.github: Add aarch64 cross build to release

Fixes: #3099

Signed-off-by: Rob Bradford <robert.bradford@intel.com>

.github/workflows/build.yaml

@@ -31,7 +31,7 @@ jobs:
 
       - name: Debug Check (default features)
         run: |
-          git rev-list origin/master..$GITHUB_SHA | xargs -t -I % sh -c 'git checkout %; cargo check --all --target=${{ matrix.target }}'
+          git rev-list origin/main..$GITHUB_SHA | xargs -t -I % sh -c 'git checkout %; cargo check --all --target=${{ matrix.target }}'
           git checkout $GITHUB_SHA
 
       - name: Build (acpi,kvm)
@@ -39,6 +39,15 @@ jobs:
 
       - name: Build (kvm)
         run: cargo rustc --bin cloud-hypervisor --no-default-features --features "kvm"  -- -D warnings
+
+      - name: Build (acpi,mshv)
+        run: cargo rustc --bin cloud-hypervisor --no-default-features --features "acpi,mshv"  -- -D warnings
+
+      - name: Build (mshv)
+        run: cargo rustc --bin cloud-hypervisor --no-default-features --features "mshv"  -- -D warnings
         
       - name: Release Build (default features)
         run: cargo build --all --release --target=${{ matrix.target }}
+
+      - name: Check build did not modify any files
+        run: test -z "$(git status --porcelain)"

.github/workflows/docker-image.yaml

@@ -2,7 +2,7 @@ name: Cloud-Hypervisor's Docker image update
 
 on:
   push:
-    branches: master
+    branches: main
     paths: resources/Dockerfile
 
 jobs:

.github/workflows/quality-aarch64.yaml

@@ -31,9 +31,31 @@ jobs:
             components: rustfmt, clippy
       - name: Formatting (rustfmt)
         run: cargo fmt -- --check
+
       - name: Clippy (kvm)
         uses: actions-rs/cargo@v1
         with:
           use-cross: true
           command: clippy
-          args: --target=${{ matrix.target }} --no-default-features --features "kvm" -- -D warnings
+          args: --target=${{ matrix.target }} --all --no-default-features --features "kvm" -- -D warnings
+
+      - name: Clippy (kvm,acpi)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: true
+          command: clippy
+          args: --target=${{ matrix.target }} --all --no-default-features --features "kvm,acpi" -- -D warnings
+
+      - name: Clippy (all features,kvm)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: true
+          command: clippy
+          args: --target=${{ matrix.target }} --all --no-default-features --features "common,kvm" -- -D warnings
+
+      - name: Clippy (default)
+        uses: actions-rs/cargo@v1
+        with:
+          use-cross: true
+          command: clippy
+          args: --target=${{ matrix.target }} --all -- -D warnings

.github/workflows/quality.yaml

@@ -56,3 +56,6 @@ jobs:
 
       - name: Clippy (integration tests)
         run: cargo clippy --all --all-targets --tests --features "integration_tests" -- -D warnings
+
+      - name: Check build did not modify any files
+        run: test -z "$(git status --porcelain)"

.github/workflows/release.yaml

@@ -25,6 +25,18 @@ jobs:
         run: cargo build --all --release --target=x86_64-unknown-linux-musl
       - name: Strip cloud-hypervisor binaries
         run: strip target/*/release/cloud-hypervisor
+      - name: Install Rust toolchain (aarch64-unknown-linux-musl)
+        uses: actions-rs/toolchain@v1
+        with:
+            toolchain: stable
+            target: aarch64-unknown-linux-musl
+            override: true
+      - name: Static Build (AArch64)
+        uses: actions-rs/cargo@v1
+        with:
+            use-cross: true
+            command: build
+            args: --all --release --target=aarch64-unknown-linux-musl
       - name: Create Release
         id: create_release
         uses: actions/create-release@v1
@@ -65,3 +77,23 @@ jobs:
           asset_path: target/x86_64-unknown-linux-gnu/release/ch-remote
           asset_name: ch-remote
           asset_content_type: application/octet-stream
+      - name: Upload static AArch64 cloud-hypervisor
+        id: upload-release-static-aarch64-cloud-hypervisor
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/aarch64-unknown-linux-musl/release/cloud-hypervisor
+          asset_name: cloud-hypervisor-static-aarch64
+          asset_content_type: application/octet-stream
+      - name: Upload static AArch64 ch-remote
+        id: upload-release-static-aarch64-ch-remote
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: target/aarch64-unknown-linux-musl/release/ch-remote
+          asset_name: ch-remote-static-aarch64
+          asset_content_type: application/octet-stream

CONTRIBUTING.md

@@ -55,7 +55,7 @@ you want to merge your changes to `cloud-hypervisor`:
    into your github organization.
 2. Within your fork, create a branch for your contribution.
 3. [Create a pull request](https://help.github.com/articles/creating-a-pull-request-from-a-fork/)
-   against the master branch of the Cloud Hypervisor repository.
+   against the main branch of the Cloud Hypervisor repository.
 4. Add reviewers to your pull request and then work with your reviewers to address
    any comments and obtain minimum of 2 [maintainers](MAINTAINERS.md) approvals.
    To update your pull request amend existing commits whenever applicable and

Cargo.lock

@@ -11,9 +11,9 @@ dependencies = [
 
 [[package]]
 name = "addr2line"
-version = "0.15.2"
+version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e7a2e47a1fbe209ee101dd6d61285226744c6c8d3c21c8dc878ba6cb9f467f3a"
+checksum = "3e61f2b7f93d2c7d2b08263acaa4a363b3e276806c68af6134c44f523bf1aacd"
 dependencies = [
  "gimli",
 ]
@@ -44,19 +44,22 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.40"
+version = "1.0.43"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28b2cd92db5cbd74e8e5028f7e27dd7aa3090e89e4f2a197cc7c8dfb69c7063b"
+checksum = "28ae2b3dec75a406790005a200b1bd89785afc02517a00ca99ecfe093ee9e6cf"
 
 [[package]]
 name = "api_client"
 version = "0.1.0"
+dependencies = [
+ "vmm-sys-util",
+]
 
 [[package]]
 name = "arc-swap"
-version = "1.3.0"
+version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e906254e445520903e7fc9da4f709886c84ae4bc4ddaf0e093188d66df4dc820"
+checksum = "b5ab7d9e73059c86c36473f459b52adbd99c3554a4fec492caef460806006f00"
 
 [[package]]
 name = "arch"
@@ -65,6 +68,7 @@ dependencies = [
  "acpi_tables",
  "anyhow",
  "byteorder",
+ "fdt",
  "hypervisor",
  "libc",
  "linux-loader",
@@ -76,6 +80,7 @@ dependencies = [
  "vm-fdt",
  "vm-memory",
  "vm-migration",
+ "vmm-sys-util",
 ]
 
 [[package]]
@@ -97,9 +102,9 @@ checksum = "cdb031dd78e28731d87d56cc8ffef4a8f36ca26c38fe2de700543e627f8a464a"
 
 [[package]]
 name = "backtrace"
-version = "0.3.60"
+version = "0.3.61"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b7815ea54e4d821e791162e078acbebfd6d8c8939cd559c9335dceb1c8ca7282"
+checksum = "e7a905d892734eea339e896738c14b9afce22b5318f64b951e70bf3844419b01"
 dependencies = [
  "addr2line",
  "cc",
@@ -121,9 +126,9 @@ dependencies = [
 
 [[package]]
 name = "bitflags"
-version = "1.2.1"
+version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf1de2fe8c75bc145a2f577add951f8134889b4795d47466a54a5c846d691693"
+checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "block_util"
@@ -136,6 +141,7 @@ dependencies = [
  "thiserror",
  "versionize",
  "versionize_derive",
+ "vhdx",
  "virtio-bindings",
  "vm-memory",
  "vm-virtio",
@@ -150,9 +156,9 @@ checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
 [[package]]
 name = "cc"
-version = "1.0.68"
+version = "1.0.70"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4a72c244c1ff497a746a7e1fb3d14bd08420ecda70c8f25c7112f2781652d787"
+checksum = "d26a6ce4b6a484fa3edb70f7efa6fc430fd2b87285fe8b84304fd0936faa0dc0"
 
 [[package]]
 name = "cfg-if"
@@ -184,7 +190,7 @@ dependencies = [
 
 [[package]]
 name = "cloud-hypervisor"
-version = "16.0.0"
+version = "18.0.0"
 dependencies = [
  "anyhow",
  "api_client",
@@ -199,7 +205,7 @@ dependencies = [
  "log",
  "net_util",
  "option_parser",
- "seccomp",
+ "seccompiler",
  "serde_json",
  "signal-hook",
  "test_infra",
@@ -219,6 +225,15 @@ dependencies = [
  "bitflags",
 ]
 
+[[package]]
+name = "crc32c"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "210cdf933e6a81212bfabf90cd8762f471b5922e5f6b709547673ad8e04b9448"
+dependencies = [
+ "rustc_version",
+]
+
 [[package]]
 name = "crc64"
 version = "1.0.0"
@@ -277,9 +292,9 @@ dependencies = [
 
 [[package]]
 name = "env_logger"
-version = "0.8.3"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "17392a012ea30ef05a610aa97dfb49496e71c9f676b27879922ea5bdf60d9d3f"
+checksum = "0b2cf0344971ee6c64c31be0d530793fba457d322dfec2810c453d0ef228f9c3"
 dependencies = [
  "atty",
  "humantime",
@@ -330,6 +345,12 @@ dependencies = [
  "synstructure",
 ]
 
+[[package]]
+name = "fdt"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b643857cf70949306b81d7e92cb9d47add673868edac9863c4a49c42feaf3f1e"
+
 [[package]]
 name = "getrandom"
 version = "0.2.3"
@@ -343,9 +364,9 @@ dependencies = [
 
 [[package]]
 name = "gimli"
-version = "0.24.0"
+version = "0.25.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0e4075386626662786ddb0ec9081e7c7eeb1ba31951f447ca780ef9f5d568189"
+checksum = "f0a01e0497841a3b2db4f8afa483cce65f7e96a3498bd6c541734792aeac8fe7"
 
 [[package]]
 name = "glob"
@@ -355,9 +376,9 @@ checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
 
 [[package]]
 name = "hermit-abi"
-version = "0.1.18"
+version = "0.1.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "322f4de77956e22ed0e5032c359a0f1273f1f7f0d79bfa3b8ffbc730d7fbcc5c"
+checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
 dependencies = [
  "libc",
 ]
@@ -392,9 +413,9 @@ dependencies = [
 
 [[package]]
 name = "iced-x86"
-version = "1.11.3"
+version = "1.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6d907dfc273d9ed0da940e8145ceb77759056a1fb2110b44b83d1b203cddb906"
+checksum = "7383772b06135cede839b7270023b46403656a9148024886e721e82639d3f90e"
 dependencies = [
  "lazy_static",
  "static_assertions",
@@ -402,9 +423,9 @@ dependencies = [
 
 [[package]]
 name = "io-uring"
-version = "0.5.1"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb82832e05cc4ca298f198a8db108837b4f7b7b1248e3cba8e48f151aece80cf"
+checksum = "8d75829ed9377bab6c90039fe47b9d84caceb4b5063266142e21bcce6550cda8"
 dependencies = [
  "bitflags",
  "libc",
@@ -421,9 +442,9 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dd25036021b0de88a0aff6b850051563c6516d0bf53f8638938edbb9de732736"
+checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
 
 [[package]]
 name = "kvm-bindings"
@@ -454,9 +475,9 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
-version = "0.2.96"
+version = "0.2.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5600b4e6efc5421841a2138a6b082e07fe12f9aaa12783d50e5d13325b26b4fc"
+checksum = "3cb00336871be5ed2c8ed44b60ae9959dc5b9f08539422ed43f09e34ecaeba21"
 
 [[package]]
 name = "libssh2-sys"
@@ -513,14 +534,14 @@ dependencies = [
 
 [[package]]
 name = "memchr"
-version = "2.4.0"
+version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b16bd47d9e329435e309c58469fe0791c2d0d1ba96ec0954152a5ae2b04387dc"
+checksum = "308cc39be01b73d0d18f82a0e7b2a3df85245f84af96fdddc5d202d27e47b86a"
 
 [[package]]
 name = "micro_http"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#9b605a8b61df602cda62076d30d9f70307ea336f"
+source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#36e59a083e76a2449e0f58e4283d201bc72fdf13"
 dependencies = [
  "libc",
  "vmm-sys-util",
@@ -539,7 +560,7 @@ dependencies = [
 [[package]]
 name = "mshv-bindings"
 version = "0.1.0"
-source = "git+https://github.com/cloud-hypervisor/mshv?branch=master#1024e9a821d33079452c20477b6ecb976ff795ad"
+source = "git+https://github.com/rust-vmm/mshv?branch=main#0d6e4e82b9b575798de333e362129515e81049cb"
 dependencies = [
  "libc",
  "serde",
@@ -551,7 +572,7 @@ dependencies = [
 [[package]]
 name = "mshv-ioctls"
 version = "0.1.0"
-source = "git+https://github.com/cloud-hypervisor/mshv?branch=master#1024e9a821d33079452c20477b6ecb976ff795ad"
+source = "git+https://github.com/rust-vmm/mshv?branch=main#0d6e4e82b9b575798de333e362129515e81049cb"
 dependencies = [
  "libc",
  "mshv-bindings",
@@ -588,18 +609,18 @@ dependencies = [
 
 [[package]]
 name = "object"
-version = "0.25.2"
+version = "0.26.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8bc1d42047cf336f0f939c99e97183cf31551bf0f2865a2ec9c8d91fd4ffb5e"
+checksum = "39f37e50073ccad23b6d09bcb5b263f4e76d3bb6038e4a3c08e52162ffa8abc2"
 dependencies = [
  "memchr",
 ]
 
 [[package]]
 name = "openssl-sys"
-version = "0.9.63"
+version = "0.9.66"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6b0d6fb7d80f877617dfcb014e605e2b5ab2fb0afdf27935219bb6bd984cb98"
+checksum = "1996d2d305e561b70d1ee0c53f1542833f4e1ac6ce9a6708b6ff2738ca67dc82"
 dependencies = [
  "autocfg",
  "cc",
@@ -645,10 +666,12 @@ dependencies = [
  "hypervisor",
  "libc",
  "log",
+ "thiserror",
  "versionize",
  "versionize_derive",
  "vfio-bindings",
  "vfio-ioctls",
+ "vfio_user",
  "vm-allocator",
  "vm-device",
  "vm-memory",
@@ -752,9 +775,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.27"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f0d8caf72986c1a598726adc988bb5984792ef84f5ee5aa50209145ee8077038"
+checksum = "b9f5105d4fdaab20335ca9565e106a5d9b82b6219b5ba735731124ac6711d23d"
 dependencies = [
  "unicode-xid",
 ]
@@ -796,9 +819,9 @@ checksum = "41cc0f7e4d5d4544e8861606a285bb08d3e70712ccc7d2b84d7c0ccfaf4b05ce"
 
 [[package]]
 name = "redox_syscall"
-version = "0.2.8"
+version = "0.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "742739e41cd49414de871ea5e549afb7e2a3ac77b589bcbebe8c82fab37147fc"
+checksum = "8383f39639269cde97d255a32bdb68c047337295414940c68bdd30c2e13203ff"
 dependencies = [
  "bitflags",
 ]
@@ -810,7 +833,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "528532f3d801c87aec9def2add9ca802fe569e44a544afe633765267840abe64"
 dependencies = [
  "getrandom",
- "redox_syscall 0.2.8",
+ "redox_syscall 0.2.10",
 ]
 
 [[package]]
@@ -843,9 +866,18 @@ dependencies = [
 
 [[package]]
 name = "rustc-demangle"
-version = "0.1.19"
+version = "0.1.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "410f7acf3cb3a44527c5d9546bad4bf4e6c460915d5f9f2fc524498bfe8f70ce"
+checksum = "7ef03e0a2b150c7a90d01faf6254c9c48a41e95fb2a8c2ac1c6f0d2b9aefc342"
+
+[[package]]
+name = "rustc_version"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "138e3e0acb6c9fb258b19b67cb8abd63c00679d2851805ea151465464fe9030a"
+dependencies = [
+ "semver",
+]
 
 [[package]]
 name = "ryu"
@@ -860,24 +892,39 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
 
 [[package]]
-name = "seccomp"
+name = "seccompiler"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/firecracker?tag=v0.24.4#8f44986a0e956a77f2b2324c12f73bec16130c82"
+source = "git+https://github.com/rust-vmm/seccompiler#da5788d52f1ae8886d8ed4624199b7e9fa64ac04"
 dependencies = [
  "libc",
 ]
 
 [[package]]
-name = "serde"
-version = "1.0.126"
+name = "semver"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec7505abeacaec74ae4778d9d9328fe5a5d04253220a85c4ee022239fc996d03"
+checksum = "1d7eb9ef2c18661902cc47e535f9bc51b78acd254da71d375c2f6720d9a40403"
+dependencies = [
+ "semver-parser",
+]
+
+[[package]]
+name = "semver-parser"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
+
+[[package]]
+name = "serde"
+version = "1.0.130"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f12d06de37cf59146fbdecab66aa99f9fe4f78722e3607577a5375d66bd0c913"
 
 [[package]]
 name = "serde_derive"
-version = "1.0.126"
+version = "1.0.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "963a7dbc9895aeac7ac90e74f34a5d5261828f79df35cbed41e10189d3804d43"
+checksum = "d7bc1a1ab1961464eae040d96713baa5a724a8152c1222492465b54322ec508b"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -886,9 +933,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.64"
+version = "1.0.67"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "799e97dc9fdae36a5c8b8f2cae9ce2ee9fdce2058c57a93e6099d919fd982f79"
+checksum = "a7f9e390c27c3c0ce8bc5d725f6e4d30a29d26659494aa4b17535f7522c5c950"
 dependencies = [
  "itoa",
  "ryu",
@@ -897,9 +944,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook"
-version = "0.3.9"
+version = "0.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "470c5a6397076fae0094aaf06a08e6ba6f37acb77d3b1b91ea92b4d6c8650c39"
+checksum = "9c98891d737e271a2954825ef19e46bd16bdb98e2746f2eec4f7a4ef7946efd1"
 dependencies = [
  "libc",
  "signal-hook-registry",
@@ -946,9 +993,9 @@ checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
 
 [[package]]
 name = "syn"
-version = "1.0.73"
+version = "1.0.76"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f71489ff30030d2ae598524f61326b902466f72a0fb1a8564c001cc63425bcc7"
+checksum = "c6f107db402c2c2055242dbf4d2af0e69197202e9faacbef9571bbe47f5a1b84"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -957,9 +1004,9 @@ dependencies = [
 
 [[package]]
 name = "synstructure"
-version = "0.12.4"
+version = "0.12.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b834f2d66f734cb897113e34aaff2f1ab4719ca946f9a7358dba8f8064148701"
+checksum = "474aaa926faa1603c40b7885a9eaea29b444d1cb2850cb7c0e37bb1a4182f4fa"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1010,18 +1057,18 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "1.0.25"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa6f76457f59514c7eeb4e59d891395fab0b2fd1d40723ae737d64153392e9c6"
+checksum = "602eca064b2d83369e2b2f34b09c70b605402801927c65c11071ac911d299b88"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.25"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a36768c0fbf1bb15eca10defa29526bda730a2376c2ab4393ccfa16fb1a318d"
+checksum = "bad553cc2c78e8de258400763a647e80e6d1b31ee237275d756f6836d204494c"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1045,12 +1092,15 @@ name = "uuid"
 version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bc5cf98d8186244414c848017f0e2676b3fcb46807f6668a97dfe67359a3c4b7"
+dependencies = [
+ "getrandom",
+]
 
 [[package]]
 name = "vcpkg"
-version = "0.2.13"
+version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "025ce40a007e1907e58d5bc1a594def78e5573bb0b1160bc389634e8f12e4faa"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
 
 [[package]]
 name = "vec_map"
@@ -1097,24 +1147,58 @@ dependencies = [
 [[package]]
 name = "vfio-ioctls"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=master#0f7eb6f855b80d60a7e09ac6df43b46ba69f9e9e"
+source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=main#a8ee64b978ccd000df88732814d626651a091891"
 dependencies = [
  "byteorder",
  "kvm-bindings",
  "kvm-ioctls",
  "log",
+ "mshv-bindings",
+ "mshv-ioctls",
  "vfio-bindings",
  "vm-memory",
  "vmm-sys-util",
 ]
 
+[[package]]
+name = "vfio_user"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "libc",
+ "log",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "thiserror",
+ "vfio-bindings",
+ "vm-memory",
+ "vmm-sys-util",
+]
+
+[[package]]
+name = "vhdx"
+version = "0.1.0"
+dependencies = [
+ "byteorder",
+ "crc32c",
+ "libc",
+ "log",
+ "remain",
+ "thiserror",
+ "uuid",
+ "vmm-sys-util",
+]
+
 [[package]]
 name = "vhost"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vhost?branch=master#30ba3e7bbe9e0542cf480f44bc6845a8dbd2a6ba"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a6b90237e10f1a61b35fba73885c3567e1a5a8c40d44daae335f7710210a7dc"
 dependencies = [
  "bitflags",
  "libc",
+ "vm-memory",
  "vmm-sys-util",
 ]
 
@@ -1138,6 +1222,7 @@ version = "0.1.0"
 dependencies = [
  "block_util",
  "clap",
+ "env_logger",
  "epoll",
  "libc",
  "log",
@@ -1155,6 +1240,7 @@ name = "vhost_user_net"
 version = "0.1.0"
 dependencies = [
  "clap",
+ "env_logger",
  "epoll",
  "libc",
  "log",
@@ -1190,7 +1276,7 @@ dependencies = [
  "net_util",
  "pci",
  "rate_limiter",
- "seccomp",
+ "seccompiler",
  "serde",
  "serde_derive",
  "serde_json",
@@ -1232,12 +1318,13 @@ dependencies = [
 [[package]]
 name = "vm-fdt"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vm-fdt?branch=master#2e4ebdeb27be5b450b51b79fdeeeee3750d42182"
+source = "git+https://github.com/rust-vmm/vm-fdt?branch=main#06cbff3a0248ec654467a87b1be7c0bcf78a41a8"
 
 [[package]]
 name = "vm-memory"
-version = "0.5.0"
-source = "git+https://github.com/rust-vmm/vm-memory?rev=5bd7138758183a73ac0da27ce40c004d95f1a7e9#5bd7138758183a73ac0da27ce40c004d95f1a7e9"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0a8ebcb86ca457f9d6e14cf97009f679952eba42f0113de5db596e514cd0e43b"
 dependencies = [
  "arc-swap",
  "libc",
@@ -1292,7 +1379,7 @@ dependencies = [
  "option_parser",
  "pci",
  "qcow",
- "seccomp",
+ "seccompiler",
  "serde",
  "serde_derive",
  "serde_json",
@@ -1302,6 +1389,7 @@ dependencies = [
  "versionize",
  "versionize_derive",
  "vfio-ioctls",
+ "vhdx",
  "virtio-devices",
  "vm-allocator",
  "vm-device",
@@ -1371,9 +1459,9 @@ checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
 [[package]]
 name = "zerocopy"
-version = "0.3.0"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6580539ad917b7c026220c4b3f2c08d52ce54d6ce0dc491e66002e35388fab46"
+checksum = "5e59ec1d2457bd6c0dd89b50e7d9d6b0b647809bf3f0a59ac85557046950b7b2"
 dependencies = [
  "byteorder",
  "zerocopy-derive",
@@ -1381,9 +1469,9 @@ dependencies = [
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.2.0"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d498dbd1fd7beb83c86709ae1c33ca50942889473473d287d56ce4770a18edfb"
+checksum = "0af017aca1fa6181f5dd7a802456fe6f7666ecdcc18d0910431f0fc89d474e51"
 dependencies = [
  "proc-macro2",
  "syn",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cloud-hypervisor"
-version = "16.0.0"
+version = "18.0.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 default-run = "cloud-hypervisor"
@@ -13,22 +13,22 @@ homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
 lto = true
 
 [dependencies]
-anyhow = "1.0.40"
+anyhow = "1.0.43"
 api_client = { path = "api_client" }
 clap = { version = "2.33.3", features = ["wrap_help"] }
 epoll = "4.3.1"
 event_monitor = { path = "event_monitor" }
 hypervisor = { path = "hypervisor" }
-libc = "0.2.96"
+libc = "0.2.101"
 log = { version = "0.4.14", features = ["std"] }
 option_parser = { path = "option_parser" }
-seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.24.4" }
-serde_json = "1.0.64"
-signal-hook = "0.3.9"
-thiserror = "1.0.25"
+seccompiler = { git = "https://github.com/rust-vmm/seccompiler"}
+serde_json = "1.0.67"
+signal-hook = "0.3.10"
+thiserror = "1.0.29"
 vmm = { path = "vmm" }
 vmm-sys-util = "0.8.0"
-vm-memory = "0.5.0"
+vm-memory = "0.6.0"
 
 [build-dependencies]
 clap = { version = "2.33.3", features = ["wrap_help"] }
@@ -37,14 +37,13 @@ clap = { version = "2.33.3", features = ["wrap_help"] }
 [patch.crates-io]
 kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"] }
 versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
-vm-memory = { git = "https://github.com/rust-vmm/vm-memory", rev = "5bd7138758183a73ac0da27ce40c004d95f1a7e9"}
 
 [dev-dependencies]
 credibility = "0.1.3"
 dirs = "3.0.2"
 lazy_static= "1.4.0"
 net_util = { path = "net_util" }
-serde_json = "1.0.64"
+serde_json = "1.0.67"
 test_infra = { path = "test_infra" }
 wait-timeout = "0.2.0"
 
@@ -78,6 +77,8 @@ members = [
     "pci",
     "qcow",
     "rate_limiter",
+    "vfio_user",
+    "vhdx",
     "vhost_user_backend",
     "vhost_user_block",
     "vhost_user_net",

Jenkinsfile

@@ -2,7 +2,7 @@ pipeline{
 	agent none
 	stages {
 		stage ('Early checks') {
-			agent { node { label 'master' } }
+			agent { node { label 'built-in' } }
 			stages {
 				stage ('Check for RFC/WIP builds') {
 					when {
@@ -14,7 +14,7 @@ pipeline{
 					}
 				}
 				stage ('Cancel older builds') {
-					when { not { branch 'master' } }
+					when { not { branch 'main' } }
 					steps {
 						cancelPreviousBuilds()
 					}
@@ -24,7 +24,7 @@ pipeline{
 		stage ('Build') {
             		parallel {
 				stage ('Worker build') {
-					agent { node { label 'groovy' } }
+					agent { node { label 'hirsute' } }
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -83,7 +83,7 @@ pipeline{
 					}
 				}
 				stage ('Worker build (musl)') {
-					agent { node { label 'groovy' } }
+					agent { node { label 'hirsute' } }
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -110,7 +110,7 @@ pipeline{
 					agent { node { label 'bionic-sgx' } }
 					when {
 						beforeAgent true
-						branch 'master'
+						branch 'main'
 					}
 					stages {
 						stage ('Checkout') {
@@ -146,7 +146,7 @@ pipeline{
 					agent { node { label 'bionic-vfio' } }
 					when {
 						beforeAgent true
-						branch 'master'
+						branch 'main'
 					}
 					stages {
 						stage ('Checkout') {
@@ -179,7 +179,10 @@ pipeline{
 					}
 				}
 				stage ('Worker build - Windows guest') {
-					agent { node { label 'groovy' } }
+					agent { node { label 'hirsute' } }
+					environment {
+        					AZURE_CONNECTION_STRING = credentials('46b4e7d6-315f-4cc1-8333-b58780863b9b')
+					}
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -188,17 +191,10 @@ pipeline{
 						}
 						stage ('Download assets') {
 							steps {
+								sh "sudo apt install -y azure-cli"
 								sh "mkdir ${env.HOME}/workloads"
-								azureDownload(storageCredentialId: 'ch-image-store',
-											  containerName: 'private-images',
-											  includeFilesPattern: 'OVMF-4b47d0c6c8.fd',
-											  downloadType: 'container',
-											  downloadDirLoc: "${env.HOME}/workloads")
-								azureDownload(storageCredentialId: 'ch-image-store',
-											  containerName: 'private-images',
-											  includeFilesPattern: 'windows-server-2019.raw',
-											  downloadType: 'container',
-											  downloadDirLoc: "${env.HOME}/workloads")
+								sh 'az storage blob download --container-name private-images --file "$HOME/workloads/OVMF-4b47d0c6c8.fd" --name OVMF-4b47d0c6c8.fd --connection-string "$AZURE_CONNECTION_STRING"'
+								sh 'az storage blob download --container-name private-images --file "$HOME/workloads/windows-server-2019.raw" --name windows-server-2019.raw --connection-string "$AZURE_CONNECTION_STRING"'
 							}
 						}
 						stage ('Run Windows guest integration tests') {
@@ -219,21 +215,47 @@ pipeline{
 						}
 					}
 				}
+				stage ('Worker build - Live Migration') {
+					agent { node { label 'hirsute-small' } }
+					stages {
+						stage ('Checkout') {
+							steps {
+								checkout scm
+							}
+						}
+						stage ('Run live-migration integration tests') {
+							options {
+								timeout(time: 1, unit: 'HOURS')
+							}
+							steps {
+								sh "scripts/dev_cli.sh tests --integration-live-migration"
+							}
+						}
+						stage ('Run live-migration integration tests for musl') {
+							options {
+								timeout(time: 1, unit: 'HOURS')
+							}
+							steps {
+								sh "scripts/dev_cli.sh tests --integration-live-migration --libc musl"
+							}
+						}
+					}
+				}
 			}
 		}
 	}
 	post {
 		regression {
 			script {
-				if (env.BRANCH_NAME == 'master') {
-					slackSend (color: '#ff0000', message: '"master" branch build is now failing')
+				if (env.BRANCH_NAME == 'main') {
+					slackSend (color: '#ff0000', message: '"main" branch build is now failing')
 				}
 			}
 		}
 		fixed {
 			script {
-				if (env.BRANCH_NAME == 'master') {
-					slackSend (color: '#00ff00', message: '"master" branch build is now fixed')
+				if (env.BRANCH_NAME == 'main') {
+					slackSend (color: '#00ff00', message: '"main" branch build is now fixed')
 				}
 			}
 		}

MAINTAINERS.md

@@ -1,6 +1,7 @@
 # Maintainers
 
-- Sebastien Boeuf <sebastien.boeuf@intel.com> @sboeuf
-- Robert Bradford <robert.bradford@intel.com> @rbradford
-- Samuel Ortiz <sameo@linux.intel.com> @sameo
-- Chao P Peng <chao.p.peng@linux.intel.com> @chao-p
+- Sebastien Boeuf - @sboeuf
+- Robert Bradford - @rbradford
+- Samuel Ortiz - @sameo
+- Wei Liu - @liuw
+- Michael Zhao - @michael2012z

README.md

@@ -1,11 +1,10 @@
-[![Build Status](https://travis-ci.com/cloud-hypervisor/cloud-hypervisor.svg?branch=master)](https://travis-ci.com/cloud-hypervisor/cloud-hypervisor)
-
 - [1. What is Cloud Hypervisor?](#1-what-is-cloud-hypervisor)
   - [Objectives](#objectives)
     - [High Level](#high-level)
     - [Architectures](#architectures)
     - [Guest OS](#guest-os)
 - [2. Getting Started](#2-getting-started)
+  - [Install prerequisites](#install-prerequisites)
   - [Clone and build](#clone-and-build)
     - [Containerized builds and tests](#containerized-builds-and-tests)
   - [Run](#run)
@@ -23,6 +22,7 @@
 - [5. Community](#5-community)
   - [Contribute](#contribute)
   - [Join us](#join-us)
+  - [Security issues](#security-issues)
 
 # 1. What is Cloud Hypervisor?
 
@@ -149,7 +149,7 @@ We need to get the latest `rust-hypervisor-firmware` release and also a working
 $ pushd $CLOUDH
 $ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-amd64.img
 $ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-amd64.img focal-server-cloudimg-amd64.raw
-$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.3.1/hypervisor-fw
+$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.3.2/hypervisor-fw
 $ popd
 ```
 
@@ -180,7 +180,7 @@ To build the kernel:
 
 # Clone the Cloud Hypervisor Linux branch
 $ pushd $CLOUDH
-$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-5.12 linux-cloud-hypervisor
+$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-5.14 linux-cloud-hypervisor
 $ pushd linux-cloud-hypervisor
 
 # Use the cloud-hypervisor kernel config to build your kernel

acpi_tables/Cargo.toml

@@ -5,4 +5,4 @@ authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 
 [dependencies]
-vm-memory = "0.5.0"
+vm-memory = "0.6.0"

acpi_tables/src/rsdp.rs

@@ -36,7 +36,7 @@ impl Rsdp {
         };
 
         rsdp.checksum = super::generate_checksum(&rsdp.as_slice()[0..19]);
-        rsdp.extended_checksum = super::generate_checksum(&rsdp.as_slice());
+        rsdp.extended_checksum = super::generate_checksum(rsdp.as_slice());
         rsdp
     }
 

acpi_tables/src/sdt.rs

@@ -75,7 +75,7 @@ impl Sdt {
     }
 
     pub fn as_slice(&self) -> &[u8] {
-        &self.data.as_slice()
+        self.data.as_slice()
     }
 
     pub fn append<T>(&mut self, value: T) {

api_client/Cargo.toml

@@ -3,3 +3,6 @@ name = "api_client"
 version = "0.1.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
+
+[dependencies]
+vmm-sys-util = "0.8.0"

api_client/src/lib.rs

@@ -5,10 +5,13 @@
 
 use std::fmt;
 use std::io::{Read, Write};
+use std::os::unix::io::RawFd;
+use vmm_sys_util::sock_ctrl_msg::ScmSocket;
 
 #[derive(Debug)]
 pub enum Error {
     Socket(std::io::Error),
+    SocketSendFds(vmm_sys_util::errno::Error),
     StatusCodeParsing(std::num::ParseIntError),
     MissingProtocol,
     ContentLengthParsing(std::num::ParseIntError),
@@ -20,6 +23,7 @@ impl fmt::Display for Error {
         use Error::*;
         match self {
             Socket(e) => write!(f, "Error writing to or reading from HTTP socket: {}", e),
+            SocketSendFds(e) => write!(f, "Error writing to or reading from HTTP socket: {}", e),
             StatusCodeParsing(e) => write!(f, "Error parsing HTTP status code: {}", e),
             MissingProtocol => write!(f, "HTTP output is missing protocol statement"),
             ContentLengthParsing(e) => write!(f, "Error parsing HTTP Content-Length field: {}", e),
@@ -133,21 +137,23 @@ fn parse_http_response(socket: &mut dyn Read) -> Result<Option<String>, Error> {
     }
 }
 
-pub fn simple_api_command<T: Read + Write>(
+pub fn simple_api_command_with_fds<T: Read + Write + ScmSocket>(
     socket: &mut T,
     method: &str,
     c: &str,
     request_body: Option<&str>,
+    request_fds: Vec<RawFd>,
 ) -> Result<(), Error> {
     socket
-        .write_all(
-            format!(
+        .send_with_fds(
+            &[format!(
                 "{} /api/v1/vm.{} HTTP/1.1\r\nHost: localhost\r\nAccept: */*\r\n",
                 method, c
             )
-            .as_bytes(),
+            .as_bytes()],
+            &request_fds,
         )
-        .map_err(Error::Socket)?;
+        .map_err(Error::SocketSendFds)?;
 
     if let Some(request_body) = request_body {
         socket
@@ -170,3 +176,12 @@ pub fn simple_api_command<T: Read + Write>(
     }
     Ok(())
 }
+
+pub fn simple_api_command<T: Read + Write + ScmSocket>(
+    socket: &mut T,
+    method: &str,
+    c: &str,
+    request_body: Option<&str>,
+) -> Result<(), Error> {
+    simple_api_command_with_fds(socket, method, c, request_body, Vec::new())
+}

arch/Cargo.toml

@@ -11,17 +11,20 @@ tdx = []
 
 [dependencies]
 acpi_tables = { path = "../acpi_tables", optional = true }
-anyhow = "1.0"
+anyhow = "1.0.43"
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.96"
+libc = "0.2.101"
 linux-loader = { version = "0.3.0", features = ["elf", "bzimage", "pe"] }
 log = "0.4.14"
-serde = {version = ">=1.0.27", features = ["rc"] }
-thiserror = "1.0"
+serde = { version = "1.0.130", features = ["rc"] }
+thiserror = "1.0.29"
 versionize = "0.1.6"
 versionize_derive = "0.1.4"
-vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "master" }
-vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-bitmap"] }
+vm-memory = { version = "0.6.0", features = ["backend-mmap", "backend-bitmap"] }
 vm-migration = { path = "../vm-migration" }
+vmm-sys-util = { version = "0.8.0", features = ["with-serde"] }
 
+[target.'cfg(target_arch = "aarch64")'.dependencies]
+fdt_parser = { version = "0.1.3", package = 'fdt'}
+vm-fdt = { git = "https://github.com/rust-vmm/vm-fdt", branch = "main" }

arch/src/aarch64/fdt.rs

@@ -6,10 +6,14 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the THIRD-PARTY file.
 
+use crate::NumaNodes;
+use byteorder::{BigEndian, ByteOrder};
+use std::cmp;
 use std::collections::HashMap;
 use std::ffi::CStr;
 use std::fmt::Debug;
 use std::result;
+use std::str;
 
 use super::super::DeviceType;
 use super::super::GuestMemoryMmap;
@@ -21,7 +25,7 @@ use super::layout::{
     PCI_HIGH_BASE, PCI_MMCONFIG_SIZE, PCI_MMCONFIG_START,
 };
 use vm_fdt::{FdtWriter, FdtWriterResult};
-use vm_memory::{Address, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
+use vm_memory::{Address, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryRegion};
 
 // This is a value for uniquely identifying the FDT node declaring the interrupt controller.
 const GIC_PHANDLE: u32 = 1;
@@ -31,6 +35,9 @@ const MSI_PHANDLE: u32 = 2;
 const CLOCK_PHANDLE: u32 = 3;
 // This is a value for uniquely identifying the FDT node containing the gpio controller.
 const GPIO_PHANDLE: u32 = 4;
+// This is a value for uniquely identifying the FDT node containing the first vCPU.
+// The last number of vCPU phandle depends on the number of vCPUs.
+const FIRST_VCPU_PHANDLE: u32 = 5;
 
 // Read the documentation specified when appending the root node to the FDT.
 const ADDRESS_CELLS: u32 = 0x2;
@@ -69,17 +76,20 @@ pub enum Error {
 type Result<T> = result::Result<T, Error>;
 
 /// Creates the flattened device tree for this aarch64 VM.
+#[allow(clippy::too_many_arguments)]
 pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
     guest_mem: &GuestMemoryMmap,
     cmdline: &CStr,
     vcpu_mpidr: Vec<u64>,
+    vcpu_topology: Option<(u8, u8, u8)>,
     device_info: &HashMap<(DeviceType, String), T, S>,
     gic_device: &dyn GicDevice,
     initrd: &Option<InitramfsConfig>,
     pci_space_address: &(u64, u64),
+    numa_nodes: &NumaNodes,
 ) -> FdtWriterResult<Vec<u8>> {
     // Allocate stuff necessary for the holding the blob.
-    let mut fdt = FdtWriter::new(&[]).unwrap();
+    let mut fdt = FdtWriter::new().unwrap();
 
     // For an explanation why these nodes were introduced in the blob take a look at
     // https://github.com/torvalds/linux/blob/master/Documentation/devicetree/booting-without-of.txt#L845
@@ -95,8 +105,8 @@ pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHash
     // This is not mandatory but we use it to point the root node to the node
     // containing description of the interrupt controller for this VM.
     fdt.property_u32("interrupt-parent", GIC_PHANDLE)?;
-    create_cpu_nodes(&mut fdt, &vcpu_mpidr)?;
-    create_memory_node(&mut fdt, guest_mem)?;
+    create_cpu_nodes(&mut fdt, &vcpu_mpidr, vcpu_topology, numa_nodes)?;
+    create_memory_node(&mut fdt, guest_mem, numa_nodes)?;
     create_chosen_node(&mut fdt, cmdline.to_str().unwrap(), initrd)?;
     create_gic_node(&mut fdt, gic_device)?;
     create_timer_node(&mut fdt)?;
@@ -104,6 +114,9 @@ pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHash
     create_psci_node(&mut fdt)?;
     create_devices_node(&mut fdt, device_info)?;
     create_pci_nodes(&mut fdt, pci_space_address.0, pci_space_address.1)?;
+    if numa_nodes.len() > 1 {
+        create_distance_map_node(&mut fdt, numa_nodes)?;
+    }
 
     // End Header node.
     fdt.end_node(root_node)?;
@@ -123,14 +136,23 @@ pub fn write_fdt_to_memory(fdt_final: Vec<u8>, guest_mem: &GuestMemoryMmap) -> R
 }
 
 // Following are the auxiliary function for creating the different nodes that we append to our FDT.
-fn create_cpu_nodes(fdt: &mut FdtWriter, vcpu_mpidr: &[u64]) -> FdtWriterResult<()> {
+fn create_cpu_nodes(
+    fdt: &mut FdtWriter,
+    vcpu_mpidr: &[u64],
+    vcpu_topology: Option<(u8, u8, u8)>,
+    numa_nodes: &NumaNodes,
+) -> FdtWriterResult<()> {
     // See https://github.com/torvalds/linux/blob/master/Documentation/devicetree/bindings/arm/cpus.yaml.
     let cpus_node = fdt.begin_node("cpus")?;
     fdt.property_u32("#address-cells", 0x1)?;
     fdt.property_u32("#size-cells", 0x0)?;
-    let num_cpus = vcpu_mpidr.len();
 
-    for cpu_id in 0..num_cpus {
+    let num_cpus = vcpu_mpidr.len();
+    let threads_per_core = vcpu_topology.unwrap_or_default().0 as u8;
+    let cores_per_package = vcpu_topology.unwrap_or_default().1 as u8;
+    let packages = vcpu_topology.unwrap_or_default().2 as u8;
+
+    for (cpu_id, mpidr) in vcpu_mpidr.iter().enumerate().take(num_cpus) {
         let cpu_name = format!("cpu@{:x}", cpu_id);
         let cpu_node = fdt.begin_node(&cpu_name)?;
         fdt.property_string("device_type", "cpu")?;
@@ -139,23 +161,132 @@ fn create_cpu_nodes(fdt: &mut FdtWriter, vcpu_mpidr: &[u64]) -> FdtWriterResult<
             // This is required on armv8 64-bit. See aforementioned documentation.
             fdt.property_string("enable-method", "psci")?;
         }
-        fdt.property_u32("reg", cpu_id as u32)?;
+        // Set the field to first 24 bits of the MPIDR - Multiprocessor Affinity Register.
+        // See http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ddi0488c/BABHBJCI.html.
+        fdt.property_u32("reg", (mpidr & 0x7FFFFF) as u32)?;
+        fdt.property_u32("phandle", cpu_id as u32 + FIRST_VCPU_PHANDLE)?;
+
+        // Add `numa-node-id` property if there is any numa config.
+        if numa_nodes.len() > 1 {
+            for numa_node_idx in 0..numa_nodes.len() {
+                let numa_node = numa_nodes.get(&(numa_node_idx as u32));
+                if numa_node.unwrap().cpus.contains(&(cpu_id as u8)) {
+                    fdt.property_u32("numa-node-id", numa_node_idx as u32)?;
+                }
+            }
+        }
+
         fdt.end_node(cpu_node)?;
     }
+
+    // If there is a valid cpu topology config, create the cpu-map node.
+    if (threads_per_core > 0)
+        && (cores_per_package > 0)
+        && (packages > 0)
+        && (num_cpus as u8 == threads_per_core * cores_per_package * packages)
+    {
+        let cpu_map_node = fdt.begin_node("cpu-map")?;
+        // Create mappings between CPU index and cluster,core, and thread.
+        let mut cluster_core_thread_to_cpuidx = HashMap::new();
+        for cpu_idx in 0..num_cpus as u8 {
+            if threads_per_core > 1 {
+                cluster_core_thread_to_cpuidx.insert(
+                    (
+                        cpu_idx / (cores_per_package * threads_per_core),
+                        (cpu_idx / threads_per_core) % cores_per_package,
+                        cpu_idx % threads_per_core,
+                    ),
+                    cpu_idx,
+                );
+            } else {
+                cluster_core_thread_to_cpuidx.insert(
+                    (cpu_idx / cores_per_package, cpu_idx % cores_per_package, 0),
+                    cpu_idx,
+                );
+            }
+        }
+
+        // Create device tree nodes with regard of above mapping.
+        for cluster_idx in 0..packages {
+            let cluster_name = format!("cluster{:x}", cluster_idx);
+            let cluster_node = fdt.begin_node(&cluster_name)?;
+
+            for core_idx in 0..cores_per_package {
+                let core_name = format!("core{:x}", core_idx);
+                let core_node = fdt.begin_node(&core_name)?;
+
+                if threads_per_core > 1 {
+                    for thread_idx in 0..threads_per_core {
+                        let thread_name = format!("thread{:x}", thread_idx);
+                        let thread_node = fdt.begin_node(&thread_name)?;
+                        let cpu_idx = cluster_core_thread_to_cpuidx
+                            .get(&(cluster_idx, core_idx, thread_idx))
+                            .unwrap();
+
+                        fdt.property_u32("cpu", *cpu_idx as u32 + FIRST_VCPU_PHANDLE)?;
+                        fdt.end_node(thread_node)?;
+                    }
+                } else {
+                    let cpu_idx = cluster_core_thread_to_cpuidx
+                        .get(&(cluster_idx, core_idx, 0))
+                        .unwrap();
+
+                    fdt.property_u32("cpu", *cpu_idx as u32 + FIRST_VCPU_PHANDLE)?;
+                }
+                fdt.end_node(core_node)?;
+            }
+            fdt.end_node(cluster_node)?;
+        }
+        fdt.end_node(cpu_map_node)?;
+    } else {
+        debug!("Boot using device tree, CPU topology is not (correctly) specified");
+    }
+
     fdt.end_node(cpus_node)?;
+
     Ok(())
 }
 
-fn create_memory_node(fdt: &mut FdtWriter, guest_mem: &GuestMemoryMmap) -> FdtWriterResult<()> {
-    let mem_size = guest_mem.last_addr().raw_value() - super::layout::RAM_64BIT_START + 1;
-    // See https://github.com/torvalds/linux/blob/master/Documentation/devicetree/booting-without-of.txt#L960
-    // for an explanation of this.
-    let mem_reg_prop = [super::layout::RAM_64BIT_START as u64, mem_size as u64];
+fn create_memory_node(
+    fdt: &mut FdtWriter,
+    guest_mem: &GuestMemoryMmap,
+    numa_nodes: &NumaNodes,
+) -> FdtWriterResult<()> {
+    if numa_nodes.len() > 1 {
+        for numa_node_idx in 0..numa_nodes.len() {
+            let numa_node = numa_nodes.get(&(numa_node_idx as u32));
+            // Each memory zone of numa will have its own memory node, but
+            // different numa nodes should not share same memory zones.
+            for memory_region in numa_node.unwrap().memory_regions.iter() {
+                let memory_region_start_addr: u64 = memory_region.start_addr().raw_value();
+                let memory_region_size: u64 = memory_region.size() as u64;
+                let mem_reg_prop = [memory_region_start_addr, memory_region_size];
+                // With feature `acpi` enabled, RAM at 0-4M is for edk2 only
+                // and should be hidden to the guest.
+                #[cfg(feature = "acpi")]
+                if memory_region_start_addr == 0 {
+                    continue;
+                }
 
-    let memory_node = fdt.begin_node("memory")?;
-    fdt.property_string("device_type", "memory")?;
-    fdt.property_array_u64("reg", &mem_reg_prop)?;
-    fdt.end_node(memory_node)?;
+                let memory_node_name = format!("memory@{:x}", memory_region_start_addr);
+                let memory_node = fdt.begin_node(&memory_node_name)?;
+                fdt.property_string("device_type", "memory")?;
+                fdt.property_array_u64("reg", &mem_reg_prop)?;
+                fdt.property_u32("numa-node-id", numa_node_idx as u32)?;
+                fdt.end_node(memory_node)?;
+            }
+        }
+    } else {
+        let mem_size = guest_mem.last_addr().raw_value() - super::layout::RAM_64BIT_START + 1;
+        // See https://github.com/torvalds/linux/blob/master/Documentation/devicetree/booting-without-of.txt#L960
+        // for an explanation of this.
+        let mem_reg_prop = [super::layout::RAM_64BIT_START as u64, mem_size as u64];
+        let memory_node = fdt.begin_node("memory")?;
+
+        fdt.property_string("device_type", "memory")?;
+        fdt.property_array_u64("reg", &mem_reg_prop)?;
+        fdt.end_node(memory_node)?;
+    }
 
     Ok(())
 }
@@ -191,7 +322,7 @@ fn create_gic_node(fdt: &mut FdtWriter, gic_device: &dyn GicDevice) -> FdtWriter
     // interrupt source. The type shall be a <u32> and the value shall be 3 if no PPI affinity description
     // is required.
     fdt.property_u32("#interrupt-cells", 3)?;
-    fdt.property_array_u64("reg", &gic_reg_prop)?;
+    fdt.property_array_u64("reg", gic_reg_prop)?;
     fdt.property_u32("phandle", GIC_PHANDLE)?;
     fdt.property_u32("#address-cells", 2)?;
     fdt.property_u32("#size-cells", 2)?;
@@ -210,7 +341,7 @@ fn create_gic_node(fdt: &mut FdtWriter, gic_device: &dyn GicDevice) -> FdtWriter
         fdt.property_null("msi-controller")?;
         fdt.property_u32("phandle", MSI_PHANDLE)?;
         let msi_reg_prop = gic_device.msi_properties();
-        fdt.property_array_u64("reg", &msi_reg_prop)?;
+        fdt.property_array_u64("reg", msi_reg_prop)?;
         fdt.end_node(msic_node)?;
     }
 
@@ -476,3 +607,124 @@ fn create_pci_nodes(
 
     Ok(())
 }
+
+fn create_distance_map_node(fdt: &mut FdtWriter, numa_nodes: &NumaNodes) -> FdtWriterResult<()> {
+    let distance_map_node = fdt.begin_node("distance-map")?;
+    fdt.property_string("compatible", "numa-distance-map-v1")?;
+    // Construct the distance matrix.
+    // 1. We use the word entry to describe a distance from a node to
+    // its destination, e.g. 0 -> 1 = 20 is described as <0 1 20>.
+    // 2. Each entry represents distance from first node to second node.
+    // The distances are equal in either direction.
+    // 3. The distance from a node to self (local distance) is represented
+    // with value 10 and all internode distance should be represented with
+    // a value greater than 10.
+    // 4. distance-matrix should have entries in lexicographical ascending
+    // order of nodes.
+    let mut distance_matrix = Vec::new();
+    for numa_node_idx in 0..numa_nodes.len() {
+        let numa_node = numa_nodes.get(&(numa_node_idx as u32));
+        for dest_numa_node in 0..numa_node.unwrap().distances.len() + 1 {
+            if numa_node_idx == dest_numa_node {
+                distance_matrix.push(numa_node_idx as u32);
+                distance_matrix.push(dest_numa_node as u32);
+                distance_matrix.push(10_u32);
+                continue;
+            }
+
+            distance_matrix.push(numa_node_idx as u32);
+            distance_matrix.push(dest_numa_node as u32);
+            distance_matrix.push(
+                *numa_node
+                    .unwrap()
+                    .distances
+                    .get(&(dest_numa_node as u32))
+                    .unwrap() as u32,
+            );
+        }
+    }
+    fdt.property_array_u32("distance-matrix", distance_matrix.as_ref())?;
+    fdt.end_node(distance_map_node)?;
+
+    Ok(())
+}
+
+// Parse the DTB binary and print for debugging
+pub fn print_fdt(dtb: &[u8]) {
+    match fdt_parser::Fdt::new(dtb) {
+        Ok(fdt) => {
+            if let Some(root) = fdt.find_node("/") {
+                debug!("Printing the FDT:");
+                print_node(root, 0);
+            } else {
+                debug!("Failed to find root node in FDT for debugging.");
+            }
+        }
+        Err(_) => debug!("Failed to parse FDT for debugging."),
+    }
+}
+
+fn print_node(node: fdt_parser::node::FdtNode<'_, '_>, n_spaces: usize) {
+    debug!("{:indent$}{}/", "", node.name, indent = n_spaces);
+    for property in node.properties() {
+        let name = property.name;
+
+        // If the property is 'compatible', its value requires special handling.
+        // The u8 array could contain multiple null-terminated strings.
+        // We copy the original array and simply replace all 'null' characters with spaces.
+        let value = if name == "compatible" {
+            let mut compatible = vec![0u8; 256];
+            let handled_value = property
+                .value
+                .iter()
+                .map(|&c| if c == 0 { b' ' } else { c })
+                .collect::<Vec<_>>();
+            let len = cmp::min(255, handled_value.len());
+            compatible[..len].copy_from_slice(&handled_value[..len]);
+            compatible[..(len + 1)].to_vec()
+        } else {
+            property.value.to_vec()
+        };
+        let value = &value;
+
+        // Now the value can be either:
+        //   - A null-terminated C string, or
+        //   - Binary data
+        // We follow a very simple logic to present the value:
+        //   - At first, try to convert it to CStr and print,
+        //   - If failed, print it as u32 array.
+        let value_result = match CStr::from_bytes_with_nul(value) {
+            Ok(value_cstr) => match value_cstr.to_str() {
+                Ok(value_str) => Some(value_str),
+                Err(_e) => None,
+            },
+            Err(_e) => None,
+        };
+
+        if let Some(value_str) = value_result {
+            debug!(
+                "{:indent$}{} : {:#?}",
+                "",
+                name,
+                value_str,
+                indent = (n_spaces + 2)
+            );
+        } else {
+            let mut array = Vec::with_capacity(256);
+            array.resize(value.len() / 4, 0u32);
+            BigEndian::read_u32_into(value, &mut array);
+            debug!(
+                "{:indent$}{} : {:X?}",
+                "",
+                name,
+                array,
+                indent = (n_spaces + 2)
+            );
+        };
+    }
+
+    // Print children nodes if there is any
+    for child in node.children() {
+        print_node(child, n_spaces + 2);
+    }
+}

arch/src/aarch64/gic/dist_regs.rs

@@ -152,7 +152,7 @@ pub fn set_dist_regs(gic: &Arc<dyn hypervisor::Device>, state: &[u32]) -> Result
 
     for dreg in VGIC_DIST_REGS {
         let mut base = dreg.base + REG_SIZE as u32 * dreg.bpi as u32;
-        let end = compute_reg_len(gic, &dreg, base)?;
+        let end = compute_reg_len(gic, dreg, base)?;
 
         while base < end {
             let val = state[idx];
@@ -169,7 +169,7 @@ pub fn get_dist_regs(gic: &Arc<dyn hypervisor::Device>) -> Result<Vec<u32>> {
 
     for dreg in VGIC_DIST_REGS {
         let mut base = dreg.base + REG_SIZE as u32 * dreg.bpi as u32;
-        let end = compute_reg_len(gic, &dreg, base)?;
+        let end = compute_reg_len(gic, dreg, base)?;
 
         while base < end {
             let val: u32 = 0;

arch/src/aarch64/gic/gicv3.rs

@@ -1,5 +1,8 @@
+// Copyright 2021 Arm Limited (or its affiliates). All rights reserved.
 // Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
+//
+// This file implements the GicV3 device.
 
 pub mod kvm {
     use crate::aarch64::gic::dist_regs::{get_dist_regs, read_ctlr, set_dist_regs, write_ctlr};
@@ -50,7 +53,7 @@ pub mod kvm {
     type Result<T> = result::Result<T, Error>;
 
     pub struct KvmGicV3 {
-        /// The hypervisor agnostic device
+        /// The hypervisor agnostic device for the GicV3
         device: Arc<dyn hypervisor::Device>,
 
         /// Vector holding values of GICR_TYPER for each vCPU
@@ -106,20 +109,17 @@ pub mod kvm {
 
         /// Save the state of GIC.
         fn state(&self, gicr_typers: &[u64]) -> Result<Gicv3State> {
-            // Flush redistributors pending tables to guest RAM.
-            save_pending_tables(&self.device()).map_err(Error::SavePendingTables)?;
-
             let gicd_ctlr =
-                read_ctlr(&self.device()).map_err(Error::SaveDistributorCtrlRegisters)?;
+                read_ctlr(self.device()).map_err(Error::SaveDistributorCtrlRegisters)?;
 
             let dist_state =
-                get_dist_regs(&self.device()).map_err(Error::SaveDistributorRegisters)?;
+                get_dist_regs(self.device()).map_err(Error::SaveDistributorRegisters)?;
 
-            let rdist_state = get_redist_regs(&self.device(), &gicr_typers)
+            let rdist_state = get_redist_regs(self.device(), gicr_typers)
                 .map_err(Error::SaveRedistributorRegisters)?;
 
             let icc_state =
-                get_icc_regs(&self.device(), &gicr_typers).map_err(Error::SaveIccRegisters)?;
+                get_icc_regs(self.device(), gicr_typers).map_err(Error::SaveIccRegisters)?;
 
             Ok(Gicv3State {
                 dist: dist_state,
@@ -131,16 +131,16 @@ pub mod kvm {
 
         /// Restore the state of GIC.
         fn set_state(&mut self, gicr_typers: &[u64], state: &Gicv3State) -> Result<()> {
-            write_ctlr(&self.device(), state.gicd_ctlr)
+            write_ctlr(self.device(), state.gicd_ctlr)
                 .map_err(Error::RestoreDistributorCtrlRegisters)?;
 
-            set_dist_regs(&self.device(), &state.dist)
+            set_dist_regs(self.device(), &state.dist)
                 .map_err(Error::RestoreDistributorRegisters)?;
 
-            set_redist_regs(&self.device(), gicr_typers, &state.rdist)
+            set_redist_regs(self.device(), gicr_typers, &state.rdist)
                 .map_err(Error::RestoreRedistributorRegisters)?;
 
-            set_icc_regs(&self.device(), &gicr_typers, &state.icc)
+            set_icc_regs(self.device(), gicr_typers, &state.icc)
                 .map_err(Error::RestoreIccRegisters)?;
 
             Ok(())
@@ -168,6 +168,8 @@ pub mod kvm {
             self.vcpu_count
         }
 
+        fn set_its_device(&mut self, _its_device: Option<Arc<dyn hypervisor::Device>>) {}
+
         fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
             let gicr_typers = construct_gicr_typers(vcpu_states);
             self.gicr_typers = gicr_typers;
@@ -202,7 +204,7 @@ pub mod kvm {
 
         fn init_device_attributes(
             _vm: &Arc<dyn hypervisor::Vm>,
-            gic_device: &dyn GicDevice,
+            gic_device: &mut dyn GicDevice,
         ) -> crate::aarch64::gic::Result<()> {
             /* Setting up the distributor attribute.
              We are placing the GIC below 1GB so we need to substract the size of the distributor.
@@ -250,7 +252,16 @@ pub mod kvm {
         }
     }
 
-    impl Pausable for KvmGicV3 {}
+    impl Pausable for KvmGicV3 {
+        fn pause(&mut self) -> std::result::Result<(), MigratableError> {
+            // Flush redistributors pending tables to guest RAM.
+            save_pending_tables(self.device()).map_err(|e| {
+                MigratableError::Pause(anyhow!("Could not save GICv3 GIC pending tables {:?}", e))
+            })?;
+
+            Ok(())
+        }
+    }
     impl Transportable for KvmGicV3 {}
     impl Migratable for KvmGicV3 {}
 }

arch/src/aarch64/gic/gicv3_its.rs

@@ -1,21 +1,156 @@
-// Copyright 2020 ARM Limited
+// Copyright 2021 Arm Limited (or its affiliates). All rights reserved.
 // SPDX-License-Identifier: Apache-2.0
+//
+// This file implements the GicV3 device with ITS (Virtual Interrupt Translation Service).
 
 pub mod kvm {
-    use std::any::Any;
-    use std::sync::Arc;
-    use std::{boxed::Box, result};
-    type Result<T> = result::Result<T, Error>;
+    use crate::aarch64::gic::dist_regs::{get_dist_regs, read_ctlr, set_dist_regs, write_ctlr};
+    use crate::aarch64::gic::icc_regs::{get_icc_regs, set_icc_regs};
+    use crate::aarch64::gic::redist_regs::{
+        construct_gicr_typers, get_redist_regs, set_redist_regs,
+    };
+
     use crate::aarch64::gic::gicv3::kvm::KvmGicV3;
-    use crate::aarch64::gic::kvm::KvmGicDevice;
-    use crate::aarch64::gic::{Error, GicDevice};
+    use crate::aarch64::gic::kvm::{save_pending_tables, KvmGicDevice};
+    use crate::aarch64::gic::GicDevice;
+    use anyhow::anyhow;
     use hypervisor::kvm::kvm_bindings;
     use hypervisor::CpuState;
+    use std::any::Any;
+    use std::convert::TryInto;
+    use std::sync::Arc;
+    use std::{boxed::Box, result};
+    use versionize::{VersionMap, Versionize, VersionizeResult};
+    use versionize_derive::Versionize;
+    use vm_migration::{
+        Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable,
+        VersionMapped,
+    };
+
+    const GITS_CTLR: u32 = 0x0000;
+    const GITS_IIDR: u32 = 0x0004;
+    const GITS_CBASER: u32 = 0x0080;
+    const GITS_CWRITER: u32 = 0x0088;
+    const GITS_CREADR: u32 = 0x0090;
+    const GITS_BASER: u32 = 0x0100;
+
+    /// Errors thrown while saving/restoring the GICv3ITS.
+    #[derive(Debug)]
+    pub enum Error {
+        /// Error in saving RDIST pending tables into guest RAM.
+        SavePendingTables(crate::aarch64::gic::Error),
+        /// Error in saving GIC distributor registers.
+        SaveDistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC distributor registers.
+        RestoreDistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GIC distributor control registers.
+        SaveDistributorCtrlRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC distributor control registers.
+        RestoreDistributorCtrlRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GIC redistributor registers.
+        SaveRedistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC redistributor registers.
+        RestoreRedistributorRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GIC CPU interface registers.
+        SaveIccRegisters(crate::aarch64::gic::Error),
+        /// Error in restoring GIC CPU interface registers.
+        RestoreIccRegisters(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS IIDR register.
+        SaveITSIIDR(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS IIDR register.
+        RestoreITSIIDR(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS CBASER register.
+        SaveITSCBASER(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS CBASER register.
+        RestoreITSCBASER(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS CREADR register.
+        SaveITSCREADR(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS CREADR register.
+        RestoreITSCREADR(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS CWRITER register.
+        SaveITSCWRITER(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS CWRITER register.
+        RestoreITSCWRITER(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS BASER register.
+        SaveITSBASER(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS BASER register.
+        RestoreITSBASER(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS CTLR register.
+        SaveITSCTLR(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS CTLR register.
+        RestoreITSCTLR(crate::aarch64::gic::Error),
+        /// Error in saving GICv3ITS restore tables.
+        SaveITSTables(crate::aarch64::gic::Error),
+        /// Error in restoring GICv3ITS restore tables.
+        RestoreITSTables(crate::aarch64::gic::Error),
+    }
+
+    type Result<T> = result::Result<T, Error>;
+
+    /// Access an ITS device attribute.
+    ///
+    /// This is a helper function to get/set the ITS device attribute depending
+    /// the bool parameter `set` provided.
+    pub fn gicv3_its_attr_access(
+        its_device: &Arc<dyn hypervisor::Device>,
+        group: u32,
+        attr: u32,
+        val: &u64,
+        set: bool,
+    ) -> crate::aarch64::gic::Result<()> {
+        let mut gicv3_its_attr = kvm_bindings::kvm_device_attr {
+            group,
+            attr: attr as u64,
+            addr: val as *const u64 as u64,
+            flags: 0,
+        };
+        if set {
+            its_device
+                .set_device_attr(&gicv3_its_attr)
+                .map_err(crate::aarch64::gic::Error::SetDeviceAttribute)?;
+        } else {
+            its_device
+                .get_device_attr(&mut gicv3_its_attr)
+                .map_err(crate::aarch64::gic::Error::GetDeviceAttribute)?;
+        }
+        Ok(())
+    }
+
+    /// Function that saves/restores ITS tables into guest RAM.
+    ///
+    /// The tables get flushed to guest RAM whenever the VM gets stopped.
+    pub fn gicv3_its_tables_access(
+        its_device: &Arc<dyn hypervisor::Device>,
+        save: bool,
+    ) -> crate::aarch64::gic::Result<()> {
+        let attr: u64;
+        if save {
+            attr = u64::from(kvm_bindings::KVM_DEV_ARM_ITS_SAVE_TABLES);
+        } else {
+            attr = u64::from(kvm_bindings::KVM_DEV_ARM_ITS_RESTORE_TABLES);
+        }
+
+        let init_gic_attr = kvm_bindings::kvm_device_attr {
+            group: kvm_bindings::KVM_DEV_ARM_VGIC_GRP_CTRL,
+            attr,
+            addr: 0,
+            flags: 0,
+        };
+        its_device
+            .set_device_attr(&init_gic_attr)
+            .map_err(crate::aarch64::gic::Error::SetDeviceAttribute)
+    }
 
     pub struct KvmGicV3Its {
-        /// The hypervisor agnostic device
+        /// The hypervisor agnostic device for the GicV3
         device: Arc<dyn hypervisor::Device>,
 
+        /// The hypervisor agnostic device for the Its device
+        its_device: Option<Arc<dyn hypervisor::Device>>,
+
+        /// Vector holding values of GICR_TYPER for each vCPU
+        gicr_typers: Vec<u64>,
+
         /// GIC device properties, to be used for setting up the fdt entry
         gic_properties: [u64; 4],
 
@@ -26,6 +161,23 @@ pub mod kvm {
         vcpu_count: u64,
     }
 
+    #[derive(Versionize)]
+    pub struct Gicv3ItsState {
+        dist: Vec<u32>,
+        rdist: Vec<u32>,
+        icc: Vec<u32>,
+        // special register that enables interrupts and affinity routing
+        gicd_ctlr: u32,
+        its_ctlr: u64,
+        its_iidr: u64,
+        its_cbaser: u64,
+        its_cwriter: u64,
+        its_creadr: u64,
+        its_baser: [u64; 8],
+    }
+
+    impl VersionMapped for Gicv3ItsState {}
+
     impl KvmGicV3Its {
         const KVM_VGIC_V3_ITS_SIZE: u64 = (2 * KvmGicV3::SZ_64K);
 
@@ -36,6 +188,174 @@ pub mod kvm {
         fn get_msi_addr(vcpu_count: u64) -> u64 {
             KvmGicV3::get_redists_addr(vcpu_count) - KvmGicV3Its::get_msi_size()
         }
+
+        /// Save the state of GICv3ITS.
+        fn state(&self, gicr_typers: &[u64]) -> Result<Gicv3ItsState> {
+            let gicd_ctlr =
+                read_ctlr(self.device()).map_err(Error::SaveDistributorCtrlRegisters)?;
+
+            let dist_state =
+                get_dist_regs(self.device()).map_err(Error::SaveDistributorRegisters)?;
+
+            let rdist_state = get_redist_regs(self.device(), gicr_typers)
+                .map_err(Error::SaveRedistributorRegisters)?;
+
+            let icc_state =
+                get_icc_regs(self.device(), gicr_typers).map_err(Error::SaveIccRegisters)?;
+
+            let its_baser_state: [u64; 8] = [0; 8];
+            for i in 0..8 {
+                gicv3_its_attr_access(
+                    self.its_device().unwrap(),
+                    kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                    GITS_BASER + i * 8,
+                    &its_baser_state[i as usize],
+                    false,
+                )
+                .map_err(Error::SaveITSBASER)?;
+            }
+
+            let its_ctlr_state: u64 = 0;
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CTLR,
+                &its_ctlr_state,
+                false,
+            )
+            .map_err(Error::SaveITSCTLR)?;
+
+            let its_cbaser_state: u64 = 0;
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CBASER,
+                &its_cbaser_state,
+                false,
+            )
+            .map_err(Error::SaveITSCBASER)?;
+
+            let its_creadr_state: u64 = 0;
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CREADR,
+                &its_creadr_state,
+                false,
+            )
+            .map_err(Error::SaveITSCREADR)?;
+
+            let its_cwriter_state: u64 = 0;
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CWRITER,
+                &its_cwriter_state,
+                false,
+            )
+            .map_err(Error::SaveITSCWRITER)?;
+
+            let its_iidr_state: u64 = 0;
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_IIDR,
+                &its_iidr_state,
+                false,
+            )
+            .map_err(Error::SaveITSIIDR)?;
+
+            Ok(Gicv3ItsState {
+                dist: dist_state,
+                rdist: rdist_state,
+                icc: icc_state,
+                gicd_ctlr,
+                its_ctlr: its_ctlr_state,
+                its_iidr: its_iidr_state,
+                its_cbaser: its_cbaser_state,
+                its_cwriter: its_cwriter_state,
+                its_creadr: its_creadr_state,
+                its_baser: its_baser_state,
+            })
+        }
+
+        /// Restore the state of GICv3ITS.
+        fn set_state(&mut self, gicr_typers: &[u64], state: &Gicv3ItsState) -> Result<()> {
+            write_ctlr(self.device(), state.gicd_ctlr)
+                .map_err(Error::RestoreDistributorCtrlRegisters)?;
+
+            set_dist_regs(self.device(), &state.dist)
+                .map_err(Error::RestoreDistributorRegisters)?;
+
+            set_redist_regs(self.device(), gicr_typers, &state.rdist)
+                .map_err(Error::RestoreRedistributorRegisters)?;
+
+            set_icc_regs(self.device(), gicr_typers, &state.icc)
+                .map_err(Error::RestoreIccRegisters)?;
+
+            //Restore GICv3ITS registers
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_IIDR,
+                &state.its_iidr,
+                true,
+            )
+            .map_err(Error::RestoreITSIIDR)?;
+
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CBASER,
+                &state.its_cbaser,
+                true,
+            )
+            .map_err(Error::RestoreITSCBASER)?;
+
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CREADR,
+                &state.its_creadr,
+                true,
+            )
+            .map_err(Error::RestoreITSCREADR)?;
+
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CWRITER,
+                &state.its_cwriter,
+                true,
+            )
+            .map_err(Error::RestoreITSCWRITER)?;
+
+            for i in 0..8 {
+                gicv3_its_attr_access(
+                    self.its_device().unwrap(),
+                    kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                    GITS_BASER + i * 8,
+                    &state.its_baser[i as usize],
+                    true,
+                )
+                .map_err(Error::RestoreITSBASER)?;
+            }
+
+            // Restore ITS tables
+            gicv3_its_tables_access(self.its_device().unwrap(), false)
+                .map_err(Error::RestoreITSTables)?;
+
+            gicv3_its_attr_access(
+                self.its_device().unwrap(),
+                kvm_bindings::KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                GITS_CTLR,
+                &state.its_ctlr,
+                true,
+            )
+            .map_err(Error::RestoreITSCTLR)?;
+
+            Ok(())
+        }
     }
 
     impl GicDevice for KvmGicV3Its {
@@ -43,6 +363,10 @@ pub mod kvm {
             &self.device
         }
 
+        fn its_device(&self) -> Option<&Arc<dyn hypervisor::Device>> {
+            self.its_device.as_ref()
+        }
+
         fn fdt_compatibility(&self) -> &str {
             "arm,gic-v3"
         }
@@ -71,7 +395,14 @@ pub mod kvm {
             self.vcpu_count
         }
 
-        fn set_gicr_typers(&mut self, _vcpu_states: &[CpuState]) {}
+        fn set_its_device(&mut self, its_device: Option<Arc<dyn hypervisor::Device>>) {
+            self.its_device = its_device;
+        }
+
+        fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
+            let gicr_typers = construct_gicr_typers(vcpu_states);
+            self.gicr_typers = gicr_typers;
+        }
 
         fn as_any_concrete_mut(&mut self) -> &mut dyn Any {
             self
@@ -89,6 +420,8 @@ pub mod kvm {
         ) -> Box<dyn GicDevice> {
             Box::new(KvmGicV3Its {
                 device,
+                its_device: None,
+                gicr_typers: vec![0; vcpu_count.try_into().unwrap()],
                 gic_properties: [
                     KvmGicV3::get_dist_addr(),
                     KvmGicV3::get_dist_size(),
@@ -105,8 +438,8 @@ pub mod kvm {
 
         fn init_device_attributes(
             vm: &Arc<dyn hypervisor::Vm>,
-            gic_device: &dyn GicDevice,
-        ) -> Result<()> {
+            gic_device: &mut dyn GicDevice,
+        ) -> crate::aarch64::gic::Result<()> {
             KvmGicV3::init_device_attributes(vm, gic_device)?;
 
             let mut its_device = kvm_bindings::kvm_create_device {
@@ -117,7 +450,7 @@ pub mod kvm {
 
             let its_fd = vm
                 .create_device(&mut its_device)
-                .map_err(Error::CreateGic)?;
+                .map_err(crate::aarch64::gic::Error::CreateGic)?;
 
             Self::set_device_attribute(
                 &its_fd,
@@ -135,7 +468,49 @@ pub mod kvm {
                 0,
             )?;
 
+            gic_device.set_its_device(Some(its_fd));
+
             Ok(())
         }
     }
+
+    pub const GIC_V3_ITS_SNAPSHOT_ID: &str = "gic-v3-its";
+    impl Snapshottable for KvmGicV3Its {
+        fn id(&self) -> String {
+            GIC_V3_ITS_SNAPSHOT_ID.to_string()
+        }
+
+        fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
+            let gicr_typers = self.gicr_typers.clone();
+            Snapshot::new_from_versioned_state(&self.id(), &self.state(&gicr_typers).unwrap())
+        }
+
+        fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
+            let gicr_typers = self.gicr_typers.clone();
+            self.set_state(&gicr_typers, &snapshot.to_versioned_state(&self.id())?)
+                .map_err(|e| {
+                    MigratableError::Restore(anyhow!("Could not restore GICv3ITS state {:?}", e))
+                })
+        }
+    }
+
+    impl Pausable for KvmGicV3Its {
+        fn pause(&mut self) -> std::result::Result<(), MigratableError> {
+            // Flush redistributors pending tables to guest RAM.
+            save_pending_tables(self.device()).map_err(|e| {
+                MigratableError::Pause(anyhow!(
+                    "Could not save GICv3ITS GIC pending tables {:?}",
+                    e
+                ))
+            })?;
+            // Flush ITS tables to guest RAM.
+            gicv3_its_tables_access(self.its_device().unwrap(), true).map_err(|e| {
+                MigratableError::Pause(anyhow!("Could not save GICv3ITS ITS tables {:?}", e))
+            })?;
+
+            Ok(())
+        }
+    }
+    impl Transportable for KvmGicV3Its {}
+    impl Migratable for KvmGicV3Its {}
 }

arch/src/aarch64/gic/mod.rs

@@ -1,3 +1,4 @@
+// Copyright 2021 Arm Limited (or its affiliates). All rights reserved.
 // Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 // SPDX-License-Identifier: Apache-2.0
 
@@ -31,6 +32,11 @@ pub trait GicDevice: Send {
     /// Returns the hypervisor agnostic Device of the GIC device
     fn device(&self) -> &Arc<dyn hypervisor::Device>;
 
+    /// Returns the hypervisor agnostic Device of the ITS device
+    fn its_device(&self) -> Option<&Arc<dyn hypervisor::Device>> {
+        None
+    }
+
     /// Returns the fdt compatibility property of the device
     fn fdt_compatibility(&self) -> &str;
 
@@ -58,6 +64,8 @@ pub trait GicDevice: Send {
         &[]
     }
 
+    fn set_its_device(&mut self, its_device: Option<Arc<dyn hypervisor::Device>>);
+
     /// Get the values of GICR_TYPER for each vCPU.
     fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]);
 
@@ -88,7 +96,7 @@ pub mod kvm {
         /// Setup the device-specific attributes
         fn init_device_attributes(
             vm: &Arc<dyn hypervisor::Vm>,
-            gic_device: &dyn GicDevice,
+            gic_device: &mut dyn GicDevice,
         ) -> Result<()>;
 
         /// Initialize a GIC device
@@ -179,9 +187,9 @@ pub mod kvm {
         fn new(vm: &Arc<dyn hypervisor::Vm>, vcpu_count: u64) -> Result<Box<dyn GicDevice>> {
             let vgic_fd = Self::init_device(vm)?;
 
-            let device = Self::create_device(vgic_fd, vcpu_count);
+            let mut device = Self::create_device(vgic_fd, vcpu_count);
 
-            Self::init_device_attributes(vm, &*device)?;
+            Self::init_device_attributes(vm, &mut *device)?;
 
             Self::finalize_device(&*device)?;
 

arch/src/aarch64/gic/redist_regs.rs

@@ -62,11 +62,11 @@ macro_rules! VGIC_RDIST_REG {
 
 // List with relevant distributor registers that we will be restoring.
 static VGIC_RDIST_REGS: &'static [RdistReg] = &[
-    VGIC_RDIST_REG!(GICR_CTLR, 4),
     VGIC_RDIST_REG!(GICR_STATUSR, 4),
     VGIC_RDIST_REG!(GICR_WAKER, 4),
     VGIC_RDIST_REG!(GICR_PROPBASER, 8),
     VGIC_RDIST_REG!(GICR_PENDBASER, 8),
+    VGIC_RDIST_REG!(GICR_CTLR, 4),
 ];
 
 // List with relevant distributor registers that we will be restoring.
@@ -142,14 +142,14 @@ pub fn get_redist_regs(gic: &Arc<dyn hypervisor::Device>, gicr_typer: &[u64]) ->
     let mut idx: usize = 0;
     access_redists_aux(
         gic,
-        &gicr_typer,
+        gicr_typer,
         &mut state,
         VGIC_RDIST_REGS,
         &mut idx,
         false,
     )?;
 
-    access_redists_aux(gic, &gicr_typer, &mut state, VGIC_SGI_REGS, &mut idx, false)?;
+    access_redists_aux(gic, gicr_typer, &mut state, VGIC_SGI_REGS, &mut idx, false)?;
     Ok(state)
 }
 

arch/src/aarch64/layout.rs

@@ -46,10 +46,11 @@
 
 use vm_memory::GuestAddress;
 
-/// 0x0 ~ 0x400_0000 is reserved to uefi
+/// 0x0 ~ 0x40_0000 (4 MiB) is reserved to UEFI
+/// UEFI binary size is required less than 3 MiB, reserving 4 MiB is enough.
 pub const UEFI_START: u64 = 0x0;
 pub const MEM_UEFI_START: GuestAddress = GuestAddress(0);
-pub const UEFI_SIZE: u64 = 0x0400_0000;
+pub const UEFI_SIZE: u64 = 0x040_0000;
 
 /// Below this address will reside the GIC, above this address will reside the MMIO devices.
 pub const MAPPED_IO_START: u64 = 0x0900_0000;

arch/src/aarch64/mod.rs

@@ -14,10 +14,9 @@ pub mod regs;
 pub mod uefi;
 
 pub use self::fdt::DeviceInfoForFdt;
-use crate::DeviceType;
-use crate::GuestMemoryMmap;
-use crate::RegionType;
+use crate::{DeviceType, GuestMemoryMmap, NumaNodes, RegionType};
 use gic::GicDevice;
+use log::{log_enabled, Level};
 use std::collections::HashMap;
 use std::convert::TryInto;
 use std::ffi::CStr;
@@ -87,7 +86,7 @@ pub fn configure_vcpu(
 pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, RegionType)> {
     // Normally UEFI should be loaded to a flash area at the beginning of memory.
     // But now flash memory type is not supported.
-    // As a workaround, we take 64 MiB memory from the main RAM for UEFI.
+    // As a workaround, we take 4 MiB memory from the main RAM for UEFI.
     // As a result, the RAM that the guest can see is less than what has been
     // assigned in command line, when ACPI and UEFI is enabled.
     let ram_deduction = if cfg!(feature = "acpi") {
@@ -97,7 +96,7 @@ pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, Region
     };
 
     vec![
-        // 0 ~ 64 MiB: Reserved for UEFI space
+        // 0 ~ 4 MiB: Reserved for UEFI space
         #[cfg(feature = "acpi")]
         (GuestAddress(0), layout::UEFI_SIZE as usize, RegionType::Ram),
         #[cfg(not(feature = "acpi"))]
@@ -106,7 +105,7 @@ pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, Region
             layout::UEFI_SIZE as usize,
             RegionType::Reserved,
         ),
-        // 64 MiB ~ 256 MiB: Gic and legacy devices
+        // 4 MiB ~ 256 MiB: Gic and legacy devices
         (
             GuestAddress(layout::UEFI_SIZE),
             (layout::MEM_32BIT_DEVICES_START.0 - layout::UEFI_SIZE) as usize,
@@ -134,26 +133,35 @@ pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, Region
 }
 
 /// Configures the system and should be called once per vm before starting vcpu threads.
+#[allow(clippy::too_many_arguments)]
 pub fn configure_system<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
     guest_mem: &GuestMemoryMmap,
     cmdline_cstring: &CStr,
     vcpu_mpidr: Vec<u64>,
+    vcpu_topology: Option<(u8, u8, u8)>,
     device_info: &HashMap<(DeviceType, String), T, S>,
     initrd: &Option<super::InitramfsConfig>,
     pci_space_address: &(u64, u64),
     gic_device: &dyn GicDevice,
+    numa_nodes: &NumaNodes,
 ) -> super::Result<()> {
     let fdt_final = fdt::create_fdt(
         guest_mem,
         cmdline_cstring,
         vcpu_mpidr,
+        vcpu_topology,
         device_info,
         gic_device,
         initrd,
         pci_space_address,
+        numa_nodes,
     )
     .map_err(|_| Error::SetupFdt)?;
 
+    if log_enabled!(Level::Debug) {
+        fdt::print_fdt(&fdt_final);
+    }
+
     fdt::write_fdt_to_memory(fdt_final, guest_mem).map_err(Error::WriteFdtToMemory)?;
 
     Ok(())

arch/src/lib.rs

@@ -11,10 +11,15 @@
 #[macro_use]
 extern crate log;
 
+#[cfg(target_arch = "x86_64")]
+use crate::x86_64::SgxEpcSection;
+use std::collections::BTreeMap;
 use std::fmt;
 use std::result;
+use std::sync::Arc;
 
 type GuestMemoryMmap = vm_memory::GuestMemoryMmap<vm_memory::bitmap::AtomicBitmap>;
+type GuestRegionMmap = vm_memory::GuestRegionMmap<vm_memory::bitmap::AtomicBitmap>;
 
 /// Type for returning error code.
 #[derive(Debug)]
@@ -83,9 +88,9 @@ pub mod x86_64;
 
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::{
-    arch_memory_regions, configure_system, configure_vcpu, get_host_cpu_phys_bits,
-    initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE, layout::CMDLINE_START, regs, CpuidPatch,
-    CpuidReg, EntryPoint,
+    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,
 };
 
 /// Safe wrapper for `sysconf(_SC_PAGESIZE)`.
@@ -96,6 +101,19 @@ fn pagesize() -> usize {
     unsafe { libc::sysconf(libc::_SC_PAGESIZE) as usize }
 }
 
+#[derive(Clone, Default)]
+pub struct NumaNode {
+    pub memory_regions: Vec<Arc<GuestRegionMmap>>,
+    pub hotplug_regions: Vec<Arc<GuestRegionMmap>>,
+    pub cpus: Vec<u8>,
+    pub distances: BTreeMap<u32, u8>,
+    pub memory_zones: Vec<String>,
+    #[cfg(target_arch = "x86_64")]
+    pub sgx_epc_sections: Vec<SgxEpcSection>,
+}
+
+pub type NumaNodes = BTreeMap<u32, NumaNode>;
+
 /// Type for passing information about the initramfs in the guest memory.
 pub struct InitramfsConfig {
     /// Load address of initramfs in guest memory

arch/src/x86_64/mod.rs

@@ -15,11 +15,12 @@ pub mod regs;
 use crate::GuestMemoryMmap;
 use crate::InitramfsConfig;
 use crate::RegionType;
-use hypervisor::{CpuId, CpuIdEntry, CPUID_FLAG_VALID_INDEX};
+use hypervisor::{CpuId, CpuIdEntry, HypervisorError, CPUID_FLAG_VALID_INDEX};
 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,
@@ -30,6 +31,26 @@ use std::arch::x86_64;
 #[cfg(feature = "tdx")]
 pub mod tdx;
 
+// CPUID feature bits
+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.
+
+// KVM feature bits
+const KVM_FEATURE_ASYNC_PF_INT_BIT: u8 = 14;
+#[cfg(feature = "tdx")]
+const KVM_FEATURE_CLOCKSOURCE_BIT: u8 = 0;
+#[cfg(feature = "tdx")]
+const KVM_FEATURE_CLOCKSOURCE2_BIT: u8 = 3;
+#[cfg(feature = "tdx")]
+const KVM_FEATURE_CLOCKSOURCE_STABLE_BIT: u8 = 24;
+#[cfg(feature = "tdx")]
+const KVM_FEATURE_ASYNC_PF_BIT: u8 = 4;
+#[cfg(feature = "tdx")]
+const KVM_FEATURE_ASYNC_PF_VMEXIT_BIT: u8 = 10;
+#[cfg(feature = "tdx")]
+const KVM_FEATURE_STEAL_TIME_BIT: u8 = 5;
+
 #[derive(Debug, Copy, Clone)]
 /// Specifies the entry point address where the guest must start
 /// executing code, as well as which of the supported boot protocols
@@ -64,7 +85,7 @@ impl SgxEpcSection {
 pub struct SgxEpcRegion {
     start: GuestAddress,
     size: GuestUsize,
-    epc_sections: Vec<SgxEpcSection>,
+    epc_sections: BTreeMap<String, SgxEpcSection>,
 }
 
 impl SgxEpcRegion {
@@ -72,7 +93,7 @@ impl SgxEpcRegion {
         SgxEpcRegion {
             start,
             size,
-            epc_sections: Vec::new(),
+            epc_sections: BTreeMap::new(),
         }
     }
     pub fn start(&self) -> GuestAddress {
@@ -81,11 +102,11 @@ impl SgxEpcRegion {
     pub fn size(&self) -> GuestUsize {
         self.size
     }
-    pub fn epc_sections(&self) -> &Vec<SgxEpcSection> {
+    pub fn epc_sections(&self) -> &BTreeMap<String, SgxEpcSection> {
         &self.epc_sections
     }
-    pub fn push(&mut self, epc_section: SgxEpcSection) {
-        self.epc_sections.push(epc_section);
+    pub fn insert(&mut self, id: String, epc_section: SgxEpcSection) {
+        self.epc_sections.insert(id, epc_section);
     }
 }
 
@@ -155,6 +176,18 @@ pub enum Error {
 
     /// Missing SGX_LC CPU feature
     MissingSgxLaunchControlFeature,
+
+    /// Error getting supported CPUID through the hypervisor (kvm/mshv) API
+    CpuidGetSupported(HypervisorError),
+
+    /// Error populating CPUID with KVM HyperV emulation details
+    CpuidKvmHyperV(vmm_sys_util::fam::Error),
+
+    /// Error populating CPUID with CPU identification
+    CpuidIdentification(vmm_sys_util::fam::Error),
+
+    /// Error checking CPUID compatibility
+    CpuidCheckCompatibility,
 }
 
 impl From<Error> for super::Error {
@@ -164,7 +197,7 @@ impl From<Error> for super::Error {
 }
 
 #[allow(dead_code, clippy::upper_case_acronyms)]
-#[derive(Copy, Clone)]
+#[derive(Copy, Clone, Debug)]
 pub enum CpuidReg {
     EAX,
     EBX,
@@ -308,6 +341,386 @@ impl CpuidPatch {
     }
 }
 
+#[derive(Debug)]
+enum CpuidCompatibleCheck {
+    BitwiseSubset, // bitwise subset
+    Equal,         // equal in value
+    NumNotGreater, // smaller or equal as a number
+}
+
+pub struct CpuidFeatureEntry {
+    function: u32,
+    index: u32,
+    feature_reg: CpuidReg,
+    compatible_check: CpuidCompatibleCheck,
+}
+
+impl CpuidFeatureEntry {
+    fn checked_feature_entry_list() -> Vec<CpuidFeatureEntry> {
+        vec![
+            // The following list includes all hardware features bits from
+            // the CPUID Wiki Page: https://en.wikipedia.org/wiki/CPUID
+            // Leaf 0x1, ECX/EDX, feature bits
+            CpuidFeatureEntry {
+                function: 1,
+                index: 0,
+                feature_reg: CpuidReg::ECX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 1,
+                index: 0,
+                feature_reg: CpuidReg::EDX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            // Leaf 0x7, EAX/EBX/ECX/EDX, extended features
+            CpuidFeatureEntry {
+                function: 7,
+                index: 0,
+                feature_reg: CpuidReg::EAX,
+                compatible_check: CpuidCompatibleCheck::NumNotGreater,
+            },
+            CpuidFeatureEntry {
+                function: 7,
+                index: 0,
+                feature_reg: CpuidReg::EBX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 7,
+                index: 0,
+                feature_reg: CpuidReg::ECX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 7,
+                index: 0,
+                feature_reg: CpuidReg::EDX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            // Leaf 0x7 subleaf 0x1, EAX, extended features
+            CpuidFeatureEntry {
+                function: 7,
+                index: 1,
+                feature_reg: CpuidReg::EAX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            // Leaf 0x8000_0001, ECX/EDX, CPUID features bits
+            CpuidFeatureEntry {
+                function: 0x8000_0001,
+                index: 0,
+                feature_reg: CpuidReg::ECX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 0x8000_0001,
+                index: 0,
+                feature_reg: CpuidReg::EDX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            // KVM CPUID bits: https://www.kernel.org/doc/html/latest/virt/kvm/cpuid.html
+            // Leaf 0x4000_0000, EAX/EBX/ECX/EDX, KVM CPUID SIGNATURE
+            CpuidFeatureEntry {
+                function: 0x4000_0000,
+                index: 0,
+                feature_reg: CpuidReg::EAX,
+                compatible_check: CpuidCompatibleCheck::NumNotGreater,
+            },
+            CpuidFeatureEntry {
+                function: 0x4000_0000,
+                index: 0,
+                feature_reg: CpuidReg::EBX,
+                compatible_check: CpuidCompatibleCheck::Equal,
+            },
+            CpuidFeatureEntry {
+                function: 0x4000_0000,
+                index: 0,
+                feature_reg: CpuidReg::ECX,
+                compatible_check: CpuidCompatibleCheck::Equal,
+            },
+            CpuidFeatureEntry {
+                function: 0x4000_0000,
+                index: 0,
+                feature_reg: CpuidReg::EDX,
+                compatible_check: CpuidCompatibleCheck::Equal,
+            },
+            // Leaf 0x4000_0001, EAX/EBX/ECX/EDX, KVM CPUID features
+            CpuidFeatureEntry {
+                function: 0x4000_0001,
+                index: 0,
+                feature_reg: CpuidReg::EAX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 0x4000_0001,
+                index: 0,
+                feature_reg: CpuidReg::EBX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 0x4000_0001,
+                index: 0,
+                feature_reg: CpuidReg::ECX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+            CpuidFeatureEntry {
+                function: 0x4000_0001,
+                index: 0,
+                feature_reg: CpuidReg::EDX,
+                compatible_check: CpuidCompatibleCheck::BitwiseSubset,
+            },
+        ]
+    }
+
+    fn get_features_from_cpuid(
+        cpuid: &CpuId,
+        feature_entry_list: &[CpuidFeatureEntry],
+    ) -> Vec<u32> {
+        let mut features = vec![0; feature_entry_list.len()];
+        for (i, feature_entry) in feature_entry_list.iter().enumerate() {
+            for cpuid_entry in cpuid.as_slice().iter() {
+                if cpuid_entry.function == feature_entry.function
+                    && cpuid_entry.index == feature_entry.index
+                {
+                    match feature_entry.feature_reg {
+                        CpuidReg::EAX => {
+                            features[i] = cpuid_entry.eax;
+                        }
+                        CpuidReg::EBX => {
+                            features[i] = cpuid_entry.ebx;
+                        }
+                        CpuidReg::ECX => {
+                            features[i] = cpuid_entry.ecx;
+                        }
+                        CpuidReg::EDX => {
+                            features[i] = cpuid_entry.edx;
+                        }
+                    }
+
+                    break;
+                }
+            }
+        }
+
+        features
+    }
+
+    // The function returns `Error` (a.k.a. "incompatible"), when the CPUID features from `src_vm_cpuid`
+    // is not a subset of those of the `dest_vm_cpuid`.
+    pub fn check_cpuid_compatibility(
+        src_vm_cpuid: &CpuId,
+        dest_vm_cpuid: &CpuId,
+    ) -> Result<(), Error> {
+        let feature_entry_list = &Self::checked_feature_entry_list();
+        let src_vm_features = Self::get_features_from_cpuid(src_vm_cpuid, feature_entry_list);
+        let dest_vm_features = Self::get_features_from_cpuid(dest_vm_cpuid, feature_entry_list);
+
+        // Loop on feature bit and check if the 'source vm' feature is a subset
+        // of those of the 'destination vm' feature
+        let mut compatible = true;
+        for (i, (src_vm_feature, dest_vm_feature)) in src_vm_features
+            .iter()
+            .zip(dest_vm_features.iter())
+            .enumerate()
+        {
+            let entry = &feature_entry_list[i];
+            let entry_compatible;
+            match entry.compatible_check {
+                CpuidCompatibleCheck::BitwiseSubset => {
+                    let different_feature_bits = src_vm_feature ^ dest_vm_feature;
+                    let src_vm_feature_bits_only = different_feature_bits & src_vm_feature;
+                    entry_compatible = src_vm_feature_bits_only == 0;
+                }
+                CpuidCompatibleCheck::Equal => {
+                    entry_compatible = src_vm_feature == dest_vm_feature;
+                }
+                CpuidCompatibleCheck::NumNotGreater => {
+                    entry_compatible = src_vm_feature <= dest_vm_feature;
+                }
+            };
+            if !entry_compatible {
+                error!(
+                    "Detected incompatible CPUID entry: leaf={:#02x} (subleaf={:#02x}), register='{:?}', \
+                    compatilbe_check='{:?}', source VM feature='{:#04x}', destination VM feature'{:#04x}'.",
+                    entry.function, entry.index, entry.feature_reg,
+                    entry.compatible_check, src_vm_feature, dest_vm_feature
+                    );
+
+                compatible = false;
+            }
+        }
+
+        if compatible {
+            info!("No CPU incompatibility detected.");
+            Ok(())
+        } else {
+            Err(Error::CpuidCheckCompatibility)
+        }
+    }
+}
+
+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,
+) -> super::Result<CpuId> {
+    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: Some(TSC_DEADLINE_TIMER_ECX_BIT),
+            edx_bit: None,
+        },
+        // Patch hypervisor bit
+        CpuidPatch {
+            function: 1,
+            index: 0,
+            flags_bit: None,
+            eax_bit: None,
+            ebx_bit: None,
+            ecx_bit: Some(HYPERVISOR_ECX_BIT),
+            edx_bit: None,
+        },
+        // Enable MTRR feature
+        CpuidPatch {
+            function: 1,
+            index: 0,
+            flags_bit: None,
+            eax_bit: None,
+            ebx_bit: None,
+            ecx_bit: None,
+            edx_bit: Some(MTRR_EDX_BIT),
+        },
+    ];
+
+    // Supported CPUID
+    let mut cpuid = hypervisor.get_cpuid().map_err(Error::CpuidGetSupported)?;
+
+    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 {
+        update_cpuid_sgx(&mut cpuid, sgx_epc_sections)?;
+    }
+
+    // Update some existing CPUID
+    for entry in cpuid.as_mut_slice().iter_mut() {
+        match entry.function {
+            // Set CPU physical bits
+            0x8000_0008 => {
+                entry.eax = (entry.eax & 0xffff_ff00) | (phys_bits as u32 & 0xff);
+            }
+            // Disable KVM_FEATURE_ASYNC_PF_INT
+            // This is required until we find out why the asynchronous page
+            // fault is generating unexpected behavior when using interrupt
+            // mechanism.
+            // TODO: Re-enable KVM_FEATURE_ASYNC_PF_INT (#2277)
+            0x4000_0001 => {
+                entry.eax &= !(1 << KVM_FEATURE_ASYNC_PF_INT_BIT);
+
+                // These features are not supported by TDX
+                #[cfg(feature = "tdx")]
+                if tdx_enabled {
+                    entry.eax &= !(1 << KVM_FEATURE_CLOCKSOURCE_BIT
+                        | 1 << KVM_FEATURE_CLOCKSOURCE2_BIT
+                        | 1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT
+                        | 1 << KVM_FEATURE_ASYNC_PF_BIT
+                        | 1 << KVM_FEATURE_ASYNC_PF_VMEXIT_BIT
+                        | 1 << KVM_FEATURE_STEAL_TIME_BIT)
+                }
+            }
+            _ => {}
+        }
+    }
+
+    // Copy CPU identification string
+    for i in 0x8000_0002..=0x8000_0004 {
+        cpuid.retain(|c| c.function != i);
+        let leaf = unsafe { std::arch::x86_64::__cpuid(i) };
+        cpuid
+            .push(CpuIdEntry {
+                function: i,
+                eax: leaf.eax,
+                ebx: leaf.ebx,
+                ecx: leaf.ecx,
+                edx: leaf.edx,
+                ..Default::default()
+            })
+            .map_err(Error::CpuidIdentification)?;
+    }
+
+    if kvm_hyperv {
+        // Remove conflicting entries
+        cpuid.retain(|c| c.function != 0x4000_0000);
+        cpuid.retain(|c| c.function != 0x4000_0001);
+        // See "Hypervisor Top Level Functional Specification" for details
+        // Compliance with "Hv#1" requires leaves up to 0x4000_000a
+        cpuid
+            .push(CpuIdEntry {
+                function: 0x40000000,
+                eax: 0x4000000a, // Maximum cpuid leaf
+                ebx: 0x756e694c, // "Linu"
+                ecx: 0x564b2078, // "x KV"
+                edx: 0x7648204d, // "M Hv"
+                ..Default::default()
+            })
+            .map_err(Error::CpuidKvmHyperV)?;
+        cpuid
+            .push(CpuIdEntry {
+                function: 0x40000001,
+                eax: 0x31237648, // "Hv#1"
+                ..Default::default()
+            })
+            .map_err(Error::CpuidKvmHyperV)?;
+        cpuid
+            .push(CpuIdEntry {
+                function: 0x40000002,
+                eax: 0x3839,  // "Build number"
+                ebx: 0xa0000, // "Version"
+                ..Default::default()
+            })
+            .map_err(Error::CpuidKvmHyperV)?;
+        cpuid
+            .push(CpuIdEntry {
+                function: 0x4000_0003,
+                eax: 1 << 1 // AccessPartitionReferenceCounter
+                   | 1 << 2 // AccessSynicRegs
+                   | 1 << 3 // AccessSyntheticTimerRegs
+                   | 1 << 9, // AccessPartitionReferenceTsc
+                edx: 1 << 3, // CPU dynamic partitioning
+                ..Default::default()
+            })
+            .map_err(Error::CpuidKvmHyperV)?;
+        cpuid
+            .push(CpuIdEntry {
+                function: 0x4000_0004,
+                eax: 1 << 5, // Recommend relaxed timing
+                ..Default::default()
+            })
+            .map_err(Error::CpuidKvmHyperV)?;
+        for i in 0x4000_0005..=0x4000_000a {
+            cpuid
+                .push(CpuIdEntry {
+                    function: i,
+                    ..Default::default()
+                })
+                .map_err(Error::CpuidKvmHyperV)?;
+        }
+    }
+
+    Ok(cpuid)
+}
+
 pub fn configure_vcpu(
     fd: &Arc<dyn hypervisor::Vcpu>,
     id: u8,
@@ -316,7 +729,7 @@ pub fn configure_vcpu(
     cpuid: CpuId,
     kvm_hyperv: bool,
 ) -> super::Result<()> {
-    // Per vCPU CPUID changes; common are handled via CpuManager::generate_common_cpuid()
+    // 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));
@@ -613,7 +1026,7 @@ pub fn get_host_cpu_phys_bits() -> u8 {
     }
 }
 
-pub fn update_cpuid_topology(
+fn update_cpuid_topology(
     cpuid: &mut CpuId,
     threads_per_core: u8,
     cores_per_die: u8,
@@ -678,7 +1091,7 @@ pub fn update_cpuid_topology(
 
 // The goal is to update the CPUID sub-leaves to reflect the number of EPC
 // sections exposed to the guest.
-pub fn update_cpuid_sgx(cpuid: &mut CpuId, epc_sections: Vec<SgxEpcSection>) -> Result<(), Error> {
+fn update_cpuid_sgx(cpuid: &mut CpuId, epc_sections: Vec<SgxEpcSection>) -> Result<(), Error> {
     // Something's wrong if there's no EPC section.
     if epc_sections.is_empty() {
         return Err(Error::NoSgxEpcSection);

arch/src/x86_64/tdx/mod.rs

@@ -144,6 +144,7 @@ unsafe impl ByteValued for HobHeader {}
 struct HobHandoffInfoTable {
     header: HobHeader,
     version: u32,
+    boot_mode: u32,
     efi_memory_top: u64,
     efi_memory_bottom: u64,
     efi_free_memory_top: u64,
@@ -218,6 +219,7 @@ impl TdHob {
                 reserved: 0,
             },
             version: 0x9,
+            boot_mode: 0,
             efi_memory_top: 0,
             efi_memory_bottom: 0,
             efi_free_memory_top: 0,
@@ -277,10 +279,10 @@ impl TdHob {
             },
             /* TODO:
              * QEMU currently fills it in like this:
-             * EFI_RESOURCE_ATTRIBUTE_PRESENT | EFI_RESOURCE_ATTRIBUTE_INITIALIZED | EFI_RESOURCE_ATTRIBUTE_TESTED
+             * EFI_RESOURCE_ATTRIBUTE_PRESENT | EFI_RESOURCE_ATTRIBUTE_INITIALIZED | EFI_RESOURCE_ATTRIBUTE_ENCRYPTED | EFI_RESOURCE_ATTRIBUTE_TESTED
              * which differs from the spec (due to TDVF implementation issue?)
              */
-            0x7,
+            0x04000007,
         )
     }
 

block_util/Cargo.toml

@@ -9,15 +9,16 @@ default = []
 io_uring = []
 
 [dependencies]
-io-uring = ">=0.4.0"
-libc = "0.2.96"
+io-uring = "0.5.2"
+libc = "0.2.101"
 log = "0.4.14"
 qcow = { path = "../qcow" }
-thiserror = "1.0"
+thiserror = "1.0.29"
 versionize = "0.1.6"
 versionize_derive = "0.1.4"
-virtio-bindings = { version = "0.1", features = ["virtio-v5_0_0"]}
-vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+vhdx = { path = "../vhdx" }
+virtio-bindings = { version = "0.1.0", features = ["virtio-v5_0_0"] }
+vm-memory = { version = "0.6.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-virtio = { path = "../vm-virtio" }
-vmm-sys-util = ">=0.3.1"
+vmm-sys-util = "0.8.0"
 

block_util/src/lib.rs

@@ -18,6 +18,7 @@ pub mod qcow_sync;
 pub mod raw_async;
 pub mod raw_sync;
 pub mod vhd;
+pub mod vhdx_sync;
 
 use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult, DiskFileError, DiskFileResult};
 #[cfg(feature = "io_uring")]
@@ -187,8 +188,8 @@ impl Request {
         }
 
         let mut req = Request {
-            request_type: request_type(&mem, avail_desc.addr)?,
-            sector: sector(&mem, avail_desc.addr)?,
+            request_type: request_type(mem, avail_desc.addr)?,
+            sector: sector(mem, avail_desc.addr)?,
             data_descriptors: Vec::new(),
             status_addr: GuestAddress(0),
             writeback: true,
@@ -288,7 +289,7 @@ impl Request {
                     if (*data_len as usize) < disk_id.len() {
                         return Err(ExecuteError::BadRequest(Error::InvalidOffset));
                     }
-                    mem.write_slice(&disk_id.as_slice(), *data_addr)
+                    mem.write_slice(disk_id.as_slice(), *data_addr)
                         .map_err(ExecuteError::Write)?;
                 }
                 RequestType::Unsupported(t) => return Err(ExecuteError::Unsupported(t)),
@@ -602,9 +603,11 @@ pub enum ImageType {
     FixedVhd,
     Qcow2,
     Raw,
+    Vhdx,
 }
 
 const QCOW_MAGIC: u32 = 0x5146_49fb;
+const VHDX_SIGN: u64 = 0x656C_6966_7864_6876;
 
 /// Determine image type through file parsing.
 pub fn detect_image_type(f: &mut File) -> std::io::Result<ImageType> {
@@ -623,6 +626,8 @@ pub fn detect_image_type(f: &mut File) -> std::io::Result<ImageType> {
         ImageType::Qcow2
     } else if vhd::is_fixed_vhd(f)? {
         ImageType::FixedVhd
+    } else if u64::from_le_bytes(s.data[0..8].try_into().unwrap()) == VHDX_SIGN {
+        ImageType::Vhdx
     } else {
         ImageType::Raw
     };

block_util/src/qcow_sync.rs

@@ -4,7 +4,7 @@
 
 use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileResult};
 use crate::{disk_size, fsync_sync, read_vectored_sync, write_vectored_sync};
-use qcow::{QcowFile, RawFile};
+use qcow::{QcowFile, RawFile, Result as QcowResult};
 use std::fs::File;
 use std::sync::{Arc, Mutex};
 use vmm_sys_util::eventfd::EventFd;
@@ -15,12 +15,11 @@ pub struct QcowDiskSync {
 }
 
 impl QcowDiskSync {
-    pub fn new(file: File, direct_io: bool) -> Self {
-        QcowDiskSync {
-            qcow_file: QcowFile::from(RawFile::new(file, direct_io))
-                .expect("Failed creating QcowFile"),
+    pub fn new(file: File, direct_io: bool) -> QcowResult<Self> {
+        Ok(QcowDiskSync {
+            qcow_file: QcowFile::from(RawFile::new(file, direct_io))?,
             semaphore: Arc::new(Mutex::new(())),
-        }
+        })
     }
 }
 

block_util/src/vhd.rs

@@ -175,7 +175,7 @@ mod tests {
         let mut disk_file: File = TempFile::new().unwrap().into_file();
         disk_file.set_len(0x1000_0200).unwrap();
         disk_file.seek(SeekFrom::Start(0x1000_0000)).unwrap();
-        disk_file.write_all(&footer).unwrap();
+        disk_file.write_all(footer).unwrap();
 
         testfn(disk_file); // File closed when the function exits.
     }

block_util/src/vhdx_sync.rs

@@ -0,0 +1,113 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+
+use crate::async_io::{AsyncIo, AsyncIoResult, DiskFile, DiskFileError, DiskFileResult};
+use crate::{fsync_sync, read_vectored_sync, write_vectored_sync};
+use std::fs::File;
+use std::ops::DerefMut;
+use std::sync::{Arc, Mutex};
+use vhdx::vhdx::{Result as VhdxResult, Vhdx};
+use vmm_sys_util::eventfd::EventFd;
+
+pub struct VhdxDiskSync {
+    vhdx_file: Arc<Mutex<Vhdx>>,
+    semaphore: Arc<Mutex<()>>,
+}
+
+impl VhdxDiskSync {
+    pub fn new(f: File) -> VhdxResult<Self> {
+        let vhdx = Vhdx::new(f)?;
+        let vhdx_file = Arc::new(Mutex::new(vhdx));
+
+        Ok(VhdxDiskSync {
+            vhdx_file,
+            semaphore: Arc::new(Mutex::new(())),
+        })
+    }
+}
+
+impl DiskFile for VhdxDiskSync {
+    fn size(&mut self) -> DiskFileResult<u64> {
+        Ok(self.vhdx_file.lock().unwrap().virtual_disk_size())
+    }
+
+    fn new_async_io(&self, _ring_depth: u32) -> DiskFileResult<Box<dyn AsyncIo>> {
+        Ok(Box::new(
+            VhdxSync::new(self.vhdx_file.clone(), self.semaphore.clone())
+                .map_err(DiskFileError::NewAsyncIo)?,
+        ) as Box<dyn AsyncIo>)
+    }
+}
+
+pub struct VhdxSync {
+    vhdx_file: Arc<Mutex<Vhdx>>,
+    eventfd: EventFd,
+    completion_list: Vec<(u64, i32)>,
+    semaphore: Arc<Mutex<()>>,
+}
+
+impl VhdxSync {
+    pub fn new(vhdx_file: Arc<Mutex<Vhdx>>, semaphore: Arc<Mutex<()>>) -> std::io::Result<Self> {
+        Ok(VhdxSync {
+            vhdx_file,
+            eventfd: EventFd::new(libc::EFD_NONBLOCK)?,
+            completion_list: Vec::new(),
+            semaphore,
+        })
+    }
+}
+
+impl AsyncIo for VhdxSync {
+    fn notifier(&self) -> &EventFd {
+        &self.eventfd
+    }
+
+    fn read_vectored(
+        &mut self,
+        offset: libc::off_t,
+        iovecs: Vec<libc::iovec>,
+        user_data: u64,
+    ) -> AsyncIoResult<()> {
+        read_vectored_sync(
+            offset,
+            iovecs,
+            user_data,
+            self.vhdx_file.lock().unwrap().deref_mut(),
+            &self.eventfd,
+            &mut self.completion_list,
+            &mut self.semaphore,
+        )
+    }
+
+    fn write_vectored(
+        &mut self,
+        offset: libc::off_t,
+        iovecs: Vec<libc::iovec>,
+        user_data: u64,
+    ) -> AsyncIoResult<()> {
+        write_vectored_sync(
+            offset,
+            iovecs,
+            user_data,
+            self.vhdx_file.lock().unwrap().deref_mut(),
+            &self.eventfd,
+            &mut self.completion_list,
+            &mut self.semaphore,
+        )
+    }
+
+    fn fsync(&mut self, user_data: Option<u64>) -> AsyncIoResult<()> {
+        fsync_sync(
+            user_data,
+            self.vhdx_file.lock().unwrap().deref_mut(),
+            &self.eventfd,
+            &mut self.completion_list,
+            &mut self.semaphore,
+        )
+    }
+
+    fn complete(&mut self) -> Vec<(u64, i32)> {
+        self.completion_list.drain(..).collect()
+    }
+}

devices/Cargo.toml

@@ -6,19 +6,19 @@ edition = "2018"
 
 [dependencies]
 acpi_tables = { path = "../acpi_tables", optional = true }
-anyhow = "1.0"
+anyhow = "1.0.43"
 arch = { path = "../arch" }
-bitflags = ">=1.2.1"
+bitflags = "1.3.2"
 byteorder = "1.4.3"
-epoll = ">=4.0.1"
-libc = "0.2.96"
+epoll = "4.3.1"
+libc = "0.2.101"
 log = "0.4.14"
 versionize = "0.1.6"
 versionize_derive = "0.1.4"
 vm-device = { path = "../vm-device" }
-vm-memory = "0.5.0"
+vm-memory = "0.6.0"
 vm-migration = { path = "../vm-migration" }
-vmm-sys-util = ">=0.3.1"
+vmm-sys-util = "0.8.0"
 
 [features]
 default = []

devices/src/acpi.rs

@@ -41,7 +41,7 @@ impl BusDevice for AcpiShutdownDevice {
 
     fn write(&mut self, _base: u64, _offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data[0] == 1 {
-            debug!("ACPI Reboot signalled");
+            info!("ACPI Reboot signalled");
             if let Err(e) = self.reset_evt.write(1) {
                 error!("Error triggering ACPI reset event: {}", e);
             }
@@ -51,7 +51,7 @@ impl BusDevice for AcpiShutdownDevice {
         const SLEEP_STATUS_EN_BIT: u8 = 5;
         const SLEEP_VALUE_BIT: u8 = 2;
         if data[0] == (S5_SLEEP_VALUE << SLEEP_VALUE_BIT) | (1 << SLEEP_STATUS_EN_BIT) {
-            debug!("ACPI Shutdown signalled");
+            info!("ACPI Shutdown signalled");
             if let Err(e) = self.exit_evt.write(1) {
                 error!("Error triggering ACPI shutdown event: {}", e);
             }
@@ -62,7 +62,7 @@ impl BusDevice for AcpiShutdownDevice {
 
 /// A device for handling ACPI GED event generation
 pub struct AcpiGedDevice {
-    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt: Arc<dyn InterruptSourceGroup>,
     notification_type: AcpiNotificationFlags,
     ged_irq: u32,
     address: GuestAddress,
@@ -70,7 +70,7 @@ pub struct AcpiGedDevice {
 
 impl AcpiGedDevice {
     pub fn new(
-        interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+        interrupt: Arc<dyn InterruptSourceGroup>,
         ged_irq: u32,
         address: GuestAddress,
     ) -> AcpiGedDevice {

devices/src/gic.rs

@@ -26,7 +26,7 @@ pub const IRQ_LEGACY_COUNT: usize = 32;
 //   1. Move Gic*.rs from arch/ folder here.
 //   2. Move this file and ioapic.rs to arch/, as they are architecture specific.
 pub struct Gic {
-    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
     gic_device: Option<Arc<Mutex<Box<dyn GicDevice>>>>,
 }
 

devices/src/ioapic.rs

@@ -134,7 +134,7 @@ pub struct Ioapic {
     reg_entries: [RedirectionTableEntry; NUM_IOAPIC_PINS],
     used_entries: [bool; NUM_IOAPIC_PINS],
     apic_address: GuestAddress,
-    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
 }
 
 #[derive(Versionize)]

devices/src/legacy/cmos.rs

@@ -2,12 +2,16 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
-use libc::{clock_gettime, gmtime_r, time_t, timespec, tm, CLOCK_REALTIME};
+use libc::{clock_gettime, gmtime_r, timespec, tm, CLOCK_REALTIME};
 use std::cmp::min;
 use std::mem;
 use std::sync::{Arc, Barrier};
 use vm_device::BusDevice;
 
+// https://github.com/rust-lang/libc/issues/1848
+#[cfg_attr(target_env = "musl", allow(deprecated))]
+use libc::time_t;
+
 const INDEX_MASK: u8 = 0x7f;
 const INDEX_OFFSET: u64 = 0x0;
 const DATA_OFFSET: u64 = 0x1;
@@ -85,6 +89,8 @@ impl BusDevice for Cmos {
                     let mut timespec: timespec = mem::zeroed();
                     clock_gettime(CLOCK_REALTIME, &mut timespec as *mut _);
 
+                    // https://github.com/rust-lang/libc/issues/1848
+                    #[cfg_attr(target_env = "musl", allow(deprecated))]
                     let now: time_t = timespec.tv_sec;
                     let mut tm: tm = mem::zeroed();
                     gmtime_r(&now, &mut tm as *mut _);

devices/src/legacy/gpio_pl061.rs

@@ -86,7 +86,7 @@ pub struct Gpio {
     // Mode Control Select Register
     afsel: u32,
     // GPIO irq_field
-    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt: Arc<dyn InterruptSourceGroup>,
 }
 
 #[derive(Versionize)]
@@ -106,7 +106,7 @@ impl VersionMapped for GpioState {}
 
 impl Gpio {
     /// Constructs an PL061 GPIO device.
-    pub fn new(id: String, interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Self {
+    pub fn new(id: String, interrupt: Arc<dyn InterruptSourceGroup>) -> Self {
         Self {
             id,
             data: 0,
@@ -297,7 +297,7 @@ impl BusDevice for Gpio {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() <= 4 {
-            let value = read_le_u32(&data);
+            let value = read_le_u32(data);
             if let Err(e) = self.handle_write(offset, value) {
                 warn!("Failed to write to GPIO PL061 device: {}", e);
             }
@@ -376,14 +376,14 @@ mod tests {
         let intr_evt = EventFd::new(libc::EFD_NONBLOCK).unwrap();
         let mut gpio = Gpio::new(
             String::from(GPIO_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
         );
         let mut data = [0; 4];
 
         // Read and write to the GPIODIR register.
         // Set pin 0 output pin.
         write_le_u32(&mut data, 1);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIODIR, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -391,8 +391,8 @@ mod tests {
         // Read and write to the GPIODATA register.
         write_le_u32(&mut data, 1);
         // Set pin 0 high.
-        let offset = 0x00000004 as u64;
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, offset, &mut data);
+        let offset = 0x00000004_u64;
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, offset, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, offset, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -400,7 +400,7 @@ mod tests {
         // Read and write to the GPIOIS register.
         // Configure pin 0 detecting level interrupt.
         write_le_u32(&mut data, 1);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIS, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -408,7 +408,7 @@ mod tests {
         // Read and write to the GPIOIBE register.
         // Configure pin 1 detecting both falling and rising edges.
         write_le_u32(&mut data, 2);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIBE, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 2);
@@ -416,7 +416,7 @@ mod tests {
         // Read and write to the GPIOIEV register.
         // Configure pin 2 detecting both falling and rising edges.
         write_le_u32(&mut data, 4);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIEV, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 4);
@@ -425,12 +425,12 @@ mod tests {
         // Configure pin 0...2 capable of triggering their individual interrupts
         // and then the combined GPIOINTR line.
         write_le_u32(&mut data, 7);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIE, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 7);
 
-        let mask = 0x00000002 as u32;
+        let mask = 0x00000002_u32;
         // emulate an rising pulse in pin 1.
         gpio.data |= !(gpio.data & mask) & mask;
         gpio.pl061_internal_update();
@@ -443,14 +443,14 @@ mod tests {
         // Read and Write to the GPIOIC register.
         // clear interrupt in pin 1.
         write_le_u32(&mut data, 2);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &data);
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIOIC, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 2);
 
         // Attempts to write beyond the writable space.
         write_le_u32(&mut data, 0);
-        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &mut data);
+        gpio.write(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &data);
 
         let mut data = [0; 4];
         gpio.read(LEGACY_GPIO_MAPPED_IO_START, GPIO_ID_LOW, &mut data);

devices/src/legacy/i8042.rs

@@ -34,7 +34,7 @@ impl BusDevice for I8042Device {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() == 1 && data[0] == 0xfe && offset == 3 {
-            debug!("i8042 reset signalled");
+            info!("i8042 reset signalled");
             if let Err(e) = self.reset_evt.write(1) {
                 error!("Error triggering i8042 reset event: {}", e);
             }

devices/src/legacy/rtc_pl031.rs

@@ -224,12 +224,12 @@ pub struct Rtc {
     load: u32,
     imsc: u32,
     ris: u32,
-    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt: Arc<dyn InterruptSourceGroup>,
 }
 
 impl Rtc {
     /// Constructs an AMBA PL031 RTC device.
-    pub fn new(interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Self {
+    pub fn new(interrupt: Arc<dyn InterruptSourceGroup>) -> Self {
         Self {
             // This is used only for duration measuring purposes.
             previous_now: Instant::now(),
@@ -328,7 +328,7 @@ impl BusDevice for Rtc {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() <= 4 {
-            let v = read_le_u32(&data);
+            let v = read_le_u32(data);
             if let Err(e) = self.handle_write(offset, v) {
                 warn!("Failed to write to RTC PL031 device: {}", e);
             }
@@ -450,14 +450,12 @@ mod tests {
     fn test_rtc_read_write_and_event() {
         let intr_evt = EventFd::new(libc::EFD_NONBLOCK).unwrap();
 
-        let mut rtc = Rtc::new(Arc::new(Box::new(TestInterrupt::new(
-            intr_evt.try_clone().unwrap(),
-        ))));
+        let mut rtc = Rtc::new(Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())));
         let mut data = [0; 4];
 
         // Read and write to the MR register.
         write_le_u32(&mut data, 123);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCMR, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCMR, &data);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCMR, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 123);
@@ -466,7 +464,7 @@ mod tests {
         let v = get_time(ClockType::Real);
         write_le_u32(&mut data, (v / NANOS_PER_SECOND) as u32);
         let previous_now_before = rtc.previous_now;
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCLR, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCLR, &data);
 
         assert!(rtc.previous_now > previous_now_before);
 
@@ -478,7 +476,7 @@ mod tests {
         // Test with non zero value.
         let non_zero = 1;
         write_le_u32(&mut data, non_zero);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &data);
         // The interrupt line should be on.
         assert!(rtc.interrupt.notifier(0).unwrap().read().unwrap() == 1);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
@@ -487,14 +485,14 @@ mod tests {
 
         // Now test with 0.
         write_le_u32(&mut data, 0);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &data);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCIMSC, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(0, v);
 
         // Read and write to the ICR register.
         write_le_u32(&mut data, 1);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCICR, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCICR, &data);
         // The interrupt line should be on.
         assert!(rtc.interrupt.notifier(0).unwrap().read().unwrap() > 1);
         let v_before = read_le_u32(&data);
@@ -506,7 +504,7 @@ mod tests {
 
         // Attempts to turn off the RTC should not go through.
         write_le_u32(&mut data, 0);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCCR, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, RTCCR, &data);
         rtc.read(LEGACY_RTC_MAPPED_IO_START, RTCCR, &mut data);
         let v = read_le_u32(&data);
         assert_eq!(v, 1);
@@ -514,7 +512,7 @@ mod tests {
         // Attempts to write beyond the writable space. Using here the space used to read
         // the CID and PID from.
         write_le_u32(&mut data, 0);
-        rtc.write(LEGACY_RTC_MAPPED_IO_START, AMBA_ID_LOW, &mut data);
+        rtc.write(LEGACY_RTC_MAPPED_IO_START, AMBA_ID_LOW, &data);
         // However, reading from the AMBA_ID_LOW should succeed upon read.
 
         let mut data = [0; 4];

devices/src/legacy/serial.rs

@@ -63,7 +63,7 @@ pub struct Serial {
     id: String,
     interrupt_enable: u8,
     interrupt_identification: u8,
-    interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt: Arc<dyn InterruptSourceGroup>,
     line_control: u8,
     line_status: u8,
     modem_control: u8,
@@ -91,7 +91,7 @@ impl VersionMapped for SerialState {}
 impl Serial {
     pub fn new(
         id: String,
-        interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+        interrupt: Arc<dyn InterruptSourceGroup>,
         out: Option<Box<dyn io::Write + Send>>,
     ) -> Serial {
         Serial {
@@ -113,14 +113,14 @@ impl Serial {
     /// Constructs a Serial port ready for output.
     pub fn new_out(
         id: String,
-        interrupt: Arc<Box<dyn InterruptSourceGroup>>,
+        interrupt: Arc<dyn InterruptSourceGroup>,
         out: Box<dyn io::Write + Send>,
     ) -> Serial {
         Self::new(id, interrupt, Some(out))
     }
 
     /// Constructs a Serial port with no connected output.
-    pub fn new_sink(id: String, interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Serial {
+    pub fn new_sink(id: String, interrupt: Arc<dyn InterruptSourceGroup>) -> Serial {
         Self::new(id, interrupt, None)
     }
 
@@ -370,7 +370,7 @@ mod tests {
         let serial_out = SharedBuffer::new();
         let mut serial = Serial::new_out(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
             Box::new(serial_out.clone()),
         );
 
@@ -390,7 +390,7 @@ mod tests {
         let serial_out = SharedBuffer::new();
         let mut serial = Serial::new_out(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
             Box::new(serial_out),
         );
 
@@ -427,7 +427,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
         );
 
         // write 1 to the interrupt event fd, so that read doesn't block in case the event fd
@@ -449,7 +449,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
         );
 
         serial.write(0, LCR as u64, &[LCR_DLAB_BIT]);
@@ -470,7 +470,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
         );
 
         serial.write(0, MCR as u64, &[MCR_LOOP_BIT]);
@@ -496,7 +496,7 @@ mod tests {
         let intr_evt = EventFd::new(0).unwrap();
         let mut serial = Serial::new_sink(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
         );
 
         serial.write(0, SCR as u64, &[0x12]);

devices/src/legacy/uart_pl011.rs

@@ -86,7 +86,7 @@ pub struct Pl011 {
     ifl: u32,
     read_count: u32,
     read_trigger: u32,
-    irq: Arc<Box<dyn InterruptSourceGroup>>,
+    irq: Arc<dyn InterruptSourceGroup>,
     out: Option<Box<dyn io::Write + Send>>,
 }
 
@@ -114,7 +114,7 @@ impl Pl011 {
     /// Constructs an AMBA PL011 UART device.
     pub fn new(
         id: String,
-        irq: Arc<Box<dyn InterruptSourceGroup>>,
+        irq: Arc<dyn InterruptSourceGroup>,
         out: Option<Box<dyn io::Write + Send>>,
     ) -> Self {
         Self {
@@ -341,7 +341,7 @@ impl BusDevice for Pl011 {
 
     fn write(&mut self, _base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
         if data.len() <= 4 {
-            let v = read_le_u32(&data);
+            let v = read_le_u32(data);
             if let Err(e) = self.handle_write(offset, v) {
                 warn!("Failed to write to PL011 device: {}", e);
             }
@@ -440,7 +440,7 @@ mod tests {
         let pl011_out = SharedBuffer::new();
         let mut pl011 = Pl011::new(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
             Some(Box::new(pl011_out.clone())),
         );
 
@@ -460,7 +460,7 @@ mod tests {
         let pl011_out = SharedBuffer::new();
         let mut pl011 = Pl011::new(
             String::from(SERIAL_NAME),
-            Arc::new(Box::new(TestInterrupt::new(intr_evt.try_clone().unwrap()))),
+            Arc::new(TestInterrupt::new(intr_evt.try_clone().unwrap())),
             Some(Box::new(pl011_out)),
         );
 

docs/api.md

@@ -78,27 +78,29 @@ Shut the VMM down                   | `/vmm.shutdown` | N/A          | N/A
 
 #### Virtual Machine (VM) Actions
 
-Action                             | Endpoint            | Request Body              | Response Body            | Prerequisites
------------------------------------|---------------------|---------------------------|--------------------------|---------------------------
-Create the VM                      | `/vm.create`        | `/schemas/VmConfig`       | N/A                      | The VM is not created yet
-Delete the VM                      | `/vm.delete`        | N/A                       | N/A                      | N/A
-Boot the VM                        | `/vm.boot`          | N/A                       | N/A                      | The VM is created but not booted
-Shut the VM down                   | `/vm.shutdown`      | N/A                       | N/A                      | The VM is booted
-Reboot the VM                      | `/vm.reboot`        | N/A                       | N/A                      | The VM is booted
-Pause the VM                       | `/vm.pause`         | N/A                       | N/A                      | The VM is booted
-Resume the VM                      | `/vm.resume`        | N/A                       | N/A                      | The VM is paused
-Add/remove CPUs to/from the VM     | `/vm.resize`        | `/schemas/VmResize`       | N/A                      | The VM is booted
-Add/remove memory from the VM      | `/vm.resize`        | `/schemas/VmResize`       | N/A                      | The VM is booted
-Add/remove memory from a zone      | `/vm.resize-zone`   | `/schemas/VmResizeZone`   | N/A                      | The VM is booted
-Dump the VM information            | `/vm.info`          | N/A                       | `/schemas/VmInfo`        | The VM is created
-Add VFIO PCI device to the VM      | `/vm.add-device`    | `/schemas/VmAddDevice`    | `/schemas/PciDeviceInfo` | The VM is booted
-Add disk device to the VM          | `/vm.add-disk`      | `/schemas/DiskConfig`     | `/schemas/PciDeviceInfo` | The VM is booted
-Add fs device to the VM            | `/vm.add-fs`        | `/schemas/FsConfig`       | `/schemas/PciDeviceInfo` | The VM is booted
-Add pmem device to the VM          | `/vm.add-pmem`      | `/schemas/PmemConfig`     | `/schemas/PciDeviceInfo` | The VM is booted
-Add network device to the VM       | `/vm.add-net`       | `/schemas/NetConfig`      | `/schemas/PciDeviceInfo` | The VM is booted
-Add vsock device to the VM         | `/vm.add-vsock`     | `/schemas/VsockConfig`    | `/schemas/PciDeviceInfo` | The VM is booted
-Remove device from the VM          | `/vm.remove-device` | `/schemas/VmRemoveDevice` | N/A                      | The VM is booted
-Dump the VM counters               | `/vm.counters`      | N/A                       | `/schemas/VmCounters`    | The VM is booted
+Action                             | Endpoint             | Request Body              | Response Body            | Prerequisites
+-----------------------------------|----------------------|---------------------------|--------------------------|---------------------------
+Create the VM                      | `/vm.create`         | `/schemas/VmConfig`       | N/A                      | The VM is not created yet
+Delete the VM                      | `/vm.delete`         | N/A                       | N/A                      | N/A
+Boot the VM                        | `/vm.boot`           | N/A                       | N/A                      | The VM is created but not booted
+Shut the VM down                   | `/vm.shutdown`       | N/A                       | N/A                      | The VM is booted
+Reboot the VM                      | `/vm.reboot`         | N/A                       | N/A                      | The VM is booted
+Trigger power button of the VM     | `/vm.power-button`   | N/A                       | N/A                      | The VM is booted
+Pause the VM                       | `/vm.pause`          | N/A                       | N/A                      | The VM is booted
+Resume the VM                      | `/vm.resume`         | N/A                       | N/A                      | The VM is paused
+Add/remove CPUs to/from the VM     | `/vm.resize`         | `/schemas/VmResize`       | N/A                      | The VM is booted
+Add/remove memory from the VM      | `/vm.resize`         | `/schemas/VmResize`       | N/A                      | The VM is booted
+Add/remove memory from a zone      | `/vm.resize-zone`    | `/schemas/VmResizeZone`   | N/A                      | The VM is booted
+Dump the VM information            | `/vm.info`           | N/A                       | `/schemas/VmInfo`        | The VM is created
+Add VFIO PCI device to the VM      | `/vm.add-device`     | `/schemas/VmAddDevice`    | `/schemas/PciDeviceInfo` | The VM is booted
+Add disk device to the VM          | `/vm.add-disk`       | `/schemas/DiskConfig`     | `/schemas/PciDeviceInfo` | The VM is booted
+Add fs device to the VM            | `/vm.add-fs`         | `/schemas/FsConfig`       | `/schemas/PciDeviceInfo` | The VM is booted
+Add pmem device to the VM          | `/vm.add-pmem`       | `/schemas/PmemConfig`     | `/schemas/PciDeviceInfo` | The VM is booted
+Add network device to the VM       | `/vm.add-net`        | `/schemas/NetConfig`      | `/schemas/PciDeviceInfo` | The VM is booted
+Add userspace PCI device to the VM | `/vm.add-user-device`| `/schemas/VmAddUserDevice`| `/schemas/PciDeviceInfo` | The VM is booted
+Add vsock device to the VM         | `/vm.add-vsock`      | `/schemas/VsockConfig`    | `/schemas/PciDeviceInfo` | The VM is booted
+Remove device from the VM          | `/vm.remove-device`  | `/schemas/VmRemoveDevice` | N/A                      | The VM is booted
+Dump the VM counters               | `/vm.counters`       | N/A                       | `/schemas/VmCounters`    | The VM is booted
 
 ### REST API Examples
 

docs/arm64.md

@@ -1,58 +1,116 @@
-# How to build and run Cloud-hypervisor on AArch64
+# How to build and test Cloud Hypervisor on AArch64
 
-Cloud-hypervisor is partially enabled on AArch64 architecture.
-Although all features are not ready yet, you can begin to test Cloud-hypervisor on a AArch64 host by following this guide.
+This document introduces how to build and test Cloud Hypervisor on AArch64 servers. Currently Cloud Hypervisor cannot be tested on Raspberry PI. Because on AArch64, Cloud Hypervisor requires GICv3-ITS device for PCIe MSI interrupt handling. But GICv3-ITS has not been equipped on any Raspberry PI product so far.
+
+Now Cloud Hypervisor supports 2 ways of booting on AArch64: UEFI booting and direct-kernel booting. The document covers both of the ways.
+
+All the steps are based on Ubuntu. We use the Ubuntu cloud image for guest VM disk.
+
+## Getting started
+
+We create a folder to build and run Cloud Hypervisor at `$HOME/cloud-hypervisor`
+
+```shell
+$ export CLOUDH=$HOME/cloud-hypervisor
+$ mkdir $CLOUDH
+```
 
 ## Prerequisites
 
-On AArch64 machines, Cloud-hypervisor depends on an external library `libfdt-dev` for generating Flattened Device Tree (FDT).
+You need to install some prerequisite packages to build and test Cloud Hypervisor.
 
-The long-term plan is to replace `libfdt-dev` with some pure-Rust component to get rid of such dependency.
+### Tools
 
 ```bash
-sudo apt-get update
-sudo apt-get install libfdt-dev
+# Install rust tool chain
+$ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
+# Install the tools used for building guest kernel, EDK2 and converting guest disk
+$ sudo apt-get update
+$ sudo apt-get install git build-essential m4 bison flex uuid-dev qemu-utils
 ```
 
-## Build
-
-Using PCI devices requires GICv3-ITS for MSI messaging. GICv3-ITS is very common in modern servers.
+### Building Cloud Hypervisor
 
 ```bash
-cargo build --no-default-features --features kvm
+$ pushd $CLOUDH
+$ git clone https://github.com/cloud-hypervisor/cloud-hypervisor.git
+$ cd cloud-hypervisor
+$ cargo build
+$ popd
 ```
 
-## Image
+### Disk image
 
-Download kernel binary and rootfs image from AWS.
+Download the Ubuntu cloud image and convert the image type.
 
 ```bash
-wget https://s3.amazonaws.com/spec.ccfc.min/img/aarch64/ubuntu_with_ssh/fsfiles/xenial.rootfs.ext4 -O rootfs.ext4
-wget https://s3.amazonaws.com/spec.ccfc.min/img/aarch64/ubuntu_with_ssh/kernel/vmlinux.bin -O kernel.bin
+$ pushd $CLOUDH
+$ wget https://cloud-images.ubuntu.com/focal/current/focal-server-cloudimg-arm64.img
+$ qemu-img convert -p -f qcow2 -O raw focal-server-cloudimg-arm64.img focal-server-cloudimg-arm64.raw
+$ popd
 ```
 
-## Containerized build
+## UEFI booting
 
-If you want to build and test Cloud Hypervisor without having to install all the required dependencies, you can also turn to the development script: dev_cli.sh.
+This part introduces how to build EDK2 firmware and boot Cloud Hypervisor with it.
 
-To build the development container:
+### Building EDK2
 
 ```bash
-./scripts/dev_cli.sh build-container
+$ pushd $CLOUDH
+
+# Clone source code repos
+$ git clone --depth 1 https://github.com/tianocore/edk2.git -b master
+$ cd edk2
+$ git submodule update --init
+$ cd ..
+$ git clone --depth 1 https://github.com/tianocore/edk2-platforms.git -b master
+$ git clone --depth 1 https://github.com/acpica/acpica.git -b master
+
+# Build tools
+$ export PACKAGES_PATH="$PWD/edk2:$PWD/edk2-platforms"
+$ export IASL_PREFIX="$PWD/acpica/generate/unix/bin/"
+$ make -C acpica
+$ cd edk2/
+$ . edksetup.sh
+$ cd ..
+$ make -C edk2/BaseTools
+
+# Build EDK2
+$ build -a AARCH64 -t GCC5 -p ArmVirtPkg/ArmVirtCloudHv.dsc -b RELEASE
+
+$ popd
 ```
 
-To build Cloud-hypervisor in the container:
+If the build goes well, the EDK2 binary is available at `edk2/Build/ArmVirtCloudHv-AARCH64/RELEASE_GCC5/FV/CLOUDHV_EFI.fd`.
+
+### Booting the guest VM
 
 ```bash
-./scripts/dev_cli.sh build
+$ pushd $CLOUDH
+$ sudo RUST_BACKTRACE=1 $CLOUDH/cloud-hypervisor/target/debug/cloud-hypervisor --api-socket /tmp/cloud-hypervisor.sock --kernel $CLOUDH/edk2/edk2/Build/ArmVirtCloudHv-AARCH64/RELEASE_GCC5/FV/CLOUDHV_EFI.fd --disk path=$CLOUDH/focal-server-cloudimg-arm64.raw --cpus boot=4 --memory size=4096M --serial tty --console off --log-file log.log -vvv --net tap=,mac=12:34:56:78:90:01,ip=192.168.1.1,mask=255.255.255.0
+$ popd
 ```
 
-## Run
+## Direct-kernel booting
 
-Assuming you have built Cloud-hypervisor with the development container, a VM can be started with command:
+Alternativelly, you can build your own kernel for guest VM. This way, UEFI is not involved and ACPI cannot be enabled.
+
+### Building kernel
 
 ```bash
-sudo build/cargo_target/aarch64-unknown-linux-gnu/debug/cloud-hypervisor --kernel kernel.bin --disk path=rootfs.ext4 --cmdline "keep_bootcon console=hvc0 reboot=k panic=1 root=/dev/vda rw" --cpus boot=4 --memory size=512M --serial file=serial.log --log-file log.log -vvv
+$ pushd $CLOUDH
+$ git clone --depth 1 "https://github.com/cloud-hypervisor/linux.git" -b ch-5.12
+$ cd linux
+$ cp $CLOUDH/cloud-hypervisor/resources/linux-config-aarch64 .config
+$ make -j `nproc`
+$ popd
 ```
 
-If the build was done out of the container, replace the binary path with `target/debug/cloud-hypervisor`.
+### Booting the guest VM
+
+```bash
+$ pushd $CLOUDH
+$ sudo $CLOUDH/cloud-hypervisor/target/debug/cloud-hypervisor --api-socket /tmp/cloud-hypervisor.sock --kernel $CLOUDH/linux/arch/arm64/boot/Image --disk path=focal-server-cloudimg-arm64.raw --cmdline "keep_bootcon console=ttyAMA0 reboot=k panic=1 root=/dev/vda1 rw" --cpus boot=4 --memory size=4096M --serial tty --console off --log-file log.log -vvv --net "tap=,mac=,ip=,mask="
+$ popd
+```

docs/fuzzing.md

@@ -20,10 +20,10 @@ cargo install cargo-fuzz
 
 ## Running the fuzzers
 
-e.g. To run the `qcow` fuzzer using all available CPUs:
+e.g. To run the `block` fuzzer using all available CPUs:
 
 ```
-cargo fuzz run qcow -j `nproc`
+cargo fuzz run block -j `nproc`
 ```
 
 ## Adding a new fuzzer
@@ -32,4 +32,4 @@ cargo fuzz run qcow -j `nproc`
 cargo fuzz add <new_fuzzer>
 ```
 
-Inspiration for fuzzers can be found in [crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/+/refs/heads/master/fuzz/)
+Inspiration for fuzzers can be found in [crosvm](https://chromium.googlesource.com/chromiumos/platform/crosvm/+/refs/heads/master/fuzz/)

docs/intel_sgx.md

@@ -34,7 +34,7 @@ memory, the second one being 32MiB with no pre-allocated memory.
     --disk path=focal-server-cloudimg-amd64.raw \
     --kernel vmlinux \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
-    --sgx-epc size=64M,prefault=on size=32M,prefault=off
+    --sgx-epc id=epc0,size=64M,prefault=on id=epc1,size=32M,prefault=off
 ```
 
 Once booted, and assuming your guest kernel contains the patches from the

docs/live_migration.md

@@ -36,7 +36,7 @@ $ target/release/ch-remote --api-socket=/tmp/api1 send-migration unix:/tmp/sock
 
 When the above commands completed, the source VM should be successfully
 migrated to the destination VM. Now the destination VM is running while
-the source VM is paused.
+the source VM is terminated gracefully.
 
 ## Nested-VM Migration
 
@@ -136,4 +136,4 @@ 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
 migrated to the destination VM without interrupting our testing guest
 workload. Now the destination VM is running the testing guest workload
-while the source VM is paused.
+while the source VM is terminated gracefully.

docs/memory.md

@@ -24,7 +24,7 @@ struct MemoryConfig {
 ```
 
 ```
---memory <memory>	Memory parameters "size=<guest_memory_size>,mergeable=on|off,shared=on|off,hugepages=on|off,hotplug_method=acpi|virtio-mem,hotplug_size=<hotpluggable_memory_size>,hotplugged_size=<hotplugged_memory_size>"
+--memory <memory>	Memory parameters "size=<guest_memory_size>,mergeable=on|off,shared=on|off,hugepages=on|off,hugepage_size=<hugepage_size>,hotplug_method=acpi|virtio-mem,hotplug_size=<hotpluggable_memory_size>,hotplugged_size=<hotplugged_memory_size>"
 ```
 
 ### `size`
@@ -87,7 +87,9 @@ the guest will allocate hugepages as well. Another interesting use case is VFIO
 as it speeds up the VM's boot time since the amount of IOMMU mappings are
 reduced.
 
-The user is responsible for ensuring there are sufficient huge pages of the specified size for the VMM to use. Failure to do so may result in strange VMM behaviour.
+The user is responsible for ensuring there are sufficient huge pages of the specified size for the VMM to use.
+Failure to do so may result in strange VMM behaviour, e.g. error with `ReadKernelImage` is common.
+If there is a strange error with `hugepages` enabled, just disable it or check whether there are enough huge pages.
 
 By default this option is turned off.
 
@@ -343,15 +345,16 @@ it allows for specifying the distance between each NUMA node.
 
 ```rust
 struct NumaConfig {
-    id: u32,
+    guest_numa_id: u32,
     cpus: Option<Vec<u8>>,
     distances: Option<Vec<NumaDistance>>,
     memory_zones: Option<Vec<String>>,
+    sgx_epc_sections: Option<Vec<String>>,
 }
 ```
 
 ```
---numa <numa>	Settings related to a given NUMA node "id=<node_id>,cpus=<cpus_id>,distances=<list_of_distances_to_destination_nodes>,memory_zones=<list_of_memory_zones>"
+--numa <numa>	Settings related to a given NUMA node "guest_numa_id=<node_id>,cpus=<cpus_id>,distances=<list_of_distances_to_destination_nodes>,memory_zones=<list_of_memory_zones>,sgx_epc_sections=<list_of_sgx_epc_sections>"
 ```
 
 ### `guest_numa_id`
@@ -394,8 +397,7 @@ _Example_
 
 ```
 --cpus boot=8
---numa guest_numa_id=0,cpus=1-3:7
---numa guest_numa_id=1,cpus=0:4-6
+--numa guest_numa_id=0,cpus=1-3:7 guest_numa_id=1,cpus=0:4-6
 ```
 
 ### `distances`
@@ -420,9 +422,7 @@ 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
---numa 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`
@@ -441,13 +441,38 @@ Multiple values can be provided to define the list. Each value is a string
 referring to an existing memory zone identifier. Values are separated from
 each other with the `:` separator.
 
+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 guest_numa_id=1,memory_zones=mem0`
+
 _Example_
 
 ```
 --memory size=0
---memory-zone id=mem0,size=1G
---memory-zone 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`
+
+List of SGX EPC sections attached to the guest NUMA node identified by the
+`guest_numa_id` option. This allows for describing a list of SGX EPC sections
+which must be seen by the guest as belonging to the NUMA node `guest_numa_id`.
+
+Multiple values can be provided to define the list. Each value is a string
+referring to an existing SGX EPC section identifier. Values are separated from
+each other with the `:` separator.
+
+_Example_
+
+```
+--sgx-epc id=epc0,size=32M id=epc1,size=64M id=epc2,size=32M
+--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.

docs/uefi.md

@@ -41,19 +41,20 @@ CSM is a module that allows to boot legacy operating systems using the OVMF firm
 
 ```shell
 sudo apt-get update
-sudo apt-get install uuid-dev nasm iasl build-essential python3-distutils git
+sudo apt-get install uuid-dev nasm iasl build-essential python3-distutils git libncurses-dev
 
-git checkout https://github.com/cloud-hypervisor/seabios -b ch
+git clone https://github.com/cloud-hypervisor/seabios -b ch
 cd seabios
 make menuconfig
 # Enable `CONFIG_CSM` and `CONFIG_QEMU_HARDWARE`
+# Please make sure `python` is in your path
 make CONFIG_CSM=y CONFIG_QEMU_HARDWARE=y
 cd ..
 
 git clone https://github.com/cloud-hypervisor/edk2 -b ch
 cd edk2
 . edksetup.sh
-git submodule update --init
+git submodule update --init --recursive
 cp ../seabios/out/Csm16.bin OvmfPkg/Csm/Csm16/
 
 echo "ACTIVE_PLATFORM=OvmfPkg/OvmfCh.dsc" >> Conf/target.txt
@@ -61,7 +62,7 @@ echo "TARGET_ARCH=X64" >> Conf/target.txt
 echo "TOOL_CHAIN_TAG=GCC5" >> Conf/target.txt
 
 make -C ./BaseTools
-build
+build -DCSM_ENABLE
 
 ```
 

docs/vfio-user.md

@@ -0,0 +1,77 @@
+# Cloud Hypervisor VFIO-user HOWTO
+
+VFIO-user is an *experimental* protocol for allowing devices to be implemented in another process and communicate over a socket; ie.e VFIO-user is to VFIO as virtio is to vhost-user.
+
+The protocol is documented here: https://github.com/nutanix/libvfio-user/blob/master/docs/vfio-user.rst
+
+The Cloud Hypervisor support for such devices is *experimental*. Not all Cloud Hypervisor functionality is supported in particular: virtio-mem and iommu are not supported.
+
+## Usage
+
+The `--user-device socket=<path>` parameter is used to create a vfio-user device when creating the VM specifying the socket to connect to. The device can also be hotplugged with `ch-remote add-user-device socket=<path>`.
+
+## Example (GPIO device)
+
+There is a simple GPIO device included in the libvfio-user repository: https://github.com/nutanix/libvfio-user#gpio
+
+Run the example from the libvfio-user repository:
+
+```sh
+rm /tmp/vfio-user.sock
+./build/dbg/samples/gpio-pci-idio-16 -v /tmp/vfio-user.sock &
+```
+
+Start Cloud Hypervisor:
+
+```sh
+target/debug/cloud-hypervisor \
+    --memory size=1G,shared=on \
+    --disk path=~/images/focal-server-cloudimg-amd64.raw \
+    --kernel ~/src/linux/vmlinux \
+    --cmdline "root=/dev/vda1 console=hvc0" \
+    --user-device socket=/tmp/vfio-user.sock 
+```
+
+Inside the VM you can test the device with:
+
+```sh
+cat /sys/class/gpio/gpiochip480/base > /sys/class/gpio/export
+for ((i=0;i<12;i++)); do cat /sys/class/gpio/OUT0/value; done
+```
+
+## Example (NVMe device)
+
+Use SPDK: https://github.com/spdk/spdk
+
+Compile with `./configure --with-vfio-user`
+
+Create an NVMe controller listening on a vfio-user socket with a simple block device:
+
+```sh
+sudo scripts/setup.sh
+rm ~/images/test-disk.raw
+truncate ~/images/test-disk.raw -s 128M
+mkfs.ext4  ~/images/test-disk.raw
+sudo killall ./build/bin/nvmf_tgt
+sudo ./build/bin/nvmf_tgt -i 0 -e 0xFFFF -m 0x1 &
+sleep 2
+sudo ./scripts/rpc.py nvmf_create_transport -t VFIOUSER
+sudo rm -rf /tmp/nvme-vfio-user
+sudo mkdir -p /tmp/nvme-vfio-user
+sudo ./scripts/rpc.py bdev_aio_create ~/images/test-disk.raw test 512
+sudo ./scripts/rpc.py nvmf_create_subsystem nqn.2019-07.io.spdk:cnode -a -s test
+sudo ./scripts/rpc.py nvmf_subsystem_add_ns nqn.2019-07.io.spdk:cnode test
+sudo ./scripts/rpc.py nvmf_subsystem_add_listener nqn.2019-07.io.spdk:cnode -t VFIOUSER -a /tmp/nvme-vfio-user -s 0
+sudo chown $USER.$USER -R /tmp/nvme-vfio-user
+```
+
+Start Cloud Hypervisor:
+
+```sh
+target/debug/cloud-hypervisor \
+    --memory size=1G,shared=on \
+    --disk path=~/images/focal-server-cloudimg-amd64.raw \
+    --kernel ~/src/linux/vmlinux \
+    --cmdline "root=/dev/vda1 console=hvc0" \
+    --user-device socket=/tmp/nvme-vfio-user/cntrl 
+```

docs/windows.md

@@ -30,15 +30,15 @@ This step currently requires QEMU to install Windows onto the guest. QEMU is onl
 Preparing several command parts as these will be used in the follow up sections as well.
 
 ```shell
-IMG_FILE=windows-disk.qcow
+IMG_FILE=windows-disk.raw
 WIN_ISO_FILE=en_windows_server_version_2004_updated_may_2020_x64_dvd_1e7f1cfa.iso
 VIRTIO_ISO_FILE=virtio-win-0.1.185.iso
 OVMF_DIR=./FV
 ```
 
-Create an empty image file, `qcow` or `raw` is supported.
+Create an empty image file, `raw` is supported.
 ```shell
-qemu-img create -f qcow2 $IMG_FILE 30G
+qemu-img create -f raw $IMG_FILE 30G
 ```
 
 Begin the Windows installation process under QEMU
@@ -221,7 +221,7 @@ qemu-system-x86_64 \
 	-m 4G \
 	-cdrom ./$WIN_ISO_FILE \
 	-drive file=./$VIRTIO_ISO_FILE,index=0,media=cdrom
-	-drive if=none,id=root,file=./windbg-disk.qcow \
+	-drive if=none,id=root,file=./windbg-disk.raw \
 	-device virtio-blk-pci,drive=root,disable-legacy=on \
 	-device virtio-net-pci,netdev=mynet0,disable-legacy=on \
 	-netdev user,id=mynet0,net=192.168.178.0/24,host=192.168.178.1,dhcpstart=192.168.178.64,hostname=windbg-host \
@@ -280,7 +280,7 @@ qemu-system-x86_64 \
 	-cpu host \
 	-smp 1 \
 	-m 4G \
-	-drive if=none,id=root,file=./windbg-disk.qcow \
+	-drive if=none,id=root,file=./windbg-disk.raw \
 	-device virtio-blk-pci,drive=root,disable-legacy=on \
 	-serial tcp::4445,server,nowait \
 	-device virtio-net-pci,netdev=mynet0,disable-legacy=on \

event_monitor/Cargo.toml

@@ -5,7 +5,7 @@ authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 
 [dependencies]
-libc = "0.2.96"
-serde = {version = ">=1.0.27", features = ["rc"] }
-serde_derive = ">=1.0.27"
-serde_json = ">=1.0.9"
+libc = "0.2.101"
+serde = { version = "1.0.130", features = ["rc"] }
+serde_derive = "1.0.130"
+serde_json = "1.0.67"

fuzz/Cargo.lock

@@ -20,25 +20,28 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.40"
+version = "1.0.43"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28b2cd92db5cbd74e8e5028f7e27dd7aa3090e89e4f2a197cc7c8dfb69c7063b"
+checksum = "28ae2b3dec75a406790005a200b1bd89785afc02517a00ca99ecfe093ee9e6cf"
 
 [[package]]
 name = "api_client"
 version = "0.1.0"
+dependencies = [
+ "vmm-sys-util",
+]
 
 [[package]]
 name = "arbitrary"
-version = "1.0.1"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "237430fd6ed3740afe94eefcc278ae21e050285be882804e0d6e8695f0c94691"
+checksum = "577b08a4acd7b99869f863c50011b01eb73424ccc798ecd996f2e24817adfca7"
 
 [[package]]
 name = "arc-swap"
-version = "1.3.0"
+version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e906254e445520903e7fc9da4f709886c84ae4bc4ddaf0e093188d66df4dc820"
+checksum = "b5ab7d9e73059c86c36473f459b52adbd99c3554a4fec492caef460806006f00"
 
 [[package]]
 name = "arch"
@@ -47,6 +50,7 @@ dependencies = [
  "acpi_tables",
  "anyhow",
  "byteorder",
+ "fdt",
  "hypervisor",
  "libc",
  "linux-loader",
@@ -58,6 +62,7 @@ dependencies = [
  "vm-fdt",
  "vm-memory",
  "vm-migration",
+ "vmm-sys-util",
 ]
 
 [[package]]
@@ -82,9 +87,9 @@ dependencies = [
 
 [[package]]
 name = "bitflags"
-version = "1.2.1"
+version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf1de2fe8c75bc145a2f577add951f8134889b4795d47466a54a5c846d691693"
+checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "block_util"
@@ -97,6 +102,7 @@ dependencies = [
  "thiserror",
  "versionize",
  "versionize_derive",
+ "vhdx",
  "virtio-bindings",
  "vm-memory",
  "vm-virtio",
@@ -111,9 +117,9 @@ checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
 [[package]]
 name = "cc"
-version = "1.0.68"
+version = "1.0.70"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4a72c244c1ff497a746a7e1fb3d14bd08420ecda70c8f25c7112f2781652d787"
+checksum = "d26a6ce4b6a484fa3edb70f7efa6fc430fd2b87285fe8b84304fd0936faa0dc0"
 
 [[package]]
 name = "cfg-if"
@@ -139,7 +145,7 @@ dependencies = [
 
 [[package]]
 name = "cloud-hypervisor"
-version = "15.0.0"
+version = "17.0.0"
 dependencies = [
  "anyhow",
  "api_client",
@@ -150,7 +156,7 @@ dependencies = [
  "libc",
  "log",
  "option_parser",
- "seccomp",
+ "seccompiler",
  "serde_json",
  "signal-hook",
  "thiserror",
@@ -168,13 +174,23 @@ dependencies = [
  "libc",
  "libfuzzer-sys",
  "qcow",
- "seccomp",
+ "seccompiler",
+ "vhdx",
  "virtio-devices",
  "vm-memory",
  "vm-virtio",
  "vmm-sys-util",
 ]
 
+[[package]]
+name = "crc32c"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "210cdf933e6a81212bfabf90cd8762f471b5922e5f6b709547673ad8e04b9448"
+dependencies = [
+ "rustc_version",
+]
+
 [[package]]
 name = "crc64"
 version = "1.0.0"
@@ -222,10 +238,27 @@ dependencies = [
 ]
 
 [[package]]
-name = "hermit-abi"
-version = "0.1.18"
+name = "fdt"
+version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "322f4de77956e22ed0e5032c359a0f1273f1f7f0d79bfa3b8ffbc730d7fbcc5c"
+checksum = "b643857cf70949306b81d7e92cb9d47add673868edac9863c4a49c42feaf3f1e"
+
+[[package]]
+name = "getrandom"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7fcd999463524c52659517fe2cea98493cfe485d10565e7b0fb07dbba7ad2753"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
+[[package]]
+name = "hermit-abi"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
 dependencies = [
  "libc",
 ]
@@ -251,9 +284,9 @@ dependencies = [
 
 [[package]]
 name = "iced-x86"
-version = "1.11.3"
+version = "1.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6d907dfc273d9ed0da940e8145ceb77759056a1fb2110b44b83d1b203cddb906"
+checksum = "7383772b06135cede839b7270023b46403656a9148024886e721e82639d3f90e"
 dependencies = [
  "lazy_static",
  "static_assertions",
@@ -261,9 +294,9 @@ dependencies = [
 
 [[package]]
 name = "io-uring"
-version = "0.5.1"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb82832e05cc4ca298f198a8db108837b4f7b7b1248e3cba8e48f151aece80cf"
+checksum = "8d75829ed9377bab6c90039fe47b9d84caceb4b5063266142e21bcce6550cda8"
 dependencies = [
  "bitflags",
  "libc",
@@ -271,9 +304,9 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dd25036021b0de88a0aff6b850051563c6516d0bf53f8638938edbb9de732736"
+checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
 
 [[package]]
 name = "kvm-bindings"
@@ -304,9 +337,9 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
-version = "0.2.96"
+version = "0.2.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5600b4e6efc5421841a2138a6b082e07fe12f9aaa12783d50e5d13325b26b4fc"
+checksum = "3cb00336871be5ed2c8ed44b60ae9959dc5b9f08539422ed43f09e34ecaeba21"
 
 [[package]]
 name = "libfuzzer-sys"
@@ -340,7 +373,7 @@ dependencies = [
 [[package]]
 name = "micro_http"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#9b605a8b61df602cda62076d30d9f70307ea336f"
+source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#9517a300370a158a7af0996b7eebf040d171e1a4"
 dependencies = [
  "libc",
  "vmm-sys-util",
@@ -373,9 +406,9 @@ dependencies = [
 
 [[package]]
 name = "once_cell"
-version = "1.7.2"
+version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "af8b08b04175473088b46763e51ee54da5f9a164bc162f615b91bc179dbf15a3"
+checksum = "692fcb63b64b1758029e0a96ee63e049ce8c5948587f2f7208df04625e5f6b56"
 
 [[package]]
 name = "option_parser"
@@ -390,10 +423,12 @@ dependencies = [
  "hypervisor",
  "libc",
  "log",
+ "thiserror",
  "versionize",
  "versionize_derive",
  "vfio-bindings",
  "vfio-ioctls",
+ "vfio_user",
  "vm-allocator",
  "vm-device",
  "vm-memory",
@@ -403,9 +438,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.27"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f0d8caf72986c1a598726adc988bb5984792ef84f5ee5aa50209145ee8077038"
+checksum = "b9f5105d4fdaab20335ca9565e106a5d9b82b6219b5ba735731124ac6711d23d"
 dependencies = [
  "unicode-xid",
 ]
@@ -450,6 +485,15 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "rustc_version"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "138e3e0acb6c9fb258b19b67cb8abd63c00679d2851805ea151465464fe9030a"
+dependencies = [
+ "semver",
+]
+
 [[package]]
 name = "ryu"
 version = "1.0.5"
@@ -457,24 +501,39 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "71d301d4193d031abdd79ff7e3dd721168a9572ef3fe51a1517aba235bd8f86e"
 
 [[package]]
-name = "seccomp"
+name = "seccompiler"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/firecracker?tag=v0.24.4#8f44986a0e956a77f2b2324c12f73bec16130c82"
+source = "git+https://github.com/rust-vmm/seccompiler#da5788d52f1ae8886d8ed4624199b7e9fa64ac04"
 dependencies = [
  "libc",
 ]
 
 [[package]]
-name = "serde"
-version = "1.0.126"
+name = "semver"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec7505abeacaec74ae4778d9d9328fe5a5d04253220a85c4ee022239fc996d03"
+checksum = "1d7eb9ef2c18661902cc47e535f9bc51b78acd254da71d375c2f6720d9a40403"
+dependencies = [
+ "semver-parser",
+]
+
+[[package]]
+name = "semver-parser"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
+
+[[package]]
+name = "serde"
+version = "1.0.130"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f12d06de37cf59146fbdecab66aa99f9fe4f78722e3607577a5375d66bd0c913"
 
 [[package]]
 name = "serde_derive"
-version = "1.0.126"
+version = "1.0.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "963a7dbc9895aeac7ac90e74f34a5d5261828f79df35cbed41e10189d3804d43"
+checksum = "d7bc1a1ab1961464eae040d96713baa5a724a8152c1222492465b54322ec508b"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -483,9 +542,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.64"
+version = "1.0.67"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "799e97dc9fdae36a5c8b8f2cae9ce2ee9fdce2058c57a93e6099d919fd982f79"
+checksum = "a7f9e390c27c3c0ce8bc5d725f6e4d30a29d26659494aa4b17535f7522c5c950"
 dependencies = [
  "itoa",
  "ryu",
@@ -494,9 +553,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook"
-version = "0.3.9"
+version = "0.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "470c5a6397076fae0094aaf06a08e6ba6f37acb77d3b1b91ea92b4d6c8650c39"
+checksum = "9c98891d737e271a2954825ef19e46bd16bdb98e2746f2eec4f7a4ef7946efd1"
 dependencies = [
  "libc",
  "signal-hook-registry",
@@ -525,9 +584,9 @@ checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
 
 [[package]]
 name = "syn"
-version = "1.0.73"
+version = "1.0.76"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f71489ff30030d2ae598524f61326b902466f72a0fb1a8564c001cc63425bcc7"
+checksum = "c6f107db402c2c2055242dbf4d2af0e69197202e9faacbef9571bbe47f5a1b84"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -556,18 +615,18 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "1.0.25"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa6f76457f59514c7eeb4e59d891395fab0b2fd1d40723ae737d64153392e9c6"
+checksum = "602eca064b2d83369e2b2f34b09c70b605402801927c65c11071ac911d299b88"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.25"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a36768c0fbf1bb15eca10defa29526bda730a2376c2ab4393ccfa16fb1a318d"
+checksum = "bad553cc2c78e8de258400763a647e80e6d1b31ee237275d756f6836d204494c"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -591,6 +650,9 @@ name = "uuid"
 version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bc5cf98d8186244414c848017f0e2676b3fcb46807f6668a97dfe67359a3c4b7"
+dependencies = [
+ "getrandom",
+]
 
 [[package]]
 name = "vec_map"
@@ -618,8 +680,7 @@ dependencies = [
 [[package]]
 name = "versionize_derive"
 version = "0.1.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "140aa9fd298f667ea50fa1cb0d8530076924079285c623b18b8f8a1c28386b4a"
+source = "git+https://github.com/cloud-hypervisor/versionize_derive?branch=ch#ae35ef7a3ddabd3371ab8ac0193a383aff6e4b1b"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -638,7 +699,7 @@ dependencies = [
 [[package]]
 name = "vfio-ioctls"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=master#5cb8550556620546e74b9fe6d1174e0d1fc83888"
+source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=main#a8ee64b978ccd000df88732814d626651a091891"
 dependencies = [
  "byteorder",
  "kvm-bindings",
@@ -649,13 +710,45 @@ dependencies = [
  "vmm-sys-util",
 ]
 
+[[package]]
+name = "vfio_user"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "libc",
+ "log",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "thiserror",
+ "vfio-bindings",
+ "vm-memory",
+ "vmm-sys-util",
+]
+
+[[package]]
+name = "vhdx"
+version = "0.1.0"
+dependencies = [
+ "byteorder",
+ "crc32c",
+ "libc",
+ "log",
+ "remain",
+ "thiserror",
+ "uuid",
+ "vmm-sys-util",
+]
+
 [[package]]
 name = "vhost"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vhost?branch=master#e5b930b73a47cbdd79858e2e68bcb57123d1c1f3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a6b90237e10f1a61b35fba73885c3567e1a5a8c40d44daae335f7710210a7dc"
 dependencies = [
  "bitflags",
  "libc",
+ "vm-memory",
  "vmm-sys-util",
 ]
 
@@ -682,7 +775,7 @@ dependencies = [
  "net_util",
  "pci",
  "rate_limiter",
- "seccomp",
+ "seccompiler",
  "serde",
  "serde_derive",
  "serde_json",
@@ -724,12 +817,13 @@ dependencies = [
 [[package]]
 name = "vm-fdt"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vm-fdt?branch=master#13ab882e2f8387753064351c69fbe35c422b448b"
+source = "git+https://github.com/rust-vmm/vm-fdt?branch=main#720e48e435b791ec6cbe8d2b229448b71dcb1ab9"
 
 [[package]]
 name = "vm-memory"
-version = "0.5.0"
-source = "git+https://github.com/rust-vmm/vm-memory?rev=5bd7138758183a73ac0da27ce40c004d95f1a7e9#5bd7138758183a73ac0da27ce40c004d95f1a7e9"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0a8ebcb86ca457f9d6e14cf97009f679952eba42f0113de5db596e514cd0e43b"
 dependencies = [
  "arc-swap",
  "libc",
@@ -783,7 +877,7 @@ dependencies = [
  "option_parser",
  "pci",
  "qcow",
- "seccomp",
+ "seccompiler",
  "serde",
  "serde_derive",
  "serde_json",
@@ -793,6 +887,7 @@ dependencies = [
  "versionize",
  "versionize_derive",
  "vfio-ioctls",
+ "vhdx",
  "virtio-devices",
  "vm-allocator",
  "vm-device",
@@ -814,6 +909,12 @@ dependencies = [
  "serde_derive",
 ]
 
+[[package]]
+name = "wasi"
+version = "0.10.2+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6"
+
 [[package]]
 name = "winapi"
 version = "0.3.9"
@@ -835,3 +936,8 @@ name = "winapi-x86_64-pc-windows-gnu"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
+
+[[patch.unused]]
+name = "vm-memory"
+version = "0.5.0"
+source = "git+https://github.com/rust-vmm/vm-memory?rev=5bd7138758183a73ac0da27ce40c004d95f1a7e9#5bd7138758183a73ac0da27ce40c004d95f1a7e9"

fuzz/Cargo.toml

@@ -10,14 +10,15 @@ cargo-fuzz = true
 
 [dependencies]
 block_util = { path = "../block_util" }
-libc = "0.2.96"
+libc = "0.2.101"
 libfuzzer-sys = "0.4.2"
 qcow = { path = "../qcow" }
-seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.24.4" }
+seccompiler = { git = "https://github.com/rust-vmm/seccompiler"}
+vhdx = { path = "../vhdx" }
 virtio-devices = { path = "../virtio-devices" }
 vmm-sys-util = "0.8.0"
 vm-virtio = { path = "../vm-virtio" }
-vm-memory = "0.5.0"
+vm-memory = "0.6.0"
 
 [dependencies.cloud-hypervisor]
 path = ".."
@@ -25,6 +26,7 @@ path = ".."
 [patch.crates-io]
 kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"] }
 vm-memory = { git = "https://github.com/rust-vmm/vm-memory", rev = "5bd7138758183a73ac0da27ce40c004d95f1a7e9"}
+versionize_derive = { git = "https://github.com/cloud-hypervisor/versionize_derive", branch = "ch" }
 
 # Prevent this from interfering with workspaces
 [workspace]
@@ -41,3 +43,9 @@ name = "block"
 path = "fuzz_targets/block.rs"
 test = false
 doc = false
+
+[[bin]]
+name = "vhdx"
+path = "fuzz_targets/vhdx.rs"
+test = false
+doc = false

fuzz/fuzz_targets/block.rs

@@ -4,9 +4,9 @@
 
 #![no_main]
 
-use block_util::{async_io::DiskFile, qcow_sync::QcowDiskSync};
+use block_util::{async_io::DiskFile, raw_sync::RawFileDiskSync};
 use libfuzzer_sys::fuzz_target;
-use seccomp::SeccompAction;
+use seccompiler::SeccompAction;
 use std::ffi;
 use std::fs::File;
 use std::io::{self, Cursor, Read, Seek, SeekFrom};
@@ -17,7 +17,7 @@ use std::sync::Arc;
 use virtio_devices::{Block, VirtioDevice, VirtioInterrupt, VirtioInterruptType};
 use vm_memory::{Bytes, GuestAddress, GuestMemoryAtomic, GuestMemoryMmap};
 use vm_virtio::Queue;
-use vmm_sys_util::eventfd::EventFd;
+use vmm_sys_util::eventfd::{EventFd, EFD_NONBLOCK};
 
 const MEM_SIZE: u64 = 256 * 1024 * 1024;
 const DESC_SIZE: u64 = 16; // Bytes in one virtio descriptor.
@@ -84,7 +84,7 @@ 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(QcowDiskSync::new(disk_file, false)) as Box<dyn DiskFile>;
+    let qcow_disk = Box::new(RawFileDiskSync::new(disk_file)) as Box<dyn DiskFile>;
 
     let mut block = Block::new(
         "tmp".to_owned(),
@@ -96,6 +96,7 @@ fuzz_target!(|bytes| {
         256,
         SeccompAction::Allow,
         None,
+        EventFd::new(EFD_NONBLOCK).unwrap(),
     )
     .unwrap();
 

fuzz/fuzz_targets/vhdx.rs

@@ -0,0 +1,53 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+
+#![no_main]
+use libfuzzer_sys::fuzz_target;
+use std::ffi;
+use std::fs::File;
+use std::io::{self, Read, Seek, SeekFrom, Write};
+use std::os::unix::io::{FromRawFd, RawFd};
+use vhdx::vhdx::Vhdx;
+
+// Populate the corpus directory with a test file:
+// truncate -s 16M /tmp/source
+// qemu-img convert -O vhdx /tmp/source fuzz/corpus/vhdx/test.vhdx
+// Run with:
+// cargo fuzz run vhdx -j 32 -- -max_len=16777216
+fuzz_target!(|bytes| {
+    let shm = memfd_create(&ffi::CString::new("fuzz").unwrap(), 0).unwrap();
+    let mut disk_file: File = unsafe { File::from_raw_fd(shm) };
+    disk_file.write_all(&bytes[..]).unwrap();
+    disk_file.seek(SeekFrom::Start(0)).unwrap();
+
+    if let Ok(mut vhdx) = Vhdx::new(disk_file) {
+        if vhdx.seek(SeekFrom::Start(0)).is_ok() {
+            let mut offset = 0;
+            while offset < bytes.len() {
+                let mut data = vec![0; 8192];
+                vhdx.read_exact(&mut data).ok();
+                offset += data.len();
+            }
+        }
+
+        if vhdx.seek(SeekFrom::Start(0)).is_ok() {
+            let mut offset = 0;
+            while offset < bytes.len() {
+                let data = vec![0; 8192];
+                vhdx.write_all(&data).ok();
+                offset += data.len();
+            }
+        }
+    }
+});
+
+fn memfd_create(name: &ffi::CStr, flags: u32) -> Result<RawFd, io::Error> {
+    let res = unsafe { libc::syscall(libc::SYS_memfd_create, name.as_ptr(), flags) };
+
+    if res < 0 {
+        Err(io::Error::last_os_error())
+    } else {
+        Ok(res as RawFd)
+    }
+}

hypervisor/Cargo.toml

@@ -11,25 +11,25 @@ mshv = ["mshv-ioctls", "mshv-bindings"]
 tdx = []
 
 [dependencies]
-anyhow = "1.0"
-epoll = ">=4.0.1"
-thiserror = "1.0"
-libc = "0.2.96"
+anyhow = "1.0.43"
+epoll = "4.3.1"
+thiserror = "1.0.29"
+libc = "0.2.101"
 log = "0.4.14"
-kvm-ioctls = {  version = "0.9.0", optional = true }
+kvm-ioctls = { version = "0.9.0", optional = true }
 kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"], optional  = true }
-mshv-bindings = {git = "https://github.com/cloud-hypervisor/mshv", branch = "master", features = ["with-serde", "fam-wrappers"], optional  = true }
-mshv-ioctls = { git = "https://github.com/cloud-hypervisor/mshv", branch = "master", optional  = true}
-serde = {version = ">=1.0.27", features = ["rc"] }
-serde_derive = ">=1.0.27"
-serde_json = ">=1.0.9"
-vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic"] }
-vmm-sys-util = { version = ">=0.5.0", features = ["with-serde"] }
+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 = "1.0.130", features = ["rc"] }
+serde_derive = "1.0.130"
+serde_json = "1.0.67"
+vm-memory = { version = "0.6.0", features = ["backend-mmap", "backend-atomic"] }
+vmm-sys-util = { version = "0.8.0", features = ["with-serde"] }
 
 [target.'cfg(target_arch = "x86_64")'.dependencies.iced-x86]
-version = "1.11"
+version = "1.14.0"
 default-features = false
 features = ["std", "decoder", "op_code_info", "instr_info", "fast_fmt"]
 
 [dev-dependencies]
-env_logger = "0.8.3"
+env_logger = "0.9.0"

hypervisor/src/arch/x86/emulator/mod.rs

@@ -678,7 +678,7 @@ mod mock_vmm {
             };
 
             if let Some(mem) = memory {
-                vmm.write_memory(mem.0, &mem.1).unwrap();
+                vmm.write_memory(mem.0, mem.1).unwrap();
             }
 
             vmm
@@ -693,7 +693,7 @@ mod mock_vmm {
             let ip = self.cpu_state(cpu_id).unwrap().ip();
             let mut emulator = Emulator::new(self);
 
-            let new_state = emulator.emulate_insn_stream(cpu_id, &insn, num_insn)?;
+            let new_state = emulator.emulate_insn_stream(cpu_id, insn, num_insn)?;
             if num_insn.is_none() {
                 assert_eq!(ip + insn.len() as u64, new_state.ip());
             }

hypervisor/src/cpu.rs

@@ -21,6 +21,8 @@ use crate::x86_64::{
 use crate::CpuState;
 #[cfg(feature = "kvm")]
 use crate::MpState;
+#[cfg(all(feature = "mshv", target_arch = "x86_64"))]
+use crate::SuspendRegisters;
 #[cfg(target_arch = "x86_64")]
 use crate::Xsave;
 #[cfg(feature = "mshv")]
@@ -42,6 +44,11 @@ pub enum HypervisorCpuError {
     #[error("Failed to get standard registers: {0}")]
     GetStandardRegs(#[source] anyhow::Error),
     ///
+    /// Getting suspend registers error
+    ///
+    #[error("Failed to get suspend registers: {0}")]
+    GetSuspendRegs(#[source] anyhow::Error),
+    ///
     /// Setting special register error
     ///
     #[error("Failed to set special registers: {0}")]
@@ -421,4 +428,9 @@ pub trait Vcpu: Send + Sync {
     ///
     #[cfg(feature = "tdx")]
     fn tdx_init(&self, hob_address: u64) -> Result<()>;
+    #[cfg(all(feature = "mshv", target_arch = "x86_64"))]
+    ///
+    /// Return suspend registers(explicit and intercept suspend registers)
+    ///
+    fn get_suspend_regs(&self) -> Result<SuspendRegisters>;
 }

hypervisor/src/kvm/mod.rs

@@ -22,13 +22,16 @@ use crate::vm::{self, VmmOps};
 use crate::{arm64_core_reg_id, offset__of};
 use kvm_ioctls::{NoDatamatch, VcpuFd, VmFd};
 use serde_derive::{Deserialize, Serialize};
+use std::collections::HashMap;
 #[cfg(target_arch = "aarch64")]
 use std::convert::TryInto;
+#[cfg(target_arch = "x86_64")]
+use std::fs::File;
 use std::os::unix::io::{AsRawFd, RawFd};
 use std::result;
 #[cfg(target_arch = "x86_64")]
 use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::Arc;
+use std::sync::{Arc, RwLock};
 #[cfg(target_arch = "x86_64")]
 use vm_memory::Address;
 use vmm_sys_util::eventfd::EventFd;
@@ -87,6 +90,9 @@ pub use {
     kvm_ioctls::VcpuExit,
 };
 
+#[cfg(target_arch = "x86_64")]
+const KVM_CAP_SGX_ATTRIBUTE: u32 = 196;
+
 #[cfg(feature = "tdx")]
 ioctl_iowr_nr!(KVM_MEMORY_ENCRYPT_OP, KVMIO, 0xba, std::os::raw::c_ulong);
 
@@ -105,12 +111,21 @@ enum TdxCommand {
 pub struct KvmVmState {}
 
 pub use KvmVmState as VmState;
+
+struct KvmDirtyLogSlot {
+    slot: u32,
+    guest_phys_addr: u64,
+    memory_size: u64,
+    userspace_addr: u64,
+}
+
 /// Wrapper over KVM VM ioctls.
 pub struct KvmVm {
     fd: Arc<VmFd>,
     #[cfg(target_arch = "x86_64")]
     msrs: MsrEntries,
     state: KvmVmState,
+    dirty_log_slots: Arc<RwLock<HashMap<u32, KvmDirtyLogSlot>>>,
 }
 
 ///
@@ -163,7 +178,7 @@ impl vm::Vm for KvmVm {
     fn create_vcpu(
         &self,
         id: u8,
-        vmmops: Option<Arc<Box<dyn VmmOps>>>,
+        vmmops: Option<Arc<dyn VmmOps>>,
     ) -> vm::Result<Arc<dyn cpu::Vcpu>> {
         let vc = self
             .fd
@@ -226,7 +241,7 @@ impl vm::Vm for KvmVm {
         unsafe {
             let entries_slice: &mut [kvm_irq_routing_entry] =
                 irq_routing[0].entries.as_mut_slice(entries.len());
-            entries_slice.copy_from_slice(&entries);
+            entries_slice.copy_from_slice(entries);
         }
 
         self.fd
@@ -234,7 +249,7 @@ impl vm::Vm for KvmVm {
             .map_err(|e| vm::HypervisorVmError::SetGsiRouting(e.into()))
     }
     ///
-    /// Creates a memory region structure that can be used with set_user_memory_region
+    /// Creates a memory region structure that can be used with {create/remove}_user_memory_region
     ///
     fn make_user_memory_region(
         &self,
@@ -259,14 +274,57 @@ impl vm::Vm for KvmVm {
         }
     }
     ///
-    /// Creates/modifies a guest physical memory slot.
+    /// Creates a guest physical memory region.
     ///
-    fn set_user_memory_region(&self, user_memory_region: MemoryRegion) -> vm::Result<()> {
+    fn create_user_memory_region(&self, user_memory_region: MemoryRegion) -> vm::Result<()> {
+        let mut region = user_memory_region;
+
+        if (region.flags & KVM_MEM_LOG_DIRTY_PAGES) != 0 {
+            if (region.flags & KVM_MEM_READONLY) != 0 {
+                return Err(vm::HypervisorVmError::CreateUserMemory(anyhow!(
+                    "Error creating regions with both 'dirty-pages-log' and 'read-only'."
+                )));
+            }
+
+            // Keep track of the regions that need dirty pages log
+            self.dirty_log_slots.write().unwrap().insert(
+                region.slot,
+                KvmDirtyLogSlot {
+                    slot: region.slot,
+                    guest_phys_addr: region.guest_phys_addr,
+                    memory_size: region.memory_size,
+                    userspace_addr: region.userspace_addr,
+                },
+            );
+
+            // Always create guest physical memory region without `KVM_MEM_LOG_DIRTY_PAGES`.
+            // For regions that need this flag, dirty pages log will be turned on in `start_dirty_log`.
+            region.flags = 0;
+        }
+
         // Safe because guest regions are guaranteed not to overlap.
         unsafe {
             self.fd
-                .set_user_memory_region(user_memory_region)
-                .map_err(|e| vm::HypervisorVmError::SetUserMemory(e.into()))
+                .set_user_memory_region(region)
+                .map_err(|e| vm::HypervisorVmError::CreateUserMemory(e.into()))
+        }
+    }
+    ///
+    /// Removes a guest physical memory region.
+    ///
+    fn remove_user_memory_region(&self, user_memory_region: MemoryRegion) -> vm::Result<()> {
+        let mut region = user_memory_region;
+
+        // Remove the corresponding entry from "self.dirty_log_slots" if needed
+        self.dirty_log_slots.write().unwrap().remove(&region.slot);
+
+        // Setting the size to 0 means "remove"
+        region.memory_size = 0;
+        // Safe because guest regions are guaranteed not to overlap.
+        unsafe {
+            self.fd
+                .set_user_memory_region(region)
+                .map_err(|e| vm::HypervisorVmError::RemoveUserMemory(e.into()))
         }
     }
     ///
@@ -309,6 +367,18 @@ 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 {
+            cap: KVM_CAP_SGX_ATTRIBUTE,
+            ..Default::default()
+        };
+        cap.args[0] = file.as_raw_fd() as u64;
+        self.fd
+            .enable_cap(&cap)
+            .map_err(|e| vm::HypervisorVmError::EnableSgxAttribute(e.into()))?;
+        Ok(())
+    }
     /// Retrieve guest clock.
     #[cfg(target_arch = "x86_64")]
     fn get_clock(&self) -> vm::Result<ClockData> {
@@ -351,10 +421,58 @@ impl vm::Vm for KvmVm {
         Ok(())
     }
 
+    ///
+    /// Start logging dirty pages
+    ///
+    fn start_dirty_log(&self) -> vm::Result<()> {
+        let dirty_log_slots = self.dirty_log_slots.read().unwrap();
+        for (_, s) in dirty_log_slots.iter() {
+            let region = MemoryRegion {
+                slot: s.slot,
+                guest_phys_addr: s.guest_phys_addr,
+                memory_size: s.memory_size,
+                userspace_addr: s.userspace_addr,
+                flags: KVM_MEM_LOG_DIRTY_PAGES,
+            };
+            // Safe because guest regions are guaranteed not to overlap.
+            unsafe {
+                self.fd
+                    .set_user_memory_region(region)
+                    .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))?;
+            }
+        }
+
+        Ok(())
+    }
+
+    ///
+    /// Stop logging dirty pages
+    ///
+    fn stop_dirty_log(&self) -> vm::Result<()> {
+        let dirty_log_slots = self.dirty_log_slots.read().unwrap();
+        for (_, s) in dirty_log_slots.iter() {
+            let region = MemoryRegion {
+                slot: s.slot,
+                guest_phys_addr: s.guest_phys_addr,
+                memory_size: s.memory_size,
+                userspace_addr: s.userspace_addr,
+                flags: 0,
+            };
+            // Safe because guest regions are guaranteed not to overlap.
+            unsafe {
+                self.fd
+                    .set_user_memory_region(region)
+                    .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))?;
+            }
+        }
+
+        Ok(())
+    }
+
     ///
     /// Get dirty pages bitmap (one bit per page)
     ///
-    fn get_dirty_log(&self, slot: u32, memory_size: u64) -> vm::Result<Vec<u64>> {
+    fn get_dirty_log(&self, slot: u32, _base_gpa: u64, memory_size: u64) -> vm::Result<Vec<u64>> {
         self.fd
             .get_dirty_log(slot, memory_size as usize)
             .map_err(|e| vm::HypervisorVmError::GetDirtyLog(e.into()))
@@ -368,15 +486,23 @@ impl vm::Vm for KvmVm {
         #[repr(C)]
         struct TdxInitVm {
             max_vcpus: u32,
-            reserved: u32,
+            tsc_khz: u32,
             attributes: u64,
             cpuid: u64,
+            mrconfigid: [u64; 6],
+            mrowner: [u64; 6],
+            mrownerconfig: [u64; 6],
+            reserved: [u64; 43],
         }
         let data = TdxInitVm {
             max_vcpus,
-            reserved: 0,
+            tsc_khz: 0,
             attributes: 1, // TDX1_TD_ATTRIBUTE_DEBUG,
             cpuid: cpuid.as_fam_struct_ptr() as u64,
+            mrconfigid: [0; 6],
+            mrowner: [0; 6],
+            mrownerconfig: [0; 6],
+            reserved: [0; 43],
         };
 
         tdx_command(
@@ -539,6 +665,7 @@ impl hypervisor::Hypervisor for KvmHypervisor {
                 fd: vm_fd,
                 msrs,
                 state: VmState {},
+                dirty_log_slots: Arc::new(RwLock::new(HashMap::new())),
             }))
         }
 
@@ -547,6 +674,7 @@ impl hypervisor::Hypervisor for KvmHypervisor {
             Ok(Arc::new(KvmVm {
                 fd: vm_fd,
                 state: VmState {},
+                dirty_log_slots: Arc::new(RwLock::new(HashMap::new())),
             }))
         }
     }
@@ -611,7 +739,7 @@ pub struct KvmVcpu {
     fd: VcpuFd,
     #[cfg(target_arch = "x86_64")]
     msrs: MsrEntries,
-    vmmops: Option<Arc<Box<dyn vm::VmmOps>>>,
+    vmmops: Option<Arc<dyn vm::VmmOps>>,
     #[cfg(target_arch = "x86_64")]
     hyperv_synic: AtomicBool,
 }
@@ -801,7 +929,7 @@ impl cpu::Vcpu for KvmVcpu {
     ///
     fn set_xcrs(&self, xcrs: &ExtendedControlRegisters) -> cpu::Result<()> {
         self.fd
-            .set_xcrs(&xcrs)
+            .set_xcrs(xcrs)
             .map_err(|e| cpu::HypervisorCpuError::SetXcsr(e.into()))
     }
     ///
@@ -1145,19 +1273,12 @@ impl cpu::Vcpu for KvmVcpu {
         // call KVM_GET_ONE_REG on each id in order to save all of them. We carve out from the list
         // the core registers which are represented in the kernel by kvm_regs structure and for which
         // we can calculate the id based on the offset in the structure.
-
-        reg_list.retain(|regid| *regid != 0);
-        reg_list.as_slice().to_vec().sort_unstable();
-
         reg_list.retain(|regid| is_system_register(*regid));
 
         // Now, for the rest of the registers left in the previously fetched register list, we are
         // simply calling KVM_GET_ONE_REG.
         let indices = reg_list.as_slice();
-        for (_pos, index) in indices.iter().enumerate() {
-            if _pos > 230 {
-                break;
-            }
+        for index in indices.iter() {
             state.push(kvm_bindings::kvm_one_reg {
                 id: *index,
                 addr: self

hypervisor/src/mshv/mod.rs

@@ -16,7 +16,8 @@ pub use mshv_bindings::*;
 pub use mshv_ioctls::IoEventAddress;
 use mshv_ioctls::{set_registers_64, Mshv, NoDatamatch, VcpuFd, VmFd};
 use serde_derive::{Deserialize, Serialize};
-use std::sync::Arc;
+use std::collections::HashMap;
+use std::sync::{Arc, RwLock};
 use vm::DataMatch;
 // x86_64 dependencies
 #[cfg(target_arch = "x86_64")]
@@ -28,8 +29,21 @@ pub use x86_64::VcpuMshvState as CpuState;
 #[cfg(target_arch = "x86_64")]
 pub use x86_64::*;
 
-use std::os::unix::io::AsRawFd;
-use std::sync::RwLock;
+#[cfg(target_arch = "x86_64")]
+use std::fs::File;
+use std::os::unix::io::{AsRawFd, RawFd};
+
+const DIRTY_BITMAP_CLEAR_DIRTY: u64 = 0x4;
+const DIRTY_BITMAP_SET_DIRTY: u64 = 0x8;
+
+///
+/// Export generically-named wrappers of mshv-bindings for Unix-based platforms
+///
+pub use {
+    mshv_bindings::mshv_create_device as CreateDevice,
+    mshv_bindings::mshv_device_attr as DeviceAttr,
+    mshv_bindings::mshv_msi_routing_entry as IrqRoutingEntry, mshv_ioctls::DeviceFd,
+};
 
 pub const PAGE_SHIFT: usize = 12;
 
@@ -40,6 +54,11 @@ pub struct HvState {
 
 pub use HvState as VmState;
 
+struct MshvDirtyLogSlot {
+    guest_pfn: u64,
+    memory_size: u64,
+}
+
 /// Wrapper over mshv system ioctls.
 pub struct MshvHypervisor {
     mshv: Mshv,
@@ -104,6 +123,7 @@ impl hypervisor::Hypervisor for MshvHypervisor {
             msrs,
             hv_state: hv_state_init(),
             vmmops: None,
+            dirty_log_slots: Arc::new(RwLock::new(HashMap::new())),
         }))
     }
     ///
@@ -131,7 +151,7 @@ pub struct MshvVcpu {
     cpuid: CpuId,
     msrs: MsrEntries,
     hv_state: Arc<RwLock<HvState>>, // Mshv State
-    vmmops: Option<Arc<Box<dyn vm::VmmOps>>>,
+    vmmops: Option<Arc<dyn vm::VmmOps>>,
 }
 
 /// Implementation of Vcpu trait for Microsoft Hypervisor
@@ -235,7 +255,7 @@ impl cpu::Vcpu for MshvVcpu {
     ///
     fn set_xcrs(&self, xcrs: &ExtendedControlRegisters) -> cpu::Result<()> {
         self.fd
-            .set_xcrs(&xcrs)
+            .set_xcrs(xcrs)
             .map_err(|e| cpu::HypervisorCpuError::SetXcsr(e.into()))
     }
     #[cfg(target_arch = "x86_64")]
@@ -393,22 +413,22 @@ impl cpu::Vcpu for MshvVcpu {
                 }
                 hv_message_type_HVMSG_X64_CPUID_INTERCEPT => {
                     let info = x.to_cpuid_info().unwrap();
-                    debug!("cpuid eax: {:x}", info.rax);
+                    debug!("cpuid eax: {:x}", { info.rax });
                     Ok(cpu::VmExit::Ignore)
                 }
                 hv_message_type_HVMSG_X64_MSR_INTERCEPT => {
                     let info = x.to_msr_info().unwrap();
                     if info.header.intercept_access_type == 0 {
-                        debug!("msr read: {:x}", info.msr_number);
+                        debug!("msr read: {:x}", { info.msr_number });
                     } else {
-                        debug!("msr write: {:x}", info.msr_number);
+                        debug!("msr write: {:x}", { info.msr_number });
                     }
                     Ok(cpu::VmExit::Ignore)
                 }
                 hv_message_type_HVMSG_X64_EXCEPTION_INTERCEPT => {
                     //TODO: Handler for VMCALL here.
                     let info = x.to_exception_info().unwrap();
-                    debug!("Exception Info {:?}", info.exception_vector);
+                    debug!("Exception Info {:?}", { info.exception_vector });
                     Ok(cpu::VmExit::Ignore)
                 }
                 exit => Err(cpu::HypervisorCpuError::RunVcpu(anyhow!(
@@ -534,6 +554,45 @@ impl cpu::Vcpu for MshvVcpu {
 
         Ok(r)
     }
+    #[cfg(target_arch = "x86_64")]
+    ///
+    /// X86 specific call that returns the vcpu's current "suspend registers".
+    ///
+    fn get_suspend_regs(&self) -> cpu::Result<SuspendRegisters> {
+        self.fd
+            .get_suspend_regs()
+            .map_err(|e| cpu::HypervisorCpuError::GetSuspendRegs(e.into()))
+    }
+}
+
+/// Device struct for MSHV
+pub struct MshvDevice {
+    fd: DeviceFd,
+}
+
+impl device::Device for MshvDevice {
+    ///
+    /// Set device attribute
+    ///
+    fn set_device_attr(&self, attr: &DeviceAttr) -> device::Result<()> {
+        self.fd
+            .set_device_attr(attr)
+            .map_err(|e| device::HypervisorDeviceError::SetDeviceAttribute(e.into()))
+    }
+    ///
+    /// Get device attribute
+    ///
+    fn get_device_attr(&self, attr: &mut DeviceAttr) -> device::Result<()> {
+        self.fd
+            .get_device_attr(attr)
+            .map_err(|e| device::HypervisorDeviceError::GetDeviceAttribute(e.into()))
+    }
+}
+
+impl AsRawFd for MshvDevice {
+    fn as_raw_fd(&self) -> RawFd {
+        self.fd.as_raw_fd()
+    }
 }
 
 struct MshvEmulatorContext<'a> {
@@ -559,7 +618,7 @@ impl<'a> MshvEmulatorContext<'a> {
 
         let result_code = unsafe { r.1.__bindgen_anon_1.result_code };
         match result_code {
-            hv_translate_gva_result_code_HvTranslateGvaSuccess => Ok(r.0),
+            hv_translate_gva_result_code_HV_TRANSLATE_GVA_SUCCESS => Ok(r.0),
             _ => Err(PlatformError::TranslateVirtualAddress(anyhow!(result_code))),
         }
     }
@@ -669,7 +728,8 @@ pub struct MshvVm {
     msrs: MsrEntries,
     // Hypervisor State
     hv_state: Arc<RwLock<HvState>>,
-    vmmops: Option<Arc<Box<dyn vm::VmmOps>>>,
+    vmmops: Option<Arc<dyn vm::VmmOps>>,
+    dirty_log_slots: Arc<RwLock<HashMap<u64, MshvDirtyLogSlot>>>,
 }
 
 fn hv_state_init() -> Arc<RwLock<HvState>> {
@@ -708,7 +768,7 @@ impl vm::Vm for MshvVm {
         debug!("register_irqfd fd {} gsi {}", fd.as_raw_fd(), gsi);
 
         self.fd
-            .register_irqfd(&fd, gsi)
+            .register_irqfd(fd, gsi)
             .map_err(|e| vm::HypervisorVmError::RegisterIrqFd(e.into()))?;
 
         Ok(())
@@ -720,7 +780,7 @@ impl vm::Vm for MshvVm {
         debug!("unregister_irqfd fd {} gsi {}", fd.as_raw_fd(), gsi);
 
         self.fd
-            .unregister_irqfd(&fd, gsi)
+            .unregister_irqfd(fd, gsi)
             .map_err(|e| vm::HypervisorVmError::UnregisterIrqFd(e.into()))?;
 
         Ok(())
@@ -731,7 +791,7 @@ impl vm::Vm for MshvVm {
     fn create_vcpu(
         &self,
         id: u8,
-        vmmops: Option<Arc<Box<dyn VmmOps>>>,
+        vmmops: Option<Arc<dyn VmmOps>>,
     ) -> vm::Result<Arc<dyn cpu::Vcpu>> {
         let vcpu_fd = self
             .fd
@@ -751,6 +811,10 @@ impl vm::Vm for MshvVm {
     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,
@@ -789,11 +853,36 @@ impl vm::Vm for MshvVm {
             .map_err(|e| vm::HypervisorVmError::UnregisterIoEvent(e.into()))
     }
 
-    /// Creates/modifies a guest physical memory slot.
-    fn set_user_memory_region(&self, user_memory_region: MemoryRegion) -> vm::Result<()> {
+    /// Creates a guest physical memory region.
+    fn create_user_memory_region(&self, user_memory_region: MemoryRegion) -> vm::Result<()> {
+        // No matter read only or not we keep track the slots.
+        // For readonly hypervisor can enable the dirty bits,
+        // but a VM exit happens before setting the dirty bits
+        self.dirty_log_slots.write().unwrap().insert(
+            user_memory_region.guest_pfn,
+            MshvDirtyLogSlot {
+                guest_pfn: user_memory_region.guest_pfn,
+                memory_size: user_memory_region.size,
+            },
+        );
+
         self.fd
             .map_user_memory(user_memory_region)
-            .map_err(|e| vm::HypervisorVmError::SetUserMemory(e.into()))?;
+            .map_err(|e| vm::HypervisorVmError::CreateUserMemory(e.into()))?;
+        Ok(())
+    }
+
+    /// Removes a guest physical memory region.
+    fn remove_user_memory_region(&self, user_memory_region: MemoryRegion) -> vm::Result<()> {
+        // Remove the corresponding entry from "self.dirty_log_slots" if needed
+        self.dirty_log_slots
+            .write()
+            .unwrap()
+            .remove(&user_memory_region.guest_pfn);
+
+        self.fd
+            .unmap_user_memory(user_memory_region)
+            .map_err(|e| vm::HypervisorVmError::RemoveUserMemory(e.into()))?;
         Ok(())
     }
 
@@ -819,10 +908,28 @@ impl vm::Vm for MshvVm {
         }
     }
 
+    ///
+    /// Creates an in-kernel device.
+    ///
+    /// See the documentation for `MSHV_CREATE_DEVICE`.
+    fn create_device(&self, device: &mut CreateDevice) -> vm::Result<Arc<dyn device::Device>> {
+        let fd = self
+            .fd
+            .create_device(device)
+            .map_err(|e| vm::HypervisorVmError::CreateDevice(e.into()))?;
+        let device = MshvDevice { fd };
+        Ok(Arc::new(device))
+    }
+
     fn create_passthrough_device(&self) -> vm::Result<Arc<dyn device::Device>> {
-        Err(vm::HypervisorVmError::CreatePassthroughDevice(anyhow!(
-            "No passthrough support"
-        )))
+        let mut vfio_dev = mshv_create_device {
+            type_: mshv_device_type_MSHV_DEV_TYPE_VFIO,
+            fd: 0,
+            flags: 0,
+        };
+
+        self.create_device(&mut vfio_dev)
+            .map_err(|e| vm::HypervisorVmError::CreatePassthroughDevice(e.into()))
     }
 
     fn set_gsi_routing(&self, entries: &[IrqRoutingEntry]) -> vm::Result<()> {
@@ -833,7 +940,7 @@ impl vm::Vm for MshvVm {
         unsafe {
             let entries_slice: &mut [mshv_msi_routing_entry] =
                 msi_routing[0].entries.as_mut_slice(entries.len());
-            entries_slice.copy_from_slice(&entries);
+            entries_slice.copy_from_slice(entries);
         }
 
         self.fd
@@ -854,16 +961,44 @@ impl vm::Vm for MshvVm {
         Ok(())
     }
     ///
+    /// Start logging dirty pages
+    ///
+    fn start_dirty_log(&self) -> vm::Result<()> {
+        self.fd
+            .enable_dirty_page_tracking()
+            .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))
+    }
+    ///
+    /// Stop logging dirty pages
+    ///
+    fn stop_dirty_log(&self) -> vm::Result<()> {
+        let dirty_log_slots = self.dirty_log_slots.read().unwrap();
+        // Before disabling the dirty page tracking we need
+        // to set the dirty bits in the Hypervisor
+        // This is a requirement from Microsoft Hypervisor
+        for (_, s) in dirty_log_slots.iter() {
+            self.fd
+                .get_dirty_log(s.guest_pfn, s.memory_size as usize, DIRTY_BITMAP_SET_DIRTY)
+                .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))?;
+        }
+        self.fd
+            .disable_dirty_page_tracking()
+            .map_err(|e| vm::HypervisorVmError::StartDirtyLog(e.into()))?;
+        Ok(())
+    }
+    ///
     /// Get dirty pages bitmap (one bit per page)
     ///
-    fn get_dirty_log(&self, _slot: u32, _memory_size: u64) -> vm::Result<Vec<u64>> {
-        Err(vm::HypervisorVmError::GetDirtyLog(anyhow!(
-            "get_dirty_log not implemented"
-        )))
+    fn get_dirty_log(&self, _slot: u32, base_gpa: u64, memory_size: u64) -> vm::Result<Vec<u64>> {
+        self.fd
+            .get_dirty_log(
+                base_gpa >> PAGE_SHIFT,
+                memory_size as usize,
+                DIRTY_BITMAP_CLEAR_DIRTY,
+            )
+            .map_err(|e| vm::HypervisorVmError::GetDirtyLog(e.into()))
     }
 }
 pub use hv_cpuid_entry as CpuIdEntry;
 
-pub type IrqRoutingEntry = mshv_msi_routing_entry;
-
 pub const CPUID_FLAG_VALID_INDEX: u32 = 0;

hypervisor/src/mshv/x86_64/mod.rs

@@ -7,9 +7,10 @@
 // Copyright 2018-2019 CrowdStrike, Inc.
 //
 //
-
-use crate::arch::x86::{msr_index, SegmentRegisterOps};
+use crate::arch::x86::{msr_index, SegmentRegisterOps, MTRR_ENABLE, MTRR_MEM_TYPE_WB};
 use serde_derive::{Deserialize, Serialize};
+use std::fmt;
+
 ///
 /// Export generically-named wrappers of mshv_bindings for Unix-based platforms
 ///
@@ -19,8 +20,8 @@ pub use {
     mshv_bindings::FloatingPointUnit as FpuState, mshv_bindings::LapicState,
     mshv_bindings::MsrList, mshv_bindings::Msrs as MsrEntries, mshv_bindings::Msrs,
     mshv_bindings::SegmentRegister, mshv_bindings::SpecialRegisters,
-    mshv_bindings::StandardRegisters, mshv_bindings::VcpuEvents, mshv_bindings::XSave as Xsave,
-    mshv_bindings::Xcrs as ExtendedControlRegisters,
+    mshv_bindings::StandardRegisters, mshv_bindings::SuspendRegisters, mshv_bindings::VcpuEvents,
+    mshv_bindings::XSave as Xsave, mshv_bindings::Xcrs as ExtendedControlRegisters,
 };
 
 #[derive(Clone, Serialize, Deserialize)]
@@ -36,8 +37,30 @@ pub struct VcpuMshvState {
     pub xsave: Xsave,
 }
 
-pub struct CreateDevice {}
-pub struct DeviceAttr {}
+impl fmt::Display for VcpuMshvState {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        let expected_num_msrs = self.msrs.as_fam_struct_ref().nmsrs as usize;
+        let mut msr_entries = vec![vec![0; 2]; expected_num_msrs];
+
+        for (i, entry) in self.msrs.as_slice().iter().enumerate() {
+            msr_entries[i][1] = entry.data;
+            msr_entries[i][0] = entry.index as u64;
+        }
+        write!(f, "Number of MSRs: {}: MSRs: {:#010X?}, -- VCPU Events: {:?} -- Standard registers: {:?} Special Registers: {:?} ---- Floating Point Unit: {:?} --- Extended Control Register: {:?} --- Local APIC: {:?} --- DBG: {:?} --- Xsave: {:?}",
+                msr_entries.len(),
+                msr_entries,
+                self.vcpu_events,
+                self.regs,
+                self.sregs,
+                self.fpu,
+                self.xcrs,
+                self.lapic,
+                self.dbg,
+                self.xsave,
+        )
+    }
+}
+
 pub struct IrqRouting {}
 pub enum VcpuExit {}
 pub struct MpState {}
@@ -118,6 +141,7 @@ pub fn boot_msr_entries() -> MsrEntries {
         msr!(msr_index::MSR_KERNEL_GS_BASE),
         msr!(msr_index::MSR_SYSCALL_MASK),
         msr!(msr_index::MSR_IA32_TSC),
+        msr_data!(msr_index::MSR_MTRRdefType, MTRR_ENABLE | MTRR_MEM_TYPE_WB),
     ])
     .unwrap()
 }

hypervisor/src/vm.rs

@@ -16,7 +16,6 @@ use crate::device::Device;
 use crate::x86_64::CpuId;
 #[cfg(all(feature = "kvm", target_arch = "x86_64"))]
 use crate::ClockData;
-#[cfg(feature = "kvm")]
 use crate::CreateDevice;
 #[cfg(feature = "mshv")]
 use crate::HvState as VmState;
@@ -25,6 +24,8 @@ use crate::KvmVmState as VmState;
 use crate::{IoEventAddress, IrqRoutingEntry, MemoryRegion};
 #[cfg(feature = "kvm")]
 use kvm_ioctls::Cap;
+#[cfg(target_arch = "x86_64")]
+use std::fs::File;
 use std::sync::Arc;
 use thiserror::Error;
 use vmm_sys_util::eventfd::EventFd;
@@ -92,10 +93,15 @@ pub enum HypervisorVmError {
     #[error("Failed to set GSI routing: {0}")]
     SetGsiRouting(#[source] anyhow::Error),
     ///
-    /// Set user memory error
+    /// Create user memory error
     ///
-    #[error("Failed to set user memory: {0}")]
-    SetUserMemory(#[source] anyhow::Error),
+    #[error("Failed to create user memory: {0}")]
+    CreateUserMemory(#[source] anyhow::Error),
+    ///
+    /// Remove user memory region error
+    ///
+    #[error("Failed to remove user memory: {0}")]
+    RemoveUserMemory(#[source] anyhow::Error),
     ///
     /// Create device error
     ///
@@ -112,6 +118,11 @@ pub enum HypervisorVmError {
     #[error("Failed to enable split Irq: {0}")]
     EnableSplitIrq(#[source] anyhow::Error),
     ///
+    /// Enable SGX attribute error
+    ///
+    #[error("Failed to enable SGX attribute: {0}")]
+    EnableSgxAttribute(#[source] anyhow::Error),
+    ///
     /// Get clock error
     ///
     #[error("Failed to get clock: {0}")]
@@ -156,6 +167,16 @@ pub enum HypervisorVmError {
     #[error("Failed to write to IO Bus: {0}")]
     IoBusWrite(#[source] anyhow::Error),
     ///
+    /// Start dirty log error
+    ///
+    #[error("Failed to get dirty log: {0}")]
+    StartDirtyLog(#[source] anyhow::Error),
+    ///
+    /// Stop dirty log error
+    ///
+    #[error("Failed to get dirty log: {0}")]
+    StopDirtyLog(#[source] anyhow::Error),
+    ///
     /// Get dirty log error
     ///
     #[error("Failed to get dirty log: {0}")]
@@ -206,7 +227,7 @@ pub trait Vm: Send + Sync {
     /// Unregister an event that will, when signaled, trigger the `gsi` IRQ.
     fn unregister_irqfd(&self, fd: &EventFd, gsi: u32) -> Result<()>;
     /// Creates a new KVM vCPU file descriptor and maps the memory corresponding
-    fn create_vcpu(&self, id: u8, vmmops: Option<Arc<Box<dyn VmmOps>>>) -> Result<Arc<dyn Vcpu>>;
+    fn create_vcpu(&self, id: u8, vmmops: Option<Arc<dyn VmmOps>>) -> Result<Arc<dyn Vcpu>>;
     /// Registers an event to be signaled whenever a certain address is written to.
     fn register_ioevent(
         &self,
@@ -218,7 +239,7 @@ pub trait Vm: Send + Sync {
     fn unregister_ioevent(&self, fd: &EventFd, addr: &IoEventAddress) -> Result<()>;
     /// Sets the GSI routing table entries, overwriting any previously set
     fn set_gsi_routing(&self, entries: &[IrqRoutingEntry]) -> Result<()>;
-    /// Creates a memory region structure that can be used with set_user_memory_region
+    /// Creates a memory region structure that can be used with {create/remove}_user_memory_region
     fn make_user_memory_region(
         &self,
         slot: u32,
@@ -228,9 +249,10 @@ pub trait Vm: Send + Sync {
         readonly: bool,
         log_dirty_pages: bool,
     ) -> MemoryRegion;
-    /// Creates/modifies a guest physical memory slot.
-    fn set_user_memory_region(&self, user_memory_region: MemoryRegion) -> Result<()>;
-    #[cfg(feature = "kvm")]
+    /// Creates a guest physical memory slot.
+    fn create_user_memory_region(&self, user_memory_region: MemoryRegion) -> Result<()>;
+    /// Removes a guest physical memory slot.
+    fn remove_user_memory_region(&self, user_memory_region: MemoryRegion) -> Result<()>;
     /// Creates an emulated device in the kernel.
     fn create_device(&self, device: &mut CreateDevice) -> Result<Arc<dyn Device>>;
     /// Returns the preferred CPU target type which can be emulated by KVM on underlying host.
@@ -239,6 +261,8 @@ pub trait Vm: Send + Sync {
     /// Enable split Irq capability
     #[cfg(target_arch = "x86_64")]
     fn enable_split_irq(&self) -> Result<()>;
+    #[cfg(target_arch = "x86_64")]
+    fn enable_sgx_attribute(&self, file: File) -> Result<()>;
     /// Retrieve guest clock.
     #[cfg(all(feature = "kvm", target_arch = "x86_64"))]
     fn get_clock(&self) -> Result<ClockData>;
@@ -254,8 +278,12 @@ pub trait Vm: Send + Sync {
     fn state(&self) -> Result<VmState>;
     /// Set the VM state
     fn set_state(&self, state: VmState) -> Result<()>;
+    /// Start logging dirty pages
+    fn start_dirty_log(&self) -> Result<()>;
+    /// Stop logging dirty pages
+    fn stop_dirty_log(&self) -> Result<()>;
     /// Get dirty pages bitmap
-    fn get_dirty_log(&self, slot: u32, memory_size: u64) -> Result<Vec<u64>>;
+    fn get_dirty_log(&self, slot: u32, base_gpa: u64, memory_size: u64) -> Result<Vec<u64>>;
     #[cfg(feature = "tdx")]
     /// Initalize TDX on this VM
     fn tdx_init(&self, cpuid: &CpuId, max_vcpus: u32) -> Result<()>;

net_gen/Cargo.toml

@@ -5,4 +5,4 @@ authors = ["The Chromium OS Authors"]
 edition = "2018"
 
 [dependencies]
-vmm-sys-util = ">=0.3.1"
+vmm-sys-util = "0.8.0"

net_util/Cargo.toml

@@ -5,20 +5,20 @@ authors = ["The Chromium OS Authors"]
 edition = "2018"
 
 [dependencies]
-epoll = ">=4.0.1"
-libc = "0.2.96"
+epoll = "4.3.1"
+libc = "0.2.101"
 log = "0.4.14"
 net_gen = { path = "../net_gen" }
 rate_limiter = { path = "../rate_limiter" }
-serde = "1.0.126"
+serde = "1.0.130"
 versionize = "0.1.6"
 versionize_derive = "0.1.4"
 virtio-bindings = "0.1.0"
-vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
+vm-memory = { version = "0.6.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-virtio = { path = "../vm-virtio" }
-vmm-sys-util = ">=0.3.1"
+vmm-sys-util = "0.8.0"
 
 [dev-dependencies]
-lazy_static = "1.3.0"
+lazy_static = "1.4.0"
 pnet = "0.28.0"
-serde_json = "1.0.64"
+serde_json = "1.0.67"

net_util/src/ctrl_queue.rs

@@ -47,7 +47,7 @@ impl CtrlQueue {
 
     pub fn process(&mut self, mem: &GuestMemoryMmap, queue: &mut Queue) -> Result<bool> {
         let mut used_desc_heads = Vec::new();
-        for avail_desc in queue.iter(&mem) {
+        for avail_desc in queue.iter(mem) {
             let ctrl_hdr: ControlHeader =
                 mem.read_obj(avail_desc.addr).map_err(Error::GuestMemory)?;
             let data_desc = avail_desc
@@ -111,8 +111,8 @@ impl CtrlQueue {
         }
 
         for (desc_index, len) in used_desc_heads.iter() {
-            queue.add_used(&mem, *desc_index, *len);
-            queue.update_avail_event(&mem);
+            queue.add_used(mem, *desc_index, *len);
+            queue.update_avail_event(mem);
         }
 
         Ok(!used_desc_heads.is_empty())

net_util/src/mac.rs

@@ -57,7 +57,7 @@ impl MacAddr {
         // TODO: using something like std::mem::uninitialized could avoid the extra initialization,
         // if this ever becomes a performance bottleneck.
         let mut bytes = [0u8; MAC_ADDR_LEN];
-        bytes[..].copy_from_slice(&src);
+        bytes[..].copy_from_slice(src);
 
         MacAddr { bytes }
     }

net_util/src/queue_pair.rs

@@ -2,7 +2,7 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use super::{unregister_listener, vnet_hdr_len, Tap};
+use super::{register_listener, unregister_listener, vnet_hdr_len, Tap};
 use crate::GuestMemoryMmap;
 use rate_limiter::{RateLimiter, TokenType};
 use std::io;
@@ -39,34 +39,18 @@ impl TxVirtio {
         tap: &mut Tap,
         queue: &mut Queue,
         rate_limiter: &mut Option<RateLimiter>,
-    ) -> Result<(), NetQueuePairError> {
-        while let Some(avail_desc) = queue.iter(&mem).next() {
+    ) -> Result<bool, NetQueuePairError> {
+        let mut retry_write = false;
+        let mut rate_limit_reached = false;
+        while let Some(avail_desc) = queue.iter(mem).next() {
+            if rate_limit_reached {
+                queue.go_to_previous_position();
+                break;
+            }
+
             let head_index = avail_desc.index;
             let mut next_desc = Some(avail_desc);
 
-            if let Some(rate_limiter) = rate_limiter {
-                if !rate_limiter.consume(1, TokenType::Ops) {
-                    queue.go_to_previous_position();
-                    break;
-                }
-
-                let mut bytes = Wrapping(0);
-                let mut tmp_next_desc = next_desc.clone();
-                while let Some(desc) = tmp_next_desc {
-                    if !desc.is_write_only() {
-                        bytes += Wrapping(desc.len as u64);
-                    }
-                    tmp_next_desc = desc.next_descriptor();
-                }
-                bytes -= Wrapping(vnet_hdr_len() as u64);
-                if !rate_limiter.consume(bytes.0, TokenType::Bytes) {
-                    // Revert the OPS consume().
-                    rate_limiter.manual_replenish(1, TokenType::Ops);
-                    queue.go_to_previous_position();
-                    break;
-                }
-            }
-
             let mut iovecs = Vec::new();
             while let Some(desc) = next_desc {
                 if !desc.is_write_only() && desc.len > 0 {
@@ -83,7 +67,7 @@ impl TxVirtio {
                 next_desc = desc.next_descriptor();
             }
 
-            if !iovecs.is_empty() {
+            let len = if !iovecs.is_empty() {
                 let result = unsafe {
                     libc::writev(
                         tap.as_raw_fd() as libc::c_int,
@@ -91,13 +75,14 @@ impl TxVirtio {
                         iovecs.len() as libc::c_int,
                     )
                 };
+
                 if result < 0 {
                     let e = std::io::Error::last_os_error();
-                    queue.go_to_previous_position();
 
                     /* EAGAIN */
                     if e.kind() == std::io::ErrorKind::WouldBlock {
-                        warn!("net: tx: (recoverable) failed writing to tap: {}", e);
+                        queue.go_to_previous_position();
+                        retry_write = true;
                         break;
                     }
                     error!("net: tx: failed writing to tap: {}", e);
@@ -106,13 +91,25 @@ impl TxVirtio {
 
                 self.counter_bytes += Wrapping(result as u64 - vnet_hdr_len() as u64);
                 self.counter_frames += Wrapping(1);
-            }
 
-            queue.add_used(&mem, head_index, 0);
-            queue.update_avail_event(&mem);
+                result as u32
+            } else {
+                0
+            };
+
+            queue.add_used(mem, head_index, 0);
+            queue.update_avail_event(mem);
+
+            // For the sake of simplicity (similar to the RX rate limiting), we always
+            // let the 'last' descriptor chain go-through even if it was over the rate
+            // limit, and simply stop processing oncoming `avail_desc` if any.
+            if let Some(rate_limiter) = rate_limiter {
+                rate_limit_reached = !rate_limiter.consume(1, TokenType::Ops)
+                    || !rate_limiter.consume(len as u64, TokenType::Bytes);
+            }
         }
 
-        Ok(())
+        Ok(retry_write)
     }
 }
 
@@ -146,7 +143,7 @@ impl RxVirtio {
         let mut exhausted_descs = true;
         let mut rate_limit_reached = false;
 
-        while let Some(avail_desc) = queue.iter(&mem).next() {
+        while let Some(avail_desc) = queue.iter(mem).next() {
             if rate_limit_reached {
                 exhausted_descs = false;
                 queue.go_to_previous_position();
@@ -208,8 +205,8 @@ impl RxVirtio {
                 0
             };
 
-            queue.add_used(&mem, head_index, len);
-            queue.update_avail_event(&mem);
+            queue.add_used(mem, head_index, len);
+            queue.update_avail_event(mem);
 
             // For the sake of simplicity (keeping the handling of RX_QUEUE_EVENT and
             // RX_TAP_EVENT totally asynchronous), we always let the 'last' descriptor
@@ -252,12 +249,19 @@ pub enum NetQueuePairError {
 pub struct NetQueuePair {
     pub mem: Option<GuestMemoryAtomic<GuestMemoryMmap>>,
     pub tap: Tap,
+    // With epoll each FD must be unique. So in order to filter the
+    // events we need to get a second FD responding to the original
+    // device so that we can send EPOLLOUT and EPOLLIN to separate
+    // events.
+    pub tap_for_write_epoll: Tap,
     pub rx: RxVirtio,
     pub tx: TxVirtio,
     pub epoll_fd: Option<RawFd>,
     pub rx_tap_listening: bool,
+    pub tx_tap_listening: bool,
     pub counters: NetCounters,
-    pub tap_event_id: u16,
+    pub tap_rx_event_id: u16,
+    pub tap_tx_event_id: u16,
     pub rx_desc_avail: bool,
     pub rx_rate_limiter: Option<RateLimiter>,
     pub tx_rate_limiter: Option<RateLimiter>,
@@ -271,8 +275,35 @@ impl NetQueuePair {
             .ok_or(NetQueuePairError::NoMemoryConfigured)
             .map(|m| m.memory())?;
 
-        self.tx
-            .process_desc_chain(&mem, &mut self.tap, &mut queue, &mut self.tx_rate_limiter)?;
+        let tx_tap_retry = self.tx.process_desc_chain(
+            &mem,
+            &mut self.tap,
+            &mut queue,
+            &mut self.tx_rate_limiter,
+        )?;
+
+        // We got told to try again when writing to the tap. Wait for the TAP to be writable
+        if tx_tap_retry && !self.tx_tap_listening {
+            register_listener(
+                self.epoll_fd.unwrap(),
+                self.tap_for_write_epoll.as_raw_fd(),
+                epoll::Events::EPOLLOUT,
+                u64::from(self.tap_tx_event_id),
+            )
+            .map_err(NetQueuePairError::RegisterListener)?;
+            self.tx_tap_listening = true;
+            info!("Writing to TAP returned EAGAIN. Listening for TAP to become writable.");
+        } else if !tx_tap_retry && self.tx_tap_listening {
+            unregister_listener(
+                self.epoll_fd.unwrap(),
+                self.tap_for_write_epoll.as_raw_fd(),
+                epoll::Events::EPOLLOUT,
+                u64::from(self.tap_tx_event_id),
+            )
+            .map_err(NetQueuePairError::UnregisterListener)?;
+            self.tx_tap_listening = false;
+            info!("Writing to TAP succeeded. No longer listening for TAP to become writable.");
+        }
 
         self.counters
             .tx_bytes
@@ -312,7 +343,7 @@ impl NetQueuePair {
                 self.epoll_fd.unwrap(),
                 self.tap.as_raw_fd(),
                 epoll::Events::EPOLLIN,
-                u64::from(self.tap_event_id),
+                u64::from(self.tap_rx_event_id),
             )
             .map_err(NetQueuePairError::UnregisterListener)?;
             self.rx_tap_listening = false;

net_util/src/tap.rs

@@ -384,7 +384,7 @@ impl Read for Tap {
 
 impl Write for Tap {
     fn write(&mut self, buf: &[u8]) -> IoResult<usize> {
-        self.tap_file.write(&buf)
+        self.tap_file.write(buf)
     }
 
     fn flush(&mut self) -> IoResult<()> {

pci/Cargo.toml

@@ -4,19 +4,26 @@ version = "0.1.0"
 authors = ["Samuel Ortiz <sameo@linux.intel.com>"]
 edition = "2018"
 
+[features]
+default = []
+kvm = ["vfio-ioctls/kvm"]
+mshv = ["vfio-ioctls/mshv"]
+
 [dependencies]
-anyhow = "1.0"
+anyhow = "1.0.43"
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-vfio-ioctls = { git = "https://github.com/rust-vmm/vfio-ioctls", branch = "master" }
-vmm-sys-util = ">=0.3.1"
-libc = "0.2.96"
+vfio-ioctls = { git = "https://github.com/rust-vmm/vfio-ioctls", branch = "main", default-features = false }
+vfio_user = { path = "../vfio_user" }
+vmm-sys-util = "0.8.0"
+libc = "0.2.101"
 log = "0.4.14"
+thiserror = "1.0.29"
 versionize = "0.1.6"
 versionize_derive = "0.1.4"
 vm-allocator = { path = "../vm-allocator" }
 vm-device = { path = "../vm-device" }
-vm-memory = "0.5.0"
+vm-memory = "0.6.0"
 vm-migration = { path = "../vm-migration" }
 
 [dependencies.vfio-bindings]

pci/src/configuration.rs

@@ -317,7 +317,7 @@ pub struct PciConfiguration {
 }
 
 /// See pci_regs.h in kernel
-#[derive(Copy, Clone, PartialEq, Versionize)]
+#[derive(Copy, Clone, PartialEq, Versionize, Debug)]
 pub enum PciBarRegionType {
     Memory32BitRegion = 0,
     IoRegion = 0x01,
@@ -794,9 +794,9 @@ impl PciConfiguration {
                     return None;
                 }
 
-                debug!(
-                    "DETECT BAR REPROG: current 0x{:x}, new 0x{:x}",
-                    self.registers[reg_idx], value
+                info!(
+                    "Detected BAR reprogramming: (BAR {}) 0x{:x}->0x{:x}",
+                    reg_idx, self.registers[reg_idx], value
                 );
                 let old_base = u64::from(self.bars[bar_idx].addr & mask);
                 let new_base = u64::from(value & mask);
@@ -820,9 +820,9 @@ impl PciConfiguration {
                     != (self.bars[bar_idx - 1].addr & self.writable_bits[reg_idx - 1])
                     || (value & mask) != (self.bars[bar_idx].addr & mask))
             {
-                debug!(
-                    "DETECT BAR REPROG: current 0x{:x}, new 0x{:x}",
-                    self.registers[reg_idx], value
+                info!(
+                    "Detected BAR reprogramming: (BAR {}) 0x{:x}->0x{:x}",
+                    reg_idx, self.registers[reg_idx], value
                 );
                 let old_base = u64::from(self.bars[bar_idx].addr & mask) << 32
                     | u64::from(self.bars[bar_idx - 1].addr & self.writable_bits[reg_idx - 1]);
@@ -850,9 +850,9 @@ impl PciConfiguration {
                 return None;
             }
 
-            debug!(
-                "DETECT ROM BAR REPROG: current 0x{:x}, new 0x{:x}",
-                self.registers[reg_idx], value
+            info!(
+                "Detected ROM BAR reprogramming: (BAR {}) 0x{:x}->0x{:x}",
+                reg_idx, self.registers[reg_idx], value
             );
             let old_base = u64::from(self.rom_bar_addr & mask);
             let new_base = u64::from(value & mask);

pci/src/lib.rs

@@ -12,6 +12,7 @@ mod device;
 mod msi;
 mod msix;
 mod vfio;
+mod vfio_user;
 
 pub use self::bus::{PciBus, PciConfigIo, PciConfigMmio, PciRoot, PciRootError};
 pub use self::configuration::{
@@ -25,6 +26,7 @@ pub use self::device::{
 pub use self::msi::{msi_num_enabled_vectors, MsiCap, MsiConfig};
 pub use self::msix::{MsixCap, MsixConfig, MsixTableEntry, MSIX_TABLE_ENTRY_SIZE};
 pub use self::vfio::{VfioPciDevice, VfioPciError};
+pub use self::vfio_user::{VfioUserPciDevice, VfioUserPciDeviceError};
 
 /// PCI has four interrupt pins A->D.
 #[derive(Copy, Clone)]

pci/src/msi.rs

@@ -159,11 +159,11 @@ impl MsiCap {
 
 pub struct MsiConfig {
     cap: MsiCap,
-    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
 }
 
 impl MsiConfig {
-    pub fn new(msg_ctl: u16, interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>) -> Self {
+    pub fn new(msg_ctl: u16, interrupt_source_group: Arc<dyn InterruptSourceGroup>) -> Self {
         let cap = MsiCap {
             msg_ctl,
             ..Default::default()

pci/src/msix.rs

@@ -74,7 +74,7 @@ pub struct MsixConfig {
     pub table_entries: Vec<MsixTableEntry>,
     pub pba_entries: Vec<u64>,
     pub devid: u32,
-    interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
+    interrupt_source_group: Arc<dyn InterruptSourceGroup>,
     masked: bool,
     enabled: bool,
 }
@@ -82,7 +82,7 @@ pub struct MsixConfig {
 impl MsixConfig {
     pub fn new(
         msix_vectors: u16,
-        interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
+        interrupt_source_group: Arc<dyn InterruptSourceGroup>,
         devid: u32,
     ) -> Self {
         assert!(msix_vectors <= MAX_MSIX_VECTORS_PER_DEVICE);

pci/src/vfio_user.rs

@@ -0,0 +1,485 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use crate::vfio::{Interrupt, Vfio, VfioCommon, VfioError};
+use crate::{BarReprogrammingParams, PciBarRegionType, VfioPciError};
+use crate::{
+    PciClassCode, PciConfiguration, PciDevice, PciDeviceError, PciHeaderType, PciSubclass,
+};
+use hypervisor::HypervisorVmError;
+use std::any::Any;
+use std::os::unix::prelude::AsRawFd;
+use std::path::Path;
+use std::ptr::null_mut;
+use std::sync::{Arc, Barrier, Mutex};
+use std::u32;
+use thiserror::Error;
+use vfio_bindings::bindings::vfio::*;
+use vfio_ioctls::VfioIrq;
+use vfio_user::{Client, Error as VfioUserError};
+use vm_allocator::SystemAllocator;
+use vm_device::interrupt::{InterruptManager, InterruptSourceGroup, MsiIrqGroupConfig};
+use vm_device::BusDevice;
+use vm_memory::bitmap::AtomicBitmap;
+use vm_memory::{Address, GuestAddress, GuestMemoryRegion, GuestRegionMmap, GuestUsize};
+use vmm_sys_util::eventfd::EventFd;
+
+pub struct VfioUserPciDevice {
+    vm: Arc<dyn hypervisor::Vm>,
+    client: Arc<Mutex<Client>>,
+    vfio_wrapper: VfioUserClientWrapper,
+    common: VfioCommon,
+}
+
+#[derive(Error, Debug)]
+pub enum VfioUserPciDeviceError {
+    #[error("Client error: {0}")]
+    Client(#[source] VfioUserError),
+    #[error("Failed to map VFIO PCI region into guest: {0}")]
+    MapRegionGuest(#[source] HypervisorVmError),
+    #[error("Failed to DMA map: {0}")]
+    DmaMap(#[source] VfioUserError),
+    #[error("Failed to DMA unmap: {0}")]
+    DmaUnmap(#[source] VfioUserError),
+    #[error("Failed to initialize legacy interrupts: {0}")]
+    InitializeLegacyInterrupts(#[source] VfioPciError),
+}
+
+#[derive(Copy, Clone)]
+enum PciVfioUserSubclass {
+    VfioUserSubclass = 0xff,
+}
+
+impl PciSubclass for PciVfioUserSubclass {
+    fn get_register_value(&self) -> u8 {
+        *self as u8
+    }
+}
+
+impl VfioUserPciDevice {
+    pub fn new(
+        vm: &Arc<dyn hypervisor::Vm>,
+        path: &Path,
+        msi_interrupt_manager: &Arc<dyn InterruptManager<GroupConfig = MsiIrqGroupConfig>>,
+        legacy_interrupt_group: Option<Arc<dyn InterruptSourceGroup>>,
+    ) -> Result<Self, VfioUserPciDeviceError> {
+        let mut client = Client::new(path).map_err(VfioUserPciDeviceError::Client)?;
+
+        // This is used for the BAR and capabilities only
+        let configuration = PciConfiguration::new(
+            0,
+            0,
+            0,
+            PciClassCode::Other,
+            &PciVfioUserSubclass::VfioUserSubclass,
+            None,
+            PciHeaderType::Device,
+            0,
+            0,
+            None,
+        );
+        if client.resettable() {
+            client.reset().map_err(VfioUserPciDeviceError::Client)?;
+        }
+
+        let client = Arc::new(Mutex::new(client));
+
+        let vfio_wrapper = VfioUserClientWrapper {
+            client: client.clone(),
+        };
+
+        let mut common = VfioCommon {
+            mmio_regions: Vec::new(),
+            configuration,
+            interrupt: Interrupt {
+                intx: None,
+                msi: None,
+                msix: None,
+            },
+        };
+
+        common.parse_capabilities(msi_interrupt_manager, &vfio_wrapper);
+        common
+            .initialize_legacy_interrupt(legacy_interrupt_group, &vfio_wrapper)
+            .map_err(VfioUserPciDeviceError::InitializeLegacyInterrupts)?;
+
+        Ok(Self {
+            vm: vm.clone(),
+            client,
+            vfio_wrapper,
+            common,
+        })
+    }
+}
+
+impl BusDevice for VfioUserPciDevice {
+    fn read(&mut self, base: u64, offset: u64, data: &mut [u8]) {
+        self.read_bar(base, offset, data)
+    }
+
+    fn write(&mut self, base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+        self.write_bar(base, offset, data)
+    }
+}
+
+#[repr(u32)]
+#[derive(Debug, PartialEq, Eq, PartialOrd, Ord)]
+#[allow(dead_code)]
+enum Regions {
+    Bar0,
+    Bar1,
+    Bar2,
+    Bar3,
+    Bar4,
+    Bar5,
+    Rom,
+    Config,
+    Vga,
+    Migration,
+}
+
+struct VfioUserClientWrapper {
+    client: Arc<Mutex<Client>>,
+}
+
+impl Vfio for VfioUserClientWrapper {
+    fn region_read(&self, index: u32, offset: u64, data: &mut [u8]) {
+        self.client
+            .lock()
+            .unwrap()
+            .region_read(index, offset, data)
+            .ok();
+    }
+
+    fn region_write(&self, index: u32, offset: u64, data: &[u8]) {
+        self.client
+            .lock()
+            .unwrap()
+            .region_write(index, offset, data)
+            .ok();
+    }
+
+    fn get_irq_info(&self, irq_index: u32) -> Option<VfioIrq> {
+        self.client
+            .lock()
+            .unwrap()
+            .get_irq_info(irq_index)
+            .ok()
+            .map(|i| VfioIrq {
+                index: i.index,
+                flags: i.flags,
+                count: i.count,
+            })
+    }
+
+    fn enable_irq(&self, irq_index: u32, event_fds: Vec<&EventFd>) -> Result<(), VfioError> {
+        info!(
+            "Enabling IRQ {:x} number of fds = {:?}",
+            irq_index,
+            event_fds.len()
+        );
+        let fds: Vec<i32> = event_fds.iter().map(|e| e.as_raw_fd()).collect();
+
+        self.client
+            .lock()
+            .unwrap()
+            .set_irqs(
+                irq_index,
+                VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER,
+                0,
+                event_fds.len() as u32,
+                &fds,
+            )
+            .map_err(VfioError::VfioUser)
+    }
+
+    fn disable_irq(&self, irq_index: u32) -> Result<(), VfioError> {
+        info!("Disabling IRQ {:x}", irq_index);
+        self.client
+            .lock()
+            .unwrap()
+            .set_irqs(
+                irq_index,
+                VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
+                0,
+                0,
+                &[],
+            )
+            .map_err(VfioError::VfioUser)
+    }
+
+    fn unmask_irq(&self, irq_index: u32) -> Result<(), VfioError> {
+        info!("Unmasking IRQ {:x}", irq_index);
+        self.client
+            .lock()
+            .unwrap()
+            .set_irqs(
+                irq_index,
+                VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
+                0,
+                1,
+                &[],
+            )
+            .map_err(VfioError::VfioUser)
+    }
+}
+
+impl PciDevice for VfioUserPciDevice {
+    fn allocate_bars(
+        &mut self,
+        allocator: &mut SystemAllocator,
+    ) -> Result<Vec<(GuestAddress, GuestUsize, PciBarRegionType)>, PciDeviceError> {
+        self.common.allocate_bars(allocator, &self.vfio_wrapper)
+    }
+
+    fn free_bars(&mut self, allocator: &mut SystemAllocator) -> Result<(), PciDeviceError> {
+        self.common.free_bars(allocator)
+    }
+
+    fn as_any(&mut self) -> &mut dyn Any {
+        self
+    }
+
+    fn detect_bar_reprogramming(
+        &mut self,
+        reg_idx: usize,
+        data: &[u8],
+    ) -> Option<BarReprogrammingParams> {
+        self.common
+            .configuration
+            .detect_bar_reprogramming(reg_idx, data)
+    }
+
+    fn write_config_register(
+        &mut self,
+        reg_idx: usize,
+        offset: u64,
+        data: &[u8],
+    ) -> Option<Arc<Barrier>> {
+        self.common
+            .write_config_register(reg_idx, offset, data, &self.vfio_wrapper)
+    }
+
+    fn read_config_register(&mut self, reg_idx: usize) -> u32 {
+        self.common
+            .read_config_register(reg_idx, &self.vfio_wrapper)
+    }
+
+    fn read_bar(&mut self, base: u64, offset: u64, data: &mut [u8]) {
+        self.common.read_bar(base, offset, data, &self.vfio_wrapper)
+    }
+
+    fn write_bar(&mut self, base: u64, offset: u64, data: &[u8]) -> Option<Arc<Barrier>> {
+        self.common
+            .write_bar(base, offset, data, &self.vfio_wrapper)
+    }
+
+    fn move_bar(&mut self, old_base: u64, new_base: u64) -> Result<(), std::io::Error> {
+        info!("Moving BAR 0x{:x} -> 0x{:x}", old_base, new_base);
+        for mmio_region in self.common.mmio_regions.iter_mut() {
+            if mmio_region.start.raw_value() == old_base {
+                mmio_region.start = GuestAddress(new_base);
+
+                if let Some(mem_slot) = mmio_region.mem_slot {
+                    if let Some(host_addr) = mmio_region.host_addr {
+                        // Remove original region
+                        let old_region = self.vm.make_user_memory_region(
+                            mem_slot,
+                            old_base,
+                            mmio_region.length as u64,
+                            host_addr as u64,
+                            false,
+                            false,
+                        );
+
+                        self.vm
+                            .remove_user_memory_region(old_region)
+                            .map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e))?;
+
+                        let new_region = self.vm.make_user_memory_region(
+                            mem_slot,
+                            new_base,
+                            mmio_region.length as u64,
+                            host_addr as u64,
+                            false,
+                            false,
+                        );
+
+                        self.vm
+                            .create_user_memory_region(new_region)
+                            .map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e))?;
+                    }
+                }
+                info!("Moved bar 0x{:x} -> 0x{:x}", old_base, new_base);
+            }
+        }
+
+        Ok(())
+    }
+}
+
+impl VfioUserPciDevice {
+    pub fn map_mmio_regions<F>(
+        &mut self,
+        vm: &Arc<dyn hypervisor::Vm>,
+        mem_slot: F,
+    ) -> Result<(), VfioUserPciDeviceError>
+    where
+        F: Fn() -> u32,
+    {
+        for mmio_region in &mut self.common.mmio_regions {
+            let region_flags = self
+                .client
+                .lock()
+                .unwrap()
+                .region(mmio_region.index)
+                .unwrap()
+                .flags;
+            let file_offset = self
+                .client
+                .lock()
+                .unwrap()
+                .region(mmio_region.index)
+                .unwrap()
+                .file_offset
+                .clone();
+
+            if region_flags & VFIO_REGION_INFO_FLAG_MMAP != 0 {
+                let mut prot = 0;
+                if region_flags & VFIO_REGION_INFO_FLAG_READ != 0 {
+                    prot |= libc::PROT_READ;
+                }
+                if region_flags & VFIO_REGION_INFO_FLAG_WRITE != 0 {
+                    prot |= libc::PROT_WRITE;
+                }
+
+                let host_addr = unsafe {
+                    libc::mmap(
+                        null_mut(),
+                        mmio_region.length as usize,
+                        prot,
+                        libc::MAP_SHARED,
+                        file_offset.as_ref().unwrap().file().as_raw_fd(),
+                        file_offset.as_ref().unwrap().start() as libc::off_t,
+                    )
+                };
+
+                if host_addr == libc::MAP_FAILED {
+                    error!(
+                        "Could not mmap regions, error:{}",
+                        std::io::Error::last_os_error()
+                    );
+                    continue;
+                }
+
+                let slot = mem_slot();
+                let mem_region = vm.make_user_memory_region(
+                    slot,
+                    mmio_region.start.0,
+                    mmio_region.length as u64,
+                    host_addr as u64,
+                    false,
+                    false,
+                );
+
+                vm.create_user_memory_region(mem_region)
+                    .map_err(VfioUserPciDeviceError::MapRegionGuest)?;
+
+                mmio_region.mem_slot = Some(slot);
+                mmio_region.host_addr = Some(host_addr as u64);
+                mmio_region.mmap_size = Some(mmio_region.length as usize);
+            }
+        }
+
+        Ok(())
+    }
+
+    pub fn unmap_mmio_regions(&mut self) {
+        for mmio_region in self.common.mmio_regions.iter() {
+            if let (Some(host_addr), Some(mmap_size), Some(mem_slot)) = (
+                mmio_region.host_addr,
+                mmio_region.mmap_size,
+                mmio_region.mem_slot,
+            ) {
+                // Remove region
+                let r = self.vm.make_user_memory_region(
+                    mem_slot,
+                    mmio_region.start.raw_value(),
+                    mmap_size as u64,
+                    host_addr as u64,
+                    false,
+                    false,
+                );
+
+                if let Err(e) = self.vm.remove_user_memory_region(r) {
+                    error!("Could not remove the userspace memory region: {}", e);
+                }
+
+                let ret = unsafe { libc::munmap(host_addr as *mut libc::c_void, mmap_size) };
+                if ret != 0 {
+                    error!(
+                        "Could not unmap region {}, error:{}",
+                        mmio_region.index,
+                        std::io::Error::last_os_error()
+                    );
+                }
+            }
+        }
+    }
+
+    pub fn dma_map(
+        &mut self,
+        region: &GuestRegionMmap<AtomicBitmap>,
+    ) -> Result<(), VfioUserPciDeviceError> {
+        let (fd, offset) = match region.file_offset() {
+            Some(_file_offset) => (_file_offset.file().as_raw_fd(), _file_offset.start()),
+            None => return Ok(()),
+        };
+
+        self.client
+            .lock()
+            .unwrap()
+            .dma_map(
+                offset,
+                region.start_addr().raw_value(),
+                region.len() as u64,
+                fd,
+            )
+            .map_err(VfioUserPciDeviceError::DmaMap)
+    }
+
+    pub fn dma_unmap(
+        &mut self,
+        region: &GuestRegionMmap<AtomicBitmap>,
+    ) -> Result<(), VfioUserPciDeviceError> {
+        self.client
+            .lock()
+            .unwrap()
+            .dma_unmap(region.start_addr().raw_value(), region.len() as u64)
+            .map_err(VfioUserPciDeviceError::DmaUnmap)
+    }
+}
+
+impl Drop for VfioUserPciDevice {
+    fn drop(&mut self) {
+        self.unmap_mmio_regions();
+
+        if let Some(msix) = &self.common.interrupt.msix {
+            if msix.bar.enabled() {
+                self.common.disable_msix(&self.vfio_wrapper);
+            }
+        }
+
+        if let Some(msi) = &self.common.interrupt.msi {
+            if msi.cfg.enabled() {
+                self.common.disable_msi(&self.vfio_wrapper)
+            }
+        }
+
+        if self.common.interrupt.intx_in_use() {
+            self.common.disable_intx(&self.vfio_wrapper);
+        }
+    }
+}

qcow/Cargo.toml

@@ -10,7 +10,7 @@ path = "src/qcow.rs"
 
 [dependencies]
 byteorder = "1.4.3"
-libc = "0.2.96"
+libc = "0.2.101"
 log = "0.4.14"
 remain = "0.2.2"
-vmm-sys-util = ">=0.3.1"
+vmm-sys-util = "0.8.0"

qcow/src/qcow.rs

@@ -576,7 +576,7 @@ impl QcowFile {
 
     /// Returns the L1 lookup table for this file. This is only useful for debugging.
     pub fn l1_table(&self) -> &[u64] {
-        &self.l1_table.get_values()
+        self.l1_table.get_values()
     }
 
     /// Returns an L2_table of cluster addresses, only used for debugging.
@@ -613,7 +613,7 @@ impl QcowFile {
 
     /// Returns the refcount table for this file. This is only useful for debugging.
     pub fn ref_table(&self) -> &[u64] {
-        &self.refcounts.ref_table()
+        self.refcounts.ref_table()
     }
 
     /// Returns the `index`th refcount block from the file.
@@ -831,7 +831,7 @@ impl QcowFile {
 
             // Rewrite the top-level refcount table.
             raw_file
-                .write_pointer_table(header.refcount_table_offset, &ref_table, 0)
+                .write_pointer_table(header.refcount_table_offset, ref_table, 0)
                 .map_err(Error::WritingHeader)?;
 
             // Rewrite the header again, now with lazy refcounts disabled.
@@ -1379,7 +1379,7 @@ impl QcowFile {
         let mut sync_required = if self.l1_table.dirty() {
             self.raw_file.write_pointer_table(
                 self.header.l1_table_offset,
-                &self.l1_table.get_values(),
+                self.l1_table.get_values(),
                 0,
             )?;
             self.l1_table.mark_clean();
@@ -1783,7 +1783,7 @@ mod tests {
         F: FnMut(RawFile),
     {
         let mut disk_file: RawFile = RawFile::new(TempFile::new().unwrap().into_file(), false);
-        disk_file.write_all(&header).unwrap();
+        disk_file.write_all(header).unwrap();
         disk_file.set_len(0x1_0000_0000).unwrap();
         disk_file.seek(SeekFrom::Start(0)).unwrap();
 

qcow/src/refcount.rs

@@ -171,7 +171,7 @@ impl RefCount {
         if self.ref_table.dirty() {
             raw_file.write_pointer_table(
                 self.refcount_table_offset,
-                &self.ref_table.get_values(),
+                self.ref_table.get_values(),
                 0,
             )?;
             self.ref_table.mark_clean();
@@ -210,7 +210,7 @@ impl RefCount {
 
     /// Returns the refcount table for this file. This is only useful for debugging.
     pub fn ref_table(&self) -> &[u64] {
-        &self.ref_table.get_values()
+        self.ref_table.get_values()
     }
 
     /// Returns the refcounts stored in the given block.

rate_limiter/Cargo.toml

@@ -4,6 +4,6 @@ version = "0.1.0"
 edition = "2018"
 
 [dependencies]
-libc = "0.2.96"
+libc = "0.2.101"
 log = "0.4.14"
 vmm-sys-util = "0.8.0"

release-notes.md

@@ -1,10 +1,29 @@
+- [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)
+    - [VHDX disk image support](#vhdx-disk-image-support)
+    - [Device pass through on MSHV hypervisor](#device-pass-through-on-mshv-hypervisor)
+    - [AArch64 for support `virtio-mem`](#aarch64-for-support-virtio-mem)
+    - [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)
+    - [Contributors](#contributors)
+- [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-1)
+    - [Contributors](#contributors-1)
 - [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)
+    - [Notable bug fixes](#notable-bug-fixes-2)
     - [Removed functionality](#removed-functionality)
-    - [Contributors](#contributors)
+    - [Contributors](#contributors-2)
 - [v15.0](#v150)
     - [Version numbering and stability guarantees](#version-numbering-and-stability-guarantees)
     - [Network device rate limiting](#network-device-rate-limiting)
@@ -12,7 +31,7 @@
     - [`--api-socket` supports file descriptor parameter](#--api-socket-supports-file-descriptor-parameter)
     - [Bug fixes](#bug-fixes)
     - [Deprecations](#deprecations)
-    - [Contributors](#contributors-1)
+    - [Contributors](#contributors-3)
 - [v0.14.1](#v0141)
 - [v0.14.0](#v0140)
     - [Structured event monitoring](#structured-event-monitoring)
@@ -22,7 +41,7 @@
     - [PTY control for serial and `virtio-console`](#pty-control-for-serial-and-virtio-console)
     - [Block device rate limiting](#block-device-rate-limiting)
     - [Deprecations](#deprecations-1)
-    - [Contributors](#contributors-2)
+    - [Contributors](#contributors-4)
 - [v0.13.0](#v0130)
     - [Wider VFIO device support](#wider-vfio-device-support)
     - [Improved huge page support](#improved-huge-page-support)
@@ -30,13 +49,13 @@
     - [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-3)
+    - [Contributors](#contributors-5)
 - [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-4)
+    - [Contributors](#contributors-6)
 - [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)
@@ -48,15 +67,15 @@
     - [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-1)
-    - [Contributors](#contributors-5)
+    - [Notable Bug Fixes](#notable-bug-fixes-3)
+    - [Contributors](#contributors-7)
 - [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-2)
-    - [Contributors](#contributors-6)
+    - [Notable Bug Fixes](#notable-bug-fixes-4)
+    - [Contributors](#contributors-8)
 - [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)
@@ -69,17 +88,17 @@
     - [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-3)
-    - [Contributors](#contributors-7)
+    - [Notable Bug Fixes](#notable-bug-fixes-5)
+    - [Contributors](#contributors-9)
 - [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-4)
+    - [Notable Bug Fixes](#notable-bug-fixes-6)
     - [Command Line and API Changes](#command-line-and-api-changes)
-    - [Contributors](#contributors-8)
+    - [Contributors](#contributors-10)
 - [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)
@@ -89,14 +108,14 @@
     - [`Seccomp` Sandboxing](#seccomp-sandboxing)
     - [Updated Distribution Support](#updated-distribution-support)
     - [Command Line and API Changes](#command-line-and-api-changes-1)
-    - [Contributors](#contributors-9)
+    - [Contributors](#contributors-11)
 - [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-10)
+    - [Contributors](#contributors-12)
 - [v0.5.1](#v051)
 - [v0.5.0](#v050)
     - [Virtual Machine Dynamic Resizing](#virtual-machine-dynamic-resizing)
@@ -104,7 +123,7 @@
     - [New Interrupt Management Framework](#new-interrupt-management-framework)
     - [Development Tools](#development-tools)
     - [Kata Containers Integration](#kata-containers-integration)
-    - [Contributors](#contributors-11)
+    - [Contributors](#contributors-13)
 - [v0.4.0](#v040)
     - [Dynamic virtual CPUs addition](#dynamic-virtual-cpus-addition)
     - [Programmatic firmware tables generation](#programmatic-firmware-tables-generation)
@@ -113,7 +132,7 @@
     - [Userspace IOAPIC by default](#userspace-ioapic-by-default)
     - [PCI BAR reprogramming](#pci-bar-reprogramming)
     - [New `cloud-hypervisor` organization](#new-cloud-hypervisor-organization)
-    - [Contributors](#contributors-12)
+    - [Contributors](#contributors-14)
 - [v0.3.0](#v030)
     - [Block device offloading](#block-device-offloading)
     - [Network device backend](#network-device-backend)
@@ -140,6 +159,137 @@
     - [Unit testing](#unit-testing)
     - [Integration tests parallelization](#integration-tests-parallelization)
 
+# v18.0
+
+This release has been tracked through the [v18.0
+project](https://github.com/cloud-hypervisor/cloud-hypervisor/projects/21).
+
+### Experimental User Device (`vfio-user`) support
+
+Experimental support for running PCI devices in userspace via `vfio-user`
+has been included. This allows the use of the SPDK NVMe `vfio-user` controller
+with Cloud Hypervisor. This is enabled by `--user-device` on the command line.
+
+### Migration support for `vhost-user` devices
+
+Devices exposed into the VM via `vhost-user` can now be migrated using the live
+migration support. This requires support from the backend however the commonly
+used DPDK `vhost-user` backend does support this.
+
+### VHDX disk image support
+
+Images using the VHDX disk image format can now be used with Cloud Hypervisor.
+
+### Device pass through on MSHV hypervisor
+
+When running on the MSHV hypervisor it is possible to pass through devices from
+the host through to the guest (e.g with `--device`)
+
+### AArch64 for support `virtio-mem`
+
+The reference Linux kernel we recommend for using with Cloud Hypervisor now supports `virtio-mem` on AArch64.
+
+### Live migration on MSHV hypervisor
+
+Live migration is now supported when running on the MSHV hypervisor including
+efficient tracking of dirty pages.
+
+### AArch64 CPU topology support
+
+The CPU topology (as configured through `--cpu topology=`) can now be
+configured on AArch64 platforms and is conveyed through either ACPI or device
+tree.
+
+### Power button support on AArch64
+
+Use of the ACPI power button (e.g `ch-remote --api-socket=<API socket> power-button`) 
+is now supported when running on AArch64.
+
+### Notable bug fixes
+
+* Using two PTY outputs e.g. `--serial pty --console pty` now works correctly (#3012)
+* TTY input is now always sent to the correct destination (#3005)
+* The boot is no longer blocked when using a unattached PTY on the serial console (#3004)
+* Live migration is now supported on AArch64 (#3049)
+* Ensure signal handlers are run on the correct thread (#3069)
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release:
+
+* Alyssa Ross <hi@alyssa.is>
+* Anatol Belski <anbelski@linux.microsoft.com>
+* Arafatms <arafatms@outlook.com>
+* Bo Chen <chen.bo@intel.com>
+* Fazla Mehrab <akm.fazla.mehrab@vt.edu>
+* Henry Wang <Henry.Wang@arm.com>
+* Jianyong Wu <jianyong.wu@arm.com>
+* Jiaqi Gao <jiaqi.gao@intel.com>
+* Markus Theil <markus.theil@tu-ilmenau.de>
+* Muminul Islam <muislam@microsoft.com>
+* Rob Bradford <robert.bradford@intel.com>
+* Sebastien Boeuf <sebastien.boeuf@intel.com>
+* Wei Liu <liuwe@microsoft.com>
+* Yu Li <liyu.yukiteru@bytedance.com>
+
+# v17.0
+
+This release has been tracked through the [v17.0
+project](https://github.com/cloud-hypervisor/cloud-hypervisor/projects/20).
+
+### ARM64 NUMA support using ACPI
+
+The support for ACPI on ARM64 has been enhanced to include support for
+specifying a NUMA configuration using the existing control options.
+
+### `Seccomp` support for MSHV backend
+
+The `seccomp` rules have now been extended to support running against the MSHV
+hypervisor backend.
+
+### Hotplug of `macvtap` devices
+
+Hotplug of `macvtap` devices is now supported with the file descriptor for the
+network device if opened by the user and passed to the VMM. The `ch-remote`
+tool supports this functionality when adding a network device.
+
+### Improved SGX support
+
+The SGX support has been updated to match the latest Linux kernel support and
+now supports SGX provisioning and associating EPC sections to NUMA nodes.
+
+### Inflight tracking for `vhost-user` devices
+
+Support for handling inflight tracking of I/O requests has been added to the
+`vhost-user` devices allowing recovery after device reconnection.
+
+### Notable bug fixes
+
+* VFIO PCI BAR calculation code now correctly handles I/O BARs (#2821).
+* The VMM side of `vhost-user` devices no longer advertise the
+  `VIRTIO_F_RING_PACKED` feature as they are not yet supported in the VMM
+(#2833).
+* On ARM64 VMs can be created with more than 16 vCPUs (#2763).
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release:
+
+* Anatol Belski <anbelski@linux.microsoft.com>
+* Arafatms <arafatms@outlook.com>
+* Bo Chen <chen.bo@intel.com>
+* Fei Li <lifei.shirley@bytedance.com>
+* Henry Wang <Henry.Wang@arm.com>
+* Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
+* Jianyong Wu <jianyong.wu@arm.com>
+* Li Hangjing <lihangjing@bytedance.com>
+* Michael Zhao <michael.zhao@arm.com>
+* Muminul Islam <muislam@microsoft.com>
+* Rob Bradford <robert.bradford@intel.com>
+* Sebastien Boeuf <sebastien.boeuf@intel.com>
+* Wei Liu <liuwe@microsoft.com>
+* Yukiteru <wfly1998@sina.com>
+
 # v16.0
 
 This release has been tracked through the [v16.0 project](https://github.com/cloud-hypervisor/cloud-hypervisor/projects/19).

resources/Dockerfile

@@ -1,7 +1,7 @@
 FROM ubuntu:20.04 as dev
 
 ARG TARGETARCH
-ARG RUST_TOOLCHAIN="1.52.1"
+ARG RUST_TOOLCHAIN="1.54.0"
 ARG CLH_SRC_DIR="/cloud-hypervisor"
 ARG CLH_BUILD_DIR="$CLH_SRC_DIR/build"
 ARG CARGO_REGISTRY_DIR="$CLH_BUILD_DIR/cargo_registry"

resources/linux-config-aarch64

@@ -1,11 +1,13 @@
 #
 # Automatically generated file; DO NOT EDIT.
-# Linux/arm64 5.12.0 Kernel Configuration
+# Linux/arm64 5.14.0 Kernel Configuration
 #
 CONFIG_CC_VERSION_TEXT="gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0"
 CONFIG_CC_IS_GCC=y
 CONFIG_GCC_VERSION=90300
 CONFIG_CLANG_VERSION=0
+CONFIG_AS_IS_GNU=y
+CONFIG_AS_VERSION=23400
 CONFIG_LD_IS_BFD=y
 CONFIG_LD_VERSION=23400
 CONFIG_LLD_VERSION=0
@@ -13,6 +15,7 @@ CONFIG_CC_CAN_LINK=y
 CONFIG_CC_CAN_LINK_STATIC=y
 CONFIG_CC_HAS_ASM_GOTO=y
 CONFIG_CC_HAS_ASM_INLINE=y
+CONFIG_CC_HAS_NO_PROFILE_FN_ATTR=y
 CONFIG_IRQ_WORK=y
 CONFIG_BUILDTIME_TABLE_SORT=y
 CONFIG_THREAD_INFO_IN_TASK=y
@@ -60,7 +63,6 @@ CONFIG_SPARSE_IRQ=y
 # CONFIG_GENERIC_IRQ_DEBUGFS is not set
 # end of IRQ subsystem
 
-CONFIG_GENERIC_IRQ_MULTI_HANDLER=y
 CONFIG_GENERIC_TIME_VSYSCALL=y
 CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_ARCH_HAS_TICK_BROADCAST=y
@@ -78,9 +80,22 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 # end of Timers subsystem
 
+CONFIG_BPF=y
+CONFIG_HAVE_EBPF_JIT=y
+CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
+
+#
+# BPF subsystem
+#
+CONFIG_BPF_SYSCALL=y
+# CONFIG_BPF_UNPRIV_DEFAULT_OFF is not set
+# CONFIG_BPF_PRELOAD is not set
+# end of BPF subsystem
+
 CONFIG_PREEMPT_NONE=y
 # CONFIG_PREEMPT_VOLUNTARY is not set
 # CONFIG_PREEMPT is not set
+# CONFIG_SCHED_CORE is not set
 
 #
 # CPU/Task time and stats accounting
@@ -151,6 +166,7 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
 CONFIG_CGROUP_BPF=y
+# CONFIG_CGROUP_MISC is not set
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_SOCK_CGROUP_DATA=y
 CONFIG_NAMESPACES=y
@@ -179,7 +195,6 @@ CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
 CONFIG_LD_ORPHAN_WARN=y
 CONFIG_SYSCTL=y
 CONFIG_SYSCTL_EXCEPTION_TRACE=y
-CONFIG_BPF=y
 CONFIG_EXPERT=y
 CONFIG_MULTIUSER=y
 CONFIG_SGETMASK_SYSCALL=y
@@ -202,13 +217,11 @@ CONFIG_SHMEM=y
 CONFIG_AIO=y
 CONFIG_IO_URING=y
 CONFIG_ADVISE_SYSCALLS=y
+CONFIG_HAVE_ARCH_USERFAULTFD_MINOR=y
 CONFIG_MEMBARRIER=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 CONFIG_KALLSYMS_BASE_RELATIVE=y
-CONFIG_BPF_SYSCALL=y
-CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
-# CONFIG_BPF_PRELOAD is not set
 CONFIG_USERFAULTFD=y
 CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y
 # CONFIG_KCMP is not set
@@ -258,10 +271,7 @@ CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CSUM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_ZONE_DMA=y
-CONFIG_ZONE_DMA32=y
-CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
-CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
+CONFIG_ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE=y
 CONFIG_SMP=y
 CONFIG_KERNEL_MODE_NEON=y
 CONFIG_FIX_EARLYCON_MEM=y
@@ -273,10 +283,9 @@ CONFIG_ARCH_PROC_KCORE_TEXT=y
 # Platform selection
 #
 # CONFIG_ARCH_ACTIONS is not set
-# CONFIG_ARCH_AGILEX is not set
-# CONFIG_ARCH_N5X is not set
 # CONFIG_ARCH_SUNXI is not set
 # CONFIG_ARCH_ALPINE is not set
+# CONFIG_ARCH_APPLE is not set
 # CONFIG_ARCH_BCM2835 is not set
 # CONFIG_ARCH_BCM4908 is not set
 # CONFIG_ARCH_BCM_IPROC is not set
@@ -300,7 +309,7 @@ CONFIG_ARCH_PROC_KCORE_TEXT=y
 # CONFIG_ARCH_ROCKCHIP is not set
 # CONFIG_ARCH_S32 is not set
 # CONFIG_ARCH_SEATTLE is not set
-# CONFIG_ARCH_STRATIX10 is not set
+# CONFIG_ARCH_INTEL_SOCFPGA is not set
 # CONFIG_ARCH_SYNQUACER is not set
 # CONFIG_ARCH_TEGRA is not set
 # CONFIG_ARCH_SPRD is not set
@@ -328,6 +337,7 @@ CONFIG_ARM64_ERRATUM_819472=y
 CONFIG_ARM64_ERRATUM_832075=y
 CONFIG_ARM64_ERRATUM_834220=y
 CONFIG_ARM64_ERRATUM_843419=y
+CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419=y
 CONFIG_ARM64_ERRATUM_1024718=y
 CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT=y
 CONFIG_ARM64_ERRATUM_1165522=y
@@ -373,7 +383,6 @@ CONFIG_NODES_SHIFT=10
 CONFIG_USE_PERCPU_NUMA_NODE_ID=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
 CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
-CONFIG_HOLES_IN_ZONE=y
 # CONFIG_HZ_100 is not set
 CONFIG_HZ_250=y
 # CONFIG_HZ_300 is not set
@@ -381,12 +390,8 @@ CONFIG_HZ_250=y
 CONFIG_HZ=250
 CONFIG_SCHED_HRTICK=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
-CONFIG_ARCH_SPARSEMEM_DEFAULT=y
-CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_HW_PERF_EVENTS=y
-CONFIG_SYS_SUPPORTS_HUGETLBFS=y
-CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
-CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
+CONFIG_ARCH_HAS_FILTER_PGPROT=y
 CONFIG_PARAVIRT=y
 CONFIG_PARAVIRT_TIME_ACCOUNTING=y
 # CONFIG_KEXEC is not set
@@ -411,7 +416,6 @@ CONFIG_AS_HAS_LDAPR=y
 CONFIG_AS_HAS_LSE_ATOMICS=y
 CONFIG_ARM64_LSE_ATOMICS=y
 CONFIG_ARM64_USE_LSE_ATOMICS=y
-CONFIG_ARM64_VHE=y
 # end of ARMv8.1 architectural features
 
 #
@@ -426,10 +430,9 @@ CONFIG_ARM64_CNP=y
 # ARMv8.3 architectural features
 #
 CONFIG_ARM64_PTR_AUTH=y
-CONFIG_CC_HAS_BRANCH_PROT_PAC_RET=y
+CONFIG_ARM64_PTR_AUTH_KERNEL=y
 CONFIG_CC_HAS_SIGN_RETURN_ADDRESS=y
 CONFIG_AS_HAS_PAC=y
-CONFIG_AS_HAS_CFI_NEGATE_RA_STATE=y
 # end of ARMv8.3 architectural features
 
 #
@@ -443,22 +446,22 @@ CONFIG_ARM64_TLB_RANGE=y
 #
 # ARMv8.5 architectural features
 #
-CONFIG_AS_HAS_ARMV8_5=y
 CONFIG_ARM64_BTI=y
-CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI=y
 CONFIG_ARM64_E0PD=y
 CONFIG_ARCH_RANDOM=y
-CONFIG_ARM64_AS_HAS_MTE=y
-CONFIG_ARM64_MTE=y
 # end of ARMv8.5 architectural features
 
+#
+# ARMv8.7 architectural features
+#
+CONFIG_ARM64_EPAN=y
+# end of ARMv8.7 architectural features
+
 CONFIG_ARM64_SVE=y
 # CONFIG_ARM64_PSEUDO_NMI is not set
 CONFIG_RELOCATABLE=y
 CONFIG_RANDOMIZE_BASE=y
 CONFIG_RANDOMIZE_MODULE_REGION_FULL=y
-CONFIG_CC_HAVE_STACKPROTECTOR_SYSREG=y
-CONFIG_STACKPROTECTOR_PER_TASK=y
 # end of Kernel Features
 
 #
@@ -471,9 +474,6 @@ CONFIG_EFI=y
 CONFIG_DMI=y
 # end of Boot options
 
-CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y
-CONFIG_ARCH_ENABLE_THP_MIGRATION=y
-
 #
 # Power management options
 #
@@ -553,6 +553,7 @@ CONFIG_FIRMWARE_MEMMAP=y
 CONFIG_DMIID=y
 CONFIG_DMI_SYSFS=y
 # CONFIG_FW_CFG_SYSFS is not set
+# CONFIG_ARM_FFA_TRANSPORT is not set
 # CONFIG_GOOGLE_FIRMWARE is not set
 
 #
@@ -623,6 +624,7 @@ CONFIG_ACPI_IORT=y
 CONFIG_ACPI_GTDT=y
 CONFIG_ACPI_PPTT=y
 # CONFIG_PMIC_OPREGION is not set
+CONFIG_ACPI_VIOT=y
 CONFIG_IRQ_BYPASS_MANAGER=y
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=y
@@ -661,6 +663,7 @@ CONFIG_ARCH_HAS_KEEPINITRD=y
 CONFIG_ARCH_HAS_SET_MEMORY=y
 CONFIG_ARCH_HAS_SET_DIRECT_MAP=y
 CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST=y
+CONFIG_ARCH_WANTS_NO_INSTR=y
 CONFIG_HAVE_ASM_MODVERSIONS=y
 CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
 CONFIG_HAVE_RSEQ=y
@@ -688,6 +691,7 @@ CONFIG_STACKPROTECTOR_STRONG=y
 CONFIG_ARCH_SUPPORTS_LTO_CLANG=y
 CONFIG_ARCH_SUPPORTS_LTO_CLANG_THIN=y
 CONFIG_LTO_NONE=y
+CONFIG_ARCH_SUPPORTS_CFI_CLANG=y
 CONFIG_HAVE_CONTEXT_TRACKING=y
 CONFIG_HAVE_VIRT_CPU_ACCOUNTING_GEN=y
 CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
@@ -705,6 +709,8 @@ CONFIG_CLONE_BACKWARDS=y
 # CONFIG_COMPAT_32BIT_TIME is not set
 CONFIG_HAVE_ARCH_VMAP_STACK=y
 CONFIG_VMAP_STACK=y
+CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET=y
+# CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT is not set
 CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y
 CONFIG_STRICT_KERNEL_RWX=y
 CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
@@ -742,9 +748,10 @@ CONFIG_BLK_DEV_THROTTLING=y
 # CONFIG_BLK_DEV_THROTTLING_LOW is not set
 CONFIG_BLK_CMDLINE_PARSER=y
 CONFIG_BLK_WBT=y
+CONFIG_BLK_WBT_MQ=y
 # CONFIG_BLK_CGROUP_IOLATENCY is not set
 # CONFIG_BLK_CGROUP_IOCOST is not set
-CONFIG_BLK_WBT_MQ=y
+# CONFIG_BLK_CGROUP_IOPRIO is not set
 CONFIG_BLK_DEBUG_FS=y
 # CONFIG_BLK_SED_OPAL is not set
 # CONFIG_BLK_INLINE_ENCRYPTION is not set
@@ -863,10 +870,7 @@ CONFIG_COREDUMP=y
 #
 # Memory Management options
 #
-CONFIG_SELECT_MEMORY_MODEL=y
-CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_SPARSEMEM=y
-CONFIG_NEED_MULTIPLE_NODES=y
 CONFIG_SPARSEMEM_EXTREME=y
 CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
 CONFIG_SPARSEMEM_VMEMMAP=y
@@ -874,19 +878,24 @@ CONFIG_HAVE_FAST_GUP=y
 CONFIG_ARCH_KEEP_MEMBLOCK=y
 CONFIG_NUMA_KEEP_MEMINFO=y
 CONFIG_MEMORY_ISOLATION=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTPLUG_SPARSE=y
-# CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE is not set
+CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
 CONFIG_MEMORY_HOTREMOVE=y
+CONFIG_MHP_MEMMAP_ON_MEMORY=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
 CONFIG_MEMORY_BALLOON=y
 CONFIG_BALLOON_COMPACTION=y
 CONFIG_COMPACTION=y
 CONFIG_PAGE_REPORTING=y
 CONFIG_MIGRATION=y
+CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y
+CONFIG_ARCH_ENABLE_THP_MIGRATION=y
 CONFIG_CONTIG_ALLOC=y
 CONFIG_PHYS_ADDR_T_64BIT=y
-CONFIG_BOUNCE=y
 CONFIG_MMU_NOTIFIER=y
 CONFIG_KSM=y
 CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
@@ -919,15 +928,19 @@ CONFIG_ZSMALLOC_STAT=y
 CONFIG_GENERIC_EARLY_IOREMAP=y
 # CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set
 # CONFIG_IDLE_PAGE_TRACKING is not set
+CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_ARCH_HAS_PTE_DEVMAP=y
+CONFIG_ARCH_HAS_ZONE_DMA_SET=y
+CONFIG_ZONE_DMA=y
+CONFIG_ZONE_DMA32=y
 CONFIG_ZONE_DEVICE=y
 CONFIG_DEV_PAGEMAP_OPS=y
 # CONFIG_DEVICE_PRIVATE is not set
-CONFIG_ARCH_USES_HIGH_VMA_FLAGS=y
 CONFIG_PERCPU_STATS=y
 # CONFIG_GUP_TEST is not set
 # CONFIG_READ_ONLY_THP_FOR_FS is not set
 CONFIG_ARCH_HAS_PTE_SPECIAL=y
+CONFIG_SECRETMEM=y
 # end of Memory Management options
 
 CONFIG_NET=y
@@ -991,7 +1004,6 @@ CONFIG_NET_PTP_CLASSIFY=y
 # CONFIG_ATM is not set
 # CONFIG_L2TP is not set
 # CONFIG_BRIDGE is not set
-CONFIG_HAVE_NET_DSA=y
 # CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
@@ -1019,6 +1031,7 @@ CONFIG_VIRTIO_VSOCKETS_COMMON=y
 # CONFIG_NET_L3_MASTER_DEV is not set
 # CONFIG_QRTR is not set
 # CONFIG_NET_NCSI is not set
+CONFIG_PCPU_DEV_REFCNT=y
 CONFIG_RPS=y
 CONFIG_RFS_ACCEL=y
 CONFIG_SOCK_RX_QUEUE_MAPPING=y
@@ -1056,7 +1069,6 @@ CONFIG_GRO_CELLS=y
 CONFIG_NET_SOCK_MSG=y
 CONFIG_FAILOVER=y
 # CONFIG_ETHTOOL_NETLINK is not set
-CONFIG_HAVE_EBPF_JIT=y
 
 #
 # Device Drivers
@@ -1128,7 +1140,6 @@ CONFIG_PCI_HOST_GENERIC=y
 #
 # Mobiveil PCIe Core Support
 #
-# CONFIG_PCIE_LAYERSCAPE_GEN4 is not set
 # end of Mobiveil PCIe Core Support
 
 #
@@ -1229,7 +1240,6 @@ CONFIG_ZRAM_DEF_COMP_LZORLE=y
 CONFIG_ZRAM_DEF_COMP="lzo-rle"
 # CONFIG_ZRAM_WRITEBACK is not set
 # CONFIG_ZRAM_MEMORY_TRACKING is not set
-# CONFIG_BLK_DEV_UMEM is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
 CONFIG_BLK_DEV_CRYPTOLOOP=y
@@ -1250,6 +1260,7 @@ CONFIG_VIRTIO_BLK=y
 #
 # CONFIG_BLK_DEV_NVME is not set
 # CONFIG_NVME_FC is not set
+# CONFIG_NVME_TCP is not set
 # CONFIG_NVME_TARGET is not set
 # end of NVME Support
 
@@ -1262,9 +1273,9 @@ CONFIG_VIRTIO_BLK=y
 # CONFIG_ENCLOSURE_SERVICES is not set
 # CONFIG_HP_ILO is not set
 # CONFIG_SRAM is not set
+# CONFIG_DW_XDATA_PCIE is not set
 # CONFIG_PCI_ENDPOINT_TEST is not set
 # CONFIG_XILINX_SDFEC is not set
-# CONFIG_PVPANIC is not set
 # CONFIG_C2PORT is not set
 
 #
@@ -1291,6 +1302,7 @@ CONFIG_VIRTIO_BLK=y
 # CONFIG_MISC_RTSX_PCI is not set
 # CONFIG_HABANA_AI is not set
 # CONFIG_UACCE is not set
+# CONFIG_PVPANIC is not set
 # end of Misc devices
 
 #
@@ -1335,13 +1347,6 @@ CONFIG_VETH=y
 CONFIG_VIRTIO_NET=y
 # CONFIG_NLMON is not set
 # CONFIG_ARCNET is not set
-
-#
-# Distributed Switch Architecture drivers
-#
-# CONFIG_NET_DSA_MV88E6XXX_PTP is not set
-# end of Distributed Switch Architecture drivers
-
 # CONFIG_ETHERNET is not set
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
@@ -1362,6 +1367,13 @@ CONFIG_VIRTIO_NET=y
 #
 # CONFIG_WLAN is not set
 # CONFIG_WAN is not set
+
+#
+# Wireless WAN
+#
+# CONFIG_WWAN is not set
+# end of Wireless WAN
+
 # CONFIG_VMXNET3 is not set
 # CONFIG_FUJITSU_ES is not set
 # CONFIG_NETDEVSIM is not set
@@ -1497,7 +1509,6 @@ CONFIG_SERIAL_MCTRL_GPIO=y
 # CONFIG_N_GSM is not set
 # CONFIG_NOZOMI is not set
 # CONFIG_NULL_TTY is not set
-# CONFIG_TRACE_SINK is not set
 CONFIG_HVC_DRIVER=y
 # CONFIG_HVC_DCC is not set
 CONFIG_SERIAL_DEV_BUS=y
@@ -1514,8 +1525,6 @@ CONFIG_HW_RANDOM_CAVIUM=y
 # CONFIG_HW_RANDOM_XIPHERA is not set
 # CONFIG_APPLICOM is not set
 CONFIG_DEVMEM=y
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=256
 CONFIG_DEVPORT=y
 # CONFIG_TCG_TPM is not set
 # CONFIG_XILLYBUS is not set
@@ -1556,6 +1565,7 @@ CONFIG_PTP_1588_CLOCK=y
 #
 # Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
 #
+CONFIG_PTP_1588_CLOCK_KVM=y
 # CONFIG_PTP_1588_CLOCK_OCP is not set
 # end of PTP clock support
 
@@ -1632,6 +1642,7 @@ CONFIG_POWER_SUPPLY=y
 # CONFIG_CHARGER_MAX8903 is not set
 # CONFIG_CHARGER_GPIO is not set
 # CONFIG_CHARGER_LT3651 is not set
+# CONFIG_BATTERY_GOLDFISH is not set
 # CONFIG_HWMON is not set
 CONFIG_THERMAL=y
 # CONFIG_THERMAL_NETLINK is not set
@@ -1655,6 +1666,7 @@ CONFIG_WATCHDOG_CORE=y
 CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED=y
 CONFIG_WATCHDOG_OPEN_TIMEOUT=0
 # CONFIG_WATCHDOG_SYSFS is not set
+# CONFIG_WATCHDOG_HRTIMER_PRETIMEOUT is not set
 
 #
 # Watchdog Pretimeout Governors
@@ -1705,7 +1717,6 @@ CONFIG_BCMA_POSSIBLE=y
 # CONFIG_MFD_MT6397 is not set
 # CONFIG_MFD_RDC321X is not set
 # CONFIG_MFD_SM501 is not set
-# CONFIG_ABX500_CORE is not set
 # CONFIG_MFD_SYSCON is not set
 # CONFIG_MFD_TI_AM335X_TSCADC is not set
 # CONFIG_MFD_TQMX86 is not set
@@ -1869,6 +1880,7 @@ CONFIG_HID_REDRAGON=y
 # CONFIG_HID_PRIMAX is not set
 # CONFIG_HID_SAITEK is not set
 # CONFIG_HID_SAMSUNG is not set
+# CONFIG_HID_SEMITEK is not set
 # CONFIG_HID_SPEEDLINK is not set
 # CONFIG_HID_STEAM is not set
 # CONFIG_HID_STEELSERIES is not set
@@ -1878,7 +1890,6 @@ CONFIG_HID_REDRAGON=y
 # CONFIG_HID_SMARTJOYPLUS is not set
 # CONFIG_HID_TIVO is not set
 # CONFIG_HID_TOPSEED is not set
-# CONFIG_HID_THRUSTMASTER is not set
 # CONFIG_HID_UDRAW_PS3 is not set
 # CONFIG_HID_XINMO is not set
 # CONFIG_HID_ZEROPLUS is not set
@@ -2033,6 +2044,7 @@ CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_PCI_LEGACY=y
 CONFIG_VIRTIO_PMEM=y
 CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_MEM=y
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
@@ -2048,15 +2060,23 @@ CONFIG_VHOST_MENU=y
 # end of Microsoft Hyper-V guest support
 
 # CONFIG_GREYBUS is not set
+# CONFIG_COMEDI is not set
 # CONFIG_STAGING is not set
 # CONFIG_GOLDFISH is not set
 # CONFIG_CHROME_PLATFORMS is not set
 # CONFIG_MELLANOX_PLATFORM is not set
 # CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_HAVE_CLK=y
-CONFIG_CLKDEV_LOOKUP=y
 CONFIG_HAVE_CLK_PREPARE=y
 CONFIG_COMMON_CLK=y
+
+#
+# Clock driver for ARM Reference designs
+#
+# CONFIG_ICST is not set
+# CONFIG_CLK_SP810 is not set
+# end of Clock driver for ARM Reference designs
+
 # CONFIG_COMMON_CLK_AXI_CLKGEN is not set
 # CONFIG_COMMON_CLK_XGENE is not set
 # CONFIG_COMMON_CLK_FIXED_MMIO is not set
@@ -2104,9 +2124,6 @@ CONFIG_IOMMU_DMA=y
 # CONFIG_ARM_SMMU is not set
 # CONFIG_ARM_SMMU_V3 is not set
 CONFIG_VIRTIO_IOMMU=y
-CONFIG_VIRTIO_IOMMU_TOPOLOGY_HELPERS=y
-CONFIG_VIRTIO_IOMMU_TOPOLOGY=y
-CONFIG_ACPI_VIOT=y
 
 #
 # Remoteproc drivers
@@ -2199,6 +2216,7 @@ CONFIG_PARTITION_PERCPU=y
 #
 # CONFIG_GENERIC_PHY is not set
 # CONFIG_PHY_XGENE is not set
+# CONFIG_PHY_CAN_TRANSCEIVER is not set
 # CONFIG_BCM_KONA_USB2_PHY is not set
 # CONFIG_PHY_CADENCE_TORRENT is not set
 # CONFIG_PHY_CADENCE_DPHY is not set
@@ -2327,6 +2345,8 @@ CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW=y
 #
 # Caches
 #
+CONFIG_NETFS_SUPPORT=y
+# CONFIG_NETFS_STATS is not set
 CONFIG_FSCACHE=y
 # CONFIG_FSCACHE_STATS is not set
 # CONFIG_FSCACHE_HISTOGRAM is not set
@@ -2371,6 +2391,7 @@ CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_TMPFS_XATTR=y
 # CONFIG_TMPFS_INODE64 is not set
+CONFIG_ARCH_SUPPORTS_HUGETLBFS=y
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
 CONFIG_MEMFD_CREATE=y
@@ -2545,6 +2566,7 @@ CONFIG_CRYPTO_CRYPTD=y
 # CONFIG_CRYPTO_RSA is not set
 # CONFIG_CRYPTO_DH is not set
 # CONFIG_CRYPTO_ECDH is not set
+# CONFIG_CRYPTO_ECDSA is not set
 # CONFIG_CRYPTO_ECRDSA is not set
 # CONFIG_CRYPTO_SM2 is not set
 # CONFIG_CRYPTO_CURVE25519 is not set
@@ -2673,6 +2695,8 @@ CONFIG_SYSTEM_BLACKLIST_KEYRING=y
 CONFIG_SYSTEM_BLACKLIST_HASH_LIST=""
 # end of Certificates for signature checking
 
+CONFIG_BINARY_PRINTF=y
+
 #
 # Library routines
 #
@@ -2682,6 +2706,7 @@ CONFIG_HAVE_ARCH_BITREVERSE=y
 CONFIG_GENERIC_STRNCPY_FROM_USER=y
 CONFIG_GENERIC_STRNLEN_USER=y
 CONFIG_GENERIC_NET_UTILS=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
 # CONFIG_CORDIC is not set
 # CONFIG_PRIME_NUMBERS is not set
 CONFIG_RATIONAL=y
@@ -2770,7 +2795,6 @@ CONFIG_FONT_8x16=y
 CONFIG_MEMREGION=y
 CONFIG_ARCH_STACKWALK=y
 CONFIG_SBITMAP=y
-# CONFIG_STRING_SELFTEST is not set
 # end of Library routines
 
 CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED=y
@@ -2784,6 +2808,7 @@ CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED=y
 #
 CONFIG_PRINTK_TIME=y
 # CONFIG_PRINTK_CALLER is not set
+# CONFIG_STACKTRACE_BUILD_ID is not set
 CONFIG_CONSOLE_LOGLEVEL_DEFAULT=7
 CONFIG_CONSOLE_LOGLEVEL_QUIET=4
 CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4
@@ -2804,9 +2829,10 @@ CONFIG_STRIP_ASM_SYMS=y
 # CONFIG_HEADERS_INSTALL is not set
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_SECTION_MISMATCH_WARN_ONLY=y
-# CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_32B is not set
+# CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B is not set
 CONFIG_ARCH_WANT_FRAME_POINTERS=y
 CONFIG_FRAME_POINTER=y
+# CONFIG_VMLINUX_MAP is not set
 # CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
 # end of Compile-time checks and compiler options
 
@@ -2858,10 +2884,8 @@ CONFIG_DEBUG_MEMORY_INIT=y
 # CONFIG_DEBUG_PER_CPU_MAPS is not set
 CONFIG_HAVE_ARCH_KASAN=y
 CONFIG_HAVE_ARCH_KASAN_SW_TAGS=y
-CONFIG_HAVE_ARCH_KASAN_HW_TAGS=y
+CONFIG_HAVE_ARCH_KASAN_VMALLOC=y
 CONFIG_CC_HAS_KASAN_GENERIC=y
-CONFIG_CC_HAS_WORKING_NOSANITIZE_ADDRESS=y
-# CONFIG_KASAN is not set
 CONFIG_HAVE_ARCH_KFENCE=y
 # CONFIG_KFENCE is not set
 # end of Memory Debugging
@@ -2913,7 +2937,6 @@ CONFIG_LOCK_DEBUGGING_SUPPORT=y
 CONFIG_STACKTRACE=y
 # CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set
 # CONFIG_DEBUG_KOBJECT is not set
-CONFIG_HAVE_DEBUG_BUGVERBOSE=y
 
 #
 # Debug kernel data structures
@@ -2945,7 +2968,6 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=59
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
-CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
 CONFIG_HAVE_C_RECORDMCOUNT=y
@@ -2973,19 +2995,21 @@ CONFIG_CC_HAS_SANCOV_TRACE_PC=y
 # CONFIG_KCOV is not set
 CONFIG_RUNTIME_TESTING_MENU=y
 # CONFIG_LKDTM is not set
-# CONFIG_TEST_LIST_SORT is not set
 # CONFIG_TEST_MIN_HEAP is not set
 # CONFIG_TEST_SORT is not set
+# CONFIG_TEST_DIV64 is not set
 # CONFIG_BACKTRACE_SELF_TEST is not set
 # CONFIG_RBTREE_TEST is not set
 # CONFIG_REED_SOLOMON_TEST is not set
 # CONFIG_INTERVAL_TREE_TEST is not set
 # CONFIG_ATOMIC64_SELFTEST is not set
 # CONFIG_TEST_HEXDUMP is not set
+# CONFIG_STRING_SELFTEST is not set
 # CONFIG_TEST_STRING_HELPERS is not set
 # CONFIG_TEST_STRSCPY is not set
 # CONFIG_TEST_KSTRTOX is not set
 # CONFIG_TEST_PRINTF is not set
+# CONFIG_TEST_SCANF is not set
 # CONFIG_TEST_BITMAP is not set
 # CONFIG_TEST_UUID is not set
 # CONFIG_TEST_XARRAY is not set
@@ -3001,6 +3025,7 @@ CONFIG_RUNTIME_TESTING_MENU=y
 # CONFIG_TEST_STACKINIT is not set
 # CONFIG_TEST_MEMINIT is not set
 # CONFIG_TEST_FREE_PAGES is not set
+CONFIG_ARCH_USE_MEMTEST=y
 # CONFIG_MEMTEST is not set
 # end of Kernel Testing and Coverage
 # end of Kernel hacking

resources/linux-config-x86_64

@@ -1,11 +1,13 @@
 #
 # Automatically generated file; DO NOT EDIT.
-# Linux/x86 5.12.0 Kernel Configuration
+# Linux/x86 5.14.0 Kernel Configuration
 #
-CONFIG_CC_VERSION_TEXT="gcc (GCC) 10.2.1 20201125 (Red Hat 10.2.1-9)"
+CONFIG_CC_VERSION_TEXT="gcc (Ubuntu 10.3.0-1ubuntu1) 10.3.0"
 CONFIG_CC_IS_GCC=y
-CONFIG_GCC_VERSION=100201
+CONFIG_GCC_VERSION=100300
 CONFIG_CLANG_VERSION=0
+CONFIG_AS_IS_GNU=y
+CONFIG_AS_VERSION=23500
 CONFIG_LD_IS_BFD=y
 CONFIG_LD_VERSION=23500
 CONFIG_LLD_VERSION=0
@@ -13,6 +15,7 @@ CONFIG_CC_CAN_LINK=y
 CONFIG_CC_CAN_LINK_STATIC=y
 CONFIG_CC_HAS_ASM_GOTO=y
 CONFIG_CC_HAS_ASM_INLINE=y
+CONFIG_CC_HAS_NO_PROFILE_FN_ATTR=y
 CONFIG_IRQ_WORK=y
 CONFIG_BUILDTIME_TABLE_SORT=y
 CONFIG_THREAD_INFO_IN_TASK=y
@@ -97,9 +100,22 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 # end of Timers subsystem
 
+CONFIG_BPF=y
+CONFIG_HAVE_EBPF_JIT=y
+CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
+
+#
+# BPF subsystem
+#
+CONFIG_BPF_SYSCALL=y
+# CONFIG_BPF_UNPRIV_DEFAULT_OFF is not set
+# CONFIG_BPF_PRELOAD is not set
+# end of BPF subsystem
+
 CONFIG_PREEMPT_NONE=y
 # CONFIG_PREEMPT_VOLUNTARY is not set
 # CONFIG_PREEMPT is not set
+# CONFIG_SCHED_CORE is not set
 
 #
 # CPU/Task time and stats accounting
@@ -173,6 +189,7 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
 CONFIG_CGROUP_BPF=y
+# CONFIG_CGROUP_MISC is not set
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_SOCK_CGROUP_DATA=y
 CONFIG_NAMESPACES=y
@@ -202,7 +219,6 @@ CONFIG_LD_ORPHAN_WARN=y
 CONFIG_SYSCTL=y
 CONFIG_SYSCTL_EXCEPTION_TRACE=y
 CONFIG_HAVE_PCSPKR_PLATFORM=y
-CONFIG_BPF=y
 CONFIG_EXPERT=y
 CONFIG_MULTIUSER=y
 CONFIG_SGETMASK_SYSCALL=y
@@ -226,14 +242,12 @@ CONFIG_AIO=y
 CONFIG_IO_URING=y
 CONFIG_ADVISE_SYSCALLS=y
 CONFIG_HAVE_ARCH_USERFAULTFD_WP=y
+CONFIG_HAVE_ARCH_USERFAULTFD_MINOR=y
 CONFIG_MEMBARRIER=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 CONFIG_KALLSYMS_ABSOLUTE_PERCPU=y
 CONFIG_KALLSYMS_BASE_RELATIVE=y
-CONFIG_BPF_SYSCALL=y
-CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
-# CONFIG_BPF_PRELOAD is not set
 CONFIG_USERFAULTFD=y
 CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y
 # CONFIG_KCMP is not set
@@ -280,7 +294,6 @@ CONFIG_GENERIC_BUG=y
 CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
 CONFIG_ARCH_HAS_CPU_RELAX=y
-CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_ARCH_HAS_FILTER_PGPROT=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
 CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
@@ -288,7 +301,6 @@ CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
 CONFIG_ARCH_HIBERNATION_POSSIBLE=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_ARCH_WANT_GENERAL_HUGETLB=y
-CONFIG_ZONE_DMA32=y
 CONFIG_AUDIT_ARCH=y
 CONFIG_X86_64_SMP=y
 CONFIG_ARCH_SUPPORTS_UPROBES=y
@@ -300,7 +312,6 @@ CONFIG_CC_HAS_SANE_STACKPROTECTOR=y
 #
 # Processor type and features
 #
-CONFIG_ZONE_DMA=y
 CONFIG_SMP=y
 CONFIG_X86_FEATURE_NAMES=y
 CONFIG_X86_X2APIC=y
@@ -398,7 +409,6 @@ CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000
 # CONFIG_X86_PMEM_LEGACY is not set
 CONFIG_X86_CHECK_BIOS_CORRUPTION=y
 CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
-CONFIG_X86_RESERVE_LOW=64
 CONFIG_MTRR=y
 CONFIG_MTRR_SANITIZER=y
 CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT=0
@@ -447,12 +457,8 @@ CONFIG_HAVE_LIVEPATCH=y
 # end of Processor type and features
 
 CONFIG_ARCH_HAS_ADD_PAGES=y
-CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
-CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
+CONFIG_ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE=y
 CONFIG_USE_PERCPU_NUMA_NODE_ID=y
-CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
-CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y
-CONFIG_ARCH_ENABLE_THP_MIGRATION=y
 
 #
 # Power management and ACPI options
@@ -520,7 +526,9 @@ CONFIG_HAVE_ACPI_APEI_NMI=y
 # CONFIG_ACPI_DPTF is not set
 # CONFIG_ACPI_CONFIGFS is not set
 # CONFIG_PMIC_OPREGION is not set
+CONFIG_ACPI_VIOT=y
 CONFIG_X86_PM_TIMER=y
+# CONFIG_ACPI_PRMT is not set
 
 #
 # CPU Frequency scaling
@@ -639,6 +647,7 @@ CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT=y
 CONFIG_HAVE_KVM_IRQ_BYPASS=y
 CONFIG_HAVE_KVM_NO_POLL=y
 CONFIG_KVM_XFER_TO_GUEST_WORK=y
+CONFIG_HAVE_KVM_PM_NOTIFIER=y
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=y
 # CONFIG_KVM_WERROR is not set
@@ -678,6 +687,7 @@ CONFIG_ARCH_HAS_SET_MEMORY=y
 CONFIG_ARCH_HAS_SET_DIRECT_MAP=y
 CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST=y
 CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT=y
+CONFIG_ARCH_WANTS_NO_INSTR=y
 CONFIG_HAVE_ASM_MODVERSIONS=y
 CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
 CONFIG_HAVE_RSEQ=y
@@ -734,6 +744,8 @@ CONFIG_HAVE_RELIABLE_STACKTRACE=y
 # CONFIG_COMPAT_32BIT_TIME is not set
 CONFIG_HAVE_ARCH_VMAP_STACK=y
 CONFIG_VMAP_STACK=y
+CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET=y
+# CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT is not set
 CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y
 CONFIG_STRICT_KERNEL_RWX=y
 CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
@@ -768,14 +780,16 @@ CONFIG_BLK_CGROUP_RWSTAT=y
 CONFIG_BLK_DEV_BSG=y
 CONFIG_BLK_DEV_BSGLIB=y
 CONFIG_BLK_DEV_INTEGRITY=y
+CONFIG_BLK_DEV_INTEGRITY_T10=y
 # CONFIG_BLK_DEV_ZONED is not set
 CONFIG_BLK_DEV_THROTTLING=y
 # CONFIG_BLK_DEV_THROTTLING_LOW is not set
 CONFIG_BLK_CMDLINE_PARSER=y
 CONFIG_BLK_WBT=y
+CONFIG_BLK_WBT_MQ=y
 # CONFIG_BLK_CGROUP_IOLATENCY is not set
 # CONFIG_BLK_CGROUP_IOCOST is not set
-CONFIG_BLK_WBT_MQ=y
+# CONFIG_BLK_CGROUP_IOPRIO is not set
 CONFIG_BLK_DEBUG_FS=y
 # CONFIG_BLK_SED_OPAL is not set
 # CONFIG_BLK_INLINE_ENCRYPTION is not set
@@ -849,7 +863,6 @@ CONFIG_COREDUMP=y
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_SPARSEMEM=y
-CONFIG_NEED_MULTIPLE_NODES=y
 CONFIG_SPARSEMEM_EXTREME=y
 CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
 CONFIG_SPARSEMEM_VMEMMAP=y
@@ -857,19 +870,24 @@ CONFIG_HAVE_FAST_GUP=y
 CONFIG_NUMA_KEEP_MEMINFO=y
 CONFIG_MEMORY_ISOLATION=y
 CONFIG_HAVE_BOOTMEM_INFO_NODE=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTPLUG_SPARSE=y
 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
 CONFIG_MEMORY_HOTREMOVE=y
+CONFIG_MHP_MEMMAP_ON_MEMORY=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
 CONFIG_MEMORY_BALLOON=y
 CONFIG_BALLOON_COMPACTION=y
 CONFIG_COMPACTION=y
 CONFIG_PAGE_REPORTING=y
 CONFIG_MIGRATION=y
+CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y
+CONFIG_ARCH_ENABLE_THP_MIGRATION=y
 CONFIG_CONTIG_ALLOC=y
 CONFIG_PHYS_ADDR_T_64BIT=y
-CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_MMU_NOTIFIER=y
 CONFIG_KSM=y
@@ -903,7 +921,11 @@ CONFIG_ZSMALLOC_STAT=y
 CONFIG_GENERIC_EARLY_IOREMAP=y
 # CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set
 # CONFIG_IDLE_PAGE_TRACKING is not set
+CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_ARCH_HAS_PTE_DEVMAP=y
+CONFIG_ARCH_HAS_ZONE_DMA_SET=y
+CONFIG_ZONE_DMA=y
+CONFIG_ZONE_DMA32=y
 CONFIG_ZONE_DEVICE=y
 CONFIG_DEV_PAGEMAP_OPS=y
 # CONFIG_DEVICE_PRIVATE is not set
@@ -911,6 +933,7 @@ CONFIG_PERCPU_STATS=y
 # CONFIG_GUP_TEST is not set
 # CONFIG_READ_ONLY_THP_FOR_FS is not set
 CONFIG_ARCH_HAS_PTE_SPECIAL=y
+CONFIG_SECRETMEM=y
 # end of Memory Management options
 
 CONFIG_NET=y
@@ -974,7 +997,6 @@ CONFIG_NET_PTP_CLASSIFY=y
 # CONFIG_ATM is not set
 # CONFIG_L2TP is not set
 # CONFIG_BRIDGE is not set
-CONFIG_HAVE_NET_DSA=y
 # CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
@@ -994,6 +1016,7 @@ CONFIG_VSOCKETS_DIAG=y
 # CONFIG_VSOCKETS_LOOPBACK is not set
 CONFIG_VIRTIO_VSOCKETS=y
 CONFIG_VIRTIO_VSOCKETS_COMMON=y
+# CONFIG_HYPERV_VSOCKETS is not set
 # CONFIG_NETLINK_DIAG is not set
 # CONFIG_MPLS is not set
 # CONFIG_NET_NSH is not set
@@ -1002,6 +1025,7 @@ CONFIG_VIRTIO_VSOCKETS_COMMON=y
 # CONFIG_NET_L3_MASTER_DEV is not set
 # CONFIG_QRTR is not set
 # CONFIG_NET_NCSI is not set
+CONFIG_PCPU_DEV_REFCNT=y
 CONFIG_RPS=y
 CONFIG_RFS_ACCEL=y
 CONFIG_SOCK_RX_QUEUE_MAPPING=y
@@ -1039,7 +1063,6 @@ CONFIG_GRO_CELLS=y
 CONFIG_NET_SOCK_MSG=y
 CONFIG_FAILOVER=y
 # CONFIG_ETHTOOL_NETLINK is not set
-CONFIG_HAVE_EBPF_JIT=y
 
 #
 # Device Drivers
@@ -1073,6 +1096,7 @@ CONFIG_PCI_LOCKLESS_CONFIG=y
 # CONFIG_PCI_PASID is not set
 # CONFIG_PCI_P2PDMA is not set
 CONFIG_PCI_LABEL=y
+# CONFIG_PCI_HYPERV is not set
 # CONFIG_PCIE_BUS_TUNE_OFF is not set
 CONFIG_PCIE_BUS_DEFAULT=y
 # CONFIG_PCIE_BUS_SAFE is not set
@@ -1088,6 +1112,7 @@ CONFIG_HOTPLUG_PCI_ACPI=y
 # PCI controller drivers
 #
 # CONFIG_VMD is not set
+# CONFIG_PCI_HYPERV_INTERFACE is not set
 
 #
 # DesignWare PCI Core Support
@@ -1182,7 +1207,6 @@ CONFIG_ZRAM_DEF_COMP_LZORLE=y
 CONFIG_ZRAM_DEF_COMP="lzo-rle"
 # CONFIG_ZRAM_WRITEBACK is not set
 # CONFIG_ZRAM_MEMORY_TRACKING is not set
-# CONFIG_BLK_DEV_UMEM is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
 CONFIG_BLK_DEV_CRYPTOLOOP=y
@@ -1201,8 +1225,11 @@ CONFIG_VIRTIO_BLK=y
 #
 # NVME Support
 #
-# CONFIG_BLK_DEV_NVME is not set
+CONFIG_NVME_CORE=y
+CONFIG_BLK_DEV_NVME=y
+# CONFIG_NVME_MULTIPATH is not set
 # CONFIG_NVME_FC is not set
+# CONFIG_NVME_TCP is not set
 # CONFIG_NVME_TARGET is not set
 # end of NVME Support
 
@@ -1216,9 +1243,9 @@ CONFIG_VIRTIO_BLK=y
 # CONFIG_ENCLOSURE_SERVICES is not set
 # CONFIG_HP_ILO is not set
 # CONFIG_SRAM is not set
+# CONFIG_DW_XDATA_PCIE is not set
 # CONFIG_PCI_ENDPOINT_TEST is not set
 # CONFIG_XILINX_SDFEC is not set
-# CONFIG_PVPANIC is not set
 # CONFIG_C2PORT is not set
 
 #
@@ -1232,6 +1259,7 @@ CONFIG_VIRTIO_BLK=y
 #
 # Texas Instruments shared transport line discipline
 #
+# CONFIG_TI_ST is not set
 # end of Texas Instruments shared transport line discipline
 
 #
@@ -1248,11 +1276,9 @@ CONFIG_VIRTIO_BLK=y
 # CONFIG_MISC_RTSX_PCI is not set
 # CONFIG_HABANA_AI is not set
 # CONFIG_UACCE is not set
+# CONFIG_PVPANIC is not set
 # end of Misc devices
 
-CONFIG_HAVE_IDE=y
-# CONFIG_IDE is not set
-
 #
 # SCSI device support
 #
@@ -1295,13 +1321,6 @@ CONFIG_VETH=y
 CONFIG_VIRTIO_NET=y
 # CONFIG_NLMON is not set
 # CONFIG_ARCNET is not set
-
-#
-# Distributed Switch Architecture drivers
-#
-# CONFIG_NET_DSA_MV88E6XXX_PTP is not set
-# end of Distributed Switch Architecture drivers
-
 # CONFIG_ETHERNET is not set
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
@@ -1322,8 +1341,16 @@ CONFIG_VIRTIO_NET=y
 #
 # CONFIG_WLAN is not set
 # CONFIG_WAN is not set
+
+#
+# Wireless WAN
+#
+# CONFIG_WWAN is not set
+# end of Wireless WAN
+
 # CONFIG_VMXNET3 is not set
 # CONFIG_FUJITSU_ES is not set
+# CONFIG_HYPERV_NET is not set
 # CONFIG_NETDEVSIM is not set
 CONFIG_NET_FAILOVER=y
 # CONFIG_ISDN is not set
@@ -1354,6 +1381,9 @@ CONFIG_INPUT_EVDEV=y
 CONFIG_INPUT_KEYBOARD=y
 # CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_GPIO is not set
+# CONFIG_KEYBOARD_GPIO_POLLED is not set
+# CONFIG_KEYBOARD_MATRIX is not set
 # CONFIG_KEYBOARD_NEWTON is not set
 # CONFIG_KEYBOARD_OPENCORES is not set
 # CONFIG_KEYBOARD_SAMSUNG is not set
@@ -1368,8 +1398,12 @@ CONFIG_INPUT_MISC=y
 # CONFIG_INPUT_AD714X is not set
 # CONFIG_INPUT_E3X0_BUTTON is not set
 # CONFIG_INPUT_PCSPKR is not set
+# CONFIG_INPUT_GPIO_BEEPER is not set
+# CONFIG_INPUT_GPIO_DECODER is not set
+# CONFIG_INPUT_GPIO_VIBRA is not set
 # CONFIG_INPUT_ATLAS_BTNS is not set
 CONFIG_INPUT_UINPUT=y
+# CONFIG_INPUT_GPIO_ROTARY_ENCODER is not set
 # CONFIG_INPUT_ADXL34X is not set
 # CONFIG_INPUT_CMA3000 is not set
 # CONFIG_RMI4_CORE is not set
@@ -1440,11 +1474,11 @@ CONFIG_SERIAL_ARC_NR_PORTS=1
 # CONFIG_SERIAL_SPRD is not set
 # end of Serial drivers
 
+CONFIG_SERIAL_MCTRL_GPIO=y
 # CONFIG_SERIAL_NONSTANDARD is not set
 # CONFIG_N_GSM is not set
 # CONFIG_NOZOMI is not set
 # CONFIG_NULL_TTY is not set
-# CONFIG_TRACE_SINK is not set
 CONFIG_HVC_DRIVER=y
 CONFIG_SERIAL_DEV_BUS=y
 CONFIG_SERIAL_DEV_CTRL_TTYPORT=y
@@ -1462,10 +1496,7 @@ CONFIG_HW_RANDOM_VIRTIO=y
 # CONFIG_APPLICOM is not set
 # CONFIG_MWAVE is not set
 CONFIG_DEVMEM=y
-# CONFIG_DEVKMEM is not set
 CONFIG_NVRAM=y
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=256
 CONFIG_DEVPORT=y
 # CONFIG_HPET is not set
 CONFIG_HANGCHECK_TIMER=y
@@ -1515,7 +1546,60 @@ CONFIG_PTP_1588_CLOCK_KVM=y
 # end of PTP clock support
 
 # CONFIG_PINCTRL is not set
-# CONFIG_GPIOLIB is not set
+CONFIG_GPIOLIB=y
+CONFIG_GPIOLIB_FASTPATH_LIMIT=512
+CONFIG_GPIO_ACPI=y
+CONFIG_GPIOLIB_IRQCHIP=y
+# CONFIG_DEBUG_GPIO is not set
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_CDEV=y
+CONFIG_GPIO_CDEV_V1=y
+
+#
+# Memory mapped GPIO drivers
+#
+# CONFIG_GPIO_AMDPT is not set
+# CONFIG_GPIO_DWAPB is not set
+# CONFIG_GPIO_EXAR is not set
+# CONFIG_GPIO_GENERIC_PLATFORM is not set
+# CONFIG_GPIO_MB86S7X is not set
+# CONFIG_GPIO_VX855 is not set
+# CONFIG_GPIO_AMD_FCH is not set
+# end of Memory mapped GPIO drivers
+
+#
+# Port-mapped I/O GPIO drivers
+#
+# CONFIG_GPIO_F7188X is not set
+# CONFIG_GPIO_IT87 is not set
+# CONFIG_GPIO_SCH311X is not set
+# CONFIG_GPIO_WINBOND is not set
+# CONFIG_GPIO_WS16C48 is not set
+# end of Port-mapped I/O GPIO drivers
+
+#
+# MFD GPIO expanders
+#
+# end of MFD GPIO expanders
+
+#
+# PCI GPIO expanders
+#
+# CONFIG_GPIO_AMD8111 is not set
+# CONFIG_GPIO_BT8XX is not set
+# CONFIG_GPIO_ML_IOH is not set
+CONFIG_GPIO_PCI_IDIO_16=y
+# CONFIG_GPIO_PCIE_IDIO_24 is not set
+# CONFIG_GPIO_RDC321X is not set
+# end of PCI GPIO expanders
+
+#
+# Virtual GPIO drivers
+#
+# CONFIG_GPIO_AGGREGATOR is not set
+# CONFIG_GPIO_MOCKUP is not set
+# end of Virtual GPIO drivers
+
 # CONFIG_W1 is not set
 # CONFIG_POWER_RESET is not set
 # CONFIG_POWER_SUPPLY is not set
@@ -1549,6 +1633,7 @@ CONFIG_X86_THERMAL_VECTOR=y
 # end of ACPI INT340X thermal drivers
 
 # CONFIG_INTEL_PCH_THERMAL is not set
+# CONFIG_INTEL_TCC_COOLING is not set
 # end of Intel thermal drivers
 
 CONFIG_WATCHDOG=y
@@ -1557,6 +1642,7 @@ CONFIG_WATCHDOG_CORE=y
 CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED=y
 CONFIG_WATCHDOG_OPEN_TIMEOUT=0
 # CONFIG_WATCHDOG_SYSFS is not set
+# CONFIG_WATCHDOG_HRTIMER_PRETIMEOUT is not set
 
 #
 # Watchdog Pretimeout Governors
@@ -1606,6 +1692,7 @@ CONFIG_WATCHDOG_OPEN_TIMEOUT=0
 # CONFIG_SBC_EPX_C3_WATCHDOG is not set
 # CONFIG_NI903X_WDT is not set
 # CONFIG_NIC7018_WDT is not set
+# CONFIG_MEN_A21_WDT is not set
 CONFIG_VIRTIO_WDT=y
 
 #
@@ -1634,7 +1721,6 @@ CONFIG_BCMA_POSSIBLE=y
 # CONFIG_MFD_MT6397 is not set
 # CONFIG_MFD_RDC321X is not set
 # CONFIG_MFD_SM501 is not set
-# CONFIG_ABX500_CORE is not set
 # CONFIG_MFD_SYSCON is not set
 # CONFIG_MFD_TI_AM335X_TSCADC is not set
 # CONFIG_MFD_TQMX86 is not set
@@ -1713,6 +1799,7 @@ CONFIG_FB=y
 # CONFIG_FB_VIRTUAL is not set
 # CONFIG_FB_METRONOME is not set
 # CONFIG_FB_MB862XX is not set
+# CONFIG_FB_HYPERV is not set
 # CONFIG_FB_SIMPLE is not set
 # CONFIG_FB_SM712 is not set
 # end of Frame buffer Devices
@@ -1723,9 +1810,11 @@ CONFIG_FB=y
 CONFIG_LCD_CLASS_DEVICE=y
 # CONFIG_LCD_PLATFORM is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
+# CONFIG_BACKLIGHT_KTD253 is not set
 # CONFIG_BACKLIGHT_APPLE is not set
 # CONFIG_BACKLIGHT_QCOM_WLED is not set
 # CONFIG_BACKLIGHT_SAHARA is not set
+# CONFIG_BACKLIGHT_GPIO is not set
 # end of Backlight & LCD device support
 
 #
@@ -1806,16 +1895,17 @@ CONFIG_HID_REDRAGON=y
 # CONFIG_HID_PRIMAX is not set
 # CONFIG_HID_SAITEK is not set
 # CONFIG_HID_SAMSUNG is not set
+# CONFIG_HID_SEMITEK is not set
 # CONFIG_HID_SPEEDLINK is not set
 # CONFIG_HID_STEAM is not set
 # CONFIG_HID_STEELSERIES is not set
 # CONFIG_HID_SUNPLUS is not set
 # CONFIG_HID_RMI is not set
 # CONFIG_HID_GREENASIA is not set
+# CONFIG_HID_HYPERV_MOUSE is not set
 # CONFIG_HID_SMARTJOYPLUS is not set
 # CONFIG_HID_TIVO is not set
 # CONFIG_HID_TOPSEED is not set
-# CONFIG_HID_THRUSTMASTER is not set
 # CONFIG_HID_UDRAW_PS3 is not set
 # CONFIG_HID_XINMO is not set
 # CONFIG_HID_ZEROPLUS is not set
@@ -1864,7 +1954,6 @@ CONFIG_DMA_ACPI=y
 # CONFIG_INTEL_IDXD is not set
 # CONFIG_INTEL_IOATDMA is not set
 # CONFIG_PLX_DMA is not set
-# CONFIG_XILINX_ZYNQMP_DPDMA is not set
 # CONFIG_QCOM_HIDMA_MGMT is not set
 # CONFIG_QCOM_HIDMA is not set
 CONFIG_DW_DMAC_CORE=y
@@ -1902,6 +1991,7 @@ CONFIG_UIO_DMEM_GENIRQ=y
 # CONFIG_UIO_NETX is not set
 # CONFIG_UIO_PRUSS is not set
 # CONFIG_UIO_MF624 is not set
+# CONFIG_UIO_HV_GENERIC is not set
 CONFIG_VFIO_IOMMU_TYPE1=y
 CONFIG_VFIO_VIRQFD=y
 CONFIG_VFIO=y
@@ -1915,6 +2005,7 @@ CONFIG_VFIO_PCI_INTX=y
 CONFIG_IRQ_BYPASS_MANAGER=y
 # CONFIG_VIRT_DRIVERS is not set
 CONFIG_VIRTIO=y
+CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS=y
 CONFIG_VIRTIO_PCI_LIB=y
 CONFIG_VIRTIO_MENU=y
 CONFIG_VIRTIO_PCI=y
@@ -1931,10 +2022,14 @@ CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
 #
 # Microsoft Hyper-V guest support
 #
-# CONFIG_HYPERV is not set
+CONFIG_HYPERV=y
+CONFIG_HYPERV_TIMER=y
+# CONFIG_HYPERV_UTILS is not set
+# CONFIG_HYPERV_BALLOON is not set
 # end of Microsoft Hyper-V guest support
 
 # CONFIG_GREYBUS is not set
+# CONFIG_COMEDI is not set
 # CONFIG_STAGING is not set
 # CONFIG_X86_PLATFORM_DEVICES is not set
 CONFIG_PMC_ATOM=y
@@ -1942,9 +2037,16 @@ CONFIG_PMC_ATOM=y
 # CONFIG_MELLANOX_PLATFORM is not set
 # CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_HAVE_CLK=y
-CONFIG_CLKDEV_LOOKUP=y
 CONFIG_HAVE_CLK_PREPARE=y
 CONFIG_COMMON_CLK=y
+
+#
+# Clock driver for ARM Reference designs
+#
+# CONFIG_ICST is not set
+# CONFIG_CLK_SP810 is not set
+# end of Clock driver for ARM Reference designs
+
 # CONFIG_XILINX_VCU is not set
 # CONFIG_HWSPINLOCK is not set
 
@@ -1974,10 +2076,8 @@ CONFIG_IOMMU_DMA=y
 # CONFIG_AMD_IOMMU is not set
 # CONFIG_INTEL_IOMMU is not set
 # CONFIG_IRQ_REMAP is not set
+CONFIG_HYPERV_IOMMU=y
 CONFIG_VIRTIO_IOMMU=y
-CONFIG_VIRTIO_IOMMU_TOPOLOGY_HELPERS=y
-CONFIG_VIRTIO_IOMMU_TOPOLOGY=y
-CONFIG_ACPI_VIOT=y
 
 #
 # Remoteproc drivers
@@ -2056,6 +2156,7 @@ CONFIG_ACPI_VIOT=y
 # PHY Subsystem
 #
 # CONFIG_GENERIC_PHY is not set
+# CONFIG_PHY_CAN_TRANSCEIVER is not set
 # CONFIG_BCM_KONA_USB2_PHY is not set
 # CONFIG_PHY_PXA_28NM_HSIC is not set
 # CONFIG_PHY_PXA_28NM_USB2 is not set
@@ -2165,6 +2266,8 @@ CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW=y
 #
 # Caches
 #
+CONFIG_NETFS_SUPPORT=y
+# CONFIG_NETFS_STATS is not set
 CONFIG_FSCACHE=y
 # CONFIG_FSCACHE_STATS is not set
 # CONFIG_FSCACHE_HISTOGRAM is not set
@@ -2212,6 +2315,8 @@ CONFIG_TMPFS_XATTR=y
 # CONFIG_TMPFS_INODE64 is not set
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
+CONFIG_HUGETLB_PAGE_FREE_VMEMMAP=y
+# CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON is not set
 CONFIG_MEMFD_CREATE=y
 CONFIG_ARCH_HAS_GIGANTIC_PAGE=y
 CONFIG_CONFIGFS_FS=y
@@ -2350,6 +2455,7 @@ CONFIG_CRYPTO_SIMD=y
 # CONFIG_CRYPTO_RSA is not set
 # CONFIG_CRYPTO_DH is not set
 # CONFIG_CRYPTO_ECDH is not set
+# CONFIG_CRYPTO_ECDSA is not set
 # CONFIG_CRYPTO_ECRDSA is not set
 # CONFIG_CRYPTO_SM2 is not set
 # CONFIG_CRYPTO_CURVE25519 is not set
@@ -2507,6 +2613,8 @@ CONFIG_SYSTEM_BLACKLIST_KEYRING=y
 CONFIG_SYSTEM_BLACKLIST_HASH_LIST=""
 # end of Certificates for signature checking
 
+CONFIG_BINARY_PRINTF=y
+
 #
 # Library routines
 #
@@ -2598,7 +2706,6 @@ CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE=y
 CONFIG_ARCH_HAS_COPY_MC=y
 CONFIG_ARCH_STACKWALK=y
 CONFIG_SBITMAP=y
-# CONFIG_STRING_SELFTEST is not set
 # end of Library routines
 
 #
@@ -2610,6 +2717,7 @@ CONFIG_SBITMAP=y
 #
 CONFIG_PRINTK_TIME=y
 # CONFIG_PRINTK_CALLER is not set
+# CONFIG_STACKTRACE_BUILD_ID is not set
 CONFIG_CONSOLE_LOGLEVEL_DEFAULT=7
 CONFIG_CONSOLE_LOGLEVEL_QUIET=4
 CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4
@@ -2630,9 +2738,10 @@ CONFIG_STRIP_ASM_SYMS=y
 # CONFIG_HEADERS_INSTALL is not set
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_SECTION_MISMATCH_WARN_ONLY=y
-# CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_32B is not set
+# CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B is not set
 CONFIG_FRAME_POINTER=y
 CONFIG_STACK_VALIDATION=y
+# CONFIG_VMLINUX_MAP is not set
 # CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
 # end of Compile-time checks and compiler options
 
@@ -2830,19 +2939,21 @@ CONFIG_CC_HAS_SANCOV_TRACE_PC=y
 # CONFIG_KCOV is not set
 CONFIG_RUNTIME_TESTING_MENU=y
 # CONFIG_LKDTM is not set
-# CONFIG_TEST_LIST_SORT is not set
 # CONFIG_TEST_MIN_HEAP is not set
 # CONFIG_TEST_SORT is not set
+# CONFIG_TEST_DIV64 is not set
 # CONFIG_BACKTRACE_SELF_TEST is not set
 # CONFIG_RBTREE_TEST is not set
 # CONFIG_REED_SOLOMON_TEST is not set
 # CONFIG_INTERVAL_TREE_TEST is not set
 # CONFIG_ATOMIC64_SELFTEST is not set
 # CONFIG_TEST_HEXDUMP is not set
+# CONFIG_STRING_SELFTEST is not set
 # CONFIG_TEST_STRING_HELPERS is not set
 # CONFIG_TEST_STRSCPY is not set
 # CONFIG_TEST_KSTRTOX is not set
 # CONFIG_TEST_PRINTF is not set
+# CONFIG_TEST_SCANF is not set
 # CONFIG_TEST_BITMAP is not set
 # CONFIG_TEST_UUID is not set
 # CONFIG_TEST_XARRAY is not set
@@ -2859,6 +2970,9 @@ CONFIG_RUNTIME_TESTING_MENU=y
 # CONFIG_TEST_MEMINIT is not set
 # CONFIG_TEST_FREE_PAGES is not set
 # CONFIG_TEST_FPU is not set
+# CONFIG_TEST_CLOCKSOURCE_WATCHDOG is not set
+CONFIG_ARCH_USE_MEMTEST=y
 # CONFIG_MEMTEST is not set
+# CONFIG_HYPERV_TESTING is not set
 # end of Kernel Testing and Coverage
 # end of Kernel hacking

rpm/cloud-hypervisor.spec

@@ -1,6 +1,6 @@
 Name:           cloud-hypervisor
 Summary:        Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on top of KVM.
-Version:        15.0
+Version:        18.0
 Release:        0%{?dist}
 License:        ASL 2.0 or BSD-3-clause
 Group:          Applications/System

scripts/dev_cli.sh

@@ -178,16 +178,17 @@ cmd_help() {
     echo ""
     echo "    tests [--unit|--cargo|--all] [--libc musl|gnu] [-- [<cargo test args>]]"
     echo "        Run the Cloud Hypervisor tests."
-    echo "        --unit                Run the unit tests."
-    echo "        --cargo               Run the cargo tests."
-    echo "        --integration         Run the integration tests."
-    echo "        --integration-sgx     Run the SGX integration tests."
-    echo "        --integration-vfio    Run the VFIO integration tests."
-    echo "        --integration-windows Run the Windows guest integration tests."
-    echo "        --libc                Select the C library Cloud Hypervisor will be built against. Default is gnu"
-    echo "        --volumes             Hash separated volumes to be exported. Example --volumes /mnt:/mnt#/myvol:/myvol"
-    echo "        --hypervisor          Underlying hypervisor. Options kvm, mshv"
-    echo "        --all                 Run all tests."
+    echo "        --unit                       Run the unit tests."
+    echo "        --cargo                      Run the cargo tests."
+    echo "        --integration                Run the integration tests."
+    echo "        --integration-sgx            Run the SGX integration tests."
+    echo "        --integration-vfio           Run the VFIO integration tests."
+    echo "        --integration-windows        Run the Windows guest integration tests."
+    echo "        --integration-live-migration Run the live-migration integration tests."
+    echo "        --libc                       Select the C library Cloud Hypervisor will be built against. Default is gnu"
+    echo "        --volumes                    Hash separated volumes to be exported. Example --volumes /mnt:/mnt#/myvol:/myvol"
+    echo "        --hypervisor                 Underlying hypervisor. Options kvm, mshv"
+    echo "        --all                        Run all tests."
     echo ""
     echo "    build-container [--type]"
     echo "        Build the Cloud Hypervisor container."
@@ -198,6 +199,7 @@ cmd_help() {
     echo ""
     echo "    shell"
     echo "        Run the development container into an interactive, privileged BASH shell."
+    echo "        --volumes             Hash separated volumes to be exported. Example --volumes /mnt:/mnt#/myvol:/myvol"
     echo ""
     echo "    help"
     echo "        Display this help message."
@@ -238,9 +240,7 @@ cmd_build() {
     done
 
     ensure_build_dir
-    if [ $(uname -m) = "x86_64" ]; then
-	ensure_latest_ctr
-    fi
+    ensure_latest_ctr
 
     process_volumes_args
     if [[ "$hypervisor" != "kvm" ]]; then
@@ -279,9 +279,7 @@ cmd_clean() {
     cargo_args=("$@")
 
     ensure_build_dir
-    if [ $(uname -m) = "x86_64" ]; then
-	ensure_latest_ctr
-    fi
+    ensure_latest_ctr
 
     $DOCKER_RUNTIME run \
 	   --user "$(id -u):$(id -g)" \
@@ -301,19 +299,21 @@ cmd_tests() {
     integration_sgx=false
     integration_vfio=false
     integration_windows=false
+    integration_live_migration=false
     libc="gnu"
     arg_vols=""
     hypervisor="kvm"
     exported_device="/dev/kvm"
     while [ $# -gt 0 ]; do
 	case "$1" in
-            "-h"|"--help")           { cmd_help; exit 1; } ;;
-            "--unit")                { unit=true; } ;;
-            "--cargo")               { cargo=true; } ;;
-            "--integration")         { integration=true; } ;;
-            "--integration-sgx")     { integration_sgx=true; } ;;
-            "--integration-vfio")    { integration_vfio=true; } ;;
-            "--integration-windows") { integration_windows=true; } ;;
+            "-h"|"--help")                  { cmd_help; exit 1; } ;;
+            "--unit")                       { unit=true; } ;;
+            "--cargo")                      { cargo=true; } ;;
+            "--integration")                { integration=true; } ;;
+            "--integration-sgx")            { integration_sgx=true; } ;;
+            "--integration-vfio")           { integration_vfio=true; } ;;
+            "--integration-windows")        { integration_windows=true; } ;;
+            "--integration-live-migration") { integration_live_migration=true; } ;;
             "--libc")
                 shift
                 [[ "$1" =~ ^(musl|gnu)$ ]] || \
@@ -345,9 +345,7 @@ cmd_tests() {
     set -- "$@" '--hypervisor' $hypervisor
 
     ensure_build_dir
-    if [ $(uname -m) = "x86_64" ]; then
-	ensure_latest_ctr
-    fi
+    ensure_latest_ctr
 
     process_volumes_args
     target="$(uname -m)-unknown-linux-${libc}"
@@ -459,6 +457,25 @@ cmd_tests() {
 	       "$CTR_IMAGE" \
 	       ./scripts/run_integration_tests_windows.sh "$@" || fix_dir_perms $? || exit $?
     fi
+
+    if [ "$integration_live_migration" = true ] ;  then
+	say "Running 'live migration' integration tests for $target..."
+	$DOCKER_RUNTIME run \
+	       --workdir "$CTR_CLH_ROOT_DIR" \
+	       --rm \
+	       --privileged \
+	       --security-opt seccomp=unconfined \
+	       --ipc=host \
+	       --net="$CTR_CLH_NET" \
+	       --mount type=tmpfs,destination=/tmp \
+	       --volume /dev:/dev \
+	       --volume "$CLH_ROOT_DIR:$CTR_CLH_ROOT_DIR"  $exported_volumes \
+	       --volume "$CLH_INTEGRATION_WORKLOADS:$CTR_CLH_INTEGRATION_WORKLOADS" \
+	       --env USER="root" \
+	       --env CH_LIBC="${libc}" \
+	       "$CTR_IMAGE" \
+	       ./scripts/run_integration_tests_live_migration.sh "$@" || fix_dir_perms $? || exit $?
+    fi
     fix_dir_perms $?
 }
 
@@ -478,9 +495,7 @@ cmd_build-container() {
     done
 
     ensure_build_dir
-    if [ $(uname -m) = "x86_64" ]; then
-	ensure_latest_ctr
-    fi
+    ensure_latest_ctr
 
     BUILD_DIR=/tmp/cloud-hypervisor/container/
 
@@ -499,10 +514,22 @@ cmd_build-container() {
 }
 
 cmd_shell() {
+    while [ $# -gt 0 ]; do
+	case "$1" in
+            "-h"|"--help")  { cmd_help; exit 1; } ;;
+            "--volumes")
+                shift
+                arg_vols="$1"
+                ;;
+            "--")           { shift; break; } ;;
+            *)
+		;;
+	esac
+	shift
+    done
     ensure_build_dir
-    if [ $(uname -m) = "x86_64" ]; then
-	ensure_latest_ctr
-    fi
+    ensure_latest_ctr
+    process_volumes_args
     say_warn "Starting a privileged shell prompt as root ..."
     say_warn "WARNING: Your $CLH_ROOT_DIR folder will be bind-mounted in the container under $CTR_CLH_ROOT_DIR"
     $DOCKER_RUNTIME run \

scripts/run_integration_tests_aarch64.sh

@@ -13,9 +13,9 @@ EDK2_BUILD_DIR="$WORKLOADS_DIR/edk2_build"
 mkdir -p "$WORKLOADS_DIR"
 
 build_edk2() {
-    EDK2_REPO="https://github.com/cloud-hypervisor/edk2.git"
+    EDK2_REPO="https://github.com/tianocore/edk2.git"
     EDK2_DIR="edk2"
-    EDK2_BRANCH="ch-aarch64"
+    EDK2_BRANCH="master"
     EDK2_PLAT_REPO="https://github.com/tianocore/edk2-platforms.git"
     EDK2_PLAT_DIR="edk2-platforms"
     ACPICA_REPO="https://github.com/acpica/acpica.git"
@@ -79,7 +79,7 @@ update_workloads() {
     cp scripts/sha1sums-aarch64 $WORKLOADS_DIR
 
     BIONIC_OS_IMAGE_DOWNLOAD_NAME="bionic-server-cloudimg-arm64.img"
-    BIONIC_OS_IMAGE_DOWNLOAD_URL="https://cloudhypervisorstorage.blob.core.windows.net/images/$BIONIC_OS_IMAGE_DOWNLOAD_NAME"
+    BIONIC_OS_IMAGE_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$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
@@ -106,7 +106,7 @@ update_workloads() {
     fi
 
     FOCAL_OS_RAW_IMAGE_NAME="focal-server-cloudimg-arm64-custom.raw"
-    FOCAL_OS_RAW_IMAGE_DOWNLOAD_URL="https://cloudhypervisorstorage.blob.core.windows.net/images/$FOCAL_OS_RAW_IMAGE_NAME"
+    FOCAL_OS_RAW_IMAGE_DOWNLOAD_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_RAW_IMAGE_NAME"
     FOCAL_OS_RAW_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_RAW_IMAGE_NAME"
     if [ ! -f "$FOCAL_OS_RAW_IMAGE" ]; then
         pushd $WORKLOADS_DIR
@@ -117,7 +117,7 @@ update_workloads() {
     # Convert the raw image to qcow2 image to remove compressed blocks from the disk. Therefore letting the
     # qcow2 format image can be directly used in the integration test.
     FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME="focal-server-cloudimg-arm64-custom.qcow2"
-    FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_DOWNLOAD_URL="https://cloudhypervisorstorage.blob.core.windows.net/images/$FOCAL_OS_QCOW2_IMAGE_UNCOMPRESSED_NAME"
+    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
@@ -171,7 +171,7 @@ update_workloads() {
     }
 
     SRCDIR=$PWD
-    LINUX_CUSTOM_BRANCH="ch-5.12"
+    LINUX_CUSTOM_BRANCH="ch-5.14"
 
     # Check whether the local HEAD commit same as the remote HEAD or not. Remove the folder if they are different.
     if [ -d "$LINUX_CUSTOM_DIR" ]; then
@@ -249,14 +249,12 @@ process_common_args "$@"
 
 # aarch64 not supported for MSHV
 if [[ "$hypervisor" = "mshv" ]]; then
-    echo "Aarch64 is not supported in Microsoft Hypervisor"
+    echo "AArch64 is not supported in Microsoft Hypervisor"
     exit 1
 fi
 
-features_build_fdt="--no-default-features --features $hypervisor"
-features_build_acpi="--no-default-features --features $hypervisor,acpi"
-features_test_fdt="--no-default-features --features integration_tests,$hypervisor"
-features_test_acpi="--no-default-features --features integration_tests,$hypervisor,acpi"
+features_build=""
+features_test="--features integration_tests"
 
 # lock the workloads folder to avoid parallel updating by different containers
 (
@@ -283,7 +281,7 @@ fi
 export RUST_BACKTRACE=1
 
 # Test without ACPI
-cargo build --all --release $features_build_fdt --target $BUILD_TARGET
+cargo build --all --release $features_build --target $BUILD_TARGET
 strip target/$BUILD_TARGET/release/cloud-hypervisor
 strip target/$BUILD_TARGET/release/vhost_user_net
 strip target/$BUILD_TARGET/release/ch-remote
@@ -301,20 +299,33 @@ ovs-vsctl init
 ovs-vsctl set Open_vSwitch . other_config:dpdk-init=true
 service openvswitch-switch restart
 
-time cargo test $features_test_fdt "tests::parallel::$test_filter"
+# Run all direct kernel boot (Device Tree) test cases in mod `parallel`
+time cargo test $features_test "tests::parallel::$test_filter"
 RES=$?
-echo "Integration test on FDT finished with result $RES."
 
+# Run some tests in sequence since the result could be affected by other tests
+# running in parallel.
 if [ $RES -eq 0 ]; then
-    # Test with EDK2 + ACPI
-    cargo build --all --release $features_build_acpi --target $BUILD_TARGET
-    strip target/$BUILD_TARGET/release/cloud-hypervisor
-    strip target/$BUILD_TARGET/release/vhost_user_net
-    strip target/$BUILD_TARGET/release/ch-remote
-
-    time cargo test $features_test_acpi "tests::parallel::test_edk2_acpi_launch"
+    time cargo test $features_test "tests::sequential::$test_filter" -- --test-threads=1
     RES=$?
-    echo "Integration test on UEFI & ACPI finished with result $RES."
+else
+    exit $RES
+fi
+
+# Run all ACPI test cases
+if [ $RES -eq 0 ]; then
+    time cargo test $features_test "tests::aarch64_acpi::$test_filter"
+    RES=$?
+else
+    exit $RES
+fi
+
+# Run all test cases related to live migration
+if [ $RES -eq 0 ]; then
+    time cargo test $features_test "tests::live_migration::$test_filter" -- --test-threads=1
+    RES=$?
+else
+    exit $RES
 fi
 
 exit $RES

scripts/run_integration_tests_live_migration.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+set -x
+
+source $HOME/.cargo/env
+source $(dirname "$0")/test-util.sh
+
+export BUILD_TARGET=${BUILD_TARGET-x86_64-unknown-linux-gnu}
+
+WORKLOADS_DIR="$HOME/workloads"
+mkdir -p "$WORKLOADS_DIR"
+
+process_common_args "$@"
+
+# For now these values are deafult for kvm
+features_build=""
+features_test="--features integration_tests"
+
+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
+    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
+grep focal sha1sums-x86_64 | sha1sum --check
+if [ $? -ne 0 ]; then
+    echo "sha1sum validation of images failed, remove invalid images to fix the issue."
+    exit 1
+fi
+popd
+
+# Build custom kernel based on virtio-pmem and virtio-fs upstream patches
+VMLINUX_IMAGE="$WORKLOADS_DIR/vmlinux"
+
+LINUX_CUSTOM_DIR="$WORKLOADS_DIR/linux-custom"
+
+if [ ! -f "$VMLINUX_IMAGE" ]; then
+    SRCDIR=$PWD
+    pushd $WORKLOADS_DIR
+    time git clone --depth 1 "https://github.com/cloud-hypervisor/linux.git" -b "ch-5.14" $LINUX_CUSTOM_DIR
+    cp $SRCDIR/resources/linux-config-x86_64 $LINUX_CUSTOM_DIR/.config
+    popd
+fi
+
+if [ ! -f "$VMLINUX_IMAGE" ]; then
+    pushd $LINUX_CUSTOM_DIR
+    time make bzImage -j `nproc`
+    cp vmlinux $VMLINUX_IMAGE || exit 1
+    popd
+fi
+
+if [ -d "$LINUX_CUSTOM_DIR" ]; then
+    rm -rf $LINUX_CUSTOM_DIR
+fi
+
+BUILD_TARGET="$(uname -m)-unknown-linux-${CH_LIBC}"
+CFLAGS=""
+TARGET_CC=""
+if [[ "${BUILD_TARGET}" == "x86_64-unknown-linux-musl" ]]; then
+    TARGET_CC="musl-gcc"
+    CFLAGS="-I /usr/include/x86_64-linux-musl/ -idirafter /usr/include/"
+fi
+
+cargo build --all --release $features_build --target $BUILD_TARGET
+strip target/$BUILD_TARGET/release/cloud-hypervisor
+strip target/$BUILD_TARGET/release/vhost_user_net
+strip target/$BUILD_TARGET/release/ch-remote
+
+export RUST_BACKTRACE=1
+
+time cargo test $features_test "tests::live_migration::$test_filter" -- --test-threads=1
+RES=$?
+
+exit $RES

scripts/run_integration_tests_x86_64.sh

@@ -26,7 +26,7 @@ if [ ! -f "$FW" ]; then
 fi
 
 BIONIC_OS_IMAGE_NAME="bionic-server-cloudimg-amd64.qcow2"
-BIONIC_OS_IMAGE_URL="https://cloudhypervisorstorage.blob.core.windows.net/images/$BIONIC_OS_IMAGE_NAME"
+BIONIC_OS_IMAGE_URL="https://cloud-hypervisor.azureedge.net/$BIONIC_OS_IMAGE_NAME"
 BIONIC_OS_IMAGE="$WORKLOADS_DIR/$BIONIC_OS_IMAGE_NAME"
 if [ ! -f "$BIONIC_OS_IMAGE" ]; then
     pushd $WORKLOADS_DIR
@@ -44,7 +44,7 @@ fi
 
 
 FOCAL_OS_IMAGE_NAME="focal-server-cloudimg-amd64-custom-20210609-0.qcow2"
-FOCAL_OS_IMAGE_URL="https://cloudhypervisorstorage.blob.core.windows.net/images/$FOCAL_OS_IMAGE_NAME"
+FOCAL_OS_IMAGE_URL="https://cloud-hypervisor.azureedge.net/$FOCAL_OS_IMAGE_NAME"
 FOCAL_OS_IMAGE="$WORKLOADS_DIR/$FOCAL_OS_IMAGE_NAME"
 if [ ! -f "$FOCAL_OS_IMAGE" ]; then
     pushd $WORKLOADS_DIR
@@ -102,7 +102,7 @@ LINUX_CUSTOM_DIR="$WORKLOADS_DIR/linux-custom"
 if [ ! -f "$VMLINUX_IMAGE" ]; then
     SRCDIR=$PWD
     pushd $WORKLOADS_DIR
-    time git clone --depth 1 "https://github.com/cloud-hypervisor/linux.git" -b "ch-5.12" $LINUX_CUSTOM_DIR
+    time git clone --depth 1 "https://github.com/cloud-hypervisor/linux.git" -b "ch-5.14" $LINUX_CUSTOM_DIR
     cp $SRCDIR/resources/linux-config-x86_64 $LINUX_CUSTOM_DIR/.config
     popd
 fi

src/bin/ch-remote.rs

@@ -7,6 +7,7 @@
 extern crate clap;
 
 use api_client::simple_api_command;
+use api_client::simple_api_command_with_fds;
 use api_client::Error as ApiClientError;
 use clap::{App, AppSettings, Arg, ArgMatches, SubCommand};
 use option_parser::{ByteSized, ByteSizedParseError};
@@ -26,6 +27,7 @@ enum Error {
     AddFsConfig(vmm::config::Error),
     AddPmemConfig(vmm::config::Error),
     AddNetConfig(vmm::config::Error),
+    AddUserDeviceConfig(vmm::config::Error),
     AddVsockConfig(vmm::config::Error),
     Restore(vmm::config::Error),
 }
@@ -44,6 +46,7 @@ impl fmt::Display for Error {
             AddFsConfig(e) => write!(f, "Error parsing filesystem syntax: {}", e),
             AddPmemConfig(e) => write!(f, "Error parsing persistent memory syntax: {}", e),
             AddNetConfig(e) => write!(f, "Error parsing network syntax: {}", e),
+            AddUserDeviceConfig(e) => write!(f, "Error parsing user device syntax: {}", e),
             AddVsockConfig(e) => write!(f, "Error parsing vsock syntax: {}", e),
             Restore(e) => write!(f, "Error parsing restore syntax: {}", e),
         }
@@ -129,6 +132,19 @@ fn add_device_api_command(socket: &mut UnixStream, config: &str) -> Result<(), E
     .map_err(Error::ApiClient)
 }
 
+fn add_user_device_api_command(socket: &mut UnixStream, config: &str) -> Result<(), Error> {
+    let device_config =
+        vmm::config::UserDeviceConfig::parse(config).map_err(Error::AddUserDeviceConfig)?;
+
+    simple_api_command(
+        socket,
+        "PUT",
+        "add-user-device",
+        Some(&serde_json::to_string(&device_config).unwrap()),
+    )
+    .map_err(Error::ApiClient)
+}
+
 fn remove_device_api_command(socket: &mut UnixStream, id: &str) -> Result<(), Error> {
     let remove_device_data = vmm::api::VmRemoveDeviceData { id: id.to_owned() };
 
@@ -178,13 +194,20 @@ fn add_pmem_api_command(socket: &mut UnixStream, config: &str) -> Result<(), Err
 }
 
 fn add_net_api_command(socket: &mut UnixStream, config: &str) -> Result<(), Error> {
-    let net_config = vmm::config::NetConfig::parse(config).map_err(Error::AddNetConfig)?;
+    let mut net_config = vmm::config::NetConfig::parse(config).map_err(Error::AddNetConfig)?;
 
-    simple_api_command(
+    // NetConfig is modified on purpose here by taking the list of file
+    // descriptors out. Keeping the list and send it to the server side
+    // process would not make any sense since the file descriptor may be
+    // represented with different values.
+    let fds = net_config.fds.take().unwrap_or_default();
+
+    simple_api_command_with_fds(
         socket,
         "PUT",
         "add-net",
         Some(&serde_json::to_string(&net_config).unwrap()),
+        fds,
     )
     .map_err(Error::ApiClient)
 }
@@ -340,6 +363,14 @@ fn do_command(matches: &ArgMatches) -> Result<(), Error> {
                 .value_of("net_config")
                 .unwrap(),
         ),
+        Some("add-user-device") => add_user_device_api_command(
+            &mut socket,
+            matches
+                .subcommand_matches("add-user-device")
+                .unwrap()
+                .value_of("device_config")
+                .unwrap(),
+        ),
         Some("add-vsock") => add_vsock_api_command(
             &mut socket,
             matches
@@ -443,6 +474,15 @@ fn main() {
                         .help(vmm::config::NetConfig::SYNTAX),
                 ),
         )
+        .subcommand(
+            SubCommand::with_name("add-user-device")
+                .about("Add userspace device")
+                .arg(
+                    Arg::with_name("device_config")
+                        .index(1)
+                        .help(vmm::config::UserDeviceConfig::SYNTAX),
+                ),
+        )
         .subcommand(
             SubCommand::with_name("add-vsock")
                 .about("Add vsock device")

src/main.rs

@@ -12,7 +12,7 @@ use clap::{App, Arg, ArgGroup, ArgMatches};
 use libc::EFD_NONBLOCK;
 use log::LevelFilter;
 use option_parser::OptionParser;
-use seccomp::SeccompAction;
+use seccompiler::SeccompAction;
 use signal_hook::{
     consts::SIGSYS,
     iterator::{exfiltrator::WithRawSiginfo, SignalsInfo},
@@ -26,6 +26,7 @@ use std::thread;
 use thiserror::Error;
 use vmm::config;
 use vmm_sys_util::eventfd::EventFd;
+use vmm_sys_util::signal::block_signal;
 
 #[derive(Error, Debug)]
 enum Error {
@@ -150,7 +151,7 @@ fn create_app<'a, 'b>(
                     topology=<threads_per_core>:<cores_per_die>:<dies_per_package>:<packages>,\
                     kvm_hyperv=on|off,max_phys_bits=<maximum_number_of_physical_bits>",
                 )
-                .default_value(&default_vcpus)
+                .default_value(default_vcpus)
                 .group("vm-config"),
         )
         .arg(
@@ -159,12 +160,12 @@ fn create_app<'a, 'b>(
                 .help(
                     "Memory parameters \
                      \"size=<guest_memory_size>,mergeable=on|off,shared=on|off,\
-                     hugepages=on|off,hugepage_size=<hugepage_size>\
+                     hugepages=on|off,hugepage_size=<hugepage_size>,\
                      hotplug_method=acpi|virtio-mem,\
                      hotplug_size=<hotpluggable_memory_size>,\
                      hotplugged_size=<hotplugged_memory_size>\"",
                 )
-                .default_value(&default_memory)
+                .default_value(default_memory)
                 .group("vm-config"),
         )
         .arg(
@@ -174,7 +175,7 @@ fn create_app<'a, 'b>(
                     "User defined memory zone parameters \
                      \"size=<guest_memory_region_size>,file=<backing_file>,\
                      shared=on|off,\
-                     hugepages=on|off,hugepage_size=<hugepage_size>\
+                     hugepages=on|off,hugepage_size=<hugepage_size>,\
                      host_numa_node=<node_id>,\
                      id=<zone_identifier>,hotplug_size=<hotpluggable_memory_size>,\
                      hotplugged_size=<hotplugged_memory_size>\"",
@@ -229,7 +230,7 @@ fn create_app<'a, 'b>(
                 .help(
                     "Random number generator parameters \"src=<entropy_source_path>,iommu=on|off\"",
                 )
-                .default_value(&default_rng)
+                .default_value(default_rng)
                 .group("vm-config"),
         )
         .arg(
@@ -279,6 +280,14 @@ fn create_app<'a, 'b>(
                 .min_values(1)
                 .group("vm-config"),
         )
+        .arg(
+            Arg::with_name("user-device")
+                .long("user-device")
+                .help(config::UserDeviceConfig::SYNTAX)
+                .takes_value(true)
+                .min_values(1)
+                .group("vm-config"),
+        )
         .arg(
             Arg::with_name("vsock")
                 .long("vsock")
@@ -488,6 +497,13 @@ fn start_vmm(cmd_arguments: ArgMatches) -> Result<Option<String>, Error> {
             .unwrap();
     }
 
+    // Before we start any threads, mask the signals we'll be
+    // installing handlers for, to make sure they only ever run on the
+    // dedicated signal handling thread we'll start in a bit.
+    for sig in vmm::vm::HANDLED_SIGNALS {
+        block_signal(sig).unwrap();
+    }
+
     event!("vmm", "starting");
 
     let hypervisor = hypervisor::new().map_err(Error::CreateHypervisor)?;
@@ -656,6 +672,7 @@ mod unit_tests {
                     iommu: false,
                 },
                 devices: None,
+                user_devices: None,
                 vsock: None,
                 iommu: false,
                 #[cfg(target_arch = "x86_64")]

test_data/cloud-init/ubuntu/user-data

@@ -36,15 +36,18 @@ write_files:
         #!/bin/bash
 
         mount /dev/vdc /mnt
+        bash -c "echo 1af4 1042 > /sys/bus/pci/drivers/vfio-pci/new_id"
+        bash -c "echo 0000:00:05.0 > /sys/bus/pci/devices/0000\:00\:05.0/driver/unbind"
+        bash -c "echo 0000:00:05.0 > /sys/bus/pci/drivers/vfio-pci/bind"
         bash -c "echo 1af4 1041 > /sys/bus/pci/drivers/vfio-pci/new_id"
-        bash -c "echo 0000:00:06.0 > /sys/bus/pci/devices/0000\:00\:06.0/driver/unbind"
-        bash -c "echo 0000:00:06.0 > /sys/bus/pci/drivers/vfio-pci/bind"
         bash -c "echo 0000:00:07.0 > /sys/bus/pci/devices/0000\:00\:07.0/driver/unbind"
         bash -c "echo 0000:00:07.0 > /sys/bus/pci/drivers/vfio-pci/bind"
+        bash -c "echo 0000:00:08.0 > /sys/bus/pci/devices/0000\:00\:08.0/driver/unbind"
+        bash -c "echo 0000:00:08.0 > /sys/bus/pci/drivers/vfio-pci/bind"
         # 1G ram requires 512 pages
         echo 512 | sudo tee /proc/sys/vm/nr_hugepages
         sudo chmod a+rwX /dev/hugepages
-        /mnt/cloud-hypervisor --kernel /mnt/vmlinux --cmdline "console=hvc0 reboot=k panic=1 nomodules root=/dev/vda1 VFIOTAG" --disk path=/mnt/focal-server-cloudimg-amd64-custom-20210609-0.qcow2 path=/mnt/cloudinit.img --cpus boot=1 --memory size=512M,hotplug_size=1G,hugepages=on --device path=/sys/bus/pci/devices/0000:00:06.0/ path=/sys/bus/pci/devices/0000:00:07.0/ --api-socket /tmp/ch_api.sock
+        /mnt/cloud-hypervisor --kernel /mnt/vmlinux --cmdline "console=hvc0 reboot=k panic=1 nomodules root=/dev/vda1 VFIOTAG" --disk path=/mnt/focal-server-cloudimg-amd64-custom-20210609-0.qcow2 path=/mnt/cloudinit.img --cpus boot=1 --memory size=512M,hotplug_size=1G,hugepages=on --device path=/sys/bus/pci/devices/0000:00:05.0/ path=/sys/bus/pci/devices/0000:00:07.0/ path=/sys/bus/pci/devices/0000:00:08.0/ --api-socket /tmp/ch_api.sock
 
   -
     path: /etc/systemd/system/notify-booted.service

test_infra/src/lib.rs

@@ -226,7 +226,7 @@ impl DiskConfig for UbuntuDiskConfig {
             .expect("Expected reading user-data file in to succeed");
         user_data_string = user_data_string.replace(
             "@DEFAULT_TCP_LISTENER_MESSAGE",
-            &DEFAULT_TCP_LISTENER_MESSAGE,
+            DEFAULT_TCP_LISTENER_MESSAGE,
         );
         user_data_string = user_data_string.replace("@HOST_IP", &network.host_ip);
         user_data_string =
@@ -234,7 +234,7 @@ impl DiskConfig for UbuntuDiskConfig {
 
         fs::File::create(cloud_init_directory.join("user-data"))
             .unwrap()
-            .write_all(&user_data_string.as_bytes())
+            .write_all(user_data_string.as_bytes())
             .expect("Expected writing out user-data to succeed");
 
         let mut network_config_string = String::new();
@@ -260,7 +260,7 @@ impl DiskConfig for UbuntuDiskConfig {
 
         fs::File::create(cloud_init_directory.join("network-config"))
             .unwrap()
-            .write_all(&network_config_string.as_bytes())
+            .write_all(network_config_string.as_bytes())
             .expect("Expected writing out network-config to succeed");
 
         std::process::Command::new("mkdosfs")
@@ -595,12 +595,12 @@ pub fn exec_host_command_status(command: &str) -> ExitStatus {
     std::process::Command::new("bash")
         .args(&["-c", command])
         .status()
-        .expect(&format!("Expected '{}' to run", command))
+        .unwrap_or_else(|_| panic!("Expected '{}' to run", command))
 }
 
 pub fn exec_host_command_output(command: &str) -> Output {
     std::process::Command::new("bash")
         .args(&["-c", command])
         .output()
-        .expect(&format!("Expected '{}' to run", command))
+        .unwrap_or_else(|_| panic!("Expected '{}' to run", command))
 }

vfio_user/Cargo.toml

@@ -0,0 +1,20 @@
+[package]
+name = "vfio_user"
+version = "0.1.0"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2018"
+
+[dependencies]
+anyhow = "1.0.43"
+libc = "0.2.101"
+log = "0.4.14"
+serde = {version = ">=1.0.27", features = ["rc"] }
+serde_derive = ">=1.0.27"
+serde_json = ">=1.0.9"
+thiserror = "1.0.29"
+vm-memory = { version = "0.6.0", features = ["backend-mmap", "backend-atomic"] }
+vmm-sys-util = ">=0.3.1"
+
+[dependencies.vfio-bindings]
+version = "0.2.0"
+features = ["fam-wrappers"]

vfio_user/src/lib.rs

@@ -0,0 +1,675 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+use std::ffi::CString;
+use std::io::{IoSlice, Read, Write};
+use std::num::Wrapping;
+use std::os::unix::net::UnixStream;
+use std::os::unix::prelude::RawFd;
+use std::path::Path;
+use thiserror::Error;
+use vfio_bindings::bindings::vfio::*;
+use vm_memory::{ByteValued, FileOffset};
+use vmm_sys_util::sock_ctrl_msg::ScmSocket;
+
+#[macro_use]
+extern crate serde_derive;
+
+#[macro_use]
+extern crate log;
+
+#[allow(dead_code)]
+#[repr(u16)]
+#[derive(Clone, Copy, Debug)]
+enum Command {
+    Unknown = 0,
+    Version = 1,
+    DmaMap = 2,
+    DmaUnmap = 3,
+    DeviceGetInfo = 4,
+    DeviceGetRegionInfo = 5,
+    GetRegionIoFds = 6,
+    GetIrqInfo = 7,
+    SetIrqs = 8,
+    RegionRead = 9,
+    RegionWrite = 10,
+    DmaRead = 11,
+    DmaWrite = 12,
+    DeviceReset = 13,
+    UserDirtyPages = 14,
+}
+
+impl Default for Command {
+    fn default() -> Self {
+        Command::Unknown
+    }
+}
+
+#[allow(dead_code)]
+#[repr(u32)]
+#[derive(Clone, Copy, Debug, PartialEq)]
+enum HeaderFlags {
+    Command = 0,
+    Reply = 1,
+    NoReply = 1 << 4,
+    Error = 1 << 5,
+}
+
+impl Default for HeaderFlags {
+    fn default() -> Self {
+        HeaderFlags::Command
+    }
+}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct Header {
+    message_id: u16,
+    command: Command,
+    message_size: u32,
+    flags: u32,
+    error: u32,
+}
+
+unsafe impl ByteValued for Header {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct Version {
+    header: Header,
+    major: u16,
+    minor: u16,
+}
+unsafe impl ByteValued for Version {}
+
+#[derive(Serialize, Deserialize, Debug)]
+struct MigrationCapabilities {
+    pgsize: u32,
+}
+
+const fn default_max_msg_fds() -> u32 {
+    1
+}
+
+const fn default_max_data_xfer_size() -> u32 {
+    1048576
+}
+
+const fn default_migration_capabilities() -> MigrationCapabilities {
+    MigrationCapabilities { pgsize: 4096 }
+}
+
+#[repr(u32)]
+#[derive(Clone, Copy, Debug)]
+#[allow(dead_code)]
+enum DmaMapFlags {
+    Unknown = 0,
+    ReadOnly = 1,
+    WriteOnly = 2,
+    ReadWrite = 3,
+}
+
+impl Default for DmaMapFlags {
+    fn default() -> Self {
+        Self::Unknown
+    }
+}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct DmaMap {
+    header: Header,
+    argsz: u32,
+    flags: DmaMapFlags,
+    offset: u64,
+    address: u64,
+    size: u64,
+}
+
+unsafe impl ByteValued for DmaMap {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct DmaUnmap {
+    header: Header,
+    argsz: u32,
+    flags: u32,
+    address: u64,
+    size: u64,
+}
+
+unsafe impl ByteValued for DmaUnmap {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct DeviceGetInfo {
+    header: Header,
+    argsz: u32,
+    flags: u32,
+    num_regions: u32,
+    num_irqs: u32,
+}
+
+unsafe impl ByteValued for DeviceGetInfo {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct DeviceGetRegionInfo {
+    header: Header,
+    region_info: vfio_region_info,
+}
+
+unsafe impl ByteValued for DeviceGetRegionInfo {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct RegionAccess {
+    header: Header,
+    offset: u64,
+    region: u32,
+    count: u32,
+}
+
+unsafe impl ByteValued for RegionAccess {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct GetIrqInfo {
+    header: Header,
+    argsz: u32,
+    flags: u32,
+    index: u32,
+    count: u32,
+}
+
+unsafe impl ByteValued for GetIrqInfo {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct SetIrqs {
+    header: Header,
+    argsz: u32,
+    flags: u32,
+    index: u32,
+    start: u32,
+    count: u32,
+}
+
+unsafe impl ByteValued for SetIrqs {}
+
+#[repr(C)]
+#[derive(Default, Clone, Copy, Debug)]
+struct DeviceReset {
+    header: Header,
+}
+
+unsafe impl ByteValued for DeviceReset {}
+
+#[derive(Serialize, Deserialize, Debug)]
+struct Capabilities {
+    #[serde(default = "default_max_msg_fds")]
+    max_msg_fds: u32,
+    #[serde(default = "default_max_data_xfer_size")]
+    max_data_xfer_size: u32,
+    #[serde(default = "default_migration_capabilities")]
+    migration: MigrationCapabilities,
+}
+
+impl Default for Capabilities {
+    fn default() -> Self {
+        Self {
+            max_msg_fds: default_max_msg_fds(),
+            max_data_xfer_size: default_max_data_xfer_size(),
+            migration: default_migration_capabilities(),
+        }
+    }
+}
+
+pub struct Client {
+    stream: UnixStream,
+    next_message_id: Wrapping<u16>,
+    num_irqs: u32,
+    resettable: bool,
+    regions: Vec<Region>,
+}
+
+#[derive(Debug)]
+pub struct Region {
+    pub flags: u32,
+    pub index: u32,
+    pub size: u64,
+    pub file_offset: Option<FileOffset>,
+}
+
+#[derive(Debug)]
+pub struct IrqInfo {
+    pub index: u32,
+    pub flags: u32,
+    pub count: u32,
+}
+
+#[derive(Error, Debug)]
+pub enum Error {
+    #[error("Error connecting: {0}")]
+    Connect(#[source] std::io::Error),
+    #[error("Error serializing capabilities: {0}")]
+    SerializeCapabilites(#[source] serde_json::Error),
+    #[error("Error deserializing capabilities: {0}")]
+    DeserializeCapabilites(#[source] serde_json::Error),
+    #[error("Error writing to stream: {0}")]
+    StreamWrite(#[source] std::io::Error),
+    #[error("Error reading from stream: {0}")]
+    StreamRead(#[source] std::io::Error),
+    #[error("Error writing with file descriptors: {0}")]
+    SendWithFd(#[source] vmm_sys_util::errno::Error),
+    #[error("Error reading with file descriptors: {0}")]
+    ReceiveWithFd(#[source] vmm_sys_util::errno::Error),
+    #[error("Not a PCI device")]
+    NotPciDevice,
+}
+
+impl Client {
+    pub fn new(path: &Path) -> Result<Client, Error> {
+        let stream = UnixStream::connect(path).map_err(Error::Connect)?;
+
+        let mut client = Client {
+            next_message_id: Wrapping(0),
+            stream,
+            num_irqs: 0,
+            resettable: false,
+            regions: Vec::new(),
+        };
+
+        client.negotiate_version()?;
+
+        client.regions = client.get_regions()?;
+
+        Ok(client)
+    }
+
+    fn negotiate_version(&mut self) -> Result<(), Error> {
+        let caps = Capabilities::default();
+
+        let version_data = serde_json::to_string(&caps).map_err(Error::SerializeCapabilites)?;
+
+        let version = Version {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::Version,
+                flags: HeaderFlags::Command as u32,
+                message_size: (std::mem::size_of::<Version>() + version_data.len() + 1) as u32,
+                ..Default::default()
+            },
+            major: 0,
+            minor: 1,
+        };
+        info!("Command: {:?}", version);
+
+        let version_data = CString::new(version_data.as_bytes()).unwrap();
+        let bufs = vec![
+            IoSlice::new(version.as_slice()),
+            IoSlice::new(version_data.as_bytes_with_nul()),
+        ];
+
+        // TODO: Use write_all_vectored() when ready
+        let _ = self
+            .stream
+            .write_vectored(&bufs)
+            .map_err(Error::StreamWrite)?;
+
+        info!(
+            "Sent client version information: major = {} minor = {} capabilities = {:?}",
+            version.major, version.minor, &caps
+        );
+
+        self.next_message_id += Wrapping(1);
+
+        let mut server_version: Version = Version::default();
+        self.stream
+            .read_exact(server_version.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+
+        info!("Reply: {:?}", server_version);
+
+        let mut server_version_data = Vec::new();
+        server_version_data.resize(
+            server_version.header.message_size as usize - std::mem::size_of::<Version>(),
+            0,
+        );
+        self.stream
+            .read_exact(server_version_data.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+
+        let server_caps: Capabilities =
+            serde_json::from_slice(&server_version_data[0..server_version_data.len() - 1])
+                .map_err(Error::DeserializeCapabilites)?;
+
+        info!(
+            "Received server version information: major = {} minor = {} capabilities = {:?}",
+            server_version.major, server_version.minor, &server_caps
+        );
+
+        Ok(())
+    }
+
+    pub fn dma_map(
+        &mut self,
+        offset: u64,
+        address: u64,
+        size: u64,
+        fd: RawFd,
+    ) -> Result<(), Error> {
+        let dma_map = DmaMap {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::DmaMap,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<DmaMap>() as u32,
+                ..Default::default()
+            },
+            argsz: (std::mem::size_of::<DmaMap>() - std::mem::size_of::<Header>()) as u32,
+            flags: DmaMapFlags::ReadWrite,
+            offset,
+            address,
+            size,
+        };
+        info!("Command: {:?}", dma_map);
+        self.next_message_id += Wrapping(1);
+        self.stream
+            .send_with_fd(dma_map.as_slice(), fd)
+            .map_err(Error::SendWithFd)?;
+
+        let mut reply = Header::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+
+        Ok(())
+    }
+
+    pub fn dma_unmap(&mut self, address: u64, size: u64) -> Result<(), Error> {
+        let dma_unmap = DmaUnmap {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::DmaUnmap,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<DmaUnmap>() as u32,
+                ..Default::default()
+            },
+            argsz: (std::mem::size_of::<DmaUnmap>() - std::mem::size_of::<Header>()) as u32,
+            flags: 0,
+            address,
+            size,
+        };
+        info!("Command: {:?}", dma_unmap);
+        self.next_message_id += Wrapping(1);
+        self.stream
+            .write_all(dma_unmap.as_slice())
+            .map_err(Error::StreamWrite)?;
+
+        let mut reply = DmaUnmap::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+
+        Ok(())
+    }
+
+    pub fn reset(&mut self) -> Result<(), Error> {
+        let reset = DeviceReset {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::DeviceReset,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<DeviceReset>() as u32,
+                ..Default::default()
+            },
+        };
+        info!("Command: {:?}", reset);
+        self.next_message_id += Wrapping(1);
+        self.stream
+            .write_all(reset.as_slice())
+            .map_err(Error::StreamWrite)?;
+
+        let mut reply = Header::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+
+        Ok(())
+    }
+
+    fn get_regions(&mut self) -> Result<Vec<Region>, Error> {
+        let get_info = DeviceGetInfo {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::DeviceGetInfo,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<DeviceGetInfo>() as u32,
+                ..Default::default()
+            },
+            argsz: std::mem::size_of::<DeviceGetInfo>() as u32,
+            ..Default::default()
+        };
+        info!("Command: {:?}", get_info);
+        self.next_message_id += Wrapping(1);
+
+        self.stream
+            .write_all(get_info.as_slice())
+            .map_err(Error::StreamWrite)?;
+
+        let mut reply = DeviceGetInfo::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+        self.num_irqs = reply.num_irqs;
+
+        if reply.flags & VFIO_DEVICE_FLAGS_PCI != VFIO_DEVICE_FLAGS_PCI {
+            return Err(Error::NotPciDevice);
+        }
+
+        self.resettable = reply.flags & VFIO_DEVICE_FLAGS_RESET != VFIO_DEVICE_FLAGS_RESET;
+
+        let num_regions = reply.num_regions;
+        let mut regions = Vec::new();
+        for index in 0..num_regions {
+            let get_region_info = DeviceGetRegionInfo {
+                header: Header {
+                    message_id: self.next_message_id.0,
+                    command: Command::DeviceGetRegionInfo,
+                    flags: HeaderFlags::Command as u32,
+                    message_size: std::mem::size_of::<DeviceGetRegionInfo>() as u32,
+                    ..Default::default()
+                },
+                region_info: vfio_region_info {
+                    argsz: 1024, // Arbitrary max size
+                    index,
+                    ..Default::default()
+                },
+            };
+            info!("Command: {:?}", get_region_info);
+            self.next_message_id += Wrapping(1);
+
+            self.stream
+                .write_all(get_region_info.as_slice())
+                .map_err(Error::StreamWrite)?;
+
+            let mut reply = DeviceGetRegionInfo::default();
+            let (_, fd) = self
+                .stream
+                .recv_with_fd(reply.as_mut_slice())
+                .map_err(Error::ReceiveWithFd)?;
+            info!("Reply: {:?}", reply);
+
+            regions.push(Region {
+                flags: reply.region_info.flags,
+                index: reply.region_info.index,
+                size: reply.region_info.size,
+                file_offset: fd.map(|fd| FileOffset::new(fd, reply.region_info.offset)),
+            });
+
+            // TODO: Handle region with capabilities
+            let mut _cap_data = Vec::with_capacity(
+                reply.header.message_size as usize - std::mem::size_of::<DeviceGetRegionInfo>(),
+            );
+            _cap_data.resize(_cap_data.capacity(), 0u8);
+            self.stream
+                .read_exact(_cap_data.as_mut_slice())
+                .map_err(Error::StreamRead)?;
+        }
+
+        Ok(regions)
+    }
+
+    pub fn region_read(&mut self, region: u32, offset: u64, data: &mut [u8]) -> Result<(), Error> {
+        let region_read = RegionAccess {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::RegionRead,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<RegionAccess>() as u32,
+                ..Default::default()
+            },
+            offset,
+            count: data.len() as u32,
+            region,
+        };
+        info!("Command: {:?}", region_read);
+        self.next_message_id += Wrapping(1);
+        self.stream
+            .write_all(region_read.as_slice())
+            .map_err(Error::StreamWrite)?;
+
+        let mut reply = RegionAccess::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+        self.stream.read_exact(data).map_err(Error::StreamRead)?;
+        Ok(())
+    }
+
+    pub fn region_write(&mut self, region: u32, offset: u64, data: &[u8]) -> Result<(), Error> {
+        let region_write = RegionAccess {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::RegionWrite,
+                flags: HeaderFlags::Command as u32,
+                message_size: (std::mem::size_of::<RegionAccess>() + data.len()) as u32,
+                ..Default::default()
+            },
+            offset,
+            count: data.len() as u32,
+            region,
+        };
+        info!("Command: {:?}", region_write);
+        self.next_message_id += Wrapping(1);
+
+        let bufs = vec![IoSlice::new(region_write.as_slice()), IoSlice::new(data)];
+
+        // TODO: Use write_all_vectored() when ready
+        let _ = self
+            .stream
+            .write_vectored(&bufs)
+            .map_err(Error::StreamWrite)?;
+
+        let mut reply = RegionAccess::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+        Ok(())
+    }
+
+    pub fn get_irq_info(&mut self, index: u32) -> Result<IrqInfo, Error> {
+        let get_irq_info = GetIrqInfo {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::GetIrqInfo,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<GetIrqInfo>() as u32,
+                ..Default::default()
+            },
+            argsz: (std::mem::size_of::<GetIrqInfo>() - std::mem::size_of::<Header>()) as u32,
+            flags: 0,
+            index,
+            count: 0,
+        };
+        info!("Command: {:?}", get_irq_info);
+        self.next_message_id += Wrapping(1);
+
+        self.stream
+            .write_all(get_irq_info.as_slice())
+            .map_err(Error::StreamWrite)?;
+
+        let mut reply = GetIrqInfo::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+
+        Ok(IrqInfo {
+            index: reply.index,
+            flags: reply.flags,
+            count: reply.count,
+        })
+    }
+
+    pub fn set_irqs(
+        &mut self,
+        index: u32,
+        flags: u32,
+        start: u32,
+        count: u32,
+        fds: &[RawFd],
+    ) -> Result<(), Error> {
+        let set_irqs = SetIrqs {
+            header: Header {
+                message_id: self.next_message_id.0,
+                command: Command::SetIrqs,
+                flags: HeaderFlags::Command as u32,
+                message_size: std::mem::size_of::<SetIrqs>() as u32,
+                ..Default::default()
+            },
+            argsz: (std::mem::size_of::<SetIrqs>() - std::mem::size_of::<Header>()) as u32,
+            flags,
+            start,
+            index,
+            count,
+        };
+        info!("Command: {:?}", set_irqs);
+        self.next_message_id += Wrapping(1);
+
+        self.stream
+            .send_with_fds(&[set_irqs.as_slice()], fds)
+            .map_err(Error::SendWithFd)?;
+
+        let mut reply = Header::default();
+        self.stream
+            .read_exact(reply.as_mut_slice())
+            .map_err(Error::StreamRead)?;
+        info!("Reply: {:?}", reply);
+
+        Ok(())
+    }
+
+    pub fn region(&self, region_index: u32) -> Option<&Region> {
+        for region in &self.regions {
+            if region.index == region_index {
+                return Some(region);
+            }
+        }
+
+        None
+    }
+
+    pub fn resettable(&self) -> bool {
+        self.resettable
+    }
+}

vhdx/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "vhdx"
+version = "0.1.0"
+authors = ["The Cloud Hypervisor Authors"]
+edition = "2018"
+license = "Apache-2.0"
+
+[dependencies]
+byteorder = "1.4.3"
+crc32c = "0.6.0"
+libc = "0.2.101"
+log = "0.4.14"
+remain = "0.2.2"
+thiserror = "1.0"
+uuid = { version = "0.8.2", features = ["v4"] }
+vmm-sys-util = ">=0.3.1"

vhdx/src/lib.rs

@@ -0,0 +1,31 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+
+use byteorder::{BigEndian, ByteOrder};
+use std::result::Result;
+use uuid::Uuid;
+
+macro_rules! div_round_up {
+    ($n:expr,$d:expr) => {
+        ($n + $d - 1) / $d
+    };
+}
+
+pub mod vhdx;
+mod vhdx_bat;
+mod vhdx_header;
+mod vhdx_io;
+mod vhdx_metadata;
+
+pub(crate) fn uuid_from_guid(buf: &[u8]) -> Result<Uuid, uuid::Error> {
+    // The first 3 fields of UUID are stored in Big Endian format, and
+    // the last 8 bytes are stored as byte array. Therefore, we read the
+    // first 3 fields in Big Endian format instead of Little Endian.
+    Uuid::from_fields_le(
+        BigEndian::read_u32(&buf[0..4]),
+        BigEndian::read_u16(&buf[4..6]),
+        BigEndian::read_u16(&buf[6..8]),
+        &buf[8..16],
+    )
+}

vhdx/src/vhdx.rs

@@ -0,0 +1,212 @@
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+
+use crate::vhdx_bat::{BatEntry, VhdxBatError};
+use crate::vhdx_header::{self, RegionInfo, RegionTableEntry, VhdxHeader, VhdxHeaderError};
+use crate::vhdx_io::{self, VhdxIoError};
+use crate::vhdx_metadata::{DiskSpec, VhdxMetadataError};
+use remain::sorted;
+use std::collections::btree_map::BTreeMap;
+use std::fs::File;
+use std::io::{Read, Seek, SeekFrom, Write};
+use thiserror::Error;
+
+#[sorted]
+#[derive(Error, Debug)]
+pub enum VhdxError {
+    #[error("Not a VHDx file {0}")]
+    NotVhdx(#[source] VhdxHeaderError),
+    #[error("Failed to parse VHDx header {0}")]
+    ParseVhdxHeader(#[source] VhdxHeaderError),
+    #[error("Failed to parse VHDx metadata {0}")]
+    ParseVhdxMetadata(#[source] VhdxMetadataError),
+    #[error("Failed to parse VHDx region entries {0}")]
+    ParseVhdxRegionEntry(#[source] VhdxHeaderError),
+    #[error("Failed reading metadata {0}")]
+    ReadBatEntry(#[source] VhdxBatError),
+    #[error("Failed reading sector from disk {0}")]
+    ReadFailed(#[source] VhdxIoError),
+    #[error("Failed writing to sector on disk {0}")]
+    WriteFailed(#[source] VhdxIoError),
+}
+
+pub type Result<T> = std::result::Result<T, VhdxError>;
+
+#[derive(Debug)]
+pub struct Vhdx {
+    file: File,
+    vhdx_header: VhdxHeader,
+    region_entries: BTreeMap<u64, u64>,
+    bat_entry: RegionTableEntry,
+    mdr_entry: RegionTableEntry,
+    disk_spec: DiskSpec,
+    bat_entries: Vec<BatEntry>,
+    current_offset: u64,
+    first_write: bool,
+}
+
+impl Vhdx {
+    /// Parse the Vhdx header, BAT, and metadata from a file and store info
+    // in Vhdx structure.
+    pub fn new(mut file: File) -> Result<Vhdx> {
+        let vhdx_header = VhdxHeader::new(&mut file).map_err(VhdxError::ParseVhdxHeader)?;
+
+        let collected_entries = RegionInfo::new(
+            &mut file,
+            vhdx_header::REGION_TABLE_1_START,
+            vhdx_header.region_entry_count(),
+        )
+        .map_err(VhdxError::ParseVhdxRegionEntry)?;
+
+        let bat_entry = collected_entries.bat_entry;
+        let mdr_entry = collected_entries.mdr_entry;
+
+        let disk_spec =
+            DiskSpec::new(&mut file, &mdr_entry).map_err(VhdxError::ParseVhdxMetadata)?;
+        let bat_entries = BatEntry::collect_bat_entries(&mut file, &disk_spec, &bat_entry)
+            .map_err(VhdxError::ReadBatEntry)?;
+
+        Ok(Vhdx {
+            file,
+            vhdx_header,
+            region_entries: collected_entries.region_entries,
+            bat_entry,
+            mdr_entry,
+            disk_spec,
+            bat_entries,
+            current_offset: 0,
+            first_write: true,
+        })
+    }
+
+    pub fn virtual_disk_size(&self) -> u64 {
+        self.disk_spec.virtual_disk_size
+    }
+}
+
+impl Read for Vhdx {
+    /// Wrapper function to satisfy Read trait implementation for VHDx disk.
+    /// Convert the offset to sector index and buffer length to sector count.
+    fn read(&mut self, buf: &mut [u8]) -> std::result::Result<usize, std::io::Error> {
+        let sector_count =
+            div_round_up!(buf.len() as u64, self.disk_spec.logical_sector_size as u64);
+        let sector_index = self.current_offset / self.disk_spec.logical_sector_size as u64;
+
+        vhdx_io::read(
+            &mut self.file,
+            buf,
+            &self.disk_spec,
+            &self.bat_entries,
+            sector_index,
+            sector_count,
+        )
+        .map_err(|e| {
+            std::io::Error::new(
+                std::io::ErrorKind::Other,
+                format!(
+                    "Failed reading {} sectors from VHDx at index {}: {}",
+                    sector_count, sector_index, e
+                ),
+            )
+        })
+    }
+}
+
+impl Write for Vhdx {
+    fn flush(&mut self) -> std::result::Result<(), std::io::Error> {
+        self.file.flush()
+    }
+
+    /// Wrapper function to satisfy Write trait implementation for VHDx disk.
+    /// Convert the offset to sector index and buffer length to sector count.
+    fn write(&mut self, buf: &[u8]) -> std::result::Result<usize, std::io::Error> {
+        let sector_count =
+            div_round_up!(buf.len() as u64, self.disk_spec.logical_sector_size as u64);
+        let sector_index = self.current_offset / self.disk_spec.logical_sector_size as u64;
+
+        if self.first_write {
+            self.first_write = false;
+            self.vhdx_header.update(&mut self.file).map_err(|e| {
+                std::io::Error::new(
+                    std::io::ErrorKind::Other,
+                    format!("Failed to update VHDx header: {}", e),
+                )
+            })?;
+        }
+
+        vhdx_io::write(
+            &mut self.file,
+            buf,
+            &mut self.disk_spec,
+            self.bat_entry.file_offset,
+            &mut self.bat_entries,
+            sector_index,
+            sector_count,
+        )
+        .map_err(|e| {
+            std::io::Error::new(
+                std::io::ErrorKind::Other,
+                format!(
+                    "Failed writing {} sectors on VHDx at index {}: {}",
+                    sector_count, sector_index, e
+                ),
+            )
+        })
+    }
+}
+
+impl Seek for Vhdx {
+    /// Wrapper function to satisfy Seek trait implementation for VHDx disk.
+    /// Updates the offset field in the Vhdx struct.
+    fn seek(&mut self, pos: SeekFrom) -> std::io::Result<u64> {
+        let new_offset: Option<u64> = match pos {
+            SeekFrom::Start(off) => Some(off),
+            SeekFrom::End(off) => {
+                if off < 0 {
+                    0i64.checked_sub(off).and_then(|increment| {
+                        self.virtual_disk_size().checked_sub(increment as u64)
+                    })
+                } else {
+                    self.virtual_disk_size().checked_add(off as u64)
+                }
+            }
+            SeekFrom::Current(off) => {
+                if off < 0 {
+                    0i64.checked_sub(off)
+                        .and_then(|increment| self.current_offset.checked_sub(increment as u64))
+                } else {
+                    self.current_offset.checked_add(off as u64)
+                }
+            }
+        };
+
+        if let Some(o) = new_offset {
+            if o <= self.virtual_disk_size() {
+                self.current_offset = o;
+                return Ok(o);
+            }
+        }
+
+        Err(std::io::Error::new(
+            std::io::ErrorKind::InvalidData,
+            "Failed seek operation",
+        ))
+    }
+}
+
+impl Clone for Vhdx {
+    fn clone(&self) -> Self {
+        Vhdx {
+            file: self.file.try_clone().unwrap(),
+            vhdx_header: self.vhdx_header.clone(),
+            region_entries: self.region_entries.clone(),
+            bat_entry: self.bat_entry,
+            mdr_entry: self.mdr_entry,
+            disk_spec: self.disk_spec.clone(),
+            bat_entries: self.bat_entries.clone(),
+            current_offset: self.current_offset,
+            first_write: self.first_write,
+        }
+    }
+}