_string(),
+                rate_limiter,
+                handles: Mutex::new(Vec::new()),
+            }),
+            epoll_file,
+            kill_evt,
+            epoll_thread: None,
+        })
+    }
+
+    /// Create a new RateLimiterGroupHandle.
+    pub fn new_handle(&self) -> result::Result<RateLimiterGroupHandle, Error> {
+        RateLimiterGroupHandle::new(self.inner.clone())
+    }
+
+    /// Start a worker thread to broadcast an event to each RateLimiterGroupHandle
+    /// when the RateLimiter becomes unblocked.
+    pub fn start_thread(&mut self, exit_evt: EventFd) -> result::Result<(), Error> {
+        let inner = self.inner.clone();
+        let epoll_fd = self.epoll_file.as_raw_fd();
+        thread::Builder::new()
+            .name(format!("rate-limit-group-{}", inner.id))
+            .spawn(move || {
+                let res = std::panic::catch_unwind(AssertUnwindSafe(move || {
+                    const EPOLL_EVENTS_LEN: usize = 2;
+
+                    let mut events =
+                        [epoll::Event::new(epoll::Events::empty(), 0); EPOLL_EVENTS_LEN];
+
+                    loop {
+                        let num_events = match epoll::wait(epoll_fd, -1, &mut events[..]) {
+                            Ok(res) => res,
+                            Err(e) => {
+                                if e.kind() == io::ErrorKind::Interrupted {
+                                    continue;
+                                } else {
+                                    return Err(Error::Epoll(e));
+                                }
+                            }
+                        };
+
+                        for event in events.iter().take(num_events) {
+                            let dispatch_event: EpollDispatch = event.data.into();
+                            match dispatch_event {
+                                EpollDispatch::Unknown => {
+                                    let event = event.data;
+                                    warn!("Unknown rate-limiter loop event: {}", event);
+                                }
+                                EpollDispatch::Unblocked => {
+                                    inner.rate_limiter.event_handler().unwrap();
+                                    let handles = inner.handles.lock().unwrap();
+                                    for handle in handles.iter() {
+                                        handle.write(1).map_err(Error::EventFdWrite)?
+                                    }
+                                }
+                                EpollDispatch::Kill => {
+                                    info!(
+                                        "KILL_EVENT received, stopping rate-limit-group epoll loop"
+                                    );
+                                    return Ok(());
+                                }
+                            }
+                        }
+                    }
+                }));
+
+                match res {
+                    Ok(res) => {
+                        if let Err(e) = res {
+                            error!("Error running rate-limit-group worker: {:?}", e);
+                            exit_evt.write(1).unwrap();
+                        }
+                    }
+                    Err(_) => {
+                        error!("rate-limit-group worker panicked");
+                        exit_evt.write(1).unwrap();
+                    }
+                };
+            })
+            .map(|thread| self.epoll_thread.insert(thread))
+            .map_err(Error::ThreadSpawn)?;
+
+        Ok(())
+    }
+}
+
+impl Drop for RateLimiterGroup {
+    fn drop(&mut self) {
+        self.kill_evt.write(1).unwrap();
+
+        if let Some(t) = self.epoll_thread.take() {
+            if let Err(e) = t.join() {
+                error!("Error joining thread: {:?}", e);
+            }
+        }
+    }
+}
+
+#[cfg(test)]
+pub(crate) mod tests {
+    use super::RateLimiterGroupHandle;
+    use crate::{group::RateLimiterGroup, TokenBucket, TokenType, REFILL_TIMER_INTERVAL_MS};
+    use std::{os::fd::AsRawFd, thread, time::Duration};
+    use vmm_sys_util::eventfd::EventFd;
+
+    impl RateLimiterGroupHandle {
+        pub fn bandwidth(&self) -> Option<TokenBucket> {
+            let guard = self.inner.rate_limiter.inner.lock().unwrap();
+            guard.bandwidth.clone()
+        }
+
+        pub fn ops(&self) -> Option<TokenBucket> {
+            let guard = self.inner.rate_limiter.inner.lock().unwrap();
+            guard.ops.clone()
+        }
+    }
+
+    #[test]
+    fn test_rate_limiter_group_new() {
+        let l = RateLimiterGroup::new("test", 1000, 1001, 1002, 1003, 1004, 1005).unwrap();
+        let h = l.new_handle().unwrap();
+        let bw = h.bandwidth().unwrap();
+        assert_eq!(bw.capacity(), 1000);
+        assert_eq!(bw.one_time_burst(), 1001);
+        assert_eq!(bw.refill_time_ms(), 1002);
+        assert_eq!(bw.budget(), 1000);
+
+        let ops = h.ops().unwrap();
+        assert_eq!(ops.capacity(), 1003);
+        assert_eq!(ops.one_time_burst(), 1004);
+        assert_eq!(ops.refill_time_ms(), 1005);
+        assert_eq!(ops.budget(), 1003);
+    }
+
+    #[test]
+    fn test_rate_limiter_group_manual_replenish() {
+        // rate limiter with limit of 1000 bytes/s and 1000 ops/s
+        let l = RateLimiterGroup::new("test", 1000, 0, 1000, 1000, 0, 1000).unwrap();
+        let h = l.new_handle().unwrap();
+
+        // consume 123 bytes
+        assert!(h.consume(123, TokenType::Bytes));
+        h.manual_replenish(23, TokenType::Bytes);
+        {
+            let bytes_tb = h.bandwidth().unwrap();
+            assert_eq!(bytes_tb.budget(), 900);
+        }
+        // consume 123 ops
+        assert!(h.consume(123, TokenType::Ops));
+        h.manual_replenish(23, TokenType::Ops);
+        {
+            let bytes_tb = h.ops().unwrap();
+            assert_eq!(bytes_tb.budget(), 900);
+        }
+    }
+
+    #[test]
+    fn test_rate_limiter_group_bandwidth() {
+        // rate limiter with limit of 1000 bytes/s
+        let mut l = RateLimiterGroup::new("test", 1000, 0, 1000, 0, 0, 0).unwrap();
+        l.start_thread(EventFd::new(0).unwrap()).unwrap();
+
+        let h = l.new_handle().unwrap();
+
+        // limiter should not be blocked
+        assert!(!h.is_blocked());
+        // raw FD for this disabled should be valid
+        assert!(h.as_raw_fd() > 0);
+
+        // ops/s limiter should be disabled so consume(whatever) should work
+        assert!(h.consume(u64::max_value(), TokenType::Ops));
+
+        // do full 1000 bytes
+        assert!(h.consume(1000, TokenType::Bytes));
+        // try and fail on another 100
+        assert!(!h.consume(100, TokenType::Bytes));
+        // since consume failed, limiter should be blocked now
+        assert!(h.is_blocked());
+        // wait half the timer period
+        thread::sleep(Duration::from_millis(REFILL_TIMER_INTERVAL_MS / 2));
+        // limiter should still be blocked
+        assert!(h.is_blocked());
+        // wait the other half of the timer period
+        thread::sleep(Duration::from_millis(REFILL_TIMER_INTERVAL_MS / 2));
+        // the timer_fd should have an event on it by now
+        assert!(h.event_handler().is_ok());
+        // limiter should now be unblocked
+        assert!(!h.is_blocked());
+        // try and succeed on another 100 bytes this time
+        assert!(h.consume(100, TokenType::Bytes));
+    }
+
+    #[test]
+    fn test_rate_limiter_group_ops() {
+        // rate limiter with limit of 1000 ops/s
+        let mut l = RateLimiterGroup::new("test", 0, 0, 0, 1000, 0, 1000).unwrap();
+        l.start_thread(EventFd::new(0).unwrap()).unwrap();
+
+        let h = l.new_handle().unwrap();
+
+        // limiter should not be blocked
+        assert!(!h.is_blocked());
+        // raw FD for this disabled should be valid
+        assert!(h.as_raw_fd() > 0);
+
+        // bytes/s limiter should be disabled so consume(whatever) should work
+        assert!(h.consume(u64::max_value(), TokenType::Bytes));
+
+        // do full 1000 ops
+        assert!(h.consume(1000, TokenType::Ops));
+        // try and fail on another 100
+        assert!(!h.consume(100, TokenType::Ops));
+        // since consume failed, limiter should be blocked now
+        assert!(h.is_blocked());
+        // wait half the timer period
+        thread::sleep(Duration::from_millis(REFILL_TIMER_INTERVAL_MS / 2));
+        // limiter should still be blocked
+        assert!(h.is_blocked());
+        // wait the other half of the timer period
+        thread::sleep(Duration::from_millis(REFILL_TIMER_INTERVAL_MS / 2));
+        // the timer_fd should have an event on it by now
+        assert!(h.event_handler().is_ok());
+        // limiter should now be unblocked
+        assert!(!h.is_blocked());
+        // try and succeed on another 100 ops this time
+        assert!(h.consume(100, TokenType::Ops));
+    }
+
+    #[test]
+    fn test_rate_limiter_group_full() {
+        // rate limiter with limit of 1000 bytes/s and 1000 ops/s
+        let mut l = RateLimiterGroup::new("test", 1000, 0, 1000, 1000, 0, 1000).unwrap();
+        l.start_thread(EventFd::new(0).unwrap()).unwrap();
+
+        let h = l.new_handle().unwrap();
+
+        // limiter should not be blocked
+        assert!(!h.is_blocked());
+        // raw FD for this disabled should be valid
+        assert!(h.as_raw_fd() > 0);
+
+        // do full 1000 bytes
+        assert!(h.consume(1000, TokenType::Ops));
+        // do full 1000 bytes
+        assert!(h.consume(1000, TokenType::Bytes));
+        // try and fail on another 100 ops
+        assert!(!h.consume(100, TokenType::Ops));
+        // try and fail on another 100 bytes
+        assert!(!h.consume(100, TokenType::Bytes));
+        // since consume failed, limiter should be blocked now
+        assert!(h.is_blocked());
+        // wait half the timer period
+        thread::sleep(Duration::from_millis(REFILL_TIMER_INTERVAL_MS / 2));
+        // limiter should still be blocked
+        assert!(h.is_blocked());
+        // wait the other half of the timer period
+        thread::sleep(Duration::from_millis(REFILL_TIMER_INTERVAL_MS / 2));
+        // the timer_fd should have an event on it by now
+        assert!(h.event_handler().is_ok());
+        // limiter should now be unblocked
+        assert!(!h.is_blocked());
+        // try and succeed on another 100 ops this time
+        assert!(h.consume(100, TokenType::Ops));
+        // try and succeed on another 100 bytes this time
+        assert!(h.consume(100, TokenType::Bytes));
+    }
+
+    #[test]
+    fn test_rate_limiter_group_overconsumption() {
+        // initialize the rate limiter
+        let mut l = RateLimiterGroup::new("test", 1000, 0, 1000, 1000, 0, 1000).unwrap();
+        l.start_thread(EventFd::new(0).unwrap()).unwrap();
+
+        let h = l.new_handle().unwrap();
+
+        // try to consume 2.5x the bucket size
+        // we are "borrowing" 1.5x the bucket size in tokens since
+        // the bucket is full
+        assert!(h.consume(2500, TokenType::Bytes));
+
+        // check that even after a whole second passes, the rate limiter
+        // is still blocked
+        thread::sleep(Duration::from_millis(1000));
+        assert!(h.is_blocked());
+
+        // after 1.5x the replenish time has passed, the rate limiter
+        // is available again
+        thread::sleep(Duration::from_millis(500));
+        assert!(h.event_handler().is_ok());
+        assert!(!h.is_blocked());
+
+        // reset the rate limiter
+        let mut l = RateLimiterGroup::new("test", 1000, 0, 1000, 1000, 0, 1000).unwrap();
+        l.start_thread(EventFd::new(0).unwrap()).unwrap();
+
+        let h = l.new_handle().unwrap();
+        // try to consume 1.5x the bucket size
+        // we are "borrowing" 1.5x the bucket size in tokens since
+        // the bucket is full, should arm the timer to 0.5x replenish
+        // time, which is 500 ms
+        assert!(h.consume(1500, TokenType::Bytes));
+
+        // check that after more than the minimum refill time,
+        // the rate limiter is still blocked
+        thread::sleep(Duration::from_millis(200));
+        assert!(h.is_blocked());
+
+        // try to consume some tokens, which should fail as the timer
+        // is still active
+        assert!(!h.consume(100, TokenType::Bytes));
+        assert!(h.is_blocked());
+
+        // check that after the minimum refill time, the timer was not
+        // overwritten and the rate limiter is still blocked from the
+        // borrowing we performed earlier
+        thread::sleep(Duration::from_millis(100));
+        assert!(h.is_blocked());
+        assert!(!h.consume(100, TokenType::Bytes));
+
+        // after waiting out the full duration, rate limiter should be
+        // available again
+        thread::sleep(Duration::from_millis(200));
+        assert!(h.event_handler().is_ok());
+        assert!(!h.is_blocked());
+        assert!(h.consume(100, TokenType::Bytes));
+    }
+}

rate_limiter/src/lib.rs

@@ -53,6 +53,9 @@ use std::sync::Mutex;
 use std::time::{Duration, Instant};
 use vmm_sys_util::timerfd::TimerFd;
 
+/// Module for group rate limiting.
+pub mod group;
+
 #[derive(Debug)]
 /// Describes the errors that may occur while handling rate limiter events.
 pub enum Error {

release-notes.md

@@ -1,42 +1,69 @@
+- [v38.0](#v380)
+    - [Group Rate Limiter on Block Devices](#group-rate-limiter-on-block-devices)
+    - [CPU Pinning Support for Block Device Worker Thread](#cpu-pinning-support-for-block-device-worker-thread)
+    - [Optimized Boot Time with Parallel Memory Prefault](#optimized-boot-time-with-parallel-memory-prefault)
+    - [New 'debug-console' Device](#new-debug-console-device)
+    - [Improved VFIO Device Support](#improved-vfio-device-support)
+    - [Extended CPU Affinity Support](#extended-cpu-affinity-support)
+    - [Notable Bug Fixes](#notable-bug-fixes)
+    - [Contributors](#contributors)
+- [v37.0](#v370)
+    - [Long Term Support (LTS) Release](#long-term-support-lts-release)
+    - [Multiple PCI segments Support for 32-bit VFIO devices](#multiple-pci-segments-support-for-32-bit-vfio-devices)
+    - [Configurable Named TAP Devices](#configurable-named-tap-devices)
+    - [TTY Output from Both Serial Device and Virtio Console](#tty-output-from-both-serial-device-and-virtio-console)
+    - [Faster VM Restoration from Snapshots](#faster-vm-restoration-from-snapshots)
+    - [Notable Bug Fixes](#notable-bug-fixes-1)
+    - [Contributors](#contributors-1)
+- [v36.0](#v360)
+    - [Command Line Changes](#command-line-changes)
+    - [Enabled Features Reported via API Endpoint and CLI](#enabled-features-reported-via-api-endpoint-and-cli)
+    - [NUMA Support for PCI segments](#numa-support-for-pci-segments)
+    - [CPU Topology Support on AMD Platforms](#cpu-topology-support-on-amd-platforms)
+    - [Unix Socket Backend for Serial Port](#unix-socket-backend-for-serial-port)
+    - [AIO Backend for Block Devices](#aio-backend-for-block-devices)
+    - [Documentation Improvements](#documentation-improvements)
+    - [Notable Bug Fixes](#notable-bug-fixes-2)
+    - [Contributors](#contributors-2)
 - [v35.0](#v350)
     - [`virtio-vsock` Support for Linux Guest Kernel v6.3+](#virtio-vsock-support-for-linux-guest-kernel-v63)
     - [User Specified Serial Number for `virtio-block`](#user-specified-serial-number-for-virtio-block)
     - [vCPU TSC Frequency Included in Migration State](#vcpu-tsc-frequency-included-in-migration-state)
-    - [Notable Bug Fixes](#notable-bug-fixes)
-    - [Contributors](#contributors)
+    - [Notable Bug Fixes](#notable-bug-fixes-3)
+    - [Contributors](#contributors-3)
 - [v34.0](#v340)
     - [Paravirtualised Panic Device Support](#paravirtualised-panic-device-support)
     - [Improvements to VM Core Dump](#improvements-to-vm-core-dump)
     - [QCOW2 Support for Backing Files](#qcow2-support-for-backing-files)
     - [Minimum Host Kernel Bump](#minimum-host-kernel-bump)
-    - [Notable Bug Fixes](#notable-bug-fixes-1)
-    - [Contributors](#contributors-1)
+    - [Notable Bug Fixes](#notable-bug-fixes-4)
+    - [Contributors](#contributors-4)
 - [v33.0](#v330)
     - [D-Bus based API](#d-bus-based-api)
     - [Expose Host CPU Cache Details for AArch64](#expose-host-cpu-cache-details-for-aarch64)
-    - [Notable Bug Fixes](#notable-bug-fixes-2)
-    - [Contributors](#contributors-2)
+    - [Notable Bug Fixes](#notable-bug-fixes-5)
+    - [Contributors](#contributors-5)
 - [v32.0](#v320)
     - [Increased PCI Segment Limit](#increased-pci-segment-limit)
     - [API Changes](#api-changes)
-    - [Notable Bug Fixes](#notable-bug-fixes-3)
-    - [Contributors](#contributors-3)
+    - [Notable Bug Fixes](#notable-bug-fixes-6)
+    - [Contributors](#contributors-6)
 - [v31.1](#v311)
 - [v31.0](#v310)
     - [Update to Latest `acpi_tables`](#update-to-latest-acpi_tables)
     - [Update Reference Kernel to 6.2](#update-reference-kernel-to-62)
     - [Improvements on Console `SIGWINCH` Handler](#improvements-on-console-sigwinch-handler)
     - [Remove Directory Support from `MemoryZoneConfig::file`](#remove-directory-support-from-memoryzoneconfigfile)
-    - [Documentation Improvements](#documentation-improvements)
-    - [Notable Bug Fixes](#notable-bug-fixes-4)
-    - [Contributors](#contributors-4)
+    - [Documentation Improvements](#documentation-improvements-1)
+    - [Notable Bug Fixes](#notable-bug-fixes-7)
+    - [Contributors](#contributors-7)
 - [v30.0](#v300)
     - [Command Line Changes for Reduced Binary Size](#command-line-changes-for-reduced-binary-size)
     - [Basic vfio-user Server Support](#basic-vfio-user-server-support)
     - [Heap Profiling Support](#heap-profiling-support)
-    - [Documentation Improvements](#documentation-improvements-1)
-    - [Notable Bug Fixes](#notable-bug-fixes-5)
-    - [Contributors](#contributors-5)
+    - [Documentation Improvements](#documentation-improvements-2)
+    - [Notable Bug Fixes](#notable-bug-fixes-8)
+    - [Contributors](#contributors-8)
 - [v28.2](#v282)
 - [v29.0](#v290)
     - [Release Binary Supports Both MSHV and KVM](#release-binary-supports-both-mshv-and-kvm)
@@ -46,20 +73,20 @@
     - [`AArch64` Documentation Integration](#aarch64-documentation-integration)
     - [`virtio-block` Counters Enhancement](#virtio-block-counters-enhancement)
     - [TCP Offload Control](#tcp-offload-control)
-    - [Notable Bug Fixes](#notable-bug-fixes-6)
+    - [Notable Bug Fixes](#notable-bug-fixes-9)
     - [Removals](#removals)
     - [Deprecations](#deprecations)
-    - [Contributors](#contributors-6)
+    - [Contributors](#contributors-9)
 - [v28.1](#v281)
 - [v28.0](#v280)
     - [Community Engagement (Reminder)](#community-engagement-reminder)
-    - [Long Term Support (LTS) Release](#long-term-support-lts-release)
+    - [Long Term Support (LTS) Release](#long-term-support-lts-release-1)
     - [Virtualised TPM Support](#virtualised-tpm-support)
     - [Transparent Huge Page Support](#transparent-huge-page-support)
     - [README Quick Start Improved](#readme-quick-start-improved)
-    - [Notable Bug Fixes](#notable-bug-fixes-7)
+    - [Notable Bug Fixes](#notable-bug-fixes-10)
     - [Removals](#removals-1)
-    - [Contributors](#contributors-7)
+    - [Contributors](#contributors-10)
 - [v27.0](#v270)
     - [Community Engagement](#community-engagement)
     - [Prebuilt Packages](#prebuilt-packages)
@@ -68,41 +95,41 @@
     - [Simplified Build Feature Flags](#simplified-build-feature-flags)
     - [Asynchronous Kernel Loading](#asynchronous-kernel-loading)
     - [GDB Support for AArch64](#gdb-support-for-aarch64)
-    - [Notable Bug Fixes](#notable-bug-fixes-8)
+    - [Notable Bug Fixes](#notable-bug-fixes-11)
     - [Deprecations](#deprecations-1)
-    - [Contributors](#contributors-8)
+    - [Contributors](#contributors-11)
 - [v26.0](#v260)
     - [SMBIOS Improvements via `--platform`](#smbios-improvements-via---platform)
     - [Unified Binary MSHV and KVM Support](#unified-binary-mshv-and-kvm-support)
-    - [Notable Bug Fixes](#notable-bug-fixes-9)
+    - [Notable Bug Fixes](#notable-bug-fixes-12)
     - [Deprecations](#deprecations-2)
     - [Removals](#removals-2)
-    - [Contributors](#contributors-9)
+    - [Contributors](#contributors-12)
 - [v25.0](#v250)
     - [`ch-remote` Improvements](#ch-remote-improvements-1)
     - [VM "Coredump" Support](#vm-coredump-support)
-    - [Notable Bug Fixes](#notable-bug-fixes-10)
+    - [Notable Bug Fixes](#notable-bug-fixes-13)
     - [Removals](#removals-3)
-    - [Contributors](#contributors-10)
+    - [Contributors](#contributors-13)
 - [v24.0](#v240)
     - [Bypass Mode for `virtio-iommu`](#bypass-mode-for-virtio-iommu)
     - [Ensure Identifiers Uniqueness](#ensure-identifiers-uniqueness)
     - [Sparse Mmap support](#sparse-mmap-support)
     - [Expose Platform Serial Number](#expose-platform-serial-number)
-    - [Notable Bug Fixes](#notable-bug-fixes-11)
+    - [Notable Bug Fixes](#notable-bug-fixes-14)
     - [Notable Improvements](#notable-improvements)
     - [Deprecations](#deprecations-3)
     - [New on the Website](#new-on-the-website)
-    - [Contributors](#contributors-11)
+    - [Contributors](#contributors-14)
 - [v23.1](#v231)
 - [v23.0](#v230)
     - [vDPA Support](#vdpa-support)
     - [Updated OS Support list](#updated-os-support-list)
     - [`AArch64` Memory Map Improvements](#aarch64-memory-map-improvements)
     - [`AMX` Support](#amx-support)
-    - [Notable Bug Fixes](#notable-bug-fixes-12)
+    - [Notable Bug Fixes](#notable-bug-fixes-15)
     - [Deprecations](#deprecations-4)
-    - [Contributors](#contributors-12)
+    - [Contributors](#contributors-15)
 - [v22.1](#v221)
 - [v22.0](#v220)
     - [GDB Debug Stub Support](#gdb-debug-stub-support)
@@ -113,13 +140,13 @@
     - [PMU Support for AArch64](#pmu-support-for-aarch64)
     - [Documentation Under CC-BY-4.0 License](#documentation-under-cc-by-40-license)
     - [Deprecation of "Classic" `virtiofsd`](#deprecation-of-classic-virtiofsd)
-    - [Notable Bug Fixes](#notable-bug-fixes-13)
-    - [Contributors](#contributors-13)
+    - [Notable Bug Fixes](#notable-bug-fixes-16)
+    - [Contributors](#contributors-16)
 - [v21.0](#v210)
     - [Efficient Local Live Migration (for Live Upgrade)](#efficient-local-live-migration-for-live-upgrade)
     - [Recommended Kernel is Now 5.15](#recommended-kernel-is-now-515)
-    - [Notable Bug fixes](#notable-bug-fixes-14)
-    - [Contributors](#contributors-14)
+    - [Notable Bug fixes](#notable-bug-fixes-17)
+    - [Contributors](#contributors-17)
 - [v20.2](#v202)
 - [v20.1](#v201)
 - [v20.0](#v200)
@@ -128,8 +155,8 @@
     - [Improved VFIO support](#improved-vfio-support)
     - [Safer code](#safer-code)
     - [Extended documentation](#extended-documentation)
-    - [Notable bug fixes](#notable-bug-fixes-15)
-    - [Contributors](#contributors-15)
+    - [Notable bug fixes](#notable-bug-fixes-18)
+    - [Contributors](#contributors-18)
 - [v19.0](#v190)
     - [Improved PTY handling for serial and `virtio-console`](#improved-pty-handling-for-serial-and-virtio-console)
     - [PCI boot time optimisations](#pci-boot-time-optimisations)
@@ -137,8 +164,8 @@
     - [Live migration enhancements](#live-migration-enhancements)
     - [`virtio-mem` support with `vfio-user`](#virtio-mem-support-with-vfio-user)
     - [AArch64 for `virtio-iommu`](#aarch64-for-virtio-iommu)
-    - [Notable bug fixes](#notable-bug-fixes-16)
-    - [Contributors](#contributors-16)
+    - [Notable bug fixes](#notable-bug-fixes-19)
+    - [Contributors](#contributors-19)
 - [v18.0](#v180)
     - [Experimental User Device (`vfio-user`) support](#experimental-user-device-vfio-user-support)
     - [Migration support for `vhost-user` devices](#migration-support-for-vhost-user-devices)
@@ -148,23 +175,23 @@
     - [Live migration on MSHV hypervisor](#live-migration-on-mshv-hypervisor)
     - [AArch64 CPU topology support](#aarch64-cpu-topology-support)
     - [Power button support on AArch64](#power-button-support-on-aarch64)
-    - [Notable bug fixes](#notable-bug-fixes-17)
-    - [Contributors](#contributors-17)
+    - [Notable bug fixes](#notable-bug-fixes-20)
+    - [Contributors](#contributors-20)
 - [v17.0](#v170)
     - [ARM64 NUMA support using ACPI](#arm64-numa-support-using-acpi)
     - [`Seccomp` support for MSHV backend](#seccomp-support-for-mshv-backend)
     - [Hotplug of `macvtap` devices](#hotplug-of-macvtap-devices)
     - [Improved SGX support](#improved-sgx-support)
     - [Inflight tracking for `vhost-user` devices](#inflight-tracking-for-vhost-user-devices)
-    - [Notable bug fixes](#notable-bug-fixes-18)
-    - [Contributors](#contributors-18)
+    - [Notable bug fixes](#notable-bug-fixes-21)
+    - [Contributors](#contributors-21)
 - [v16.0](#v160)
     - [Improved live migration support](#improved-live-migration-support)
     - [Improved `vhost-user` support](#improved-vhost-user-support)
     - [ARM64 ACPI and UEFI support](#arm64-acpi-and-uefi-support)
-    - [Notable bug fixes](#notable-bug-fixes-19)
+    - [Notable bug fixes](#notable-bug-fixes-22)
     - [Removed functionality](#removed-functionality)
-    - [Contributors](#contributors-19)
+    - [Contributors](#contributors-22)
 - [v15.0](#v150)
     - [Version numbering and stability guarantees](#version-numbering-and-stability-guarantees)
     - [Network device rate limiting](#network-device-rate-limiting)
@@ -172,7 +199,7 @@
     - [`--api-socket` supports file descriptor parameter](#--api-socket-supports-file-descriptor-parameter)
     - [Bug fixes](#bug-fixes)
     - [Deprecations](#deprecations-5)
-    - [Contributors](#contributors-20)
+    - [Contributors](#contributors-23)
 - [v0.14.1](#v0141)
 - [v0.14.0](#v0140)
     - [Structured event monitoring](#structured-event-monitoring)
@@ -182,7 +209,7 @@
     - [PTY control for serial and `virtio-console`](#pty-control-for-serial-and-virtio-console)
     - [Block device rate limiting](#block-device-rate-limiting)
     - [Deprecations](#deprecations-6)
-    - [Contributors](#contributors-21)
+    - [Contributors](#contributors-24)
 - [v0.13.0](#v0130)
     - [Wider VFIO device support](#wider-vfio-device-support)
     - [Improved huge page support](#improved-huge-page-support)
@@ -190,13 +217,13 @@
     - [VHD disk image support](#vhd-disk-image-support)
     - [Improved Virtio device threading](#improved-virtio-device-threading)
     - [Clean shutdown support via synthetic power button](#clean-shutdown-support-via-synthetic-power-button)
-    - [Contributors](#contributors-22)
+    - [Contributors](#contributors-25)
 - [v0.12.0](#v0120)
     - [ARM64 enhancements](#arm64-enhancements)
     - [Removal of `vhost-user-net` and `vhost-user-block` self spawning](#removal-of-vhost-user-net-and-vhost-user-block-self-spawning)
     - [Migration of `vhost-user-fs` backend](#migration-of-vhost-user-fs-backend)
     - [Enhanced "info" API](#enhanced-info-api)
-    - [Contributors](#contributors-23)
+    - [Contributors](#contributors-26)
 - [v0.11.0](#v0110)
     - [`io_uring` support by default for `virtio-block`](#io_uring-support-by-default-for-virtio-block)
     - [Windows Guest Support](#windows-guest-support)
@@ -208,15 +235,15 @@
     - [Default Log Level Changed](#default-log-level-changed)
     - [New `--balloon` Parameter Added](#new---balloon-parameter-added)
     - [Experimental `virtio-watchdog` Support](#experimental-virtio-watchdog-support)
-    - [Notable Bug Fixes](#notable-bug-fixes-20)
-    - [Contributors](#contributors-24)
+    - [Notable Bug Fixes](#notable-bug-fixes-23)
+    - [Contributors](#contributors-27)
 - [v0.10.0](#v0100)
     - [`virtio-block` Support for Multiple Descriptors](#virtio-block-support-for-multiple-descriptors)
     - [Memory Zones](#memory-zones)
     - [`Seccomp` Sandbox Improvements](#seccomp-sandbox-improvements)
     - [Preliminary KVM HyperV Emulation Control](#preliminary-kvm-hyperv-emulation-control)
-    - [Notable Bug Fixes](#notable-bug-fixes-21)
-    - [Contributors](#contributors-25)
+    - [Notable Bug Fixes](#notable-bug-fixes-24)
+    - [Contributors](#contributors-28)
 - [v0.9.0](#v090)
     - [`io_uring` Based Block Device Support](#io_uring-based-block-device-support)
     - [Block and Network Device Statistics](#block-and-network-device-statistics)
@@ -229,17 +256,17 @@
     - [Enhancements to ARM64 Support](#enhancements-to-arm64-support)
     - [Intel SGX Support](#intel-sgx-support)
     - [`Seccomp` Sandbox Improvements](#seccomp-sandbox-improvements-1)
-    - [Notable Bug Fixes](#notable-bug-fixes-22)
-    - [Contributors](#contributors-26)
+    - [Notable Bug Fixes](#notable-bug-fixes-25)
+    - [Contributors](#contributors-29)
 - [v0.8.0](#v080)
     - [Experimental Snapshot and Restore Support](#experimental-snapshot-and-restore-support)
     - [Experimental ARM64 Support](#experimental-arm64-support)
     - [Support for Using 5-level Paging in Guests](#support-for-using-5-level-paging-in-guests)
     - [Virtio Device Interrupt Suppression for Network Devices](#virtio-device-interrupt-suppression-for-network-devices)
     - [`vhost_user_fs` Improvements](#vhost_user_fs-improvements)
-    - [Notable Bug Fixes](#notable-bug-fixes-23)
+    - [Notable Bug Fixes](#notable-bug-fixes-26)
     - [Command Line and API Changes](#command-line-and-api-changes)
-    - [Contributors](#contributors-27)
+    - [Contributors](#contributors-30)
 - [v0.7.0](#v070)
     - [Block, Network, Persistent Memory (PMEM), VirtioFS and Vsock hotplug](#block-network-persistent-memory-pmem-virtiofs-and-vsock-hotplug)
     - [Alternative `libc` Support](#alternative-libc-support)
@@ -249,14 +276,14 @@
     - [`Seccomp` Sandboxing](#seccomp-sandboxing)
     - [Updated Distribution Support](#updated-distribution-support)
     - [Command Line and API Changes](#command-line-and-api-changes-1)
-    - [Contributors](#contributors-28)
+    - [Contributors](#contributors-31)
 - [v0.6.0](#v060)
     - [Directly Assigned Devices Hotplug](#directly-assigned-devices-hotplug)
     - [Shared Filesystem Improvements](#shared-filesystem-improvements)
     - [Block and Networking IO Self Offloading](#block-and-networking-io-self-offloading)
     - [Command Line Interface](#command-line-interface)
     - [PVH Boot](#pvh-boot)
-    - [Contributors](#contributors-29)
+    - [Contributors](#contributors-32)
 - [v0.5.1](#v051)
 - [v0.5.0](#v050)
     - [Virtual Machine Dynamic Resizing](#virtual-machine-dynamic-resizing)
@@ -264,7 +291,7 @@
     - [New Interrupt Management Framework](#new-interrupt-management-framework)
     - [Development Tools](#development-tools)
     - [Kata Containers Integration](#kata-containers-integration)
-    - [Contributors](#contributors-30)
+    - [Contributors](#contributors-33)
 - [v0.4.0](#v040)
     - [Dynamic virtual CPUs addition](#dynamic-virtual-cpus-addition)
     - [Programmatic firmware tables generation](#programmatic-firmware-tables-generation)
@@ -273,7 +300,7 @@
     - [Userspace IOAPIC by default](#userspace-ioapic-by-default)
     - [PCI BAR reprogramming](#pci-bar-reprogramming)
     - [New `cloud-hypervisor` organization](#new-cloud-hypervisor-organization)
-    - [Contributors](#contributors-31)
+    - [Contributors](#contributors-34)
 - [v0.3.0](#v030)
     - [Block device offloading](#block-device-offloading)
     - [Network device backend](#network-device-backend)
@@ -300,6 +327,213 @@
     - [Unit testing](#unit-testing)
     - [Integration tests parallelization](#integration-tests-parallelization)
 
+# v38.0
+
+This release has been tracked in our [roadmap
+project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
+v38.0. The following user visible changes have been made:
+
+### Group Rate Limiter on Block Devices
+
+Users now can throttle a group of block devices with the new
+`--rate-limiter-group` option. Details can be found from the [I/O
+Throttling documentation](docs/io_throttling.md)
+
+### CPU Pinning Support for Block Device Worker Thread
+
+Users now have the option to pin virt-queue threads for block devices
+to specific host cpus.
+
+### Optimized Boot Time with Parallel Memory Prefault
+
+The boot time with `prefault` option enabled is optimized via parallel
+memory prefault.
+
+### New 'debug-console' Device
+
+A 'debug-console' device is added to provide a user-configurable debug
+port for logging guest information. Details can be found from the [Debug
+IO Ports documentation](docs/debug-port.md).
+
+### Improved VFIO Device Support
+
+All non-emulated MMIO regions of VFIO devices are now mapped to the VFIO
+container, allowing PCIe P2P between all VFIO devices on the same
+VM. This is required for a wide variety of multi-GPU workloads involving
+GPUDirect P2P (DMA between two GPUs), GPUDirect RDMA (DMA between a GPU
+and an IB device).
+
+### Extended CPU Affinity Support
+
+Users now can set the vcpu affinity to a host CPU with index larger
+than 255.
+
+### Notable Bug Fixes
+
+* Enable HTT flag to avoid crashing cpu topology enumeration software
+such as hwloc in the guest (#6146)
+* Fix several security advisories from dependencies (#6134, #6141)
+* Handle non-power-of-two CPU topology properly (#6062)
+* Various bug fixes around `virtio-vsock`(#6080, #6091, #6095)
+* Enable nested virtualization on AMD if supported (#6106)
+* Align VFIO devices PCI BARs naturally (#6196)
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release:
+* Alyssa Ross <hi@alyssa.is>
+* Bo Chen <chen.bo@intel.com>
+* Daniel Farina <daniel@ubicloud.com>
+* Jinank Jain <jinankjain@microsoft.com>
+* Muminul Islam <muislam@microsoft.com>
+* Peteris Rudzusiks <rye@stripe.com>
+* Philipp Schuster <philipp.schuster@cyberus-technology.de>
+* Ravi kumar Veeramally <ravikumar.veeramally@intel.com>
+* Rob Bradford <rbradford@rivosinc.com>
+* Ruslan Mstoi <ruslan.mstoi@intel.com>
+* Sean Banko <sbanko@crusoeenergy.com>
+* Thomas Barrett <tbarrett@crusoeenergy.com>
+* Wei Liu <liuwe@microsoft.com>
+* Yi Wang <foxywang@tencent.com>
+* acarp <acarp@crusoeenergy.com>
+
+# v37.0
+
+This release has been tracked in our [roadmap
+project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
+v37.0. The following user visible changes have been made:
+
+### Long Term Support (LTS) Release
+
+This release is a LTS release. Point releases for bug fixes will be made
+for the next 18 months; live migration and live upgrade will be
+supported between the point releases of the LTS.
+
+### Multiple PCI segments Support for 32-bit VFIO devices
+
+Now VFIO devices with 32-bit memory BARs can be attached to non-zero PCI
+segments on the guest, allowing users to have more 32-bit devices and
+assign such devices to appropriate NUMA nodes for better performance.
+
+### Configurable Named TAP Devices
+
+Named TAP devices now accepts IP configuration from users, such as IP
+and MAC address, as long as the named TAP device is created by Cloud
+Hypervisor (e.g. not existing TAP devices).
+
+### TTY Output from Both Serial Device and Virtio Console
+
+Now legacy serial device and virtio console can be set as TTY mode as
+the same time. This allows users to capture early boot logs with the
+legacy serial device without losing performance benefits of using
+virtio-console, when appropriate kernel configuration is used (such as
+using kernel command-line `console=hvc0 earlyprintk=ttyS0` on x86).
+
+### Faster VM Restoration from Snapshots
+
+The speed of VM restoration from snapshots is improved with a better
+implementation of deserializing JSON files.
+
+### Notable Bug Fixes
+
+* Fix aio backend behavior for block devices when writeback cache
+  disabled (#5930)
+* Fix PvPanic device PCI BAR alignment (#5956)
+* Bug fix to OpenAPI specification file (#5967)
+* Error out early for live migration when TDX is enabled (#6025)
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release:
+
+* Bo Chen <chen.bo@intel.com>
+* Jinank Jain <jinankjain@microsoft.com>
+* Markus Sütter <markus.suetter@secunet.com>
+* Michael Zhao <michael.zhao@arm.com>
+* Muminul Islam <muislam@microsoft.com>
+* Rob Bradford <rbradford@rivosinc.com>
+* Rui Chang <rui.chang@arm.com>
+* Ruslan Mstoi <ruslan.mstoi@intel.com>
+* Thomas Barrett <tbarrett@crusoeenergy.com>
+* Wei Liu <liuwe@microsoft.com>
+* Yi Wang <foxywang@tencent.com>
+* Yong He <alexyonghe@tencent.com>
+
+# v36.0
+
+This release has been tracked in our [roadmap
+project](https://github.com/orgs/cloud-hypervisor/projects/6) as iteration
+v36.0. The following user visible changes have been made:
+
+### Command Line Changes
+
+We switched back to use the `clap` crate to create our command line,
+since the `argh` crate is barely maintained. There were several syntax
+changes:
+
+* All `--option value` commands now are `--option=value`.
+* The `--disk DISK1 --disk DISK2` command now is `--disk DISK1 DISK2`.
+* The `-v -v -v`command now is `-vvv`.
+
+Note: the released binary size increased around 0.3M due to this change.
+
+### Enabled Features Reported via API Endpoint and CLI
+
+Now the enabled (Cargo) features of the running Cloud Hypervisor
+instance can be queried via API endpoint (`/vmm.ping`) and CLI
+(`--version -v`).
+
+### NUMA Support for PCI segments
+
+The `--numa` command is augmented with a new option `pci_segment=`, so
+that users can define the relationship between PCI segments and NUMA
+nodes. Examples can be found from the [memory documentation](docs/memory.md)
+
+### CPU Topology Support on AMD Platforms
+
+Now the CPU topology on x86_64 platforms supports multiple vendors.
+
+### Unix Socket Backend for Serial Port
+
+The `--serial` command is augmented with a new option `socket=`, allowing
+users to access the serial port using a Unix socket.
+
+### AIO Backend for Block Devices
+
+An AIO backend is added for `virtio-block` devices to improve block
+device performance when the `io_uring` feature is not supported by the
+host Operating System.
+
+### Documentation Improvements
+
+* New [documentation](docs/coverage.md) for collecting coverage data
+* Various typo fixes
+
+### Notable Bug Fixes
+
+* Fix a deadlock when TDX is enabled (#5845)
+* Only advertise AMX feature bits to guest when the AMX cpu feature is
+  enabled (#5834)
+* Correct default value for vCPU topology on AArch64 (#5893)
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release:
+
+*  Anatol Belski <anbelski@linux.microsoft.com>
+*  Bo Chen <chen.bo@intel.com>
+*  Dario Nieuwenhuis <dirbaio@dirbaio.net>
+*  Jianyong Wu <jianyong.wu@arm.com>
+*  Jinank Jain <jinankjain@microsoft.com>
+*  Muminul Islam <muislam@microsoft.com>
+*  Praveen K Paladugu <prapal@linux.microsoft.com>
+*  Ravi kumar Veeramally <ravikumar.veeramally@intel.com>
+*  Rob Bradford <rbradford@rivosinc.com>
+*  Thomas Barrett <tbarrett@crusoeenergy.com>
+*  Wei Liu <liuwe@microsoft.com>
+*  Yi Wang <foxywang@tencent.com>
+*  dom.song <dom.song@amperecomputing.com>
+
 # v35.0
 
 This release has been tracked in our [roadmap

resources/Dockerfile

@@ -3,10 +3,10 @@
 # When changing this file don't forget to update the tag name in the
 # .github/workflows/docker-image.yaml file if doing multiple per day
 
-FROM ubuntu:20.04 as dev
+FROM ubuntu:22.04 as dev
 
 ARG TARGETARCH
-ARG RUST_TOOLCHAIN="1.67.1"
+ARG RUST_TOOLCHAIN="1.70.0"
 ARG CLH_SRC_DIR="/cloud-hypervisor"
 ARG CLH_BUILD_DIR="$CLH_SRC_DIR/build"
 ARG CARGO_REGISTRY_DIR="$CLH_BUILD_DIR/cargo_registry"
@@ -43,7 +43,6 @@ RUN apt-get update \
         socat \
         dosfstools \
         cpio \
-        python \
         python3 \
         python3-setuptools \
         ntfs-3g \
@@ -130,17 +129,18 @@ RUN echo 'source $CARGO_HOME/env' >> "$HOME"/.bashrc \
 RUN if [ "$TARGETARCH" = "amd64" ]; then \
        git clone https://github.com/spdk/spdk \
        && cd spdk \
-       && git checkout 6301f8915de32baed10dba1eebed556a6749211a \
+       && git checkout ef8bcce58f3f02b79c0619a297e4f17e81e62b24 \
        && git submodule update --init \
        && apt-get update \
        && ./scripts/pkgdep.sh \
        && apt-get clean \
        && ./configure --with-vfio-user \
        && make -j $(nproc) TARGET_ARCHITECTURE=skylake \
+       && rm -rf /usr/local/bin/spdk-nvme \
        && mkdir /usr/local/bin/spdk-nvme \
-       && cp ./build/bin/nvmf_tgt /usr/local/bin/spdk-nvme \
-       && cp ./scripts/rpc.py /usr/local/bin/spdk-nvme \
-       && cp -r ./scripts/rpc /usr/local/bin/spdk-nvme \
+       && cp -f ./build/bin/nvmf_tgt /usr/local/bin/spdk-nvme \
+       && cp -f ./scripts/rpc.py /usr/local/bin/spdk-nvme \
+       && cp -rf ./python /usr/local/bin \
        && cd .. && rm -rf spdk; fi
 
 # install swtpm only for x86_64 arch

resources/linux-config-x86_64

@@ -639,7 +639,7 @@ CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=y
 # CONFIG_KVM_WERROR is not set
 CONFIG_KVM_INTEL=y
-# CONFIG_KVM_AMD is not set
+CONFIG_KVM_AMD=y
 CONFIG_KVM_SMM=y
 # CONFIG_KVM_XEN is not set
 CONFIG_AS_AVX512=y

scripts/check-image-compatibility.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 : '
     This script checks if an image is compatible with Cloud Hypervisor.
     At first, it detects the image type(raw or qcow2),
@@ -8,8 +8,6 @@
     a message about the compatibility of the image.
 '
 
-
-
 usage="$(basename "$0") [-h] -f -w -- program to check Cloud Hypervisor compatible image
 
 where:
@@ -18,12 +16,11 @@ where:
     -w  directory to be used for temporary files"
 
 function check_command {
-    if ! command -v  $1 &> /dev/null
-        then
-            echo "Command $1 could not be found"
+    if ! command -v "$1" &>/dev/null; then
+        echo "Command $1 could not be found"
         exit 1
     fi
-};
+}
 
 function check_if_root {
     if [ "$EUID" -ne 0 ]; then
@@ -31,27 +28,32 @@ function check_if_root {
         exit 1
     fi
 
-};
+}
 
 check_if_root
 working_dir=""
 while getopts ':hf:w:' option; do
     case "$option" in
-        h) echo "$usage"
-            exit
-            ;;
-        f) file_name=$OPTARG
-            ;;
-        w) working_dir=$OPTARG
-            ;;
-        :) printf "missing argument for -%s\n" "$OPTARG" >&2
-            echo "$usage" >&2
-            exit 1
-            ;;
-        \?) printf "illegal option: -%s\n" "$OPTARG" >&2
-            echo "$usage" >&2
-            exit 1
-            ;;
+    h)
+        echo "$usage"
+        exit
+        ;;
+    f)
+        file_name=$OPTARG
+        ;;
+    w)
+        working_dir=$OPTARG
+        ;;
+    :)
+        printf "missing argument for -%s\n" "$OPTARG" >&2
+        echo "$usage" >&2
+        exit 1
+        ;;
+    \?)
+        printf "illegal option: -%s\n" "$OPTARG" >&2
+        echo "$usage" >&2
+        exit 1
+        ;;
     esac
 done
 
@@ -59,67 +61,64 @@ shift $((OPTIND - 1))
 
 if [ -z "${file_name}" ]; then
     echo "You must provide the image file name"
-	exit 1
+    exit 1
 fi
 if [[ ! -f ${file_name} ]]; then
     echo "File ${file_name} does not exist"
     exit 1
 fi
 
-file_abs_path=`readlink -m ${file_name}`
+file_abs_path=$(readlink -m "${file_name}")
 if [[ "${working_dir}" != "" && ! -d "${working_dir}" ]]; then
     echo "Directory ${working_dir} does not exist"
     exit 1
 elif [[ "${working_dir}" == "" ]]; then
-    working_dir=`mktemp -d`
+    working_dir=$(mktemp -d)
     tmp_created=1
 else
-    working_dir=`readlink -m ${working_dir}`
+    working_dir=$(readlink -m "${working_dir}")
 fi
 
-#get file extension and image type
-extension="${file_name##*.}"
 filename="${file_name%.*}"
 dest_file=${working_dir}/${filename}.raw
-image_type=$(qemu-img info ${file_abs_path} | grep 'file format:' | awk '{ print $3 }')
+image_type=$(qemu-img info "${file_abs_path}" | grep 'file format:' | awk '{ print $3 }')
 echo "Image type detected as ${image_type}"
 
-
 if [[ "${image_type}" == "raw" ]]; then
-	dest_file=${file_abs_path}
+    dest_file=${file_abs_path}
 elif [[ "$image_type" == "qcow2" ]]; then
-    if lsmod | grep "nbd" &> /dev/null ; then
+    if lsmod | grep "nbd" &>/dev/null; then
         echo "Module nbd is loaded!"
     else
         echo "Module nbd is not loaded. Trying to load the module"
-        modprobe nbd max_part=8
-        if [ $? != 0 ]; then
+
+        if ! modprobe nbd max_part=8; then
             echo "failed to load nbd module. Exiting"
             exit 1
         fi
     fi
     check_command qemu-img
     dest_file=/dev/nbd0
-    qemu-nbd --connect=${dest_file} ${file_abs_path} --read-only
+    qemu-nbd --connect=${dest_file} "${file_abs_path}" --read-only
 fi
 
 check_command blkid
 #get part info
-part_type=$(blkid -o value -s PTTYPE ${dest_file})
+part_type=$(blkid -o value -s PTTYPE "${dest_file}")
 
 check_command partx
-nr_partitions=`partx -g ${dest_file}  | wc -l`
+nr_partitions=$(partx -g "${dest_file}" | wc -l)
 
 check_command fdisk
-out=`fdisk -l  ${dest_file} --bytes | grep -i -A ${nr_partitions} 'Device' | tail -n +2`
+out=$(fdisk -l "${dest_file}" --bytes | grep -i -A "${nr_partitions}" 'Device' | tail -n +2)
 
 IFS='
 '
 i=0
-declare -A liness
-for x in $out ; do
-	lines[$i]=$x
-	i=$((i+1))
+declare -A lines
+for x in $out; do
+    lines[$i]=$x
+    i=$((i + 1))
 done
 
 declare -A partitions
@@ -127,89 +126,86 @@ IFS=' '
 i=0
 ROWS=${#lines[@]}
 
-for line in "${lines[@]}";
-do
-	j=0
-	read -a str_arr <<< "$line"
-	for val in "${str_arr[@]}";
-	do
-		if [[ "$val" != "*" ]]; then
-			partitions[$i,$j]=$val
-			j=$((j+1))
-		fi
-	done
-	i=$((i+1))
+for line in "${lines[@]}"; do
+    j=0
+    read -a -r str_arr <<<"$line"
+    for val in "${str_arr[@]}"; do
+        if [[ "$val" != "*" ]]; then
+            partitions[$i, $j]=$val
+            j=$((j + 1))
+        fi
+    done
+    i=$((i + 1))
 done
 
 COLUMNS=$j
-COUNT=${#partitions[@]}
 START_ADDRESS_INDEX=1
-FILE_SYS_INDEX2=$((COLUMNS-1))
-FILE_SYS_INDEX1=$((COLUMNS-2))
+FILE_SYS_INDEX2=$((COLUMNS - 1))
+FILE_SYS_INDEX1=$((COLUMNS - 2))
 DEVICE_INDEX=0
 # Here we have all the partition info now lets mount and analyze the contents
-for ((i=0;i<ROWS;i++)) do
-	if [[ "$part_type" == "gpt" && "${partitions[$i,${FILE_SYS_INDEX1}]}" == "Linux" && "${partitions[$i,${FILE_SYS_INDEX2}]}" == "filesystem" ]]; then
+for ((i = 0; i < ROWS; i++)); do
+    if [[ "$part_type" == "gpt" && "${partitions[$i, ${FILE_SYS_INDEX1}]}" == "Linux" && "${partitions[$i, ${FILE_SYS_INDEX2}]}" == "filesystem" ]]; then
         echo "The image has GPT partitions"
         MOUNT_ROW=$i
-		break
-	elif [[ "$part_type" == "dos" && "${partitions[$i,${FILE_SYS_INDEX1}]}" == "Linux" && "${partitions[$i,${FILE_SYS_INDEX2}]}" == "" ]]; then
+        break
+    elif [[ "$part_type" == "dos" && "${partitions[$i, ${FILE_SYS_INDEX1}]}" == "Linux" && "${partitions[$i, ${FILE_SYS_INDEX2}]}" == "" ]]; then
         echo "The image has DOS partitions"
         MOUNT_ROW=$i
         break
-	fi
+    fi
 done
 
-start_address=${partitions[${MOUNT_ROW},${START_ADDRESS_INDEX}]}
-offset=$((start_address*512))
+start_address=${partitions[${MOUNT_ROW}, ${START_ADDRESS_INDEX}]}
+offset=$((start_address * 512))
 
 MOUNT_DIR=/mnt/clh-img-check/
 rm -rf ${MOUNT_DIR}
 mkdir ${MOUNT_DIR}
 if [[ "${image_type}" == "raw" ]]; then
-    mount -o ro,loop,offset=$offset ${dest_file} ${MOUNT_DIR}
+    mount -o ro,loop,offset=$offset "${dest_file}" ${MOUNT_DIR}
 elif [[ "${image_type}" == "qcow2" ]]; then
-    mount -o ro ${partitions[${MOUNT_ROW},${DEVICE_INDEX}]} ${MOUNT_DIR}
+    mount -o ro "${partitions[${MOUNT_ROW}, ${DEVICE_INDEX}]}" ${MOUNT_DIR}
 fi
 
 CONFIG_DIR=${MOUNT_DIR}boot/
 if [[ "$part_type" == "dos" ]]; then
-	CONFIG_DIR=${MOUNT_DIR}
+    CONFIG_DIR=${MOUNT_DIR}
 fi
 
 #check VIRTIO
 HAS_VIRTIO=1
-for conf_file in ${CONFIG_DIR}config*; do
-    out=`grep -E "CONFIG_VIRTIO=y|CONFIG_VIRTIO_BLK=y|CONFIG_VIRTIO_BLK=m" ${conf_file} | wc -l`
+for conf_file in "${CONFIG_DIR}"config*; do
+    out=$(grep -cE "CONFIG_VIRTIO=y|CONFIG_VIRTIO_BLK=y|CONFIG_VIRTIO_BLK=m" "${conf_file}")
     if [[ "$out" != "2" ]]; then
-	    echo "VIRTIO not found"
-		HAS_VIRTIO=0
-	fi
+        echo "VIRTIO not found"
+        HAS_VIRTIO=0
+    fi
 done
 
 #clean up
 umount ${MOUNT_DIR}
 
 if [[ "${tmp_created}" == "1" ]]; then
-    rm -rf ${working_dir}
+    rm -rf "${working_dir}"
 fi
 
-if [[ "${image_type}" == "qcow2" ]];then
-    qemu-nbd --disconnect ${dest_file} > /dev/null
+if [[ "${image_type}" == "qcow2" ]]; then
+    qemu-nbd --disconnect "${dest_file}" >/dev/null
 fi
 
 result=""
 if [[ "${part_type}" == "dos" ]]; then
-	result="dos mode not supported"
+    result="dos mode not supported"
 fi
 if [[ "${HAS_VIRTIO}" == "0" ]]; then
-	if [[ "$result" != "" ]]; then
-		result="${result},"
-	fi
-	result="$result VirtIO module not found in the image"
+    if [[ "$result" != "" ]]; then
+        result="${result},"
+    fi
+    result="$result VirtIO module not found in the image"
 fi
-if [[ "$result" == "" ]];then
-	echo "No incompatibilities found"
+if [[ "$result" == "" ]]; then
+    echo "No incompatibilities found"
 else
-	echo "$result"
+    echo "$result"
 fi

scripts/common-aarch64.sh

@@ -1,6 +1,4 @@
-#!/bin/bash
-
-export BUILD_TARGET=${BUILD_TARGET-aarch64-unknown-linux-gnu}
+#!/usr/bin/env bash
 
 WORKLOADS_DIR="$HOME/workloads"
 
@@ -24,26 +22,26 @@ build_edk2() {
 
     # Prepare source code
     checkout_repo "$EDK2_DIR" "$EDK2_REPO" master "46b4606ba23498d3d0e66b53e498eb3d5d592586"
-    pushd "$EDK2_DIR"
+    pushd "$EDK2_DIR" || exit
     git submodule update --init
-    popd
+    popd || exit
     checkout_repo "$EDK2_PLAT_DIR" "$EDK2_PLAT_REPO" master "8227e9e9f6a8aefbd772b40138f835121ccb2307"
     checkout_repo "$ACPICA_DIR" "$ACPICA_REPO" master "b9c69f81a05c45611c91ea9cbce8756078d76233"
 
-    if [[ ! -f "$EDK2_DIR/.built" || \
-          ! -f "$EDK2_PLAT_DIR/.built" || \
-          ! -f "$ACPICA_DIR/.built" ]]; then
-        pushd "$EDK2_BUILD_DIR"
+    if [[ ! -f "$EDK2_DIR/.built" ||
+        ! -f "$EDK2_PLAT_DIR/.built" ||
+        ! -f "$ACPICA_DIR/.built" ]]; then
+        pushd "$EDK2_BUILD_DIR" || exit
         # Build
-        make -C acpica -j `nproc`
+        make -C acpica -j "$(nproc)"
+        # shellcheck disable=SC1091
         source edk2/edksetup.sh
-        make -C edk2/BaseTools -j `nproc`
+        make -C edk2/BaseTools -j "$(nproc)"
         build -a AARCH64 -t GCC5 -p ArmVirtPkg/ArmVirtCloudHv.dsc -b RELEASE -n 0
         cp Build/ArmVirtCloudHv-AARCH64/RELEASE_GCC5/FV/CLOUDHV_EFI.fd "$WORKLOADS_DIR"
         touch "$EDK2_DIR"/.built
         touch "$EDK2_PLAT_DIR"/.built
         touch "$ACPICA_DIR"/.built
-        popd
+        popd || exit
     fi
 }
-

scripts/create-cloud-init.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -x
 
 rm -f /tmp/ubuntu-cloudinit.img
@@ -6,4 +6,3 @@ mkdosfs -n CIDATA -C /tmp/ubuntu-cloudinit.img 8192
 mcopy -oi /tmp/ubuntu-cloudinit.img -s test_data/cloud-init/ubuntu/local/user-data ::
 mcopy -oi /tmp/ubuntu-cloudinit.img -s test_data/cloud-init/ubuntu/local/meta-data ::
 mcopy -oi /tmp/ubuntu-cloudinit.img -s test_data/cloud-init/ubuntu/local/network-config ::
-

scripts/dev_cli.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 # Copyright © 2020 Intel Corporation
@@ -7,7 +7,7 @@
 CLI_NAME="Cloud Hypervisor"
 
 CTR_IMAGE_TAG="ghcr.io/cloud-hypervisor/cloud-hypervisor"
-CTR_IMAGE_VERSION="20230804-0"
+CTR_IMAGE_VERSION="20231220-0"
 : "${CTR_IMAGE:=${CTR_IMAGE_TAG}:${CTR_IMAGE_VERSION}}"
 
 DOCKER_RUNTIME="docker"
@@ -121,9 +121,7 @@ ensure_latest_ctr() {
     if [ "$CTR_IMAGE_VERSION" = "local" ]; then
         build_container
     else
-        $DOCKER_RUNTIME pull "$CTR_IMAGE"
-
-        if [ $? -ne 0 ]; then
+        if ! $DOCKER_RUNTIME pull "$CTR_IMAGE"; then
             build_container
         fi
 
@@ -143,7 +141,8 @@ fix_dir_perms() {
         --workdir "$CTR_CLH_ROOT_DIR" \
         --rm \
         --volume /dev:/dev \
-        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+        ${exported_volumes:+"$exported_volumes"} \
         "$CTR_IMAGE" \
         chown -R "$(id -u):$(id -g)" "$CTR_CLH_ROOT_DIR"
 
@@ -158,9 +157,9 @@ process_volumes_args() {
         return
     fi
     exported_volumes=""
-    arr_vols=(${arg_vols//#/ })
+    arr_vols=("${arg_vols//#/ }")
     for var in "${arr_vols[@]}"; do
-        parts=(${var//:/ })
+        parts=("${var//:/ }")
         if [[ ! -e "${parts[0]}" ]]; then
             echo "The volume ${parts[0]} does not exist."
             exit 1
@@ -233,10 +232,10 @@ cmd_build() {
         "--debug") { build="debug"; } ;;
         "--release") { build="release"; } ;;
         "--runtime")
-	    shift
-	    DOCKER_RUNTIME="$1"
-	    export DOCKER_RUNTIME
-	    ;;
+            shift
+            DOCKER_RUNTIME="$1"
+            export DOCKER_RUNTIME
+            ;;
         "--libc")
             shift
             [[ "$1" =~ ^(musl|gnu)$ ]] ||
@@ -282,11 +281,11 @@ cmd_build() {
     [ $build = "release" ] && cargo_args+=("--release")
     cargo_args+=(--target "$target")
 
-    rustflags=""
+    # shellcheck disable=SC2153
+    rustflags="$RUSTFLAGS"
     target_cc=""
     if [ "$(uname -m)" = "aarch64" ] && [ "$libc" = "musl" ]; then
-        rustflags="-C link-arg=-lgcc -C link_arg=-specs -C link_arg=/usr/lib/aarch64-linux-musl/musl-gcc.specs"
-        target_cc="musl-gcc"
+        rustflags="$rustflags -C link-args=-Wl,-Bstatic -C link-args=-lc"
     fi
 
     $DOCKER_RUNTIME run \
@@ -294,11 +293,12 @@ cmd_build() {
         --workdir "$CTR_CLH_ROOT_DIR" \
         --rm \
         --volume $exported_device \
-        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+        ${exported_volumes:+"$exported_volumes"} \
         --env RUSTFLAGS="$rustflags" \
         --env TARGET_CC="$target_cc" \
         "$CTR_IMAGE" \
-        cargo build --all $features_build \
+        cargo build --all "$features_build" \
         --target-dir "$CTR_CLH_CARGO_TARGET" \
         "${cargo_args[@]}" && say "Binaries placed under $CLH_CARGO_TARGET/$target/$build"
 }
@@ -313,7 +313,8 @@ cmd_clean() {
         --user "$(id -u):$(id -g)" \
         --workdir "$CTR_CLH_ROOT_DIR" \
         --rm \
-        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+        ${exported_volumes:+"$exported_volumes"} \
         "$CTR_IMAGE" \
         cargo clean \
         --target-dir "$CTR_CLH_CARGO_TARGET" \
@@ -362,7 +363,6 @@ cmd_tests() {
             hypervisor="$1"
             ;;
         "--all") {
-            cargo=true
             unit=true
             integration=true
         } ;;
@@ -384,7 +384,7 @@ cmd_tests() {
         exported_device="/dev/mshv"
     fi
 
-    if [ ! -e "${exported_device}" ] ; then
+    if [ ! -e "${exported_device}" ]; then
         die "${exported_device} does not exist on the system"
     fi
 
@@ -396,6 +396,12 @@ cmd_tests() {
     process_volumes_args
     target="$(uname -m)-unknown-linux-${libc}"
 
+    rustflags="$RUSTFLAGS"
+    target_cc=""
+    if [ "$(uname -m)" = "aarch64" ] && [ "$libc" = "musl" ]; then
+        rustflags="$rustflags -C link-args=-Wl,-Bstatic -C link-args=-lc"
+    fi
+
     if [[ "$unit" = true ]]; then
         say "Running unit tests for $target..."
         $DOCKER_RUNTIME run \
@@ -404,8 +410,11 @@ cmd_tests() {
             --device $exported_device \
             --device /dev/net/tun \
             --cap-add net_admin \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
             "$CTR_IMAGE" \
             ./scripts/run_unit_tests.sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -421,10 +430,14 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             dbus-run-session ./scripts/run_integration_tests_"$(uname -m)".sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -440,10 +453,14 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             ./scripts/run_integration_tests_sgx.sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -459,10 +476,14 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             ./scripts/run_integration_tests_vfio.sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -478,10 +499,14 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             ./scripts/run_integration_tests_windows_"$(uname -m)".sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -497,10 +522,14 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             ./scripts/run_integration_tests_live_migration.sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -516,10 +545,14 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             ./scripts/run_integration_tests_rate_limiter.sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -535,11 +568,15 @@ cmd_tests() {
             --net="$CTR_CLH_NET" \
             --mount type=tmpfs,destination=/tmp \
             --volume /dev:/dev \
-            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+            --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+            ${exported_volumes:+"$exported_volumes"} \
             --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
             --env USER="root" \
-            --env CH_LIBC="${libc}" \
+            --env BUILD_TARGET="$target" \
+            --env RUSTFLAGS="$rustflags" \
+            --env TARGET_CC="$target_cc" \
             --env RUST_BACKTRACE="${RUST_BACKTRACE}" \
+            --env AUTH_DOWNLOAD_TOKEN="$AUTH_DOWNLOAD_TOKEN" \
             "$CTR_IMAGE" \
             ./scripts/run_metrics.sh "$@" || fix_dir_perms $? || exit $?
     fi
@@ -560,9 +597,9 @@ build_container() {
 
     $DOCKER_RUNTIME build \
         --target dev \
-        -t $CTR_IMAGE \
+        -t "$CTR_IMAGE" \
         -f $BUILD_DIR/Dockerfile \
-        --build-arg TARGETARCH=$TARGETARCH \
+        --build-arg TARGETARCH="$TARGETARCH" \
         $BUILD_DIR
 }
 
@@ -622,7 +659,8 @@ cmd_shell() {
         --net="$CTR_CLH_NET" \
         --tmpfs /tmp:exec \
         --volume /dev:/dev \
-        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" $exported_volumes \
+        --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR" \
+        ${exported_volumes:+"$exported_volumes"} \
         --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
         --env USER="root" \
         --entrypoint bash \

scripts/gitlint/rules.py

@@ -0,0 +1,92 @@
+from gitlint.rules import LineRule, RuleViolation, CommitMessageTitle
+import re
+
+
+class TitleStartsWithComponent(LineRule):
+    """A rule to enforce valid commit message title
+
+    Valid title format:
+    component1[, component2, componentN]: submodule: summary
+
+    Title should have at least one component
+    Components are separated by comma+space: ", "
+    Components are validated to be in valid_components
+    Components list is ended by a colon
+    Submodules are not validated
+
+    """
+
+    # A rule MUST have a human friendly name
+    name = "title-has-valid-component"
+
+    # A rule MUST have a *unique* id.
+    # We recommend starting with UL (for User-defined Line-rule)
+    id = "UL1"
+
+    # A line-rule MUST have a target (not required for CommitRules).
+    target = CommitMessageTitle
+
+    def validate(self, line, _commit):
+        valid_components = (
+            'api_client',
+            'arch',
+            'block',
+            'build',
+            'ch-remote',
+            'ci',
+            'devices',
+            'docs',
+            'event_monitor',
+            'fuzz',
+            'github',
+            'gitignore',
+            'gitlint',
+            'hypervisor',
+            'Jenkinsfile',
+            'main',
+            'misc',
+            'net_gen',
+            'net_util',
+            'option_parser',
+            'pci',
+            'performance-metrics',
+            'rate_limiter',
+            'README',
+            'resources',
+            'scripts',
+            'serial_buffer',
+            'test_data',
+            'test_infra',
+            'tests',
+            'tpm',
+            'tracer',
+            'vhost_user_block',
+            'vhost_user_net',
+            'virtio-devices',
+            'vm-allocator',
+            'vm-device',
+            'vmm',
+            'vm-migration',
+            'vm-virtio')
+
+        ptrn_title = re.compile(r'^(.+?):\s(.+)$')
+        match = ptrn_title.match(line)
+
+        if not match:
+            self.log.debug("Invalid commit title {}", line)
+            return [RuleViolation(self.id, "Commit title does not comply with "
+                                  "rule: 'component: change summary'")]
+        components = match.group(1)
+        summary = match.group(2)
+        self.log.debug(f"\nComponents: {components}\nSummary: {summary}")
+
+        ptrn_components = re.compile(r',\s')
+        components_list = re.split(ptrn_components, components)
+        self.log.debug("components list: %s" % components_list)
+
+        for component in components_list:
+            if component not in valid_components:
+                return [RuleViolation(self.id,
+                                      f"Invalid component: {component}, "
+                                      "\nValid components are: {}".format(
+                                          " ".join(valid_components)))]

scripts/prepare_vdpa.sh

@@ -1,20 +1,20 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -x
 
 sudo apt install -y libncurses-dev gawk flex bison openssl libssl-dev dkms libelf-dev libudev-dev libpci-dev libiberty-dev autoconf git make dpkg-dev libmnl-dev pkg-config iproute2
 sudo sed -i -- 's/# deb-src/deb-src/g' /etc/apt/sources.list
 sudo apt update
-apt-get source linux-image-unsigned-`uname -r`
-pushd linux-azure*/drivers/vdpa/vdpa_sim/
-cat <<'EOF' > Makefile
+apt-get source linux-image-unsigned-"$(uname -r)"
+pushd linux-azure*/drivers/vdpa/vdpa_sim/ || exit
+cat <<'EOF' >Makefile
 # SPDX-License-Identifier: GPL-2.0
 obj-m += vdpa_sim.o
 obj-m += vdpa_sim_net.o
 obj-m += vdpa_sim_blk.o
 EOF
-make -C /lib/modules/`uname -r`/build M=$PWD
-sudo make -C /lib/modules/`uname -r`/build M=$PWD modules_install
-popd
+make -C /lib/modules/"$(uname -r)"/build M="$PWD"
+sudo make -C /lib/modules/"$(uname -r)"/build M="$PWD" modules_install
+popd || exit
 sudo depmod -a
 sudo modprobe vdpa
 sudo modprobe vhost_vdpa

scripts/run_integration_tests_aarch64.sh

@@ -1,9 +1,11 @@
-#!/bin/bash
+#!/usr/bin/env bash
+# shellcheck disable=SC2048,SC2086
 set -x
 
-source $HOME/.cargo/env
-source $(dirname "$0")/test-util.sh
-source $(dirname "$0")/common-aarch64.sh
+# shellcheck source=/dev/null
+source "$HOME"/.cargo/env
+source "$(dirname "$0")"/test-util.sh
+source "$(dirname "$0")"/common-aarch64.sh
 
 WORKLOADS_LOCK="$WORKLOADS_DIR/integration_test.lock"
 
@@ -11,60 +13,63 @@ build_spdk_nvme() {
     SPDK_DIR="$WORKLOADS_DIR/spdk"
     SPDK_REPO="https://github.com/spdk/spdk.git"
     SPDK_DEPLOY_DIR="/usr/local/bin/spdk-nvme"
-    checkout_repo "$SPDK_DIR" "$SPDK_REPO" master "6301f8915de32baed10dba1eebed556a6749211a"
+    checkout_repo "$SPDK_DIR" "$SPDK_REPO" master "ef8bcce58f3f02b79c0619a297e4f17e81e62b24"
 
     if [ ! -f "$SPDK_DIR/.built" ]; then
-        pushd $SPDK_DIR
+        pushd "$SPDK_DIR" || exit
         git submodule update --init
         apt-get update
+        sed -i "/grpcio/d" scripts/pkgdep/debian.sh
         ./scripts/pkgdep.sh
         ./configure --with-vfio-user
-        chmod +x /usr/local/lib/python3.8/dist-packages/ninja/data/bin/ninja
-        make -j `nproc` || exit 1
+        chmod +x /usr/local/lib/python3.10/dist-packages/ninja/data/bin/ninja
+        make -j "$(nproc)" || exit 1
         touch .built
-        popd
+        popd || exit
     fi
     if [ ! -d "/usr/local/bin/spdk-nvme" ]; then
         mkdir -p $SPDK_DEPLOY_DIR
     fi
     cp "$WORKLOADS_DIR/spdk/build/bin/nvmf_tgt" $SPDK_DEPLOY_DIR/nvmf_tgt
     cp "$WORKLOADS_DIR/spdk/scripts/rpc.py" $SPDK_DEPLOY_DIR/rpc.py
-    cp -r "$WORKLOADS_DIR/spdk/scripts/rpc" $SPDK_DEPLOY_DIR/rpc
+    cp -r "$WORKLOADS_DIR/spdk/python/spdk/" $SPDK_DEPLOY_DIR/
+    cp -r "$WORKLOADS_DIR/spdk/python" $SPDK_DEPLOY_DIR/../
 }
 
 build_virtiofsd() {
     VIRTIOFSD_DIR="$WORKLOADS_DIR/virtiofsd_build"
     VIRTIOFSD_REPO="https://gitlab.com/virtio-fs/virtiofsd.git"
 
-    checkout_repo "$VIRTIOFSD_DIR" "$VIRTIOFSD_REPO" v1.1.0 "220405d7a2606c92636d31992b5cb3036a41047b"
+    checkout_repo "$VIRTIOFSD_DIR" "$VIRTIOFSD_REPO" v1.8.0 "97ea7908fe7f9bc59916671a771bdcfaf4044b45"
 
     if [ ! -f "$VIRTIOFSD_DIR/.built" ]; then
-        pushd $VIRTIOFSD_DIR
-        time cargo build --release
+        pushd "$VIRTIOFSD_DIR" || exit
+        rm -rf target/
+        time RUSTFLAGS="" TARGET_CC="" cargo build --release
         cp target/release/virtiofsd "$WORKLOADS_DIR/" || exit 1
         touch .built
-        popd
+        popd || exit
     fi
 }
 
 update_workloads() {
-    cp scripts/sha1sums-aarch64 $WORKLOADS_DIR
+    cp scripts/sha1sums-aarch64 "$WORKLOADS_DIR"
 
     BIONIC_OS_IMAGE_DOWNLOAD_NAME="bionic-server-cloudimg-arm64.img"
     BIONIC_OS_IMAGE_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$BIONIC_OS_IMAGE_DOWNLOAD_NAME"
     BIONIC_OS_DOWNLOAD_IMAGE="$WORKLOADS_DIR/$BIONIC_OS_IMAGE_DOWNLOAD_NAME"
     if [ ! -f "$BIONIC_OS_DOWNLOAD_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         time wget --quiet $BIONIC_OS_IMAGE_DOWNLOAD_URL || exit 1
-        popd
+        popd || exit
     fi
 
     BIONIC_OS_RAW_IMAGE_NAME="bionic-server-cloudimg-arm64.raw"
     BIONIC_OS_RAW_IMAGE="$WORKLOADS_DIR/$BIONIC_OS_RAW_IMAGE_NAME"
     if [ ! -f "$BIONIC_OS_RAW_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         time qemu-img convert -p -f qcow2 -O raw $BIONIC_OS_IMAGE_DOWNLOAD_NAME $BIONIC_OS_RAW_IMAGE_NAME || exit 1
-        popd
+        popd || exit
     fi
 
     # Convert the raw image to qcow2 image to remove compressed blocks from the disk. Therefore letting the
@@ -72,97 +77,109 @@ update_workloads() {
     BIONIC_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME="bionic-server-cloudimg-arm64.qcow2"
     BIONIC_OS_QCOW2_UNCOMPRESSED_IMAGE="$WORKLOADS_DIR/$BIONIC_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME"
     if [ ! -f "$BIONIC_OS_QCOW2_UNCOMPRESSED_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
-        time qemu-img convert -p -f raw -O qcow2 $BIONIC_OS_RAW_IMAGE_NAME $BIONIC_OS_QCOW2_UNCOMPRESSED_IMAGE || exit 1
-        popd
+        pushd "$WORKLOADS_DIR" || exit
+        time qemu-img convert -p -f raw -O qcow2 $BIONIC_OS_RAW_IMAGE_NAME "$BIONIC_OS_QCOW2_UNCOMPRESSED_IMAGE" || exit 1
+        popd || exit
     fi
 
     FOCAL_OS_RAW_IMAGE_NAME="focal-server-cloudimg-arm64-custom-20210929-0.raw"
     FOCAL_OS_RAW_IMAGE_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_RAW_IMAGE_NAME"
     FOCAL_OS_RAW_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_RAW_IMAGE_NAME"
     if [ ! -f "$FOCAL_OS_RAW_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         time wget --quiet $FOCAL_OS_RAW_IMAGE_DOWNLOAD_URL || exit 1
-        popd
+        popd || exit
     fi
 
     FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME="focal-server-cloudimg-arm64-custom-20210929-0.qcow2"
     FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME"
     FOCAL_OS_QCOW2_UNCOMPRESSED_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME"
     if [ ! -f "$FOCAL_OS_QCOW2_UNCOMPRESSED_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         time wget --quiet $FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_DOWNLOAD_URL || exit 1
-        popd
+        popd || exit
     fi
 
     FOCAL_OS_QCOW2_IMAGE_BACKING_FILE_NAME="focal-server-cloudimg-arm64-custom-20210929-0-backing.qcow2"
     FOCAL_OS_QCOW2_BACKING_FILE_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_QCOW2_IMAGE_BACKING_FILE_NAME"
     if [ ! -f "$FOCAL_OS_QCOW2_BACKING_FILE_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
-        time qemu-img create -f qcow2 -b $FOCAL_OS_QCOW2_UNCOMPRESSED_IMAGE -F qcow2 $FOCAL_OS_QCOW2_IMAGE_BACKING_FILE_NAME
-        popd
+        pushd "$WORKLOADS_DIR" || exit
+        time qemu-img create -f qcow2 -b "$FOCAL_OS_QCOW2_UNCOMPRESSED_IMAGE" -F qcow2 $FOCAL_OS_QCOW2_IMAGE_BACKING_FILE_NAME
+        popd || exit
     fi
 
     JAMMY_OS_RAW_IMAGE_NAME="jammy-server-cloudimg-arm64-custom-20220329-0.raw"
     JAMMY_OS_RAW_IMAGE_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$JAMMY_OS_RAW_IMAGE_NAME"
     JAMMY_OS_RAW_IMAGE="$WORKLOADS_DIR/$JAMMY_OS_RAW_IMAGE_NAME"
     if [ ! -f "$JAMMY_OS_RAW_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         time wget --quiet $JAMMY_OS_RAW_IMAGE_DOWNLOAD_URL || exit 1
-        popd
+        popd || exit
     fi
 
     JAMMY_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME="jammy-server-cloudimg-arm64-custom-20220329-0.qcow2"
     JAMMY_OS_QCOW2_IMAGE_UNCOMPRESSED_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$JAMMY_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME"
     JAMMY_OS_QCOW2_UNCOMPRESSED_IMAGE="$WORKLOADS_DIR/$JAMMY_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME"
     if [ ! -f "$JAMMY_OS_QCOW2_UNCOMPRESSED_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         time wget --quiet $JAMMY_OS_QCOW2_IMAGE_UNCOMPRESSED_DOWNLOAD_URL || exit 1
-        popd
+        popd || exit
     fi
 
     ALPINE_MINIROOTFS_URL="http://dl-cdn.alpinelinux.org/alpine/v3.11/releases/aarch64/alpine-minirootfs-3.11.3-aarch64.tar.gz"
     ALPINE_MINIROOTFS_TARBALL="$WORKLOADS_DIR/alpine-minirootfs-aarch64.tar.gz"
     if [ ! -f "$ALPINE_MINIROOTFS_TARBALL" ]; then
-        pushd $WORKLOADS_DIR
-        time wget --quiet $ALPINE_MINIROOTFS_URL -O $ALPINE_MINIROOTFS_TARBALL || exit 1
-        popd
+        pushd "$WORKLOADS_DIR" || exit
+        time wget --quiet $ALPINE_MINIROOTFS_URL -O "$ALPINE_MINIROOTFS_TARBALL" || exit 1
+        popd || exit
     fi
 
     ALPINE_INITRAMFS_IMAGE="$WORKLOADS_DIR/alpine_initramfs.img"
     if [ ! -f "$ALPINE_INITRAMFS_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
+        pushd "$WORKLOADS_DIR" || exit
         mkdir alpine-minirootfs
         tar xf "$ALPINE_MINIROOTFS_TARBALL" -C alpine-minirootfs
-        cat > alpine-minirootfs/init <<-EOF
+        cat >alpine-minirootfs/init <<-EOF
 			#! /bin/sh
 			mount -t devtmpfs dev /dev
 			echo \$TEST_STRING > /dev/console
 			poweroff -f
 		EOF
         chmod +x alpine-minirootfs/init
-        cd alpine-minirootfs
+        cd alpine-minirootfs || exit
         find . -print0 |
-            cpio --null --create --verbose --owner root:root --format=newc > "$ALPINE_INITRAMFS_IMAGE"
-        popd
+            cpio --null --create --verbose --owner root:root --format=newc >"$ALPINE_INITRAMFS_IMAGE"
+        popd || exit
     fi
 
-    pushd $WORKLOADS_DIR
-    sha1sum sha1sums-aarch64 --check
-    if [ $? -ne 0 ]; then
+    pushd "$WORKLOADS_DIR" || exit
+
+    if ! sha1sum sha1sums-aarch64 --check; then
         echo "sha1sum validation of images failed, remove invalid images to fix the issue."
         exit 1
     fi
-    popd
+    popd || exit
 
     # Download Cloud Hypervisor binary from its last stable release
-    LAST_RELEASE_VERSION="v34.0"
+    LAST_RELEASE_VERSION="v36.0"
     CH_RELEASE_URL="https://github.com/cloud-hypervisor/cloud-hypervisor/releases/download/$LAST_RELEASE_VERSION/cloud-hypervisor-static-aarch64"
     CH_RELEASE_NAME="cloud-hypervisor-static-aarch64"
-    pushd $WORKLOADS_DIR
-    time wget --quiet $CH_RELEASE_URL -O "$CH_RELEASE_NAME" || exit 1
-    chmod +x $CH_RELEASE_NAME
-    popd
+    pushd "$WORKLOADS_DIR" || exit
+    # Repeat a few times to workaround a random wget failure
+    WGET_RETRY_MAX=10
+    wget_retry=0
+
+    until [ "$wget_retry" -ge "$WGET_RETRY_MAX" ]; do
+        time wget $CH_RELEASE_URL -O "$CH_RELEASE_NAME" && break
+        wget_retry=$((wget_retry + 1))
+    done
+
+    if [ $wget_retry -ge "$WGET_RETRY_MAX" ]; then
+        exit 1
+    else
+        chmod +x $CH_RELEASE_NAME
+    fi
+    popd || exit
 
     # Build custom kernel for guest VMs
     build_custom_linux
@@ -183,22 +200,22 @@ update_workloads() {
     BLK_IMAGE="$WORKLOADS_DIR/blk.img"
     MNT_DIR="mount_image"
     if [ ! -f "$BLK_IMAGE" ]; then
-        pushd $WORKLOADS_DIR
-        fallocate -l 16M $BLK_IMAGE
-        mkfs.ext4 -j $BLK_IMAGE
+        pushd "$WORKLOADS_DIR" || exit
+        fallocate -l 16M "$BLK_IMAGE"
+        mkfs.ext4 -j "$BLK_IMAGE"
         mkdir $MNT_DIR
-        sudo mount -t ext4 $BLK_IMAGE $MNT_DIR
+        sudo mount -t ext4 "$BLK_IMAGE" $MNT_DIR
         sudo bash -c "echo bar > $MNT_DIR/foo" || exit 1
-        sudo umount $BLK_IMAGE
+        sudo umount "$BLK_IMAGE"
         rm -r $MNT_DIR
-        popd
+        popd || exit
     fi
 
     SHARED_DIR="$WORKLOADS_DIR/shared_dir"
     if [ ! -d "$SHARED_DIR" ]; then
-        mkdir -p $SHARED_DIR
-        echo "foo" > "$SHARED_DIR/file1"
-        echo "bar" > "$SHARED_DIR/file3" || exit 1
+        mkdir -p "$SHARED_DIR"
+        echo "foo" >"$SHARED_DIR/file1"
+        echo "bar" >"$SHARED_DIR/file3" || exit 1
     fi
 
     # Checkout and build SPDK NVMe
@@ -216,12 +233,11 @@ if [[ "$hypervisor" = "mshv" ]]; then
     exit 1
 fi
 
-
 # lock the workloads folder to avoid parallel updating by different containers
 (
     echo "try to lock $WORKLOADS_DIR folder and update"
     flock -x 12 && update_workloads
-) 12>$WORKLOADS_LOCK
+) 12>"$WORKLOADS_LOCK"
 
 # Check if there is any error in the execution of `update_workloads`.
 # If there is any error, then kill the shell. Otherwise the script will continue
@@ -231,15 +247,9 @@ if [ $RES -ne 0 ]; then
     exit 1
 fi
 
-BUILD_TARGET="aarch64-unknown-linux-${CH_LIBC}"
-if [[ "${BUILD_TARGET}" == "aarch64-unknown-linux-musl" ]]; then
-    export TARGET_CC="musl-gcc"
-    export RUSTFLAGS="-C link-arg=-lgcc -C link_arg=-specs -C link_arg=/usr/lib/aarch64-linux-musl/musl-gcc.specs"
-fi
-
 export RUST_BACKTRACE=1
 
-cargo build --all --release --target $BUILD_TARGET
+cargo build --all --release --target "$BUILD_TARGET"
 
 # Enable KSM with some reasonable parameters so that it won't take too long
 # for the memory to be merged between two processes.
@@ -248,19 +258,19 @@ sudo bash -c "echo 10 > /sys/kernel/mm/ksm/sleep_millisecs"
 sudo bash -c "echo 1 > /sys/kernel/mm/ksm/run"
 
 # Both test_vfio and ovs-dpdk rely on hugepages
-HUGEPAGESIZE=`grep Hugepagesize /proc/meminfo | awk '{print $2}'`
-PAGE_NUM=`echo $((12288 * 1024 / $HUGEPAGESIZE))`
-echo $PAGE_NUM | sudo tee /proc/sys/vm/nr_hugepages
+HUGEPAGESIZE=$(grep Hugepagesize /proc/meminfo | awk '{print $2}')
+PAGE_NUM=$((12288 * 1024 / HUGEPAGESIZE))
+echo "$PAGE_NUM" | sudo tee /proc/sys/vm/nr_hugepages
 sudo chmod a+rwX /dev/hugepages
 
 # Run all direct kernel boot (Device Tree) test cases in mod `parallel`
-time cargo test "common_parallel::$test_filter" --target $BUILD_TARGET -- ${test_binary_args[*]}
+time cargo test "common_parallel::$test_filter" --target "$BUILD_TARGET" -- ${test_binary_args[*]}
 RES=$?
 
 # Run some tests in sequence since the result could be affected by other tests
 # running in parallel.
 if [ $RES -eq 0 ]; then
-    time cargo test "common_sequential::$test_filter" --target $BUILD_TARGET -- --test-threads=1 ${test_binary_args[*]}
+    time cargo test "common_sequential::$test_filter" --target "$BUILD_TARGET" -- --test-threads=1 ${test_binary_args[*]}
     RES=$?
 else
     exit $RES
@@ -268,7 +278,7 @@ fi
 
 # Run all ACPI test cases
 if [ $RES -eq 0 ]; then
-    time cargo test "aarch64_acpi::$test_filter" --target $BUILD_TARGET -- ${test_binary_args[*]}
+    time cargo test "aarch64_acpi::$test_filter" --target "$BUILD_TARGET" -- ${test_binary_args[*]}
     RES=$?
 else
     exit $RES
@@ -276,14 +286,14 @@ fi
 
 # Run all test cases related to live migration
 if [ $RES -eq 0 ]; then
-    time cargo test "live_migration_parallel::$test_filter" --target $BUILD_TARGET -- ${test_binary_args[*]}
+    time cargo test "live_migration_parallel::$test_filter" --target "$BUILD_TARGET" -- ${test_binary_args[*]}
     RES=$?
 else
     exit $RES
 fi
 
 if [ $RES -eq 0 ]; then
-    time cargo test "live_migration_sequential::$test_filter" --target $BUILD_TARGET -- --test-threads=1 ${test_binary_args[*]}
+    time cargo test "live_migration_sequential::$test_filter" --target "$BUILD_TARGET" -- --test-threads=1 ${test_binary_args[*]}
     RES=$?
 else
     exit $RES
@@ -291,9 +301,9 @@ fi
 
 # Run tests on dbus_api
 if [ $RES -eq 0 ]; then
-    cargo build --features "dbus_api" --all --release --target $BUILD_TARGET
+    cargo build --features "dbus_api" --all --release --target "$BUILD_TARGET"
     export RUST_BACKTRACE=1
-    time cargo test "dbus_api::$test_filter" --target $BUILD_TARGET -- ${test_binary_args[*]}
+    time cargo test "dbus_api::$test_filter" --target "$BUILD_TARGET" -- ${test_binary_args[*]}
     RES=$?
 fi
 

scripts/run_integration_tests_live_migration.sh

@@ -1,10 +1,10 @@
-#!/bin/bash
+#!/usr/bin/env bash
+# shellcheck disable=SC2048,SC2086
 set -x
 
-source $HOME/.cargo/env
-source $(dirname "$0")/test-util.sh
-
-export BUILD_TARGET=${BUILD_TARGET-x86_64-unknown-linux-gnu}
+# shellcheck source=/dev/null
+source "$HOME"/.cargo/env
+source "$(dirname "$0")"/test-util.sh
 
 WORKLOADS_DIR="$HOME/workloads"
 mkdir -p "$WORKLOADS_DIR"
@@ -14,45 +14,44 @@ process_common_args "$@"
 # For now these values are default for kvm
 test_features=""
 
-if [ "$hypervisor" = "mshv" ] ;  then
+if [ "$hypervisor" = "mshv" ]; then
     test_features="--features mshv"
 fi
 
-cp scripts/sha1sums-x86_64 $WORKLOADS_DIR
+cp scripts/sha1sums-x86_64 "$WORKLOADS_DIR"
 
 FOCAL_OS_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.qcow2"
 FOCAL_OS_IMAGE_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_IMAGE_NAME"
 FOCAL_OS_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_IMAGE_NAME"
 if [ ! -f "$FOCAL_OS_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
+    pushd "$WORKLOADS_DIR" || exit
     time wget --quiet $FOCAL_OS_IMAGE_URL || exit 1
-    popd
+    popd || exit
 fi
 
 FOCAL_OS_RAW_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.raw"
 FOCAL_OS_RAW_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_RAW_IMAGE_NAME"
 if [ ! -f "$FOCAL_OS_RAW_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
+    pushd "$WORKLOADS_DIR" || exit
     time qemu-img convert -p -f qcow2 -O raw $FOCAL_OS_IMAGE_NAME $FOCAL_OS_RAW_IMAGE_NAME || exit 1
-    popd
+    popd || exit
 fi
 
-pushd $WORKLOADS_DIR
-grep focal sha1sums-x86_64 | sha1sum --check
-if [ $? -ne 0 ]; then
+pushd "$WORKLOADS_DIR" || exit
+if ! grep focal sha1sums-x86_64 | sha1sum --check; then
     echo "sha1sum validation of images failed, remove invalid images to fix the issue."
     exit 1
 fi
-popd
+popd || exit
 
 # Download Cloud Hypervisor binary from its last stable release
-LAST_RELEASE_VERSION="v34.0"
+LAST_RELEASE_VERSION="v36.0"
 CH_RELEASE_URL="https://github.com/cloud-hypervisor/cloud-hypervisor/releases/download/$LAST_RELEASE_VERSION/cloud-hypervisor-static"
 CH_RELEASE_NAME="cloud-hypervisor-static"
-pushd $WORKLOADS_DIR
+pushd "$WORKLOADS_DIR" || exit
 time wget --quiet $CH_RELEASE_URL -O "$CH_RELEASE_NAME" || exit 1
 chmod +x $CH_RELEASE_NAME
-popd
+popd || exit
 
 # Build custom kernel based on virtio-pmem and virtio-fs upstream patches
 VMLINUX_IMAGE="$WORKLOADS_DIR/vmlinux"
@@ -60,20 +59,18 @@ if [ ! -f "$VMLINUX_IMAGE" ]; then
     build_custom_linux
 fi
 
-BUILD_TARGET="$(uname -m)-unknown-linux-${CH_LIBC}"
 CFLAGS=""
-TARGET_CC=""
 if [[ "${BUILD_TARGET}" == "x86_64-unknown-linux-musl" ]]; then
-    TARGET_CC="musl-gcc"
+    # shellcheck disable=SC2034
     CFLAGS="-I /usr/include/x86_64-linux-musl/ -idirafter /usr/include/"
 fi
 
-cargo build --features mshv --all --release --target $BUILD_TARGET
+cargo build --features mshv --all --release --target "$BUILD_TARGET"
 
 # Test ovs-dpdk relies on hugepages
-HUGEPAGESIZE=`grep Hugepagesize /proc/meminfo | awk '{print $2}'`
-PAGE_NUM=`echo $((12288 * 1024 / $HUGEPAGESIZE))`
-echo $PAGE_NUM | sudo tee /proc/sys/vm/nr_hugepages
+HUGEPAGESIZE=$(grep Hugepagesize /proc/meminfo | awk '{print $2}')
+PAGE_NUM=$((12288 * 1024 / HUGEPAGESIZE))
+echo "$PAGE_NUM" | sudo tee /proc/sys/vm/nr_hugepages
 sudo chmod a+rwX /dev/hugepages
 
 export RUST_BACKTRACE=1

scripts/run_integration_tests_rate_limiter.sh

@@ -1,10 +1,10 @@
-#!/bin/bash
+#!/usr/bin/env bash
+# shellcheck disable=SC2048,SC2086
 set -x
 
-source $HOME/.cargo/env
-source $(dirname "$0")/test-util.sh
-
-export BUILD_TARGET=${BUILD_TARGET-x86_64-unknown-linux-gnu}
+# shellcheck source=/dev/null
+source "$HOME"/.cargo/env
+source "$(dirname "$0")"/test-util.sh
 
 WORKLOADS_DIR="$HOME/workloads"
 mkdir -p "$WORKLOADS_DIR"
@@ -14,48 +14,45 @@ process_common_args "$@"
 # For now these values are default for kvm
 test_features=""
 
-if [ "$hypervisor" = "mshv" ] ;  then
+if [ "$hypervisor" = "mshv" ]; then
     test_features="--features mshv"
 fi
 
-cp scripts/sha1sums-x86_64 $WORKLOADS_DIR
+cp scripts/sha1sums-x86_64 "$WORKLOADS_DIR"
 
 FOCAL_OS_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.qcow2"
 FOCAL_OS_IMAGE_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_IMAGE_NAME"
 FOCAL_OS_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_IMAGE_NAME"
 if [ ! -f "$FOCAL_OS_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
+    pushd "$WORKLOADS_DIR" || exit
     time wget --quiet $FOCAL_OS_IMAGE_URL || exit 1
-    popd
+    popd || exit
 fi
 
 FOCAL_OS_RAW_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.raw"
 FOCAL_OS_RAW_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_RAW_IMAGE_NAME"
 if [ ! -f "$FOCAL_OS_RAW_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
+    pushd "$WORKLOADS_DIR" || exit
     time qemu-img convert -p -f qcow2 -O raw $FOCAL_OS_IMAGE_NAME $FOCAL_OS_RAW_IMAGE_NAME || exit 1
-    popd
+    popd || exit
 fi
 
-pushd $WORKLOADS_DIR
-grep focal sha1sums-x86_64 | sha1sum --check
-if [ $? -ne 0 ]; then
+pushd "$WORKLOADS_DIR" || exit
+if ! grep focal sha1sums-x86_64 | sha1sum --check; then
     echo "sha1sum validation of images failed, remove invalid images to fix the issue."
     exit 1
 fi
-popd
+popd || exit
 
 build_custom_linux
 
-BUILD_TARGET="$(uname -m)-unknown-linux-${CH_LIBC}"
 CFLAGS=""
-TARGET_CC=""
 if [[ "${BUILD_TARGET}" == "x86_64-unknown-linux-musl" ]]; then
-    TARGET_CC="musl-gcc"
+    # shellcheck disable=SC2034
     CFLAGS="-I /usr/include/x86_64-linux-musl/ -idirafter /usr/include/"
 fi
 
-cargo build --features mshv --all --release --target $BUILD_TARGET
+cargo build --features mshv --all --release --target "$BUILD_TARGET"
 
 export RUST_BACKTRACE=1
 time cargo test $test_features "rate_limiter::$test_filter" -- --test-threads=1 ${test_binary_args[*]}

scripts/run_integration_tests_sgx.sh

@@ -1,8 +1,10 @@
-#!/bin/bash
+#!/usr/bin/env bash
+# shellcheck disable=SC2048,SC2086
 set -x
 
-source $HOME/.cargo/env
-source $(dirname "$0")/test-util.sh
+# shellcheck source=/dev/null
+source "$HOME"/.cargo/env
+source "$(dirname "$0")"/test-util.sh
 
 process_common_args "$@"
 
@@ -14,39 +16,32 @@ fi
 WORKLOADS_DIR="$HOME/workloads"
 mkdir -p "$WORKLOADS_DIR"
 
-FW_URL=$(curl --silent https://api.github.com/repos/cloud-hypervisor/rust-hypervisor-firmware/releases/latest | grep "browser_download_url" | grep -o 'https://.*[^ "]')
-FW="$WORKLOADS_DIR/hypervisor-fw"
-pushd $WORKLOADS_DIR
-rm -f $FW
-time wget --quiet $FW_URL || exit 1
-popd
+download_hypervisor_fw
 
 JAMMY_OS_IMAGE_NAME="jammy-server-cloudimg-amd64-custom-20230119-0.qcow2"
 JAMMY_OS_IMAGE_URL="https://cloud-hypervisor.azureedge.net/$JAMMY_OS_IMAGE_NAME"
 JAMMY_OS_IMAGE="$WORKLOADS_DIR/$JAMMY_OS_IMAGE_NAME"
 if [ ! -f "$JAMMY_OS_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
+    pushd "$WORKLOADS_DIR" || exit
     time wget --quiet $JAMMY_OS_IMAGE_URL || exit 1
-    popd
+    popd || exit
 fi
 
 JAMMY_OS_RAW_IMAGE_NAME="jammy-server-cloudimg-amd64-custom-20230119-0.raw"
 JAMMY_OS_RAW_IMAGE="$WORKLOADS_DIR/$JAMMY_OS_RAW_IMAGE_NAME"
 if [ ! -f "$JAMMY_OS_RAW_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
+    pushd "$WORKLOADS_DIR" || exit
     time qemu-img convert -p -f qcow2 -O raw $JAMMY_OS_IMAGE_NAME $JAMMY_OS_RAW_IMAGE_NAME || exit 1
-    popd
+    popd || exit
 fi
 
-BUILD_TARGET="$(uname -m)-unknown-linux-${CH_LIBC}"
 CFLAGS=""
-TARGET_CC=""
 if [[ "${BUILD_TARGET}" == "x86_64-unknown-linux-musl" ]]; then
-    TARGET_CC="musl-gcc"
+    # shellcheck disable=SC2034
     CFLAGS="-I /usr/include/x86_64-linux-musl/ -idirafter /usr/include/"
 fi
 
-cargo build --features mshv --all --release --target $BUILD_TARGET
+cargo build --features mshv --all --release --target "$BUILD_TARGET"
 
 export RUST_BACKTRACE=1
 

scripts/run_integration_tests_vfio.sh

@@ -1,100 +1,33 @@
-#!/bin/bash
+#!/usr/bin/env bash
+# shellcheck disable=SC2048,SC2086
 set -x
 
-source $HOME/.cargo/env
-source $(dirname "$0")/test-util.sh
+# This set of vfio tests require to be ran on a specific machine with
+# specific hardware (e.g. the "vfio" bera-metal worker equipped with a
+# Nvidia Tesla T4 card). So the provisioning of the running machine is
+# out of the scope of this script, including the custom guest image with
+# Nvidia drivers installed, and properly configured Nvidia Tesla T4 card.
+
+# shellcheck source=/dev/null
+source "$HOME"/.cargo/env
+source "$(dirname "$0")"/test-util.sh
 
 process_common_args "$@"
 
 WORKLOADS_DIR="$HOME/workloads"
-mkdir -p "$WORKLOADS_DIR"
 
-cp scripts/sha1sums-x86_64 $WORKLOADS_DIR
+download_hypervisor_fw
 
-FW_URL=$(curl --silent https://api.github.com/repos/cloud-hypervisor/rust-hypervisor-firmware/releases/latest | grep "browser_download_url" | grep -o 'https://.*[^ "]')
-FW="$WORKLOADS_DIR/hypervisor-fw"
-if [ ! -f "$FW" ]; then
-    pushd $WORKLOADS_DIR
-    time wget --quiet $FW_URL || exit 1
-    popd
-fi
-
-FOCAL_OS_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.qcow2"
-FOCAL_OS_IMAGE_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_IMAGE_NAME"
-FOCAL_OS_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_IMAGE_NAME"
-if [ ! -f "$FOCAL_OS_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
-    time wget --quiet $FOCAL_OS_IMAGE_URL || exit 1
-    popd
-fi
-
-FOCAL_OS_RAW_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.raw"
-FOCAL_OS_RAW_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_RAW_IMAGE_NAME"
-if [ ! -f "$FOCAL_OS_RAW_IMAGE" ]; then
-    pushd $WORKLOADS_DIR
-    time qemu-img convert -p -f qcow2 -O raw $FOCAL_OS_IMAGE_NAME $FOCAL_OS_RAW_IMAGE_NAME || exit 1
-    popd
-fi
-
-pushd $WORKLOADS_DIR
-sha1sum sha1sums-x86_64 --check --ignore-missing
-if [ $? -ne 0 ]; then
-    echo "sha1sum validation of images failed, remove invalid images to fix the issue."
-    exit 1
-fi
-popd
-
-VMLINUX_IMAGE="$WORKLOADS_DIR/vmlinux"
-build_custom_linux
-
-BLK_IMAGE="$WORKLOADS_DIR/blk.img"
-MNT_DIR="mount_image"
-rm -rf $BLK_IMAGE
-pushd $WORKLOADS_DIR
-fallocate -l 16M $BLK_IMAGE
-mkfs.ext4 -j $BLK_IMAGE
-mkdir $MNT_DIR
-sudo mount -t ext4 $BLK_IMAGE $MNT_DIR
-sudo bash -c "echo bar > $MNT_DIR/foo" || exit 1
-sudo umount $BLK_IMAGE
-rm -r $MNT_DIR
-popd
-
-VFIO_DIR="$WORKLOADS_DIR/vfio"
-VFIO_DISK_IMAGE="$WORKLOADS_DIR/vfio.img"
-rm -rf $VFIO_DIR $VFIO_DISK_IMAGE
-mkdir -p $VFIO_DIR
-cp $FOCAL_OS_RAW_IMAGE $VFIO_DIR
-cp $FW $VFIO_DIR
-cp $VMLINUX_IMAGE $VFIO_DIR || exit 1
-
-BUILD_TARGET="$(uname -m)-unknown-linux-${CH_LIBC}"
 CFLAGS=""
-TARGET_CC=""
 if [[ "${BUILD_TARGET}" == "x86_64-unknown-linux-musl" ]]; then
-TARGET_CC="musl-gcc"
-CFLAGS="-I /usr/include/x86_64-linux-musl/ -idirafter /usr/include/"
+    # shellcheck disable=SC2034
+    CFLAGS="-I /usr/include/x86_64-linux-musl/ -idirafter /usr/include/"
 fi
 
-cargo build --features mshv --all --release --target $BUILD_TARGET
-
-# We always copy a fresh version of our binary for our L2 guest.
-cp target/$BUILD_TARGET/release/cloud-hypervisor $VFIO_DIR
-cp target/$BUILD_TARGET/release/ch-remote $VFIO_DIR
-
-# test_vfio rely on hugepages
-HUGEPAGESIZE=`grep Hugepagesize /proc/meminfo | awk '{print $2}'`
-PAGE_NUM=`echo $((12288 * 1024 / $HUGEPAGESIZE))`
-echo $PAGE_NUM | sudo tee /proc/sys/vm/nr_hugepages
-sudo chmod a+rwX /dev/hugepages
+cargo build --features mshv --all --release --target "$BUILD_TARGET"
 
 export RUST_BACKTRACE=1
-time cargo test "vfio::test_vfio" -- ${test_binary_args[*]}
+time cargo test "vfio::test_nvidia" -- --test-threads=1 ${test_binary_args[*]}
 RES=$?
 
-if [ $RES -eq 0 ]; then
-	time cargo test "vfio::test_nvidia" -- --test-threads=1 ${test_binary_args[*]}
-	RES=$?
-fi
-
 exit $RES