build: Release v16.0

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

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,34 @@
+---
+name: Bug report
+about: File a bug report
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behaviour:
+
+**Version**
+
+Output of `cloud-hypervisor --version`:
+
+Did you build from source, if so build command line (e.g. features):
+
+**VM configuration**
+
+What command line did you run (or JSON config data):
+
+Guest OS version details:
+
+Host OS version details:
+
+**Logs**
+
+Output of `cloud-hypervisor -v` from either standard error or via `--log-file`:
+
+Linux kernel output:

.github/dependabot.yml

@@ -0,0 +1,18 @@
+version: 2
+updates:
+- package-ecosystem: cargo
+  directory: "/"
+  schedule:
+    interval: daily
+  open-pull-requests-limit: 3
+  allow:
+  - dependency-type: direct
+  - dependency-type: indirect
+- package-ecosystem: cargo
+  directory: "/fuzz"
+  schedule:
+    interval: daily
+  open-pull-requests-limit: 3
+  allow:
+  - dependency-type: direct
+  - dependency-type: indirect

.github/workflows/quality-aarch64.yaml

@@ -6,12 +6,19 @@ jobs:
     if: github.event_name == 'pull_request'
     name: Quality (clippy, rustfmt)
     runs-on: ubuntu-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
+      fail-fast: false
       matrix:
         rust:
           - stable
         target:
           - aarch64-unknown-linux-gnu
+        experimental: [false]
+        include:
+          - rust: beta
+            target: aarch64-unknown-linux-gnu
+            experimental: true
     steps:
       - name: Code checkout
         uses: actions/checkout@v2
@@ -22,8 +29,6 @@ jobs:
             target: ${{ matrix.target }}
             override: true
             components: rustfmt, clippy
-      - name: Install arm64 libfdt
-        run: wget http://ftp.us.debian.org/debian/pool/main/d/device-tree-compiler/libfdt-dev_1.6.0-1_arm64.deb && dpkg-deb -xv libfdt-dev_1.6.0-1_arm64.deb ./tlibfdtdev && mkdir -p target/debug/deps && sudo cp ./tlibfdtdev/usr/lib/aarch64-linux-gnu/libfdt.a target/debug/deps/libfdt.a && echo "libfdt installed"
       - name: Formatting (rustfmt)
         run: cargo fmt -- --check
       - name: Clippy (kvm)

.github/workflows/quality.yaml

@@ -6,12 +6,19 @@ jobs:
     if: github.event_name == 'pull_request'
     name: Quality (clippy, rustfmt)
     runs-on: ubuntu-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
+      fail-fast: false
       matrix:
         rust:
           - stable
         target:
           - x86_64-unknown-linux-gnu
+        experimental: [false]
+        include:
+          - rust: beta
+            target: x86_64-unknown-linux-gnu
+            experimental: true
     steps:
       - name: Code checkout
         uses: actions/checkout@v2

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cloud-hypervisor"
-version = "0.14.1"
+version = "16.0.0"
 authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 default-run = "cloud-hypervisor"
@@ -13,19 +13,19 @@ homepage = "https://github.com/cloud-hypervisor/cloud-hypervisor"
 lto = true
 
 [dependencies]
-anyhow = "1.0.39"
+anyhow = "1.0.40"
 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 = "0.2.91"
+libc = "0.2.96"
 log = { version = "0.4.14", features = ["std"] }
 option_parser = { path = "option_parser" }
-seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.22.0" }
+seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.24.4" }
 serde_json = "1.0.64"
-signal-hook = "0.3.7"
-thiserror = "1.0.24"
+signal-hook = "0.3.9"
+thiserror = "1.0.25"
 vmm = { path = "vmm" }
 vmm-sys-util = "0.8.0"
 vm-memory = "0.5.0"
@@ -36,10 +36,12 @@ clap = { version = "2.33.3", features = ["wrap_help"] }
 # List of patched crates
 [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 = "3.0.1"
+dirs = "3.0.2"
 lazy_static= "1.4.0"
 net_util = { path = "net_util" }
 serde_json = "1.0.64"
@@ -66,7 +68,6 @@ members = [
     "acpi_tables",
     "api_client",
     "arch",
-    "arch_gen",
     "block_util",
     "devices",
     "event_monitor",
@@ -76,6 +77,7 @@ members = [
     "option_parser",
     "pci",
     "qcow",
+    "rate_limiter",
     "vhost_user_backend",
     "vhost_user_block",
     "vhost_user_net",

Jenkinsfile

@@ -46,6 +46,7 @@ pipeline{
 								timeout(time: 1, unit: 'HOURS')
 							}
 							steps {
+								sh "sudo modprobe openvswitch"
 								sh "scripts/dev_cli.sh tests --integration"
 							}
 						}
@@ -69,6 +70,7 @@ pipeline{
 								timeout(time: 1, unit: 'HOURS')
 							}
 							steps {
+								sh "sudo modprobe openvswitch"
 								sh "scripts/dev_cli.sh tests --integration"
 							}
 						}
@@ -98,6 +100,7 @@ pipeline{
 								timeout(time: 1, unit: 'HOURS')
 							}
 							steps {
+								sh "sudo modprobe openvswitch"
 								sh "scripts/dev_cli.sh tests --integration --libc musl"
 							}
 						}
@@ -105,7 +108,10 @@ pipeline{
 				}
 				stage ('Worker build SGX') {
 					agent { node { label 'bionic-sgx' } }
-					when { branch 'master' }
+					when {
+						beforeAgent true
+						branch 'master'
+					}
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -138,7 +144,10 @@ pipeline{
 				}
 				stage ('Worker build VFIO') {
 					agent { node { label 'bionic-vfio' } }
-					when { branch 'master' }
+					when {
+						beforeAgent true
+						branch 'master'
+					}
 					stages {
 						stage ('Checkout') {
 							steps {
@@ -170,7 +179,7 @@ pipeline{
 					}
 				}
 				stage ('Worker build - Windows guest') {
-					agent { node { label 'groovy-win' } }
+					agent { node { label 'groovy' } }
 					stages {
 						stage ('Checkout') {
 							steps {

README.md

@@ -26,7 +26,8 @@
 
 # 1. What is Cloud Hypervisor?
 
-Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on top of [KVM](https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt).
+Cloud Hypervisor is an open source Virtual Machine Monitor (VMM) that runs on top of [KVM](https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt) and the MSHV hypervisors .
+
 The project focuses on exclusively running modern, cloud workloads, on top of a limited set of hardware architectures and platforms.
 Cloud workloads refers to those that are usually run by customers inside a cloud provider. For our purposes this means modern operating systems with most I/O handled by paravirtualised devices (i.e. virtio), no requirement for legacy devices, and 64-bit CPUs.
 
@@ -36,7 +37,7 @@ Cloud Hypervisor is implemented in [Rust](https://www.rust-lang.org/) and is bas
 
 ### High Level
 
-- KVM based
+- Runs on KVM or MSHV
 - Minimal emulation
 - Low latency
 - Low memory footprint
@@ -53,7 +54,7 @@ Cloud Hypervisor supports the `x86-64` and `AArch64` architectures. There are so
 
 ### Guest OS
 
-Cloud Hypervisor supports `64-bit Linux` with support for _modern_ 64-bit Windows guests currently under development.
+Cloud Hypervisor supports `64-bit Linux` and Windows 10/Windows Server 2019.
 
 # 2. Getting Started
 
@@ -148,7 +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/0.3.0/hypervisor-fw
+$ wget https://github.com/cloud-hypervisor/rust-hypervisor-firmware/releases/download/0.3.1/hypervisor-fw
 $ popd
 ```
 
@@ -171,7 +172,7 @@ Multiple arguments can be given to the `--disk` parameter.
 
 #### Building your kernel
 
-Cloud Hypervisor also supports direct kernel boot into a `vmlinux` ELF kernel or `bzImage`. In order to support virtio-fs and virtio-iommu we have our own development branch. You are of course able to use your own kernel but these instructions will continue with the version that we develop and test against.
+Cloud Hypervisor also supports direct kernel boot into a `vmlinux` ELF kernel. In order to support virtio-iommu we have our own development branch. You are of course able to use your own kernel but these instructions will continue with the version that we develop and test against.
 
 To build the kernel:
 
@@ -179,7 +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 virtio-fs-virtio-iommu-virtio-mem-5.6-rc4 linux-cloud-hypervisor
+$ git clone --depth 1 https://github.com/cloud-hypervisor/linux.git -b ch-5.12 linux-cloud-hypervisor
 $ pushd linux-cloud-hypervisor
 
 # Use the cloud-hypervisor kernel config to build your kernel
@@ -204,7 +205,7 @@ $ popd
 #### Booting the guest VM
 
 Now we can directly boot into our custom kernel and make it use the Ubuntu root partition.
-If we want to have 4 vCPUs and 512 MBytes of memory:
+If we want to have 4 vCPUs and 1024 MBytes of memory:
 
 ```shell
 $ pushd $CLOUDH
@@ -241,23 +242,40 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 
 # 3. Status
 
-Cloud Hypervisor is under active development. No API or feature stability is guaranteed.
+Cloud Hypervisor is under active development. The following stability guarantees are currently made:
 
-As of 2020-07-02, the following cloud images are supported:
+* The API (including command line options) will not be removed or changed in a
+  breaking way without a minimum of 2 releases notice. Where possible warnings
+  will be given about the use of deprecated functionality and the deprecations
+  will be documented in the release notes.
+* Point releases will be made between individual releases where there are
+  substantial bug fixes or security issues that need to be fixed.
+
+Currently the following items are **not** guaranteed across updates:
+
+* Snapshot/restore is not supported across different versions
+* Live migration is not supported across different versions
+* The following features are considered experimental and may change
+  substantially between releases: TDX, SGX.
+
+
+As of 2021-04-29, the following cloud images are supported:
 
 - [Ubuntu Bionic](https://cloud-images.ubuntu.com/bionic/current/) (cloudimg)
 - [Ubuntu Focal](https://cloud-images.ubuntu.com/focal/current/) (cloudimg)
+- [Ubuntu Groovy](https://cloud-images.ubuntu.com/groovy/current/) (cloudimg)
+- [Ubuntu Hirsute](https://cloud-images.ubuntu.com/hirsute/current/) (cloudimg)
 
 Direct kernel boot to userspace should work with a rootfs from most distributions.
 
 ## Hot Plug
 
-Cloud Hypervisor supports hotplug of CPUs, passthrough devices (VFIO), `virtio-{net,block,pmem,fs,vsock}` and memory resizing. This [document](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/hotplug.md) details how to add devices to
+Cloud Hypervisor supports hotplug of CPUs, passthrough devices (VFIO), `virtio-{net,block,pmem,fs,vsock}` and memory resizing. This [document](docs/hotplug.md) details how to add devices to
 a running VM.
 
 ## Device Model
 
-Details of the device model can be found in this [documentation](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/device_model.md).
+Details of the device model can be found in this [documentation](docs/device_model.md).
 
 ## TODO
 
@@ -317,3 +335,7 @@ etc, are all equal and welcome means of contribution. See the [CONTRIBUTING](CON
 
 Get an [invite to our Slack channel](https://join.slack.com/t/cloud-hypervisor/shared_invite/enQtNjY3MTE3MDkwNDQ4LWQ1MTA1ZDVmODkwMWQ1MTRhYzk4ZGNlN2UwNTI3ZmFlODU0OTcwOWZjMTkwZDExYWE3YjFmNzgzY2FmNDAyMjI)
 and [join us on Slack](https://cloud-hypervisor.slack.com/).
+
+## Security issues
+
+Please use the GitHub security advisories feature for reporting issues: https://github.com/cloud-hypervisor/cloud-hypervisor/security/advisories/new

acpi_tables/Cargo.toml

@@ -6,4 +6,3 @@ edition = "2018"
 
 [dependencies]
 vm-memory = "0.5.0"
-

acpi_tables/src/aml.rs

@@ -732,9 +732,9 @@ impl Field {
     ) -> Self {
         Field {
             path,
+            fields,
             access_type,
             update_rule,
-            fields,
         }
     }
 }
@@ -851,8 +851,8 @@ impl<'a> Aml for If<'a> {
 }
 
 pub struct Equal<'a> {
-    right: &'a dyn Aml,
     left: &'a dyn Aml,
+    right: &'a dyn Aml,
 }
 
 impl<'a> Equal<'a> {
@@ -871,8 +871,8 @@ impl<'a> Aml for Equal<'a> {
 }
 
 pub struct LessThan<'a> {
-    right: &'a dyn Aml,
     left: &'a dyn Aml,
+    right: &'a dyn Aml,
 }
 
 impl<'a> LessThan<'a> {
@@ -1056,7 +1056,7 @@ macro_rules! binary_op {
 
         impl<'a> $name<'a> {
             pub fn new(target: &'a dyn Aml, a: &'a dyn Aml, b: &'a dyn Aml) -> Self {
-                $name { target, a, b }
+                $name { a, b, target }
             }
         }
 

acpi_tables/src/sdt.rs

@@ -22,6 +22,15 @@ impl GenericAddress {
             address: u64::from(address),
         }
     }
+    pub fn mmio_address<T>(address: u64) -> Self {
+        GenericAddress {
+            address_space_id: 0,
+            register_bit_width: 8 * std::mem::size_of::<T>() as u8,
+            register_bit_offset: 0,
+            access_size: std::mem::size_of::<T>() as u8,
+            address,
+        }
+    }
 }
 
 pub struct Sdt {

api_client/src/lib.rs

@@ -76,11 +76,8 @@ impl StatusCode {
 
 fn get_header<'a>(res: &'a str, header: &'a str) -> Option<&'a str> {
     let header_str = format!("{}: ", header);
-    if let Some(o) = res.find(&header_str) {
-        Some(&res[o + header_str.len()..o + res[o..].find('\r').unwrap()])
-    } else {
-        None
-    }
+    res.find(&header_str)
+        .map(|o| &res[o + header_str.len()..o + res[o..].find('\r').unwrap()])
 }
 
 fn get_status_code(res: &str) -> Result<StatusCode, Error> {

arch/Cargo.toml

@@ -2,6 +2,7 @@
 name = "arch"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
+edition = "2018"
 
 [features]
 default = []
@@ -11,16 +12,16 @@ tdx = []
 [dependencies]
 acpi_tables = { path = "../acpi_tables", optional = true }
 anyhow = "1.0"
-arch_gen = { path = "../arch_gen" }
 byteorder = "1.4.3"
 hypervisor = { path = "../hypervisor" }
-libc = "0.2.91"
+libc = "0.2.96"
 linux-loader = { version = "0.3.0", features = ["elf", "bzimage", "pe"] }
 log = "0.4.14"
 serde = {version = ">=1.0.27", features = ["rc"] }
-serde_derive = ">=1.0.27"
-serde_json = ">=1.0.9"
 thiserror = "1.0"
-vm-memory = { version = "0.5.0", features = ["backend-mmap"] }
+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-migration = { path = "../vm-migration" }
 

arch/src/aarch64/fdt.rs

@@ -6,23 +6,22 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the THIRD-PARTY file.
 
-use libc::{c_char, c_int, c_void};
 use std::collections::HashMap;
-use std::ffi::{CStr, CString, NulError};
+use std::ffi::CStr;
 use std::fmt::Debug;
-use std::ptr::null;
-use std::{io, result};
+use std::result;
 
 use super::super::DeviceType;
+use super::super::GuestMemoryMmap;
 use super::super::InitramfsConfig;
 use super::get_fdt_addr;
 use super::gic::GicDevice;
 use super::layout::{
-    FDT_MAX_SIZE, MEM_32BIT_DEVICES_SIZE, MEM_32BIT_DEVICES_START, PCI_MMCONFIG_SIZE,
-    PCI_MMCONFIG_START,
+    IRQ_BASE, MEM_32BIT_DEVICES_SIZE, MEM_32BIT_DEVICES_START, MEM_PCI_IO_SIZE, MEM_PCI_IO_START,
+    PCI_HIGH_BASE, PCI_MMCONFIG_SIZE, PCI_MMCONFIG_START,
 };
-use crate::aarch64::fdt::Error::CstringFdtTransform;
-use vm_memory::{Address, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryMmap};
+use vm_fdt::{FdtWriter, FdtWriterResult};
+use vm_memory::{Address, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
 
 // This is a value for uniquely identifying the FDT node declaring the interrupt controller.
 const GIC_PHANDLE: u32 = 1;
@@ -51,22 +50,6 @@ const IRQ_TYPE_LEVEL_HI: u32 = 4;
 // System Power Down
 const KEY_POWER: u32 = 116;
 
-// This links to libfdt which handles the creation of the binary blob
-// flattened device tree (fdt) that is passed to the kernel and indicates
-// the hardware configuration of the machine.
-#[link(name = "fdt")]
-extern "C" {
-    fn fdt_create(buf: *mut c_void, bufsize: c_int) -> c_int;
-    fn fdt_finish_reservemap(fdt: *mut c_void) -> c_int;
-    fn fdt_begin_node(fdt: *mut c_void, name: *const c_char) -> c_int;
-    fn fdt_property(fdt: *mut c_void, name: *const c_char, val: *const c_void, len: c_int)
-        -> c_int;
-    fn fdt_end_node(fdt: *mut c_void) -> c_int;
-    fn fdt_open_into(fdt: *const c_void, buf: *mut c_void, bufsize: c_int) -> c_int;
-    fn fdt_finish(fdt: *const c_void) -> c_int;
-    fn fdt_pack(fdt: *mut c_void) -> c_int;
-}
-
 /// Trait for devices to be added to the Flattened Device Tree.
 pub trait DeviceInfoForFdt {
     /// Returns the address where this device will be loaded.
@@ -80,16 +63,6 @@ pub trait DeviceInfoForFdt {
 /// Errors thrown while configuring the Flattened Device Tree for aarch64.
 #[derive(Debug)]
 pub enum Error {
-    /// Failed to append node to the FDT.
-    AppendFdtNode(io::Error),
-    /// Failed to append a property to the FDT.
-    AppendFdtProperty(io::Error),
-    /// Syscall for creating FDT failed.
-    CreateFdt(io::Error),
-    /// Failed to obtain a C style string.
-    CstringFdtTransform(NulError),
-    /// Failure in calling syscall for terminating this FDT.
-    FinishFdtReserveMap(io::Error),
     /// Failure in writing FDT in memory.
     WriteFdtToMemory(GuestMemoryError),
 }
@@ -104,29 +77,27 @@ pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHash
     gic_device: &dyn GicDevice,
     initrd: &Option<InitramfsConfig>,
     pci_space_address: &(u64, u64),
-) -> Result<Vec<u8>> {
+) -> FdtWriterResult<Vec<u8>> {
     // Allocate stuff necessary for the holding the blob.
-    let mut fdt = vec![0; FDT_MAX_SIZE];
-
-    allocate_fdt(&mut fdt)?;
+    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
     // Look for "Required nodes and properties".
 
     // Header or the root node as per above mentioned documentation.
-    append_begin_node(&mut fdt, "")?;
-    append_property_string(&mut fdt, "compatible", "linux,dummy-virt")?;
+    let root_node = fdt.begin_node("")?;
+    fdt.property_string("compatible", "linux,dummy-virt")?;
     // For info on #address-cells and size-cells read "Note about cells and address representation"
     // from the above mentioned txt file.
-    append_property_u32(&mut fdt, "#address-cells", ADDRESS_CELLS)?;
-    append_property_u32(&mut fdt, "#size-cells", SIZE_CELLS)?;
+    fdt.property_u32("#address-cells", ADDRESS_CELLS)?;
+    fdt.property_u32("#size-cells", SIZE_CELLS)?;
     // 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.
-    append_property_u32(&mut fdt, "interrupt-parent", GIC_PHANDLE)?;
+    fdt.property_u32("interrupt-parent", GIC_PHANDLE)?;
     create_cpu_nodes(&mut fdt, &vcpu_mpidr)?;
     create_memory_node(&mut fdt, guest_mem)?;
-    create_chosen_node(&mut fdt, cmdline, initrd)?;
+    create_chosen_node(&mut fdt, cmdline.to_str().unwrap(), initrd)?;
     create_gic_node(&mut fdt, gic_device)?;
     create_timer_node(&mut fdt)?;
     create_clock_node(&mut fdt)?;
@@ -135,307 +106,136 @@ pub fn create_fdt<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHash
     create_pci_nodes(&mut fdt, pci_space_address.0, pci_space_address.1)?;
 
     // End Header node.
-    append_end_node(&mut fdt)?;
+    fdt.end_node(root_node)?;
 
-    // Allocate another buffer so we can format and then write fdt to guest.
-    let mut fdt_final = vec![0; FDT_MAX_SIZE];
-    finish_fdt(&mut fdt, &mut fdt_final)?;
+    let fdt_final = fdt.finish()?;
 
-    // Write FDT to memory.
-    let fdt_address = GuestAddress(get_fdt_addr(&guest_mem));
-    guest_mem
-        .write_slice(fdt_final.as_slice(), fdt_address)
-        .map_err(Error::WriteFdtToMemory)?;
     Ok(fdt_final)
 }
 
-// Following are auxiliary functions for allocating and finishing the FDT.
-fn allocate_fdt(fdt: &mut Vec<u8>) -> Result<()> {
-    // Safe since we allocated this array with FDT_MAX_SIZE.
-    let mut fdt_ret = unsafe { fdt_create(fdt.as_mut_ptr() as *mut c_void, FDT_MAX_SIZE as c_int) };
-
-    if fdt_ret != 0 {
-        return Err(Error::CreateFdt(io::Error::last_os_error()));
-    }
-
-    // The flattened device trees created with fdt_create() contains a list of
-    // reserved memory areas. We need to call `fdt_finish_reservemap` so as to make sure that there is a
-    // terminator in the reservemap list and whatever happened to be at the
-    // start of the FDT data section would end up being interpreted as
-    // reservemap entries.
-    // Safe since we previously allocated this array.
-    fdt_ret = unsafe { fdt_finish_reservemap(fdt.as_mut_ptr() as *mut c_void) };
-    if fdt_ret != 0 {
-        return Err(Error::FinishFdtReserveMap(io::Error::last_os_error()));
-    }
+pub fn write_fdt_to_memory(fdt_final: Vec<u8>, guest_mem: &GuestMemoryMmap) -> Result<()> {
+    // Write FDT to memory.
+    let fdt_address = GuestAddress(get_fdt_addr());
+    guest_mem
+        .write_slice(fdt_final.as_slice(), fdt_address)
+        .map_err(Error::WriteFdtToMemory)?;
     Ok(())
 }
 
-fn finish_fdt(from_fdt: &mut Vec<u8>, to_fdt: &mut Vec<u8>) -> Result<()> {
-    // Safe since we allocated `fdt_final` and previously passed in its size.
-    let mut fdt_ret = unsafe { fdt_finish(from_fdt.as_mut_ptr() as *mut c_void) };
-    if fdt_ret != 0 {
-        return Err(Error::FinishFdtReserveMap(io::Error::last_os_error()));
-    }
-
-    // Safe because we allocated both arrays with the correct size.
-    fdt_ret = unsafe {
-        fdt_open_into(
-            from_fdt.as_mut_ptr() as *mut c_void,
-            to_fdt.as_mut_ptr() as *mut c_void,
-            FDT_MAX_SIZE as i32,
-        )
-    };
-    if fdt_ret != 0 {
-        return Err(Error::FinishFdtReserveMap(io::Error::last_os_error()));
-    }
-
-    // Safe since we allocated `to_fdt`.
-    fdt_ret = unsafe { fdt_pack(to_fdt.as_mut_ptr() as *mut c_void) };
-    if fdt_ret != 0 {
-        return Err(Error::FinishFdtReserveMap(io::Error::last_os_error()));
-    }
-    Ok(())
-}
-
-// Following are auxiliary functions for appending nodes to FDT.
-fn append_begin_node(fdt: &mut Vec<u8>, name: &str) -> Result<()> {
-    let cstr_name = CString::new(name).map_err(CstringFdtTransform)?;
-
-    // Safe because we allocated fdt and converted name to a CString
-    let fdt_ret = unsafe { fdt_begin_node(fdt.as_mut_ptr() as *mut c_void, cstr_name.as_ptr()) };
-    if fdt_ret != 0 {
-        return Err(Error::AppendFdtNode(io::Error::last_os_error()));
-    }
-    Ok(())
-}
-
-fn append_end_node(fdt: &mut Vec<u8>) -> Result<()> {
-    // Safe because we allocated fdt.
-    let fdt_ret = unsafe { fdt_end_node(fdt.as_mut_ptr() as *mut c_void) };
-    if fdt_ret != 0 {
-        return Err(Error::AppendFdtNode(io::Error::last_os_error()));
-    }
-    Ok(())
-}
-
-// Following are auxiliary functions for appending property nodes to the nodes of the FDT.
-fn append_property_u32(fdt: &mut Vec<u8>, name: &str, val: u32) -> Result<()> {
-    append_property(fdt, name, &to_be32(val))
-}
-
-fn append_property_u64(fdt: &mut Vec<u8>, name: &str, val: u64) -> Result<()> {
-    append_property(fdt, name, &to_be64(val))
-}
-
-fn append_property_string(fdt: &mut Vec<u8>, name: &str, value: &str) -> Result<()> {
-    let cstr_value = CString::new(value).map_err(CstringFdtTransform)?;
-    append_property_cstring(fdt, name, &cstr_value)
-}
-
-fn append_property_cstring(fdt: &mut Vec<u8>, name: &str, cstr_value: &CStr) -> Result<()> {
-    let value_bytes = cstr_value.to_bytes_with_nul();
-    let cstr_name = CString::new(name).map_err(CstringFdtTransform)?;
-    // Safe because we allocated fdt, converted name and value to CStrings
-    let fdt_ret = unsafe {
-        fdt_property(
-            fdt.as_mut_ptr() as *mut c_void,
-            cstr_name.as_ptr(),
-            value_bytes.as_ptr() as *mut c_void,
-            value_bytes.len() as i32,
-        )
-    };
-    if fdt_ret != 0 {
-        return Err(Error::AppendFdtProperty(io::Error::last_os_error()));
-    }
-    Ok(())
-}
-
-fn append_property_null(fdt: &mut Vec<u8>, name: &str) -> Result<()> {
-    let cstr_name = CString::new(name).map_err(CstringFdtTransform)?;
-
-    // Safe because we allocated fdt, converted name to a CString
-    let fdt_ret = unsafe {
-        fdt_property(
-            fdt.as_mut_ptr() as *mut c_void,
-            cstr_name.as_ptr(),
-            null(),
-            0,
-        )
-    };
-    if fdt_ret != 0 {
-        return Err(Error::AppendFdtProperty(io::Error::last_os_error()));
-    }
-    Ok(())
-}
-
-fn append_property(fdt: &mut Vec<u8>, name: &str, val: &[u8]) -> Result<()> {
-    let cstr_name = CString::new(name).map_err(CstringFdtTransform)?;
-    let val_ptr = val.as_ptr() as *const c_void;
-
-    // Safe because we allocated fdt and converted name to a CString
-    let fdt_ret = unsafe {
-        fdt_property(
-            fdt.as_mut_ptr() as *mut c_void,
-            cstr_name.as_ptr(),
-            val_ptr,
-            val.len() as i32,
-        )
-    };
-    if fdt_ret != 0 {
-        return Err(Error::AppendFdtProperty(io::Error::last_os_error()));
-    }
-    Ok(())
-}
-
-// Auxiliary functions for writing u32/u64 numbers in big endian order.
-fn to_be32(input: u32) -> [u8; 4] {
-    u32::to_be_bytes(input)
-}
-
-fn to_be64(input: u64) -> [u8; 8] {
-    u64::to_be_bytes(input)
-}
-
-// Helper functions for generating a properly formatted byte vector using 32-bit/64-bit cells.
-fn generate_prop32(cells: &[u32]) -> Vec<u8> {
-    let mut ret: Vec<u8> = Vec::new();
-    for &e in cells {
-        ret.extend(to_be32(e).iter());
-    }
-    ret
-}
-
-fn generate_prop64(cells: &[u64]) -> Vec<u8> {
-    let mut ret: Vec<u8> = Vec::new();
-    for &e in cells {
-        ret.extend(to_be64(e).iter());
-    }
-    ret
-}
-
 // Following are the auxiliary function for creating the different nodes that we append to our FDT.
-fn create_cpu_nodes(fdt: &mut Vec<u8>, vcpu_mpidr: &[u64]) -> Result<()> {
+fn create_cpu_nodes(fdt: &mut FdtWriter, vcpu_mpidr: &[u64]) -> FdtWriterResult<()> {
     // See https://github.com/torvalds/linux/blob/master/Documentation/devicetree/bindings/arm/cpus.yaml.
-    append_begin_node(fdt, "cpus")?;
-    // As per documentation, on ARM v8 64-bit systems value should be set to 2.
-    append_property_u32(fdt, "#address-cells", 0x02)?;
-    append_property_u32(fdt, "#size-cells", 0x0)?;
+    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_index, mpidr) in vcpu_mpidr.iter().enumerate().take(num_cpus) {
-        let cpu_name = format!("cpu@{:x}", cpu_index);
-        append_begin_node(fdt, &cpu_name)?;
-        append_property_string(fdt, "device_type", "cpu")?;
-        append_property_string(fdt, "compatible", "arm,arm-v8")?;
+    for cpu_id in 0..num_cpus {
+        let cpu_name = format!("cpu@{:x}", cpu_id);
+        let cpu_node = fdt.begin_node(&cpu_name)?;
+        fdt.property_string("device_type", "cpu")?;
+        fdt.property_string("compatible", "arm,arm-v8")?;
         if num_cpus > 1 {
             // This is required on armv8 64-bit. See aforementioned documentation.
-            append_property_string(fdt, "enable-method", "psci")?;
+            fdt.property_string("enable-method", "psci")?;
         }
-        // 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.
-        append_property_u64(fdt, "reg", mpidr & 0x7FFFFF)?;
-        append_end_node(fdt)?;
+        fdt.property_u32("reg", cpu_id as u32)?;
+        fdt.end_node(cpu_node)?;
     }
-    append_end_node(fdt)?;
+    fdt.end_node(cpus_node)?;
     Ok(())
 }
 
-fn create_memory_node(fdt: &mut Vec<u8>, guest_mem: &GuestMemoryMmap) -> Result<()> {
+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 = generate_prop64(&[super::layout::RAM_64BIT_START as u64, mem_size as u64]);
+    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)?;
 
-    append_begin_node(fdt, "memory")?;
-    append_property_string(fdt, "device_type", "memory")?;
-    append_property(fdt, "reg", &mem_reg_prop)?;
-    append_end_node(fdt)?;
     Ok(())
 }
 
 fn create_chosen_node(
-    fdt: &mut Vec<u8>,
-    cmdline: &CStr,
+    fdt: &mut FdtWriter,
+    cmdline: &str,
     initrd: &Option<InitramfsConfig>,
-) -> Result<()> {
-    append_begin_node(fdt, "chosen")?;
-    append_property_cstring(fdt, "bootargs", cmdline)?;
+) -> FdtWriterResult<()> {
+    let chosen_node = fdt.begin_node("chosen")?;
+    fdt.property_string("bootargs", cmdline)?;
 
     if let Some(initrd_config) = initrd {
-        append_property_u64(
-            fdt,
-            "linux,initrd-start",
-            initrd_config.address.raw_value() as u64,
-        )?;
-        append_property_u64(
-            fdt,
-            "linux,initrd-end",
-            initrd_config.address.raw_value() + initrd_config.size as u64,
-        )?;
+        let initrd_start = initrd_config.address.raw_value() as u64;
+        let initrd_end = initrd_config.address.raw_value() + initrd_config.size as u64;
+        fdt.property_u64("linux,initrd-start", initrd_start)?;
+        fdt.property_u64("linux,initrd-end", initrd_end)?;
     }
 
-    append_end_node(fdt)?;
+    fdt.end_node(chosen_node)?;
 
     Ok(())
 }
 
-fn create_gic_node(fdt: &mut Vec<u8>, gic_device: &dyn GicDevice) -> Result<()> {
-    let gic_reg_prop = generate_prop64(gic_device.device_properties());
+fn create_gic_node(fdt: &mut FdtWriter, gic_device: &dyn GicDevice) -> FdtWriterResult<()> {
+    let gic_reg_prop = gic_device.device_properties();
 
-    append_begin_node(fdt, "intc")?;
-    append_property_string(fdt, "compatible", gic_device.fdt_compatibility())?;
-    append_property_null(fdt, "interrupt-controller")?;
+    let intc_node = fdt.begin_node("intc")?;
+
+    fdt.property_string("compatible", gic_device.fdt_compatibility())?;
+    fdt.property_null("interrupt-controller")?;
     // "interrupt-cells" field specifies the number of cells needed to encode an
     // interrupt source. The type shall be a <u32> and the value shall be 3 if no PPI affinity description
     // is required.
-    append_property_u32(fdt, "#interrupt-cells", 3)?;
-    append_property(fdt, "reg", &gic_reg_prop)?;
-    append_property_u32(fdt, "phandle", GIC_PHANDLE)?;
-    append_property_u32(fdt, "#address-cells", 2)?;
-    append_property_u32(fdt, "#size-cells", 2)?;
-    append_property_null(fdt, "ranges")?;
-    let gic_intr = [
+    fdt.property_u32("#interrupt-cells", 3)?;
+    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)?;
+    fdt.property_null("ranges")?;
+
+    let gic_intr_prop = [
         GIC_FDT_IRQ_TYPE_PPI,
         gic_device.fdt_maint_irq(),
         IRQ_TYPE_LEVEL_HI,
     ];
-    let gic_intr_prop = generate_prop32(&gic_intr);
-
-    append_property(fdt, "interrupts", &gic_intr_prop)?;
+    fdt.property_array_u32("interrupts", &gic_intr_prop)?;
 
     if gic_device.msi_compatible() {
-        append_begin_node(fdt, "msic")?;
-        append_property_string(fdt, "compatible", gic_device.msi_compatibility())?;
-        append_property_null(fdt, "msi-controller")?;
-        append_property_u32(fdt, "phandle", MSI_PHANDLE)?;
-        let msi_reg_prop = generate_prop64(gic_device.msi_properties());
-        append_property(fdt, "reg", &msi_reg_prop)?;
-        append_end_node(fdt)?;
+        let msic_node = fdt.begin_node("msic")?;
+        fdt.property_string("compatible", gic_device.msi_compatibility())?;
+        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.end_node(msic_node)?;
     }
 
-    append_end_node(fdt)?;
+    fdt.end_node(intc_node)?;
 
     Ok(())
 }
 
-fn create_clock_node(fdt: &mut Vec<u8>) -> Result<()> {
+fn create_clock_node(fdt: &mut FdtWriter) -> FdtWriterResult<()> {
     // The Advanced Peripheral Bus (APB) is part of the Advanced Microcontroller Bus Architecture
     // (AMBA) protocol family. It defines a low-cost interface that is optimized for minimal power
     // consumption and reduced interface complexity.
     // PCLK is the clock source and this node defines exactly the clock for the APB.
-    append_begin_node(fdt, "apb-pclk")?;
-    append_property_string(fdt, "compatible", "fixed-clock")?;
-    append_property_u32(fdt, "#clock-cells", 0x0)?;
-    append_property_u32(fdt, "clock-frequency", 24000000)?;
-    append_property_string(fdt, "clock-output-names", "clk24mhz")?;
-    append_property_u32(fdt, "phandle", CLOCK_PHANDLE)?;
-    append_end_node(fdt)?;
+    let clock_node = fdt.begin_node("apb-pclk")?;
+    fdt.property_string("compatible", "fixed-clock")?;
+    fdt.property_u32("#clock-cells", 0x0)?;
+    fdt.property_u32("clock-frequency", 24000000)?;
+    fdt.property_string("clock-output-names", "clk24mhz")?;
+    fdt.property_u32("phandle", CLOCK_PHANDLE)?;
+    fdt.end_node(clock_node)?;
 
     Ok(())
 }
 
-fn create_timer_node(fdt: &mut Vec<u8>) -> Result<()> {
+fn create_timer_node(fdt: &mut FdtWriter) -> FdtWriterResult<()> {
     // See
     // https://github.com/torvalds/linux/blob/master/Documentation/devicetree/bindings/interrupt-controller/arch_timer.txt
     // These are fixed interrupt numbers for the timer device.
@@ -448,123 +248,136 @@ fn create_timer_node(fdt: &mut Vec<u8>) -> Result<()> {
         timer_reg_cells.push(irq);
         timer_reg_cells.push(IRQ_TYPE_LEVEL_HI);
     }
-    let timer_reg_prop = generate_prop32(timer_reg_cells.as_slice());
 
-    append_begin_node(fdt, "timer")?;
-    append_property_string(fdt, "compatible", compatible)?;
-    append_property_null(fdt, "always-on")?;
-    append_property(fdt, "interrupts", &timer_reg_prop)?;
-    append_end_node(fdt)?;
+    let timer_node = fdt.begin_node("timer")?;
+    fdt.property_string("compatible", compatible)?;
+    fdt.property_null("always-on")?;
+    fdt.property_array_u32("interrupts", &timer_reg_cells)?;
+    fdt.end_node(timer_node)?;
 
     Ok(())
 }
 
-fn create_psci_node(fdt: &mut Vec<u8>) -> Result<()> {
+fn create_psci_node(fdt: &mut FdtWriter) -> FdtWriterResult<()> {
     let compatible = "arm,psci-0.2";
-    append_begin_node(fdt, "psci")?;
-    append_property_string(fdt, "compatible", compatible)?;
+    let psci_node = fdt.begin_node("psci")?;
+    fdt.property_string("compatible", compatible)?;
     // Two methods available: hvc and smc.
     // As per documentation, PSCI calls between a guest and hypervisor may use the HVC conduit instead of SMC.
     // So, since we are using kvm, we need to use hvc.
-    append_property_string(fdt, "method", "hvc")?;
-    append_end_node(fdt)?;
+    fdt.property_string("method", "hvc")?;
+    fdt.end_node(psci_node)?;
 
     Ok(())
 }
 
 fn create_virtio_node<T: DeviceInfoForFdt + Clone + Debug>(
-    fdt: &mut Vec<u8>,
+    fdt: &mut FdtWriter,
     dev_info: &T,
-) -> Result<()> {
-    let device_reg_prop = generate_prop64(&[dev_info.addr(), dev_info.length()]);
-    let irq = generate_prop32(&[GIC_FDT_IRQ_TYPE_SPI, dev_info.irq(), IRQ_TYPE_EDGE_RISING]);
+) -> FdtWriterResult<()> {
+    let device_reg_prop = [dev_info.addr(), dev_info.length()];
+    let irq = [GIC_FDT_IRQ_TYPE_SPI, dev_info.irq(), IRQ_TYPE_EDGE_RISING];
 
-    append_begin_node(fdt, &format!("virtio_mmio@{:x}", dev_info.addr()))?;
-    append_property_string(fdt, "compatible", "virtio,mmio")?;
-    append_property(fdt, "reg", &device_reg_prop)?;
-    append_property(fdt, "interrupts", &irq)?;
-    append_property_u32(fdt, "interrupt-parent", GIC_PHANDLE)?;
-    append_end_node(fdt)?;
+    let virtio_node = fdt.begin_node(&format!("virtio_mmio@{:x}", dev_info.addr()))?;
+    fdt.property_string("compatible", "virtio,mmio")?;
+    fdt.property_array_u64("reg", &device_reg_prop)?;
+    fdt.property_array_u32("interrupts", &irq)?;
+    fdt.property_u32("interrupt-parent", GIC_PHANDLE)?;
+    fdt.end_node(virtio_node)?;
 
     Ok(())
 }
 
 fn create_serial_node<T: DeviceInfoForFdt + Clone + Debug>(
-    fdt: &mut Vec<u8>,
+    fdt: &mut FdtWriter,
     dev_info: &T,
-) -> Result<()> {
+) -> FdtWriterResult<()> {
     let compatible = b"arm,pl011\0arm,primecell\0";
-    let serial_reg_prop = generate_prop64(&[dev_info.addr(), dev_info.length()]);
-    let irq = generate_prop32(&[GIC_FDT_IRQ_TYPE_SPI, dev_info.irq(), IRQ_TYPE_EDGE_RISING]);
+    let serial_reg_prop = [dev_info.addr(), dev_info.length()];
+    let irq = [
+        GIC_FDT_IRQ_TYPE_SPI,
+        dev_info.irq() - IRQ_BASE,
+        IRQ_TYPE_EDGE_RISING,
+    ];
 
-    append_begin_node(fdt, &format!("pl011@{:x}", dev_info.addr()))?;
-    append_property(fdt, "compatible", compatible)?;
-    append_property(fdt, "reg", &serial_reg_prop)?;
-    append_property_u32(fdt, "clocks", CLOCK_PHANDLE)?;
-    append_property_string(fdt, "clock-names", "apb_pclk")?;
-    append_property(fdt, "interrupts", &irq)?;
-    append_end_node(fdt)?;
+    let serial_node = fdt.begin_node(&format!("pl011@{:x}", dev_info.addr()))?;
+    fdt.property("compatible", compatible)?;
+    fdt.property_array_u64("reg", &serial_reg_prop)?;
+    fdt.property_u32("clocks", CLOCK_PHANDLE)?;
+    fdt.property_string("clock-names", "apb_pclk")?;
+    fdt.property_array_u32("interrupts", &irq)?;
+    fdt.end_node(serial_node)?;
 
     Ok(())
 }
 
 fn create_rtc_node<T: DeviceInfoForFdt + Clone + Debug>(
-    fdt: &mut Vec<u8>,
+    fdt: &mut FdtWriter,
     dev_info: &T,
-) -> Result<()> {
+) -> FdtWriterResult<()> {
     let compatible = b"arm,pl031\0arm,primecell\0";
-    let rtc_reg_prop = generate_prop64(&[dev_info.addr(), dev_info.length()]);
-    let irq = generate_prop32(&[GIC_FDT_IRQ_TYPE_SPI, dev_info.irq(), IRQ_TYPE_LEVEL_HI]);
-    append_begin_node(fdt, &format!("rtc@{:x}", dev_info.addr()))?;
-    append_property(fdt, "compatible", compatible)?;
-    append_property(fdt, "reg", &rtc_reg_prop)?;
-    append_property(fdt, "interrupts", &irq)?;
-    append_property_u32(fdt, "clocks", CLOCK_PHANDLE)?;
-    append_property_string(fdt, "clock-names", "apb_pclk")?;
-    append_end_node(fdt)?;
+    let rtc_reg_prop = [dev_info.addr(), dev_info.length()];
+    let irq = [
+        GIC_FDT_IRQ_TYPE_SPI,
+        dev_info.irq() - IRQ_BASE,
+        IRQ_TYPE_LEVEL_HI,
+    ];
+
+    let rtc_node = fdt.begin_node(&format!("rtc@{:x}", dev_info.addr()))?;
+    fdt.property("compatible", compatible)?;
+    fdt.property_array_u64("reg", &rtc_reg_prop)?;
+    fdt.property_array_u32("interrupts", &irq)?;
+    fdt.property_u32("clocks", CLOCK_PHANDLE)?;
+    fdt.property_string("clock-names", "apb_pclk")?;
+    fdt.end_node(rtc_node)?;
 
     Ok(())
 }
 
 fn create_gpio_node<T: DeviceInfoForFdt + Clone + Debug>(
-    fdt: &mut Vec<u8>,
+    fdt: &mut FdtWriter,
     dev_info: &T,
-) -> Result<()> {
+) -> FdtWriterResult<()> {
     // PL061 GPIO controller node
     let compatible = b"arm,pl061\0arm,primecell\0";
-    let gpio_reg_prop = generate_prop64(&[dev_info.addr(), dev_info.length()]);
-    let irq = generate_prop32(&[GIC_FDT_IRQ_TYPE_SPI, dev_info.irq(), IRQ_TYPE_EDGE_RISING]);
-    append_begin_node(fdt, &format!("pl061@{:x}", dev_info.addr()))?;
-    append_property(fdt, "compatible", compatible)?;
-    append_property(fdt, "reg", &gpio_reg_prop)?;
-    append_property(fdt, "interrupts", &irq)?;
-    append_property_null(fdt, "gpio-controller")?;
-    append_property_u32(fdt, "#gpio-cells", 2)?;
-    append_property_u32(fdt, "clocks", CLOCK_PHANDLE)?;
-    append_property_string(fdt, "clock-names", "apb_pclk")?;
-    append_property_u32(fdt, "phandle", GPIO_PHANDLE)?;
-    append_end_node(fdt)?;
+    let gpio_reg_prop = [dev_info.addr(), dev_info.length()];
+    let irq = [
+        GIC_FDT_IRQ_TYPE_SPI,
+        dev_info.irq() - IRQ_BASE,
+        IRQ_TYPE_EDGE_RISING,
+    ];
+
+    let gpio_node = fdt.begin_node(&format!("pl061@{:x}", dev_info.addr()))?;
+    fdt.property("compatible", compatible)?;
+    fdt.property_array_u64("reg", &gpio_reg_prop)?;
+    fdt.property_array_u32("interrupts", &irq)?;
+    fdt.property_null("gpio-controller")?;
+    fdt.property_u32("#gpio-cells", 2)?;
+    fdt.property_u32("clocks", CLOCK_PHANDLE)?;
+    fdt.property_string("clock-names", "apb_pclk")?;
+    fdt.property_u32("phandle", GPIO_PHANDLE)?;
+    fdt.end_node(gpio_node)?;
 
     // gpio-keys node
-    append_begin_node(fdt, "/gpio-keys")?;
-    append_property_string(fdt, "compatible", "gpio-keys")?;
-    append_property_u32(fdt, "#size-cells", 0)?;
-    append_property_u32(fdt, "#address-cells", 1)?;
-    append_begin_node(fdt, "/gpio-keys/poweroff")?;
-    append_property_string(fdt, "label", "GPIO Key Poweroff")?;
-    append_property_u32(fdt, "linux,code", KEY_POWER)?;
-    let gpios = generate_prop32(&[GPIO_PHANDLE, 3, 0]);
-    append_property(fdt, "gpios", &gpios)?;
-    append_end_node(fdt)?;
-    append_end_node(fdt)?;
+    let gpio_keys_node = fdt.begin_node("gpio-keys")?;
+    fdt.property_string("compatible", "gpio-keys")?;
+    fdt.property_u32("#size-cells", 0)?;
+    fdt.property_u32("#address-cells", 1)?;
+    let gpio_keys_poweroff_node = fdt.begin_node("button@1")?;
+    fdt.property_string("label", "GPIO Key Poweroff")?;
+    fdt.property_u32("linux,code", KEY_POWER)?;
+    let gpios = [GPIO_PHANDLE, 3, 0];
+    fdt.property_array_u32("gpios", &gpios)?;
+    fdt.end_node(gpio_keys_poweroff_node)?;
+    fdt.end_node(gpio_keys_node)?;
 
     Ok(())
 }
 
 fn create_devices_node<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
-    fdt: &mut Vec<u8>,
+    fdt: &mut FdtWriter,
     dev_info: &HashMap<(DeviceType, String), T, S>,
-) -> Result<()> {
+) -> FdtWriterResult<()> {
     // Create one temp Vec to store all virtio devices
     let mut ordered_virtio_device: Vec<&T> = Vec::new();
 
@@ -592,11 +405,40 @@ fn create_devices_node<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::Buil
     Ok(())
 }
 
-fn create_pci_nodes(fdt: &mut Vec<u8>, pci_device_base: u64, pci_device_size: u64) -> Result<()> {
+fn create_pci_nodes(
+    fdt: &mut FdtWriter,
+    pci_device_base: u64,
+    pci_device_size: u64,
+) -> FdtWriterResult<()> {
     // Add node for PCIe controller.
     // See Documentation/devicetree/bindings/pci/host-generic-pci.txt in the kernel
     // and https://elinux.org/Device_Tree_Usage.
-    let ranges = generate_prop32(&[
+
+    // EDK2 requires the PCIe high space above 4G address.
+    // The actual space in CLH follows the RAM. If the RAM space is small, the PCIe high space
+    // could fall bellow 4G.
+    // Here we put it above 512G in FDT to workaround the EDK2 check.
+    // But the address written in ACPI is not impacted.
+    let pci_device_base_64bit: u64 = if cfg!(feature = "acpi") {
+        pci_device_base + PCI_HIGH_BASE
+    } else {
+        pci_device_base
+    };
+    let pci_device_size_64bit: u64 = if cfg!(feature = "acpi") {
+        pci_device_size - PCI_HIGH_BASE
+    } else {
+        pci_device_size
+    };
+
+    let ranges = [
+        // io addresses
+        0x1000000,
+        0_u32,
+        0_u32,
+        (MEM_PCI_IO_START.0 >> 32) as u32,
+        MEM_PCI_IO_START.0 as u32,
+        (MEM_PCI_IO_SIZE >> 32) as u32,
+        MEM_PCI_IO_SIZE as u32,
         // mmio addresses
         0x2000000,                                // (ss = 10: 32-bit memory space)
         (MEM_32BIT_DEVICES_START.0 >> 32) as u32, // PCI address
@@ -606,31 +448,31 @@ fn create_pci_nodes(fdt: &mut Vec<u8>, pci_device_base: u64, pci_device_size: u6
         (MEM_32BIT_DEVICES_SIZE >> 32) as u32, // size
         MEM_32BIT_DEVICES_SIZE as u32,
         // device addresses
-        0x3000000,                      // (ss = 11: 64-bit memory space)
-        (pci_device_base >> 32) as u32, // PCI address
-        pci_device_base as u32,
-        (pci_device_base >> 32) as u32, // CPU address
-        pci_device_base as u32,
-        (pci_device_size >> 32) as u32, // size
-        pci_device_size as u32,
-    ]);
-    let bus_range = generate_prop32(&[0, 0]); // Only bus 0
-    let reg = generate_prop64(&[PCI_MMCONFIG_START.0, PCI_MMCONFIG_SIZE]);
+        0x3000000,                            // (ss = 11: 64-bit memory space)
+        (pci_device_base_64bit >> 32) as u32, // PCI address
+        pci_device_base_64bit as u32,
+        (pci_device_base_64bit >> 32) as u32, // CPU address
+        pci_device_base_64bit as u32,
+        (pci_device_size_64bit >> 32) as u32, // size
+        pci_device_size_64bit as u32,
+    ];
+    let bus_range = [0, 0]; // Only bus 0
+    let reg = [PCI_MMCONFIG_START.0, PCI_MMCONFIG_SIZE];
 
-    append_begin_node(fdt, "pci")?;
-    append_property_string(fdt, "compatible", "pci-host-ecam-generic")?;
-    append_property_string(fdt, "device_type", "pci")?;
-    append_property(fdt, "ranges", &ranges)?;
-    append_property(fdt, "bus-range", &bus_range)?;
-    append_property_u32(fdt, "#address-cells", 3)?;
-    append_property_u32(fdt, "#size-cells", 2)?;
-    append_property(fdt, "reg", &reg)?;
-    append_property_u32(fdt, "#interrupt-cells", 1)?;
-    append_property_null(fdt, "interrupt-map")?;
-    append_property_null(fdt, "interrupt-map-mask")?;
-    append_property_null(fdt, "dma-coherent")?;
-    append_property_u32(fdt, "msi-parent", MSI_PHANDLE)?;
-    append_end_node(fdt)?;
+    let pci_node = fdt.begin_node("pci")?;
+    fdt.property_string("compatible", "pci-host-ecam-generic")?;
+    fdt.property_string("device_type", "pci")?;
+    fdt.property_array_u32("ranges", &ranges)?;
+    fdt.property_array_u32("bus-range", &bus_range)?;
+    fdt.property_u32("#address-cells", 3)?;
+    fdt.property_u32("#size-cells", 2)?;
+    fdt.property_array_u64("reg", &reg)?;
+    fdt.property_u32("#interrupt-cells", 1)?;
+    fdt.property_null("interrupt-map")?;
+    fdt.property_null("interrupt-map-mask")?;
+    fdt.property_null("dma-coherent")?;
+    fdt.property_u32("msi-parent", MSI_PHANDLE)?;
+    fdt.end_node(pci_node)?;
 
     Ok(())
 }

arch/src/aarch64/gic/gicv3.rs

@@ -5,18 +5,23 @@ pub mod kvm {
     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::kvm::{save_pending_tables, KvmGicDevice};
-    use crate::aarch64::gic::redist_regs::{get_redist_regs, set_redist_regs};
+    use crate::aarch64::gic::redist_regs::{
+        construct_gicr_typers, get_redist_regs, set_redist_regs,
+    };
     use crate::aarch64::gic::GicDevice;
     use crate::layout;
     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, SnapshotDataSection, Snapshottable,
-        Transportable,
+        Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable,
+        VersionMapped,
     };
 
     /// Errors thrown while saving/restoring the GICv3.
@@ -58,7 +63,7 @@ pub mod kvm {
         vcpu_count: u64,
     }
 
-    #[derive(Serialize, Deserialize)]
+    #[derive(Versionize)]
     pub struct Gicv3State {
         dist: Vec<u32>,
         rdist: Vec<u32>,
@@ -67,6 +72,8 @@ pub mod kvm {
         gicd_ctlr: u32,
     }
 
+    impl VersionMapped for Gicv3State {}
+
     impl KvmGicV3 {
         // Unfortunately bindgen omits defines that are based on other defines.
         // See arch/arm64/include/uapi/asm/kvm.h file from the linux kernel.
@@ -161,7 +168,8 @@ pub mod kvm {
             self.vcpu_count
         }
 
-        fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>) {
+        fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]) {
+            let gicr_typers = construct_gicr_typers(vcpu_states);
             self.gicr_typers = gicr_typers;
         }
 
@@ -230,42 +238,15 @@ pub mod kvm {
 
         fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
             let gicr_typers = self.gicr_typers.clone();
-            let snapshot = serde_json::to_vec(&self.state(&gicr_typers).unwrap())
-                .map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-            let mut gic_v3_snapshot = Snapshot::new(self.id().as_str());
-            gic_v3_snapshot.add_data_section(SnapshotDataSection {
-                id: format!("{}-section", self.id()),
-                snapshot,
-            });
-
-            Ok(gic_v3_snapshot)
+            Snapshot::new_from_versioned_state(&self.id(), &self.state(&gicr_typers).unwrap())
         }
 
         fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-            if let Some(gic_v3_section) = snapshot
-                .snapshot_data
-                .get(&format!("{}-section", self.id()))
-            {
-                let gic_v3_state = match serde_json::from_slice(&gic_v3_section.snapshot) {
-                    Ok(state) => state,
-                    Err(error) => {
-                        return Err(MigratableError::Restore(anyhow!(
-                            "Could not deserialize GICv3 {}",
-                            error
-                        )))
-                    }
-                };
-
-                let gicr_typers = self.gicr_typers.clone();
-                return self.set_state(&gicr_typers, &gic_v3_state).map_err(|e| {
+            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 GICv3 state {:?}", e))
-                });
-            }
-
-            Err(MigratableError::Restore(anyhow!(
-                "Could not find GICv3 snapshot section"
-            )))
+                })
         }
     }
 

arch/src/aarch64/gic/gicv3_its.rs

@@ -3,7 +3,6 @@
 
 pub mod kvm {
     use std::any::Any;
-    use std::convert::TryInto;
     use std::sync::Arc;
     use std::{boxed::Box, result};
     type Result<T> = result::Result<T, Error>;
@@ -11,14 +10,12 @@ pub mod kvm {
     use crate::aarch64::gic::kvm::KvmGicDevice;
     use crate::aarch64::gic::{Error, GicDevice};
     use hypervisor::kvm::kvm_bindings;
+    use hypervisor::CpuState;
 
     pub struct KvmGicV3Its {
         /// The hypervisor agnostic device
         device: 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],
 
@@ -74,9 +71,7 @@ pub mod kvm {
             self.vcpu_count
         }
 
-        fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>) {
-            self.gicr_typers = gicr_typers;
-        }
+        fn set_gicr_typers(&mut self, _vcpu_states: &[CpuState]) {}
 
         fn as_any_concrete_mut(&mut self) -> &mut dyn Any {
             self
@@ -94,7 +89,6 @@ pub mod kvm {
         ) -> Box<dyn GicDevice> {
             Box::new(KvmGicV3Its {
                 device,
-                gicr_typers: vec![0; vcpu_count.try_into().unwrap()],
                 gic_properties: [
                     KvmGicV3::get_dist_addr(),
                     KvmGicV3::get_dist_size(),

arch/src/aarch64/gic/mod.rs

@@ -10,6 +10,7 @@ pub mod redist_regs;
 pub use self::dist_regs::{get_dist_regs, read_ctlr, set_dist_regs, write_ctlr};
 pub use self::icc_regs::{get_icc_regs, set_icc_regs};
 pub use self::redist_regs::{get_redist_regs, set_redist_regs};
+use hypervisor::CpuState;
 use std::any::Any;
 use std::result;
 use std::sync::Arc;
@@ -58,7 +59,7 @@ pub trait GicDevice: Send {
     }
 
     /// Get the values of GICR_TYPER for each vCPU.
-    fn set_gicr_typers(&mut self, gicr_typers: Vec<u64>);
+    fn set_gicr_typers(&mut self, vcpu_states: &[CpuState]);
 
     /// Downcast the trait object to its concrete type.
     fn as_any_concrete_mut(&mut self) -> &mut dyn Any;
@@ -111,10 +112,10 @@ pub mod kvm {
             flags: u32,
         ) -> Result<()> {
             let attr = kvm_bindings::kvm_device_attr {
+                flags,
                 group,
                 attr,
                 addr,
-                flags,
             };
             device
                 .set_device_attr(&attr)
@@ -132,10 +133,10 @@ pub mod kvm {
             flags: u32,
         ) -> Result<()> {
             let mut attr = kvm_bindings::kvm_device_attr {
+                flags,
                 group,
                 attr,
                 addr,
-                flags,
             };
             device
                 .get_device_attr(&mut attr)
@@ -149,7 +150,7 @@ pub mod kvm {
             /* We need to tell the kernel how many irqs to support with this vgic.
              * See the `layout` module for details.
              */
-            let nr_irqs: u32 = layout::IRQ_MAX - layout::IRQ_BASE + 1;
+            let nr_irqs: u32 = layout::IRQ_NUM;
             let nr_irqs_ptr = &nr_irqs as *const u32;
             Self::set_device_attribute(
                 gic_device.device(),

arch/src/aarch64/gic/redist_regs.rs

@@ -3,6 +3,7 @@
 
 use super::{Error, Result};
 use hypervisor::kvm::kvm_bindings::{kvm_device_attr, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS};
+use hypervisor::CpuState;
 use std::sync::Arc;
 
 // Relevant redistributor registers that we want to save/restore.
@@ -177,3 +178,34 @@ pub fn set_redist_regs(
         true,
     )
 }
+
+pub fn construct_gicr_typers(vcpu_states: &[CpuState]) -> Vec<u64> {
+    /* Pre-construct the GICR_TYPER:
+     * For our implementation:
+     *  Top 32 bits are the affinity value of the associated CPU
+     *  CommonLPIAff == 01 (redistributors with same Aff3 share LPI table)
+     *  Processor_Number == CPU index starting from 0
+     *  DPGS == 0 (GICR_CTLR.DPG* not supported)
+     *  Last == 1 if this is the last redistributor in a series of
+     *            contiguous redistributor pages
+     *  DirectLPI == 0 (direct injection of LPIs not supported)
+     *  VLPIS == 0 (virtual LPIs not supported)
+     *  PLPIS == 0 (physical LPIs not supported)
+     */
+    let mut gicr_typers: Vec<u64> = Vec::new();
+    for (index, state) in vcpu_states.iter().enumerate() {
+        let last = {
+            if index == vcpu_states.len() - 1 {
+                1
+            } else {
+                0
+            }
+        };
+        //calculate affinity
+        let mut cpu_affid = state.mpidr & 1095233437695;
+        cpu_affid = ((cpu_affid & 0xFF00000000) >> 8) | (cpu_affid & 0xFFFFFF);
+        gicr_typers.push((cpu_affid << 32) | (1 << 24) | (index as u64) << 8 | (last << 4));
+    }
+
+    gicr_typers
+}

arch/src/aarch64/layout.rs

@@ -19,15 +19,14 @@
 // memory)   |                                                               |
 //           |                            DRAM                               |
 //           |                                                               |
-// 2GB       +---------------------------------------------------------------+
 //           |                                                               |
-//           |                           Reserved                            |
 //           |                                                               |
-// 1G+256M   +---------------------------------------------------------------+
+// 1GB       +---------------------------------------------------------------+
 //           |                                                               |
 //           |                        PCI MMCONFIG space                     |
 //           |                                                               |
-// 1GB       +---------------------------------------------------------------+
+// 768 M     +---------------------------------------------------------------+
+//           |                                                               |
 //           |                                                               |
 //           |                           PCI MMIO space                      |
 //           |                                                               |
@@ -36,8 +35,10 @@
 //           |                        Legacy devices space                   |
 //           |                                                               |
 // 144 M     +---------------------------------------------------------------|
-//           |                                                               |
 //           |                    Reserved (now GIC is here)                 |
+// 64  M     +---------------------------------------------------------------+
+//           |                                                               |
+//           |                          UEFI space                           |
 //           |                                                               |
 // 0GB       +---------------------------------------------------------------+
 //
@@ -45,43 +46,62 @@
 
 use vm_memory::GuestAddress;
 
+/// 0x0 ~ 0x400_0000 is reserved to uefi
+pub const UEFI_START: u64 = 0x0;
+pub const MEM_UEFI_START: GuestAddress = GuestAddress(0);
+pub const UEFI_SIZE: u64 = 0x0400_0000;
+
 /// Below this address will reside the GIC, above this address will reside the MMIO devices.
 pub const MAPPED_IO_START: u64 = 0x0900_0000;
 
-/// Space 0x0900_0000 ~ 0x1000_0000 is reserved for legacy devices.
+/// Space 0x0900_0000 ~ 0x0905_0000 is reserved for legacy devices.
 pub const LEGACY_SERIAL_MAPPED_IO_START: u64 = 0x0900_0000;
 pub const LEGACY_RTC_MAPPED_IO_START: u64 = 0x0901_0000;
 pub const LEGACY_GPIO_MAPPED_IO_START: u64 = 0x0902_0000;
 
-/// Legacy space will be allocated at once whiling setting up legacy devices.
-pub const LEGACY_DEVICES_MAPPED_IO_SIZE: u64 = 0x0700_0000;
+/// Space 0x0905_0000 ~ 0x0906_0000 is reserved for pcie io address
+pub const MEM_PCI_IO_START: GuestAddress = GuestAddress(0x0905_0000);
+pub const MEM_PCI_IO_SIZE: u64 = 0x10000;
 
-/// Starting from 0x1000_0000 (256MiB), the 768MiB (ends at 1 GiB) is used for PCIE MMIO
+/// Starting from 0x1000_0000 (256MiB) to 0x3000_0000 (768MiB) is used for PCIE MMIO
 pub const MEM_32BIT_DEVICES_START: GuestAddress = GuestAddress(0x1000_0000);
-pub const MEM_32BIT_DEVICES_SIZE: u64 = 0x3000_0000;
+pub const MEM_32BIT_DEVICES_SIZE: u64 = 0x2000_0000;
 
 /// PCI MMCONFIG space (start: after the device space at 1 GiB, length: 256MiB)
-pub const PCI_MMCONFIG_START: GuestAddress = GuestAddress(0x4000_0000);
+pub const PCI_MMCONFIG_START: GuestAddress = GuestAddress(0x3000_0000);
 pub const PCI_MMCONFIG_SIZE: u64 = 256 << 20;
 
 /// Start of RAM on 64 bit ARM.
-pub const RAM_64BIT_START: u64 = 0x8000_0000;
+pub const RAM_64BIT_START: u64 = 0x4000_0000;
 
 /// Kernel command line maximum size.
 /// As per `arch/arm64/include/uapi/asm/setup.h`.
 pub const CMDLINE_MAX_SIZE: usize = 2048;
 
+/// FDT is at the beginning of RAM.
 /// Maximum size of the device tree blob as specified in https://www.kernel.org/doc/Documentation/arm64/booting.txt.
+pub const FDT_START: u64 = RAM_64BIT_START;
 pub const FDT_MAX_SIZE: usize = 0x20_0000;
 
+/// Put ACPI table above dtb
+pub const ACPI_START: u64 = RAM_64BIT_START + FDT_MAX_SIZE as u64;
+pub const ACPI_MAX_SIZE: usize = 0x20_0000;
+pub const RSDP_POINTER: GuestAddress = GuestAddress(ACPI_START);
+
+/// Kernel start after FDT and ACPI
+pub const KERNEL_START: u64 = ACPI_START + ACPI_MAX_SIZE as u64;
+
+/// Pci high memory base
+pub const PCI_HIGH_BASE: u64 = 0x80_0000_0000_u64;
+
 // As per virt/kvm/arm/vgic/vgic-kvm-device.c we need
 // the number of interrupts our GIC will support to be:
 // * bigger than 32
 // * less than 1023 and
 // * a multiple of 32.
 // We are setting up our interrupt controller to support a maximum of 256 interrupts.
-/// First usable interrupt on aarch64.
-pub const IRQ_BASE: u32 = 0;
+/// First usable interrupt on aarch64
+pub const IRQ_BASE: u32 = 32;
 
-/// Last usable interrupt on aarch64.
-pub const IRQ_MAX: u32 = 255;
+/// Number of supported interrupts
+pub const IRQ_NUM: u32 = 256;

arch/src/aarch64/mod.rs

@@ -10,25 +10,31 @@ pub mod gic;
 pub mod layout;
 /// Logic for configuring aarch64 registers.
 pub mod regs;
+/// Module for loading UEFI binary.
+pub mod uefi;
 
 pub use self::fdt::DeviceInfoForFdt;
 use crate::DeviceType;
+use crate::GuestMemoryMmap;
 use crate::RegionType;
-use aarch64::gic::GicDevice;
+use gic::GicDevice;
 use std::collections::HashMap;
+use std::convert::TryInto;
 use std::ffi::CStr;
 use std::fmt::Debug;
 use std::sync::Arc;
 use vm_memory::{
-    Address, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic, GuestMemoryMmap,
-    GuestUsize,
+    Address, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic, GuestUsize,
 };
 
 /// Errors thrown while configuring aarch64 system.
 #[derive(Debug)]
 pub enum Error {
     /// Failed to create a FDT.
-    SetupFdt(fdt::Error),
+    SetupFdt,
+
+    /// Failed to write FDT to memory.
+    WriteFdtToMemory(fdt::Error),
 
     /// Failed to create a GIC.
     SetupGic(gic::Error),
@@ -79,64 +85,78 @@ 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 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") {
+        layout::UEFI_SIZE
+    } else {
+        0
+    };
+
     vec![
-        // 0 ~ 256 MiB: Reserved
+        // 0 ~ 64 MiB: Reserved for UEFI space
+        #[cfg(feature = "acpi")]
+        (GuestAddress(0), layout::UEFI_SIZE as usize, RegionType::Ram),
+        #[cfg(not(feature = "acpi"))]
         (
             GuestAddress(0),
-            layout::MEM_32BIT_DEVICES_START.0 as usize,
+            layout::UEFI_SIZE as usize,
             RegionType::Reserved,
         ),
-        // 256 MiB ~ 1 G: MMIO space
+        // 64 MiB ~ 256 MiB: Gic and legacy devices
+        (
+            GuestAddress(layout::UEFI_SIZE),
+            (layout::MEM_32BIT_DEVICES_START.0 - layout::UEFI_SIZE) as usize,
+            RegionType::Reserved,
+        ),
+        // 256 MiB ~ 768 MiB: MMIO space
         (
             layout::MEM_32BIT_DEVICES_START,
             layout::MEM_32BIT_DEVICES_SIZE as usize,
             RegionType::SubRegion,
         ),
-        // 1G  ~ 2G: reserved. The leading 256M for PCIe MMCONFIG space
+        // 768 MiB ~ 1 GiB: reserved. The leading 256M for PCIe MMCONFIG space
         (
             layout::PCI_MMCONFIG_START,
-            (layout::RAM_64BIT_START - layout::PCI_MMCONFIG_START.0) as usize,
+            layout::PCI_MMCONFIG_SIZE as usize,
             RegionType::Reserved,
         ),
+        // 1 GiB ~ : Ram
         (
             GuestAddress(layout::RAM_64BIT_START),
-            size as usize,
+            (size - ram_deduction) as usize,
             RegionType::Ram,
         ),
     ]
 }
 
 /// Configures the system and should be called once per vm before starting vcpu threads.
-///
-/// # Arguments
-///
-/// * `guest_mem` - The memory to be used by the guest.
-/// * `num_cpus` - Number of virtual CPUs the guest will have.
-#[allow(clippy::too_many_arguments)]
 pub fn configure_system<T: DeviceInfoForFdt + Clone + Debug, S: ::std::hash::BuildHasher>(
-    vm: &Arc<dyn hypervisor::Vm>,
     guest_mem: &GuestMemoryMmap,
     cmdline_cstring: &CStr,
-    vcpu_count: u64,
     vcpu_mpidr: Vec<u64>,
     device_info: &HashMap<(DeviceType, String), T, S>,
     initrd: &Option<super::InitramfsConfig>,
     pci_space_address: &(u64, u64),
-) -> super::Result<Box<dyn GicDevice>> {
-    let gic_device = gic::kvm::create_gic(vm, vcpu_count).map_err(Error::SetupGic)?;
-
-    fdt::create_fdt(
+    gic_device: &dyn GicDevice,
+) -> super::Result<()> {
+    let fdt_final = fdt::create_fdt(
         guest_mem,
         cmdline_cstring,
         vcpu_mpidr,
         device_info,
-        &*gic_device,
+        gic_device,
         initrd,
         pci_space_address,
     )
-    .map_err(Error::SetupFdt)?;
+    .map_err(|_| Error::SetupFdt)?;
 
-    Ok(gic_device)
+    fdt::write_fdt_to_memory(fdt_final, guest_mem).map_err(Error::WriteFdtToMemory)?;
+
+    Ok(())
 }
 
 /// Returns the memory address where the initramfs could be loaded.
@@ -145,8 +165,9 @@ pub fn initramfs_load_addr(
     initramfs_size: usize,
 ) -> super::Result<u64> {
     let round_to_pagesize = |size| (size + (super::PAGE_SIZE - 1)) & !(super::PAGE_SIZE - 1);
-    match GuestAddress(get_fdt_addr(&guest_mem))
-        .checked_sub(round_to_pagesize(initramfs_size) as u64)
+    match guest_mem
+        .last_addr()
+        .checked_sub(round_to_pagesize(initramfs_size) as u64 - 1)
     {
         Some(offset) => {
             if guest_mem.address_in_range(offset) {
@@ -161,41 +182,31 @@ pub fn initramfs_load_addr(
 
 /// Returns the memory address where the kernel could be loaded.
 pub fn get_kernel_start() -> u64 {
-    layout::RAM_64BIT_START
+    layout::KERNEL_START
+}
+
+///Return guest memory address where the uefi should be loaded.
+pub fn get_uefi_start() -> u64 {
+    layout::UEFI_START
 }
 
 // Auxiliary function to get the address where the device tree blob is loaded.
-fn get_fdt_addr(mem: &GuestMemoryMmap) -> u64 {
-    // If the memory allocated is smaller than the size allocated for the FDT,
-    // we return the start of the DRAM so that
-    // we allow the code to try and load the FDT.
-
-    if let Some(addr) = mem.last_addr().checked_sub(layout::FDT_MAX_SIZE as u64 - 1) {
-        if mem.address_in_range(addr) {
-            return addr.raw_value();
-        }
-    }
-
-    layout::RAM_64BIT_START
+fn get_fdt_addr() -> u64 {
+    layout::FDT_START
 }
 
 pub fn get_host_cpu_phys_bits() -> u8 {
-    // The value returned here is used to determine the physical address space size
-    // for a VM (IPA size).
-    // In recent kernel versions, the maximum IPA size supported by the host can be
-    // known by querying cap KVM_CAP_ARM_VM_IPA_SIZE. And the IPA size for a
-    // guest can be configured smaller.
-    // But in Cloud-Hypervisor we simply use the maximum value for the VM.
-    // Reference https://lwn.net/Articles/766767/.
-    //
-    // The correct way to query KVM_CAP_ARM_VM_IPA_SIZE is via rust-vmm/kvm-ioctls,
-    // which wraps all IOCTL's and provides easy interface to user hypervisors.
-    // For now the cap hasn't been supported. A separate patch will be submitted to
-    // rust-vmm to add it.
-    // So a hardcoded value is used here as a temporary solution.
-    // It will be replace once rust-vmm/kvm-ioctls is ready.
-    //
-    40
+    // A dummy hypervisor created only for querying the host IPA size and will
+    // be freed after the query.
+    let hv = hypervisor::new().unwrap();
+    let host_cpu_phys_bits = hv.get_host_ipa_limit().try_into().unwrap();
+    if host_cpu_phys_bits == 0 {
+        // Host kernel does not support `get_host_ipa_limit`,
+        // we return the default value 40 here.
+        40
+    } else {
+        host_cpu_phys_bits
+    }
 }
 
 #[cfg(test)]
@@ -205,38 +216,9 @@ mod tests {
     #[test]
     fn test_arch_memory_regions_dram() {
         let regions = arch_memory_regions((1usize << 32) as u64); //4GB
-        assert_eq!(4, regions.len());
-        assert_eq!(GuestAddress(layout::RAM_64BIT_START), regions[3].0);
-        assert_eq!(1usize << 32, regions[3].1);
-        assert_eq!(RegionType::Ram, regions[3].2);
-    }
-
-    #[test]
-    fn test_get_fdt_addr() {
-        let mut regions = Vec::new();
-
-        regions.push((
-            GuestAddress(layout::RAM_64BIT_START),
-            (layout::FDT_MAX_SIZE - 0x1000) as usize,
-        ));
-        let mem = GuestMemoryMmap::from_ranges(&regions).expect("Cannot initialize memory");
-        assert_eq!(get_fdt_addr(&mem), layout::RAM_64BIT_START);
-        regions.clear();
-
-        regions.push((
-            GuestAddress(layout::RAM_64BIT_START),
-            (layout::FDT_MAX_SIZE) as usize,
-        ));
-        let mem = GuestMemoryMmap::from_ranges(&regions).expect("Cannot initialize memory");
-        assert_eq!(get_fdt_addr(&mem), layout::RAM_64BIT_START);
-        regions.clear();
-
-        regions.push((
-            GuestAddress(layout::RAM_64BIT_START),
-            (layout::FDT_MAX_SIZE + 0x1000) as usize,
-        ));
-        let mem = GuestMemoryMmap::from_ranges(&regions).expect("Cannot initialize memory");
-        assert_eq!(get_fdt_addr(&mem), 0x1000 + layout::RAM_64BIT_START);
-        regions.clear();
+        assert_eq!(5, regions.len());
+        assert_eq!(GuestAddress(layout::RAM_64BIT_START), regions[4].0);
+        assert_eq!(1usize << 32, regions[4].1);
+        assert_eq!(RegionType::Ram, regions[4].2);
     }
 }

arch/src/aarch64/regs.rs

@@ -6,13 +6,13 @@
 // found in the THIRD-PARTY file.
 
 use super::get_fdt_addr;
+use crate::GuestMemoryMmap;
 use hypervisor::kvm::kvm_bindings::{
     kvm_regs, user_pt_regs, KVM_REG_ARM64, KVM_REG_ARM_CORE, KVM_REG_SIZE_U64,
 };
 use hypervisor::{arm64_core_reg_id, offset__of};
 use std::sync::Arc;
 use std::{mem, result};
-use vm_memory::GuestMemoryMmap;
 
 /// Errors thrown while setting aarch64 registers.
 #[derive(Debug)]
@@ -47,7 +47,7 @@ pub fn setup_regs(
     vcpu: &Arc<dyn hypervisor::Vcpu>,
     cpu_id: u8,
     boot_ip: u64,
-    mem: &GuestMemoryMmap,
+    _mem: &GuestMemoryMmap,
 ) -> Result<()> {
     let kreg_off = offset__of!(kvm_regs, regs);
 
@@ -73,7 +73,7 @@ pub fn setup_regs(
         let regs0 = offset__of!(user_pt_regs, regs) + kreg_off;
         vcpu.set_reg(
             arm64_core_reg_id!(KVM_REG_SIZE_U64, regs0),
-            get_fdt_addr(mem) as u64,
+            get_fdt_addr() as u64,
         )
         .map_err(Error::SetCoreRegister)?;
     }

arch/src/aarch64/uefi.rs

@@ -0,0 +1,43 @@
+// Copyright 2020 Arm Limited (or its affiliates). All rights reserved.
+
+use std::io::{Read, Seek, SeekFrom};
+use std::result;
+use vm_memory::{Bytes, GuestAddress, GuestMemory};
+
+/// Errors thrown while loading UEFI binary
+#[derive(Debug)]
+pub enum Error {
+    /// Unable to seek to UEFI image start.
+    SeekUefiStart,
+    /// Unable to seek to UEFI image end.
+    SeekUefiEnd,
+    /// UEFI image too big.
+    UefiTooBig,
+    /// Unable to read UEFI image
+    ReadUefiImage,
+}
+type Result<T> = result::Result<T, Error>;
+
+pub fn load_uefi<F, M: GuestMemory>(
+    guest_mem: &M,
+    guest_addr: GuestAddress,
+    uefi_image: &mut F,
+) -> Result<()>
+where
+    F: Read + Seek,
+{
+    let uefi_size = uefi_image
+        .seek(SeekFrom::End(0))
+        .map_err(|_| Error::SeekUefiEnd)? as usize;
+
+    // edk2 image on virtual platform is smaller than 3M
+    if uefi_size > 0x300000 {
+        return Err(Error::UefiTooBig);
+    }
+    uefi_image
+        .seek(SeekFrom::Start(0))
+        .map_err(|_| Error::SeekUefiStart)?;
+    guest_mem
+        .read_exact_from(guest_addr, uefi_image, uefi_size)
+        .map_err(|_| Error::ReadUefiImage)
+}

arch/src/lib.rs

@@ -8,28 +8,14 @@
 //! Supported platforms: x86_64, aarch64.
 #![allow(clippy::transmute_ptr_to_ptr, clippy::redundant_static_lifetimes)]
 
-extern crate anyhow;
-extern crate byteorder;
-extern crate hypervisor;
-extern crate libc;
 #[macro_use]
 extern crate log;
-#[cfg(feature = "acpi")]
-extern crate acpi_tables;
-extern crate arch_gen;
-extern crate linux_loader;
-extern crate serde;
-extern crate vm_memory;
-extern crate vm_migration;
-#[cfg(target_arch = "aarch64")]
-#[macro_use]
-extern crate serde_derive;
-extern crate serde_json;
-extern crate thiserror;
 
 use std::fmt;
 use std::result;
 
+type GuestMemoryMmap = vm_memory::GuestMemoryMmap<vm_memory::bitmap::AtomicBitmap>;
+
 /// Type for returning error code.
 #[derive(Debug)]
 pub enum Error {
@@ -88,8 +74,8 @@ pub mod aarch64;
 #[cfg(target_arch = "aarch64")]
 pub use aarch64::{
     arch_memory_regions, configure_system, configure_vcpu, fdt::DeviceInfoForFdt,
-    get_host_cpu_phys_bits, get_kernel_start, initramfs_load_addr, layout,
-    layout::CMDLINE_MAX_SIZE, layout::IRQ_BASE, layout::IRQ_MAX, EntryPoint,
+    get_host_cpu_phys_bits, get_kernel_start, get_uefi_start, initramfs_load_addr, layout,
+    layout::CMDLINE_MAX_SIZE, layout::IRQ_BASE, uefi, EntryPoint,
 };
 
 #[cfg(target_arch = "x86_64")]
@@ -98,8 +84,8 @@ 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,
-    BootProtocol, CpuidPatch, CpuidReg, EntryPoint,
+    initramfs_load_addr, layout, layout::CMDLINE_MAX_SIZE, layout::CMDLINE_START, regs, CpuidPatch,
+    CpuidReg, EntryPoint,
 };
 
 /// Safe wrapper for `sysconf(_SC_PAGESIZE)`.

arch/src/x86_64/interrupts.rs

@@ -12,12 +12,6 @@ use std::mem;
 use std::result;
 use std::sync::Arc;
 
-#[derive(Debug)]
-pub enum Error {
-    GetLapic(anyhow::Error),
-    SetLapic(anyhow::Error),
-}
-
 pub type Result<T> = result::Result<T, hypervisor::HypervisorCpuError>;
 
 // Defines poached from apicdef.h kernel header.

arch/src/x86_64/mod.rs

@@ -9,40 +9,27 @@
 use std::sync::Arc;
 pub mod interrupts;
 pub mod layout;
+mod mpspec;
 mod mptable;
 pub mod regs;
+use crate::GuestMemoryMmap;
 use crate::InitramfsConfig;
 use crate::RegionType;
 use hypervisor::{CpuId, CpuIdEntry, CPUID_FLAG_VALID_INDEX};
-use linux_loader::loader::bootparam::{boot_params, setup_header};
+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::mem;
 use vm_memory::{
     Address, ByteValued, Bytes, GuestAddress, GuestAddressSpace, GuestMemory, GuestMemoryAtomic,
-    GuestMemoryMmap, GuestMemoryRegion, GuestUsize,
+    GuestMemoryRegion, GuestUsize,
 };
 mod smbios;
 use std::arch::x86_64;
 #[cfg(feature = "tdx")]
 pub mod tdx;
 
-#[derive(Debug, Copy, Clone)]
-pub enum BootProtocol {
-    LinuxBoot,
-    PvhBoot,
-}
-
-impl ::std::fmt::Display for BootProtocol {
-    fn fmt(&self, f: &mut ::std::fmt::Formatter) -> ::std::fmt::Result {
-        match self {
-            BootProtocol::LinuxBoot => write!(f, "Linux 64-bit boot protocol"),
-            BootProtocol::PvhBoot => write!(f, "PVH boot protocol"),
-        }
-    }
-}
-
 #[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
@@ -50,10 +37,6 @@ impl ::std::fmt::Display for BootProtocol {
 pub struct EntryPoint {
     /// Address in guest memory where the guest must start execution
     pub entry_addr: GuestAddress,
-    /// Specifies which boot protocol to use
-    pub protocol: BootProtocol,
-    /// This field is used for bzImage to fill zero page
-    pub setup_header: Option<setup_header>,
 }
 
 const E820_RAM: u32 = 1;
@@ -140,9 +123,6 @@ unsafe impl ByteValued for BootParamsWrapper {}
 
 #[derive(Debug)]
 pub enum Error {
-    /// Invalid e820 setup params.
-    E820Configuration,
-
     /// Error writing MP table to memory.
     MpTableSetup(mptable::Error),
 
@@ -351,17 +331,10 @@ pub fn configure_vcpu(
     regs::setup_msrs(fd).map_err(Error::MsrsConfiguration)?;
     if let Some(kernel_entry_point) = kernel_entry_point {
         // Safe to unwrap because this method is called after the VM is configured
-        regs::setup_regs(
-            fd,
-            kernel_entry_point.entry_addr.raw_value(),
-            layout::BOOT_STACK_POINTER.raw_value(),
-            layout::ZERO_PAGE_START.raw_value(),
-            kernel_entry_point.protocol,
-        )
-        .map_err(Error::RegsConfiguration)?;
+        regs::setup_regs(fd, kernel_entry_point.entry_addr.raw_value())
+            .map_err(Error::RegsConfiguration)?;
         regs::setup_fpu(fd).map_err(Error::FpuConfiguration)?;
-        regs::setup_sregs(&vm_memory.memory(), fd, kernel_entry_point.protocol)
-            .map_err(Error::SregsConfiguration)?;
+        regs::setup_sregs(&vm_memory.memory(), fd).map_err(Error::SregsConfiguration)?;
     }
     interrupts::set_lint(fd).map_err(|e| Error::LocalIntConfiguration(e.into()))?;
     Ok(())
@@ -426,12 +399,9 @@ pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, Region
 pub fn configure_system(
     guest_mem: &GuestMemoryMmap,
     cmdline_addr: GuestAddress,
-    cmdline_size: usize,
     initramfs: &Option<InitramfsConfig>,
     _num_cpus: u8,
-    setup_hdr: Option<setup_header>,
     rsdp_addr: Option<GuestAddress>,
-    boot_prot: BootProtocol,
     sgx_epc_region: Option<SgxEpcRegion>,
 ) -> super::Result<()> {
     let size = smbios::setup_smbios(guest_mem).map_err(Error::SmbiosSetup)?;
@@ -448,31 +418,13 @@ pub fn configure_system(
         }
     }
 
-    match boot_prot {
-        BootProtocol::PvhBoot => {
-            configure_pvh(
-                guest_mem,
-                cmdline_addr,
-                initramfs,
-                rsdp_addr,
-                sgx_epc_region,
-            )?;
-        }
-        BootProtocol::LinuxBoot => {
-            error!("Using deprecated LinuxBoot protocol: Please configure your kernel with CONFIG_PVH=y and supply the `vmlinux` file to `--kernel`");
-            configure_64bit_boot(
-                guest_mem,
-                cmdline_addr,
-                cmdline_size,
-                initramfs,
-                setup_hdr,
-                rsdp_addr,
-                sgx_epc_region,
-            )?;
-        }
-    }
-
-    Ok(())
+    configure_pvh(
+        guest_mem,
+        cmdline_addr,
+        initramfs,
+        rsdp_addr,
+        sgx_epc_region,
+    )
 }
 
 fn configure_pvh(
@@ -615,121 +567,6 @@ fn add_memmap_entry(memmap: &mut Vec<hvm_memmap_table_entry>, addr: u64, size: u
     });
 }
 
-fn configure_64bit_boot(
-    guest_mem: &GuestMemoryMmap,
-    cmdline_addr: GuestAddress,
-    cmdline_size: usize,
-    initramfs: &Option<InitramfsConfig>,
-    setup_hdr: Option<setup_header>,
-    rsdp_addr: Option<GuestAddress>,
-    sgx_epc_region: Option<SgxEpcRegion>,
-) -> super::Result<()> {
-    const KERNEL_BOOT_FLAG_MAGIC: u16 = 0xaa55;
-    const KERNEL_HDR_MAGIC: u32 = 0x53726448;
-    const KERNEL_LOADER_OTHER: u8 = 0xff;
-    const KERNEL_MIN_ALIGNMENT_BYTES: u32 = 0x1000000; // Must be non-zero.
-
-    let mut params: BootParamsWrapper = BootParamsWrapper(boot_params::default());
-
-    if let Some(hdr) = setup_hdr {
-        // We should use the header if the loader provides one (e.g. from a bzImage).
-        params.0.hdr = hdr;
-    } else {
-        params.0.hdr.boot_flag = KERNEL_BOOT_FLAG_MAGIC;
-        params.0.hdr.header = KERNEL_HDR_MAGIC;
-        params.0.hdr.kernel_alignment = KERNEL_MIN_ALIGNMENT_BYTES;
-    };
-
-    // Common bootparams settings
-    if params.0.hdr.type_of_loader == 0 {
-        params.0.hdr.type_of_loader = KERNEL_LOADER_OTHER;
-    }
-    params.0.hdr.cmd_line_ptr = cmdline_addr.raw_value() as u32;
-    params.0.hdr.cmdline_size = cmdline_size as u32;
-
-    if let Some(initramfs_config) = initramfs {
-        params.0.hdr.ramdisk_image = initramfs_config.address.raw_value() as u32;
-        params.0.hdr.ramdisk_size = initramfs_config.size as u32;
-    }
-
-    add_e820_entry(&mut params.0, 0, layout::EBDA_START.raw_value(), E820_RAM)?;
-
-    let mem_end = guest_mem.last_addr();
-    if mem_end < layout::MEM_32BIT_RESERVED_START {
-        add_e820_entry(
-            &mut params.0,
-            layout::HIGH_RAM_START.raw_value(),
-            mem_end.unchecked_offset_from(layout::HIGH_RAM_START) + 1,
-            E820_RAM,
-        )?;
-    } else {
-        add_e820_entry(
-            &mut params.0,
-            layout::HIGH_RAM_START.raw_value(),
-            layout::MEM_32BIT_RESERVED_START.unchecked_offset_from(layout::HIGH_RAM_START),
-            E820_RAM,
-        )?;
-        if mem_end > layout::RAM_64BIT_START {
-            add_e820_entry(
-                &mut params.0,
-                layout::RAM_64BIT_START.raw_value(),
-                mem_end.unchecked_offset_from(layout::RAM_64BIT_START) + 1,
-                E820_RAM,
-            )?;
-        }
-    }
-
-    add_e820_entry(
-        &mut params.0,
-        layout::PCI_MMCONFIG_START.0,
-        layout::PCI_MMCONFIG_SIZE,
-        E820_RESERVED,
-    )?;
-
-    if let Some(sgx_epc_region) = sgx_epc_region {
-        add_e820_entry(
-            &mut params.0,
-            sgx_epc_region.start().raw_value(),
-            sgx_epc_region.size() as u64,
-            E820_RESERVED,
-        )?;
-    }
-
-    if let Some(rsdp_addr) = rsdp_addr {
-        params.0.acpi_rsdp_addr = rsdp_addr.0;
-    }
-
-    let zero_page_addr = layout::ZERO_PAGE_START;
-    guest_mem
-        .checked_offset(zero_page_addr, mem::size_of::<boot_params>())
-        .ok_or(super::Error::ZeroPagePastRamEnd)?;
-    guest_mem
-        .write_obj(params, zero_page_addr)
-        .map_err(super::Error::ZeroPageSetup)?;
-
-    Ok(())
-}
-
-/// Add an e820 region to the e820 map.
-/// Returns Ok(()) if successful, or an error if there is no space left in the map.
-fn add_e820_entry(
-    params: &mut boot_params,
-    addr: u64,
-    size: u64,
-    mem_type: u32,
-) -> Result<(), Error> {
-    if params.e820_entries >= params.e820_table.len() as u8 {
-        return Err(Error::E820Configuration);
-    }
-
-    params.e820_table[params.e820_entries as usize].addr = addr;
-    params.e820_table[params.e820_entries as usize].size = size;
-    params.e820_table[params.e820_entries as usize].type_ = mem_type;
-    params.e820_entries += 1;
-
-    Ok(())
-}
-
 /// Returns the memory address where the initramfs could be loaded.
 pub fn initramfs_load_addr(
     guest_mem: &GuestMemoryMmap,
@@ -888,7 +725,6 @@ pub fn update_cpuid_sgx(cpuid: &mut CpuId, epc_sections: Vec<SgxEpcSection>) ->
 #[cfg(test)]
 mod tests {
     use super::*;
-    use linux_loader::loader::bootparam::boot_e820_entry;
 
     #[test]
     fn regions_lt_4gb() {
@@ -913,12 +749,9 @@ mod tests {
         let config_err = configure_system(
             &gm,
             GuestAddress(0),
-            0,
             &None,
             1,
-            None,
             Some(layout::RSDP_POINTER),
-            BootProtocol::LinuxBoot,
             None,
         );
         assert!(config_err.is_err());
@@ -932,31 +765,8 @@ mod tests {
             .map(|r| (r.0, r.1))
             .collect();
         let gm = GuestMemoryMmap::from_ranges(&ram_regions).unwrap();
-        configure_system(
-            &gm,
-            GuestAddress(0),
-            0,
-            &None,
-            no_vcpus,
-            None,
-            None,
-            BootProtocol::LinuxBoot,
-            None,
-        )
-        .unwrap();
 
-        configure_system(
-            &gm,
-            GuestAddress(0),
-            0,
-            &None,
-            no_vcpus,
-            None,
-            None,
-            BootProtocol::PvhBoot,
-            None,
-        )
-        .unwrap();
+        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
 
         // Now assigning some memory that is equal to the start of the 32bit memory hole.
         let mem_size = 3328 << 20;
@@ -967,31 +777,9 @@ mod tests {
             .map(|r| (r.0, r.1))
             .collect();
         let gm = GuestMemoryMmap::from_ranges(&ram_regions).unwrap();
-        configure_system(
-            &gm,
-            GuestAddress(0),
-            0,
-            &None,
-            no_vcpus,
-            None,
-            None,
-            BootProtocol::LinuxBoot,
-            None,
-        )
-        .unwrap();
+        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
 
-        configure_system(
-            &gm,
-            GuestAddress(0),
-            0,
-            &None,
-            no_vcpus,
-            None,
-            None,
-            BootProtocol::PvhBoot,
-            None,
-        )
-        .unwrap();
+        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
 
         // Now assigning some memory that falls after the 32bit memory hole.
         let mem_size = 3330 << 20;
@@ -1002,71 +790,9 @@ mod tests {
             .map(|r| (r.0, r.1))
             .collect();
         let gm = GuestMemoryMmap::from_ranges(&ram_regions).unwrap();
-        configure_system(
-            &gm,
-            GuestAddress(0),
-            0,
-            &None,
-            no_vcpus,
-            None,
-            None,
-            BootProtocol::LinuxBoot,
-            None,
-        )
-        .unwrap();
+        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
 
-        configure_system(
-            &gm,
-            GuestAddress(0),
-            0,
-            &None,
-            no_vcpus,
-            None,
-            None,
-            BootProtocol::PvhBoot,
-            None,
-        )
-        .unwrap();
-    }
-
-    #[test]
-    fn test_add_e820_entry() {
-        let e820_table = [(boot_e820_entry {
-            addr: 0x1,
-            size: 4,
-            type_: 1,
-        }); 128];
-
-        let expected_params = boot_params {
-            e820_table,
-            e820_entries: 1,
-            ..Default::default()
-        };
-
-        let mut params: boot_params = Default::default();
-        add_e820_entry(
-            &mut params,
-            e820_table[0].addr,
-            e820_table[0].size,
-            e820_table[0].type_,
-        )
-        .unwrap();
-        assert_eq!(
-            format!("{:?}", params.e820_table[0]),
-            format!("{:?}", expected_params.e820_table[0])
-        );
-        assert_eq!(params.e820_entries, expected_params.e820_entries);
-
-        // Exercise the scenario where the field storing the length of the e820 entry table is
-        // is bigger than the allocated memory.
-        params.e820_entries = params.e820_table.len() as u8 + 1;
-        assert!(add_e820_entry(
-            &mut params,
-            e820_table[0].addr,
-            e820_table[0].size,
-            e820_table[0].type_
-        )
-        .is_err());
+        configure_system(&gm, GuestAddress(0), &None, no_vcpus, None, None).unwrap();
     }
 
     #[test]

arch/src/x86_64/mpspec.rs

@@ -0,0 +1,112 @@
+// Copyright 2017 The Chromium OS Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE-BSD-3-Clause file.
+
+pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
+pub const MP_BUS: ::std::os::raw::c_uint = 1;
+pub const MP_IOAPIC: ::std::os::raw::c_uint = 2;
+pub const MP_INTSRC: ::std::os::raw::c_uint = 3;
+pub const MP_LINTSRC: ::std::os::raw::c_uint = 4;
+pub const CPU_ENABLED: ::std::os::raw::c_uint = 1;
+pub const CPU_BOOTPROCESSOR: ::std::os::raw::c_uint = 2;
+pub const MPC_APIC_USABLE: ::std::os::raw::c_uint = 1;
+pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpf_intel {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub physptr: ::std::os::raw::c_uint,
+    pub length: ::std::os::raw::c_uchar,
+    pub specification: ::std::os::raw::c_uchar,
+    pub checksum: ::std::os::raw::c_uchar,
+    pub feature1: ::std::os::raw::c_uchar,
+    pub feature2: ::std::os::raw::c_uchar,
+    pub feature3: ::std::os::raw::c_uchar,
+    pub feature4: ::std::os::raw::c_uchar,
+    pub feature5: ::std::os::raw::c_uchar,
+}
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_table {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub length: ::std::os::raw::c_ushort,
+    pub spec: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub oem: [::std::os::raw::c_char; 8usize],
+    pub productid: [::std::os::raw::c_char; 12usize],
+    pub oemptr: ::std::os::raw::c_uint,
+    pub oemsize: ::std::os::raw::c_ushort,
+    pub oemcount: ::std::os::raw::c_ushort,
+    pub lapic: ::std::os::raw::c_uint,
+    pub reserved: ::std::os::raw::c_uint,
+}
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_cpu {
+    pub type_: ::std::os::raw::c_uchar,
+    pub apicid: ::std::os::raw::c_uchar,
+    pub apicver: ::std::os::raw::c_uchar,
+    pub cpuflag: ::std::os::raw::c_uchar,
+    pub cpufeature: ::std::os::raw::c_uint,
+    pub featureflag: ::std::os::raw::c_uint,
+    pub reserved: [::std::os::raw::c_uint; 2usize],
+}
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_bus {
+    pub type_: ::std::os::raw::c_uchar,
+    pub busid: ::std::os::raw::c_uchar,
+    pub bustype: [::std::os::raw::c_uchar; 6usize],
+}
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_ioapic {
+    pub type_: ::std::os::raw::c_uchar,
+    pub apicid: ::std::os::raw::c_uchar,
+    pub apicver: ::std::os::raw::c_uchar,
+    pub flags: ::std::os::raw::c_uchar,
+    pub apicaddr: ::std::os::raw::c_uint,
+}
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_intsrc {
+    pub type_: ::std::os::raw::c_uchar,
+    pub irqtype: ::std::os::raw::c_uchar,
+    pub irqflag: ::std::os::raw::c_ushort,
+    pub srcbus: ::std::os::raw::c_uchar,
+    pub srcbusirq: ::std::os::raw::c_uchar,
+    pub dstapic: ::std::os::raw::c_uchar,
+    pub dstirq: ::std::os::raw::c_uchar,
+}
+
+pub const MP_IRQ_SOURCE_TYPES_MP_INT: ::std::os::raw::c_uint = 0;
+pub const MP_IRQ_SOURCE_TYPES_MP_NMI: ::std::os::raw::c_uint = 1;
+pub const MP_IRQ_SOURCE_TYPES_MP_EXT_INT: ::std::os::raw::c_uint = 3;
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_lintsrc {
+    pub type_: ::std::os::raw::c_uchar,
+    pub irqtype: ::std::os::raw::c_uchar,
+    pub irqflag: ::std::os::raw::c_ushort,
+    pub srcbusid: ::std::os::raw::c_uchar,
+    pub srcbusirq: ::std::os::raw::c_uchar,
+    pub destapic: ::std::os::raw::c_uchar,
+    pub destapiclint: ::std::os::raw::c_uchar,
+}
+
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct mpc_oemtable {
+    pub signature: [::std::os::raw::c_char; 4usize],
+    pub length: ::std::os::raw::c_ushort,
+    pub rev: ::std::os::raw::c_char,
+    pub checksum: ::std::os::raw::c_char,
+    pub mpc: [::std::os::raw::c_char; 8usize],
+}

arch/src/x86_64/mptable.rs

@@ -5,18 +5,15 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
+use crate::layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
+use crate::x86_64::mpspec;
+use crate::GuestMemoryMmap;
+use libc::c_char;
 use std::io;
 use std::mem;
 use std::result;
 use std::slice;
-
-use libc::c_char;
-
-use arch_gen::x86::mpspec;
-use layout::{APIC_START, HIGH_RAM_START, IOAPIC_START};
-use vm_memory::{
-    Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryMmap,
-};
+use vm_memory::{Address, ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError};
 
 // This is a workaround to the Rust enforcement specifying that any implementation of a foreign
 // trait (in this case `ByteValued`) where:
@@ -222,7 +219,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         let size = mem::size_of::<MpcIntsrcWrapper>();
         let mut mpc_intsrc = MpcIntsrcWrapper(mpspec::mpc_intsrc::default());
         mpc_intsrc.0.type_ = mpspec::MP_INTSRC as u8;
-        mpc_intsrc.0.irqtype = mpspec::mp_irq_source_types_mp_INT as u8;
+        mpc_intsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_INT as u8;
         mpc_intsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_intsrc.0.srcbus = 0;
         mpc_intsrc.0.srcbusirq = i;
@@ -237,7 +234,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         let size = mem::size_of::<MpcLintsrcWrapper>();
         let mut mpc_lintsrc = MpcLintsrcWrapper(mpspec::mpc_lintsrc::default());
         mpc_lintsrc.0.type_ = mpspec::MP_LINTSRC as u8;
-        mpc_lintsrc.0.irqtype = mpspec::mp_irq_source_types_mp_ExtINT as u8;
+        mpc_lintsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_EXT_INT as u8;
         mpc_lintsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_lintsrc.0.srcbusid = 0;
         mpc_lintsrc.0.srcbusirq = 0;
@@ -252,7 +249,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
         let size = mem::size_of::<MpcLintsrcWrapper>();
         let mut mpc_lintsrc = MpcLintsrcWrapper(mpspec::mpc_lintsrc::default());
         mpc_lintsrc.0.type_ = mpspec::MP_LINTSRC as u8;
-        mpc_lintsrc.0.irqtype = mpspec::mp_irq_source_types_mp_NMI as u8;
+        mpc_lintsrc.0.irqtype = mpspec::MP_IRQ_SOURCE_TYPES_MP_NMI as u8;
         mpc_lintsrc.0.irqflag = mpspec::MP_IRQDIR_DEFAULT as u16;
         mpc_lintsrc.0.srcbusid = 0;
         mpc_lintsrc.0.srcbusirq = 0;
@@ -287,7 +284,7 @@ pub fn setup_mptable(offset: GuestAddress, mem: &GuestMemoryMmap, num_cpus: u8)
 #[cfg(test)]
 mod tests {
     use super::*;
-    use layout::MPTABLE_START;
+    use crate::layout::MPTABLE_START;
     use vm_memory::{GuestAddress, GuestUsize};
 
     fn table_entry_size(type_: u8) -> usize {

arch/src/x86_64/regs.rs

@@ -6,17 +6,14 @@
 // Portions Copyright 2017 The Chromium OS Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
-use std::sync::Arc;
-use std::{mem, result};
-
-use super::BootProtocol;
+use crate::layout::{BOOT_GDT_START, BOOT_IDT_START, PVH_INFO_START};
+use crate::GuestMemoryMmap;
 use hypervisor::arch::x86::gdt::{gdt_entry, segment_from_gdt};
 use hypervisor::arch::x86::regs::*;
 use hypervisor::x86_64::{FpuState, SpecialRegisters, StandardRegisters};
-use layout::{
-    BOOT_GDT_START, BOOT_IDT_START, PDE_START, PDPTE_START, PML4_START, PML5_START, PVH_INFO_START,
-};
-use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError, GuestMemoryMmap};
+use std::sync::Arc;
+use std::{mem, result};
+use vm_memory::{Address, Bytes, GuestMemory, GuestMemoryError};
 
 #[derive(Debug)]
 pub enum Error {
@@ -81,32 +78,12 @@ pub fn setup_msrs(vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
 ///
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
 /// * `boot_ip` - Starting instruction pointer.
-/// * `boot_sp` - Starting stack pointer.
-/// * `boot_si` - Must point to zero page address per Linux ABI.
-pub fn setup_regs(
-    vcpu: &Arc<dyn hypervisor::Vcpu>,
-    boot_ip: u64,
-    boot_sp: u64,
-    boot_si: u64,
-    boot_prot: BootProtocol,
-) -> Result<()> {
-    let regs: StandardRegisters = match boot_prot {
-        // Configure regs as required by PVH boot protocol.
-        BootProtocol::PvhBoot => StandardRegisters {
-            rflags: 0x0000000000000002u64,
-            rbx: PVH_INFO_START.raw_value(),
-            rip: boot_ip,
-            ..Default::default()
-        },
-        // Configure regs as required by Linux 64-bit boot protocol.
-        BootProtocol::LinuxBoot => StandardRegisters {
-            rflags: 0x0000000000000002u64,
-            rip: boot_ip,
-            rsp: boot_sp,
-            rbp: boot_sp,
-            rsi: boot_si,
-            ..Default::default()
-        },
+pub fn setup_regs(vcpu: &Arc<dyn hypervisor::Vcpu>, boot_ip: u64) -> Result<()> {
+    let regs = StandardRegisters {
+        rflags: 0x0000000000000002u64,
+        rbx: PVH_INFO_START.raw_value(),
+        rip: boot_ip,
+        ..Default::default()
     };
     vcpu.set_regs(&regs).map_err(Error::SetBaseRegisters)
 }
@@ -117,19 +94,9 @@ pub fn setup_regs(
 ///
 /// * `mem` - The memory that will be passed to the guest.
 /// * `vcpu` - Structure for the VCPU that holds the VCPU's fd.
-pub fn setup_sregs(
-    mem: &GuestMemoryMmap,
-    vcpu: &Arc<dyn hypervisor::Vcpu>,
-    boot_prot: BootProtocol,
-) -> Result<()> {
+pub fn setup_sregs(mem: &GuestMemoryMmap, vcpu: &Arc<dyn hypervisor::Vcpu>) -> Result<()> {
     let mut sregs: SpecialRegisters = vcpu.get_sregs().map_err(Error::GetStatusRegisters)?;
-
-    configure_segments_and_sregs(mem, &mut sregs, boot_prot)?;
-
-    if let BootProtocol::LinuxBoot = boot_prot {
-        setup_page_tables(mem, &mut sregs)?; // TODO(dgreid) - Can this be done once per system instead?
-    }
-
+    configure_segments_and_sregs(mem, &mut sregs)?;
     vcpu.set_sregs(&sregs).map_err(Error::SetStatusRegisters)
 }
 
@@ -156,27 +123,15 @@ fn write_idt_value(val: u64, guest_mem: &GuestMemoryMmap) -> Result<()> {
 pub fn configure_segments_and_sregs(
     mem: &GuestMemoryMmap,
     sregs: &mut SpecialRegisters,
-    boot_prot: BootProtocol,
 ) -> Result<()> {
-    let gdt_table: [u64; BOOT_GDT_MAX as usize] = match boot_prot {
-        BootProtocol::PvhBoot => {
-            // Configure GDT entries as specified by PVH boot protocol
-            [
-                gdt_entry(0, 0, 0),               // NULL
-                gdt_entry(0xc09b, 0, 0xffffffff), // CODE
-                gdt_entry(0xc093, 0, 0xffffffff), // DATA
-                gdt_entry(0x008b, 0, 0x67),       // TSS
-            ]
-        }
-        BootProtocol::LinuxBoot => {
-            // Configure GDT entries as specified by Linux 64bit boot protocol
-            [
-                gdt_entry(0, 0, 0),            // NULL
-                gdt_entry(0xa09b, 0, 0xfffff), // CODE
-                gdt_entry(0xc093, 0, 0xfffff), // DATA
-                gdt_entry(0x808b, 0, 0xfffff), // TSS
-            ]
-        }
+    let gdt_table: [u64; BOOT_GDT_MAX as usize] = {
+        // Configure GDT entries as specified by PVH boot protocol
+        [
+            gdt_entry(0, 0, 0),               // NULL
+            gdt_entry(0xc09b, 0, 0xffffffff), // CODE
+            gdt_entry(0xc093, 0, 0xffffffff), // DATA
+            gdt_entry(0x008b, 0, 0x67),       // TSS
+        ]
     };
 
     let code_seg = segment_from_gdt(gdt_table[1], 1);
@@ -200,61 +155,17 @@ pub fn configure_segments_and_sregs(
     sregs.ss = data_seg;
     sregs.tr = tss_seg;
 
-    match boot_prot {
-        BootProtocol::PvhBoot => {
-            sregs.cr0 = CR0_PE;
-            sregs.cr4 = 0;
-        }
-        BootProtocol::LinuxBoot => {
-            /* 64-bit protected mode */
-            sregs.cr0 |= CR0_PE;
-            sregs.efer |= EFER_LME | EFER_LMA;
-        }
-    }
-
-    Ok(())
-}
-
-pub fn setup_page_tables(mem: &GuestMemoryMmap, sregs: &mut SpecialRegisters) -> Result<()> {
-    // Puts PML5 or PML4 right after zero page but aligned to 4k.
-    if unsafe { std::arch::x86_64::__cpuid(7).ecx } & (1 << 16) != 0 {
-        // Entry covering VA [0..256TB)
-        mem.write_obj(PML4_START.raw_value() | 0x03, PML5_START)
-            .map_err(Error::WritePml5Address)?;
-
-        sregs.cr3 = PML5_START.raw_value();
-        sregs.cr4 |= CR4_LA57;
-    } else {
-        sregs.cr3 = PML4_START.raw_value();
-    }
-
-    // Entry covering VA [0..512GB)
-    mem.write_obj(PDPTE_START.raw_value() | 0x03, PML4_START)
-        .map_err(Error::WritePml4Address)?;
-
-    // Entry covering VA [0..1GB)
-    mem.write_obj(PDE_START.raw_value() | 0x03, PDPTE_START)
-        .map_err(Error::WritePdpteAddress)?;
-
-    // 512 2MB entries together covering VA [0..1GB). Note we are assuming
-    // CPU supports 2MB pages (/proc/cpuinfo has 'pse'). All modern CPUs do.
-    for i in 0..512 {
-        mem.write_obj((i << 21) + 0x83u64, PDE_START.unchecked_add(i * 8))
-            .map_err(Error::WritePdeAddress)?;
-    }
-
-    sregs.cr4 |= CR4_PAE;
-    sregs.cr0 |= CR0_PG;
+    sregs.cr0 = CR0_PE;
+    sregs.cr4 = 0;
 
     Ok(())
 }
 
 #[cfg(test)]
 mod tests {
-    extern crate vm_memory;
-
     use super::*;
-    use vm_memory::{GuestAddress, GuestMemoryMmap};
+    use crate::GuestMemoryMmap;
+    use vm_memory::GuestAddress;
 
     fn create_guest_mem() -> GuestMemoryMmap {
         GuestMemoryMmap::from_ranges(&[(GuestAddress(0), 0x10000)]).unwrap()
@@ -268,36 +179,7 @@ mod tests {
     fn segments_and_sregs() {
         let mut sregs: SpecialRegisters = Default::default();
         let gm = create_guest_mem();
-        configure_segments_and_sregs(&gm, &mut sregs, BootProtocol::LinuxBoot).unwrap();
-
-        assert_eq!(0x0, read_u64(&gm, BOOT_GDT_START));
-        assert_eq!(
-            0xaf9b000000ffff,
-            read_u64(&gm, BOOT_GDT_START.unchecked_add(8))
-        );
-        assert_eq!(
-            0xcf93000000ffff,
-            read_u64(&gm, BOOT_GDT_START.unchecked_add(16))
-        );
-        assert_eq!(
-            0x8f8b000000ffff,
-            read_u64(&gm, BOOT_GDT_START.unchecked_add(24))
-        );
-        assert_eq!(0x0, read_u64(&gm, BOOT_IDT_START));
-
-        assert_eq!(0, sregs.cs.base);
-        assert_eq!(0xffffffff, sregs.ds.limit);
-        assert_eq!(0x10, sregs.es.selector);
-        assert_eq!(1, sregs.fs.present);
-        assert_eq!(1, sregs.gs.g);
-        assert_eq!(0, sregs.ss.avl);
-        assert_eq!(0, sregs.tr.base);
-        assert_eq!(0xffffffff, sregs.tr.limit);
-        assert_eq!(0, sregs.tr.avl);
-        assert_eq!(CR0_PE, sregs.cr0);
-        assert_eq!(EFER_LME | EFER_LMA, sregs.efer);
-
-        configure_segments_and_sregs(&gm, &mut sregs, BootProtocol::PvhBoot).unwrap();
+        configure_segments_and_sregs(&gm, &mut sregs).unwrap();
         assert_eq!(0x0, read_u64(&gm, BOOT_GDT_START));
         assert_eq!(
             0xcf9b000000ffff,
@@ -327,31 +209,4 @@ mod tests {
         assert_eq!(CR0_PE, sregs.cr0);
         assert_eq!(0, sregs.cr4);
     }
-
-    #[test]
-    fn page_tables() {
-        let mut sregs: SpecialRegisters = Default::default();
-        let gm = create_guest_mem();
-        setup_page_tables(&gm, &mut sregs).unwrap();
-
-        if unsafe { std::arch::x86_64::__cpuid(7).ecx } & (1 << 16) != 0 {
-            assert_eq!(0xa003, read_u64(&gm, PML5_START));
-        }
-        assert_eq!(0xb003, read_u64(&gm, PML4_START));
-        assert_eq!(0xc003, read_u64(&gm, PDPTE_START));
-        for i in 0..512 {
-            assert_eq!(
-                (i << 21) + 0x83u64,
-                read_u64(&gm, PDE_START.unchecked_add(i * 8))
-            );
-        }
-
-        if unsafe { std::arch::x86_64::__cpuid(7).ecx } & (1 << 16) != 0 {
-            assert_eq!(PML5_START.raw_value(), sregs.cr3);
-        } else {
-            assert_eq!(PML4_START.raw_value(), sregs.cr3);
-        }
-        assert_eq!(CR4_PAE, sregs.cr4);
-        assert_eq!(CR0_PG, sregs.cr0);
-    }
 }

arch/src/x86_64/smbios.rs

@@ -6,13 +6,14 @@
 //
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
-use layout::SMBIOS_START;
+use crate::layout::SMBIOS_START;
+use crate::GuestMemoryMmap;
 use std::fmt::{self, Display};
 use std::mem;
 use std::result;
 use std::slice;
 use vm_memory::ByteValued;
-use vm_memory::{Address, Bytes, GuestAddress, GuestMemoryMmap};
+use vm_memory::{Address, Bytes, GuestAddress};
 
 #[allow(unused_variables)]
 #[derive(Debug)]

arch/src/x86_64/tdx/mod.rs

@@ -1,10 +1,11 @@
 // Copyright © 2021 Intel Corporation
 //
 // SPDX-License-Identifier: Apache-2.0
+use crate::GuestMemoryMmap;
 use std::fs::File;
 use std::io::{Read, Seek, SeekFrom};
 use thiserror::Error;
-use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemoryError, GuestMemoryMmap};
+use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemoryError};
 
 #[derive(Error, Debug)]
 pub enum TdvfError {

arch_gen/Cargo.lock

@@ -1,6 +0,0 @@
-# This file is automatically @generated by Cargo.
-# It is not intended for manual editing.
-[[package]]
-name = "arch_gen"
-version = "0.1.0"
-

arch_gen/Cargo.toml

@@ -1,7 +0,0 @@
-[package]
-name = "arch_gen"
-version = "0.1.0"
-authors = ["Amazon firecracker team <firecracker-devel@amazon.com>"]
-
-[dependencies]
-

arch_gen/src/lib.rs

@@ -1,5 +0,0 @@
-// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-// SPDX-License-Identifier: Apache-2.0
-
-#[cfg(any(target_arch = "x86", target_arch = "x86_64"))]
-pub mod x86;

arch_gen/src/x86/mod.rs

@@ -1,14 +0,0 @@
-// Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
-// SPDX-License-Identifier: Apache-2.0
-//
-// Portions Copyright 2017 The Chromium OS Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE-BSD-3-Clause file.
-
-#[allow(non_upper_case_globals)]
-#[allow(non_camel_case_types)]
-#[allow(non_snake_case)]
-#[allow(non_camel_case_types)]
-#[allow(non_upper_case_globals)]
-#[allow(clippy::unreadable_literal, clippy::redundant_static_lifetimes)]
-pub mod mpspec;

arch_gen/src/x86/mpspec.rs

@@ -1,832 +0,0 @@
-// Copyright 2017 The Chromium OS Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE-BSD-3-Clause file.
-
-/* automatically generated by rust-bindgen */
-
-pub const MPC_SIGNATURE: &'static [u8; 5usize] = b"PCMP\x00";
-pub const MP_PROCESSOR: ::std::os::raw::c_uint = 0;
-pub const MP_BUS: ::std::os::raw::c_uint = 1;
-pub const MP_IOAPIC: ::std::os::raw::c_uint = 2;
-pub const MP_INTSRC: ::std::os::raw::c_uint = 3;
-pub const MP_LINTSRC: ::std::os::raw::c_uint = 4;
-pub const MP_TRANSLATION: ::std::os::raw::c_uint = 192;
-pub const CPU_ENABLED: ::std::os::raw::c_uint = 1;
-pub const CPU_BOOTPROCESSOR: ::std::os::raw::c_uint = 2;
-pub const CPU_STEPPING_MASK: ::std::os::raw::c_uint = 15;
-pub const CPU_MODEL_MASK: ::std::os::raw::c_uint = 240;
-pub const CPU_FAMILY_MASK: ::std::os::raw::c_uint = 3840;
-pub const BUSTYPE_EISA: &'static [u8; 5usize] = b"EISA\x00";
-pub const BUSTYPE_ISA: &'static [u8; 4usize] = b"ISA\x00";
-pub const BUSTYPE_INTERN: &'static [u8; 7usize] = b"INTERN\x00";
-pub const BUSTYPE_MCA: &'static [u8; 4usize] = b"MCA\x00";
-pub const BUSTYPE_VL: &'static [u8; 3usize] = b"VL\x00";
-pub const BUSTYPE_PCI: &'static [u8; 4usize] = b"PCI\x00";
-pub const BUSTYPE_PCMCIA: &'static [u8; 7usize] = b"PCMCIA\x00";
-pub const BUSTYPE_CBUS: &'static [u8; 5usize] = b"CBUS\x00";
-pub const BUSTYPE_CBUSII: &'static [u8; 7usize] = b"CBUSII\x00";
-pub const BUSTYPE_FUTURE: &'static [u8; 7usize] = b"FUTURE\x00";
-pub const BUSTYPE_MBI: &'static [u8; 4usize] = b"MBI\x00";
-pub const BUSTYPE_MBII: &'static [u8; 5usize] = b"MBII\x00";
-pub const BUSTYPE_MPI: &'static [u8; 4usize] = b"MPI\x00";
-pub const BUSTYPE_MPSA: &'static [u8; 5usize] = b"MPSA\x00";
-pub const BUSTYPE_NUBUS: &'static [u8; 6usize] = b"NUBUS\x00";
-pub const BUSTYPE_TC: &'static [u8; 3usize] = b"TC\x00";
-pub const BUSTYPE_VME: &'static [u8; 4usize] = b"VME\x00";
-pub const BUSTYPE_XPRESS: &'static [u8; 7usize] = b"XPRESS\x00";
-pub const MPC_APIC_USABLE: ::std::os::raw::c_uint = 1;
-pub const MP_IRQDIR_DEFAULT: ::std::os::raw::c_uint = 0;
-pub const MP_IRQDIR_HIGH: ::std::os::raw::c_uint = 1;
-pub const MP_IRQDIR_LOW: ::std::os::raw::c_uint = 3;
-pub const MP_APIC_ALL: ::std::os::raw::c_uint = 255;
-pub const MPC_OEM_SIGNATURE: &'static [u8; 5usize] = b"_OEM\x00";
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpf_intel {
-    pub signature: [::std::os::raw::c_char; 4usize],
-    pub physptr: ::std::os::raw::c_uint,
-    pub length: ::std::os::raw::c_uchar,
-    pub specification: ::std::os::raw::c_uchar,
-    pub checksum: ::std::os::raw::c_uchar,
-    pub feature1: ::std::os::raw::c_uchar,
-    pub feature2: ::std::os::raw::c_uchar,
-    pub feature3: ::std::os::raw::c_uchar,
-    pub feature4: ::std::os::raw::c_uchar,
-    pub feature5: ::std::os::raw::c_uchar,
-}
-#[test]
-fn bindgen_test_layout_mpf_intel() {
-    assert_eq!(
-        ::std::mem::size_of::<mpf_intel>(),
-        16usize,
-        concat!("Size of: ", stringify!(mpf_intel))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpf_intel>(),
-        4usize,
-        concat!("Alignment of ", stringify!(mpf_intel))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).signature as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(signature)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).physptr as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(physptr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).length as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(length)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).specification as *const _ as usize },
-        9usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(specification)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).checksum as *const _ as usize },
-        10usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(checksum)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).feature1 as *const _ as usize },
-        11usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(feature1)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).feature2 as *const _ as usize },
-        12usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(feature2)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).feature3 as *const _ as usize },
-        13usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(feature3)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).feature4 as *const _ as usize },
-        14usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(feature4)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpf_intel>()).feature5 as *const _ as usize },
-        15usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpf_intel),
-            "::",
-            stringify!(feature5)
-        )
-    );
-}
-impl Clone for mpf_intel {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_table {
-    pub signature: [::std::os::raw::c_char; 4usize],
-    pub length: ::std::os::raw::c_ushort,
-    pub spec: ::std::os::raw::c_char,
-    pub checksum: ::std::os::raw::c_char,
-    pub oem: [::std::os::raw::c_char; 8usize],
-    pub productid: [::std::os::raw::c_char; 12usize],
-    pub oemptr: ::std::os::raw::c_uint,
-    pub oemsize: ::std::os::raw::c_ushort,
-    pub oemcount: ::std::os::raw::c_ushort,
-    pub lapic: ::std::os::raw::c_uint,
-    pub reserved: ::std::os::raw::c_uint,
-}
-#[test]
-fn bindgen_test_layout_mpc_table() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_table>(),
-        44usize,
-        concat!("Size of: ", stringify!(mpc_table))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_table>(),
-        4usize,
-        concat!("Alignment of ", stringify!(mpc_table))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).signature as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(signature)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).length as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(length)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).spec as *const _ as usize },
-        6usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(spec)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).checksum as *const _ as usize },
-        7usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(checksum)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).oem as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(oem)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).productid as *const _ as usize },
-        16usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(productid)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).oemptr as *const _ as usize },
-        28usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(oemptr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).oemsize as *const _ as usize },
-        32usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(oemsize)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).oemcount as *const _ as usize },
-        34usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(oemcount)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).lapic as *const _ as usize },
-        36usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(lapic)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_table>()).reserved as *const _ as usize },
-        40usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_table),
-            "::",
-            stringify!(reserved)
-        )
-    );
-}
-impl Clone for mpc_table {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_cpu {
-    pub type_: ::std::os::raw::c_uchar,
-    pub apicid: ::std::os::raw::c_uchar,
-    pub apicver: ::std::os::raw::c_uchar,
-    pub cpuflag: ::std::os::raw::c_uchar,
-    pub cpufeature: ::std::os::raw::c_uint,
-    pub featureflag: ::std::os::raw::c_uint,
-    pub reserved: [::std::os::raw::c_uint; 2usize],
-}
-#[test]
-fn bindgen_test_layout_mpc_cpu() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_cpu>(),
-        20usize,
-        concat!("Size of: ", stringify!(mpc_cpu))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_cpu>(),
-        4usize,
-        concat!("Alignment of ", stringify!(mpc_cpu))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).type_ as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(type_)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).apicid as *const _ as usize },
-        1usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(apicid)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).apicver as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(apicver)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).cpuflag as *const _ as usize },
-        3usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(cpuflag)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).cpufeature as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(cpufeature)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).featureflag as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(featureflag)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_cpu>()).reserved as *const _ as usize },
-        12usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_cpu),
-            "::",
-            stringify!(reserved)
-        )
-    );
-}
-impl Clone for mpc_cpu {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_bus {
-    pub type_: ::std::os::raw::c_uchar,
-    pub busid: ::std::os::raw::c_uchar,
-    pub bustype: [::std::os::raw::c_uchar; 6usize],
-}
-#[test]
-fn bindgen_test_layout_mpc_bus() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_bus>(),
-        8usize,
-        concat!("Size of: ", stringify!(mpc_bus))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_bus>(),
-        1usize,
-        concat!("Alignment of ", stringify!(mpc_bus))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_bus>()).type_ as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_bus),
-            "::",
-            stringify!(type_)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_bus>()).busid as *const _ as usize },
-        1usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_bus),
-            "::",
-            stringify!(busid)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_bus>()).bustype as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_bus),
-            "::",
-            stringify!(bustype)
-        )
-    );
-}
-impl Clone for mpc_bus {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_ioapic {
-    pub type_: ::std::os::raw::c_uchar,
-    pub apicid: ::std::os::raw::c_uchar,
-    pub apicver: ::std::os::raw::c_uchar,
-    pub flags: ::std::os::raw::c_uchar,
-    pub apicaddr: ::std::os::raw::c_uint,
-}
-#[test]
-fn bindgen_test_layout_mpc_ioapic() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_ioapic>(),
-        8usize,
-        concat!("Size of: ", stringify!(mpc_ioapic))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_ioapic>(),
-        4usize,
-        concat!("Alignment of ", stringify!(mpc_ioapic))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_ioapic>()).type_ as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_ioapic),
-            "::",
-            stringify!(type_)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_ioapic>()).apicid as *const _ as usize },
-        1usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_ioapic),
-            "::",
-            stringify!(apicid)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_ioapic>()).apicver as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_ioapic),
-            "::",
-            stringify!(apicver)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_ioapic>()).flags as *const _ as usize },
-        3usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_ioapic),
-            "::",
-            stringify!(flags)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_ioapic>()).apicaddr as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_ioapic),
-            "::",
-            stringify!(apicaddr)
-        )
-    );
-}
-impl Clone for mpc_ioapic {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_intsrc {
-    pub type_: ::std::os::raw::c_uchar,
-    pub irqtype: ::std::os::raw::c_uchar,
-    pub irqflag: ::std::os::raw::c_ushort,
-    pub srcbus: ::std::os::raw::c_uchar,
-    pub srcbusirq: ::std::os::raw::c_uchar,
-    pub dstapic: ::std::os::raw::c_uchar,
-    pub dstirq: ::std::os::raw::c_uchar,
-}
-#[test]
-fn bindgen_test_layout_mpc_intsrc() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_intsrc>(),
-        8usize,
-        concat!("Size of: ", stringify!(mpc_intsrc))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_intsrc>(),
-        2usize,
-        concat!("Alignment of ", stringify!(mpc_intsrc))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).type_ as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(type_)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).irqtype as *const _ as usize },
-        1usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(irqtype)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).irqflag as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(irqflag)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).srcbus as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(srcbus)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).srcbusirq as *const _ as usize },
-        5usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(srcbusirq)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).dstapic as *const _ as usize },
-        6usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(dstapic)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_intsrc>()).dstirq as *const _ as usize },
-        7usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_intsrc),
-            "::",
-            stringify!(dstirq)
-        )
-    );
-}
-impl Clone for mpc_intsrc {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-pub const mp_irq_source_types_mp_INT: mp_irq_source_types = 0;
-pub const mp_irq_source_types_mp_NMI: mp_irq_source_types = 1;
-pub const mp_irq_source_types_mp_SMI: mp_irq_source_types = 2;
-pub const mp_irq_source_types_mp_ExtINT: mp_irq_source_types = 3;
-pub type mp_irq_source_types = ::std::os::raw::c_uint;
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_lintsrc {
-    pub type_: ::std::os::raw::c_uchar,
-    pub irqtype: ::std::os::raw::c_uchar,
-    pub irqflag: ::std::os::raw::c_ushort,
-    pub srcbusid: ::std::os::raw::c_uchar,
-    pub srcbusirq: ::std::os::raw::c_uchar,
-    pub destapic: ::std::os::raw::c_uchar,
-    pub destapiclint: ::std::os::raw::c_uchar,
-}
-#[test]
-fn bindgen_test_layout_mpc_lintsrc() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_lintsrc>(),
-        8usize,
-        concat!("Size of: ", stringify!(mpc_lintsrc))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_lintsrc>(),
-        2usize,
-        concat!("Alignment of ", stringify!(mpc_lintsrc))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).type_ as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(type_)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).irqtype as *const _ as usize },
-        1usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(irqtype)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).irqflag as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(irqflag)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).srcbusid as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(srcbusid)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).srcbusirq as *const _ as usize },
-        5usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(srcbusirq)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).destapic as *const _ as usize },
-        6usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(destapic)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_lintsrc>()).destapiclint as *const _ as usize },
-        7usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_lintsrc),
-            "::",
-            stringify!(destapiclint)
-        )
-    );
-}
-impl Clone for mpc_lintsrc {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-#[repr(C)]
-#[derive(Debug, Default, Copy)]
-pub struct mpc_oemtable {
-    pub signature: [::std::os::raw::c_char; 4usize],
-    pub length: ::std::os::raw::c_ushort,
-    pub rev: ::std::os::raw::c_char,
-    pub checksum: ::std::os::raw::c_char,
-    pub mpc: [::std::os::raw::c_char; 8usize],
-}
-#[test]
-fn bindgen_test_layout_mpc_oemtable() {
-    assert_eq!(
-        ::std::mem::size_of::<mpc_oemtable>(),
-        16usize,
-        concat!("Size of: ", stringify!(mpc_oemtable))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<mpc_oemtable>(),
-        2usize,
-        concat!("Alignment of ", stringify!(mpc_oemtable))
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_oemtable>()).signature as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_oemtable),
-            "::",
-            stringify!(signature)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_oemtable>()).length as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_oemtable),
-            "::",
-            stringify!(length)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_oemtable>()).rev as *const _ as usize },
-        6usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_oemtable),
-            "::",
-            stringify!(rev)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_oemtable>()).checksum as *const _ as usize },
-        7usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_oemtable),
-            "::",
-            stringify!(checksum)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*std::ptr::null::<mpc_oemtable>()).mpc as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(mpc_oemtable),
-            "::",
-            stringify!(mpc)
-        )
-    );
-}
-impl Clone for mpc_oemtable {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-pub const mp_bustype_MP_BUS_ISA: mp_bustype = 1;
-pub const mp_bustype_MP_BUS_EISA: mp_bustype = 2;
-pub const mp_bustype_MP_BUS_PCI: mp_bustype = 3;
-pub type mp_bustype = ::std::os::raw::c_uint;

block_util/Cargo.toml

@@ -10,15 +10,14 @@ io_uring = []
 
 [dependencies]
 io-uring = ">=0.4.0"
-libc = "0.2.91"
+libc = "0.2.96"
 log = "0.4.14"
 qcow = { path = "../qcow" }
-serde = ">=1.0.27"
-serde_derive = ">=1.0.27"
-serde_json = ">=1.0.9"
 thiserror = "1.0"
+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"] }
+vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-virtio = { path = "../vm-virtio" }
 vmm-sys-util = ">=0.3.1"
 

block_util/src/lib.rs

@@ -10,8 +10,6 @@
 
 #[macro_use]
 extern crate log;
-#[macro_use]
-extern crate serde_derive;
 
 pub mod async_io;
 pub mod fixed_vhd_async;
@@ -24,7 +22,6 @@ pub mod vhd;
 use crate::async_io::{AsyncIo, AsyncIoError, AsyncIoResult, DiskFileError, DiskFileResult};
 #[cfg(feature = "io_uring")]
 use io_uring::{opcode, IoUring, Probe};
-use serde::ser::{Serialize, SerializeStruct, Serializer};
 use std::cmp;
 use std::convert::TryInto;
 use std::fs::File;
@@ -35,11 +32,18 @@ use std::os::unix::io::AsRawFd;
 use std::path::Path;
 use std::result;
 use std::sync::{Arc, Mutex};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use virtio_bindings::bindings::virtio_blk::*;
-use vm_memory::{ByteValued, Bytes, GuestAddress, GuestMemory, GuestMemoryError, GuestMemoryMmap};
+use vm_memory::{
+    bitmap::AtomicBitmap, bitmap::Bitmap, ByteValued, Bytes, GuestAddress, GuestMemory,
+    GuestMemoryError,
+};
 use vm_virtio::DescriptorChain;
 use vmm_sys_util::eventfd::EventFd;
 
+type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
+
 const SECTOR_SHIFT: u8 = 9;
 pub const SECTOR_SIZE: u64 = 0x01 << SECTOR_SHIFT;
 
@@ -332,6 +336,12 @@ impl Request {
         // Queue operations expected to be submitted.
         match request_type {
             RequestType::In => {
+                for (data_addr, data_len) in &self.data_descriptors {
+                    mem.get_slice(*data_addr, *data_len as usize)
+                        .map_err(ExecuteError::GetHostAddress)?
+                        .bitmap()
+                        .mark_dirty(0, *data_len as usize);
+                }
                 disk_image
                     .read_vectored(offset, iovecs, user_data)
                     .map_err(ExecuteError::AsyncRead)?;
@@ -370,7 +380,7 @@ impl Request {
     }
 }
 
-#[derive(Copy, Clone, Debug, Default, Deserialize)]
+#[derive(Copy, Clone, Debug, Default, Versionize)]
 #[repr(C, packed)]
 pub struct VirtioBlockConfig {
     pub capacity: u64,
@@ -393,95 +403,15 @@ pub struct VirtioBlockConfig {
     pub write_zeroes_may_unmap: u8,
     pub unused1: [u8; 3],
 }
-
-// We must explicitly implement Serialize since the structure is packed and
-// it's unsafe to borrow from a packed structure. And by default, if we derive
-// Serialize from serde, it will borrow the values from the structure.
-// That's why this implementation copies each field separately before it
-// serializes the entire structure field by field.
-impl Serialize for VirtioBlockConfig {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: Serializer,
-    {
-        let capacity = self.capacity;
-        let size_max = self.size_max;
-        let seg_max = self.seg_max;
-        let geometry = self.geometry;
-        let blk_size = self.blk_size;
-        let physical_block_exp = self.physical_block_exp;
-        let alignment_offset = self.alignment_offset;
-        let min_io_size = self.min_io_size;
-        let opt_io_size = self.opt_io_size;
-        let writeback = self.writeback;
-        let unused = self.unused;
-        let num_queues = self.num_queues;
-        let max_discard_sectors = self.max_discard_sectors;
-        let max_discard_seg = self.max_discard_seg;
-        let discard_sector_alignment = self.discard_sector_alignment;
-        let max_write_zeroes_sectors = self.max_write_zeroes_sectors;
-        let max_write_zeroes_seg = self.max_write_zeroes_seg;
-        let write_zeroes_may_unmap = self.write_zeroes_may_unmap;
-        let unused1 = self.unused1;
-
-        let mut virtio_block_config = serializer.serialize_struct("VirtioBlockConfig", 60)?;
-        virtio_block_config.serialize_field("capacity", &capacity)?;
-        virtio_block_config.serialize_field("size_max", &size_max)?;
-        virtio_block_config.serialize_field("seg_max", &seg_max)?;
-        virtio_block_config.serialize_field("geometry", &geometry)?;
-        virtio_block_config.serialize_field("blk_size", &blk_size)?;
-        virtio_block_config.serialize_field("physical_block_exp", &physical_block_exp)?;
-        virtio_block_config.serialize_field("alignment_offset", &alignment_offset)?;
-        virtio_block_config.serialize_field("min_io_size", &min_io_size)?;
-        virtio_block_config.serialize_field("opt_io_size", &opt_io_size)?;
-        virtio_block_config.serialize_field("writeback", &writeback)?;
-        virtio_block_config.serialize_field("unused", &unused)?;
-        virtio_block_config.serialize_field("num_queues", &num_queues)?;
-        virtio_block_config.serialize_field("max_discard_sectors", &max_discard_sectors)?;
-        virtio_block_config.serialize_field("max_discard_seg", &max_discard_seg)?;
-        virtio_block_config
-            .serialize_field("discard_sector_alignment", &discard_sector_alignment)?;
-        virtio_block_config
-            .serialize_field("max_write_zeroes_sectors", &max_write_zeroes_sectors)?;
-        virtio_block_config.serialize_field("max_write_zeroes_seg", &max_write_zeroes_seg)?;
-        virtio_block_config.serialize_field("write_zeroes_may_unmap", &write_zeroes_may_unmap)?;
-        virtio_block_config.serialize_field("unused1", &unused1)?;
-        virtio_block_config.end()
-    }
-}
-
 unsafe impl ByteValued for VirtioBlockConfig {}
 
-#[derive(Copy, Clone, Debug, Default, Deserialize)]
+#[derive(Copy, Clone, Debug, Default, Versionize)]
 #[repr(C, packed)]
 pub struct VirtioBlockGeometry {
     pub cylinders: u16,
     pub heads: u8,
     pub sectors: u8,
 }
-
-// We must explicitly implement Serialize since the structure is packed and
-// it's unsafe to borrow from a packed structure. And by default, if we derive
-// Serialize from serde, it will borrow the values from the structure.
-// That's why this implementation copies each field separately before it
-// serializes the entire structure field by field.
-impl Serialize for VirtioBlockGeometry {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: Serializer,
-    {
-        let cylinders = self.cylinders;
-        let heads = self.heads;
-        let sectors = self.sectors;
-
-        let mut virtio_block_geometry = serializer.serialize_struct("VirtioBlockGeometry", 4)?;
-        virtio_block_geometry.serialize_field("cylinders", &cylinders)?;
-        virtio_block_geometry.serialize_field("heads", &heads)?;
-        virtio_block_geometry.serialize_field("sectors", &sectors)?;
-        virtio_block_geometry.end()
-    }
-}
-
 unsafe impl ByteValued for VirtioBlockGeometry {}
 
 /// Check if io_uring for block device can be used on the current system, as

devices/Cargo.toml

@@ -2,19 +2,20 @@
 name = "devices"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
+edition = "2018"
 
 [dependencies]
+acpi_tables = { path = "../acpi_tables", optional = true }
 anyhow = "1.0"
+arch = { path = "../arch" }
 bitflags = ">=1.2.1"
 byteorder = "1.4.3"
 epoll = ">=4.0.1"
-libc = "0.2.91"
+libc = "0.2.96"
 log = "0.4.14"
-serde = {version = ">=1.0.27", features = ["rc"] }
-serde_derive = ">=1.0.27"
-serde_json = ">=1.0.9"
+versionize = "0.1.6"
+versionize_derive = "0.1.4"
 vm-device = { path = "../vm-device" }
-acpi_tables = { path = "../acpi_tables", optional = true }
 vm-memory = "0.5.0"
 vm-migration = { path = "../vm-migration" }
 vmm-sys-util = ">=0.3.1"

devices/src/acpi.rs

@@ -3,6 +3,7 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
+use super::AcpiNotificationFlags;
 use acpi_tables::{aml, aml::Aml};
 use std::sync::{Arc, Barrier};
 use std::time::Instant;
@@ -10,7 +11,6 @@ use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_memory::GuestAddress;
 use vmm_sys_util::eventfd::EventFd;
-use AcpiNotificationFlags;
 
 pub const GED_DEVICE_ACPI_SIZE: usize = 0x1;
 
@@ -52,7 +52,6 @@ impl BusDevice for AcpiShutdownDevice {
         const SLEEP_VALUE_BIT: u8 = 2;
         if data[0] == (S5_SLEEP_VALUE << SLEEP_VALUE_BIT) | (1 << SLEEP_STATUS_EN_BIT) {
             debug!("ACPI Shutdown signalled");
-            extern crate bitflags;
             if let Err(e) = self.exit_evt.write(1) {
                 error!("Error triggering ACPI shutdown event: {}", e);
             }

devices/src/gic.rs

@@ -3,8 +3,10 @@
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use super::interrupt_controller::{Error, InterruptController};
+extern crate arch;
+use arch::aarch64::gic::GicDevice;
 use std::result;
-use std::sync::Arc;
+use std::sync::{Arc, Mutex};
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     LegacyIrqSourceConfig, MsiIrqGroupConfig,
@@ -14,7 +16,7 @@ use vmm_sys_util::eventfd::EventFd;
 type Result<T> = result::Result<T, Error>;
 
 // Reserve 32 IRQs for legacy device.
-pub const IRQ_LEGACY_BASE: usize = 0;
+pub const IRQ_LEGACY_BASE: usize = arch::layout::IRQ_BASE as usize;
 pub const IRQ_LEGACY_COUNT: usize = 32;
 
 // This Gic struct implements InterruptController to provide interrupt delivery service.
@@ -25,6 +27,7 @@ pub const IRQ_LEGACY_COUNT: usize = 32;
 //   2. Move this file and ioapic.rs to arch/, as they are architecture specific.
 pub struct Gic {
     interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
+    gic_device: Option<Arc<Mutex<Box<dyn GicDevice>>>>,
 }
 
 impl Gic {
@@ -41,8 +44,17 @@ impl Gic {
 
         Ok(Gic {
             interrupt_source_group,
+            gic_device: None,
         })
     }
+
+    pub fn set_gic_device(&mut self, gic_device: Arc<Mutex<Box<dyn GicDevice>>>) {
+        self.gic_device = Some(gic_device);
+    }
+
+    pub fn get_gic_device(&self) -> Option<&Arc<Mutex<Box<dyn GicDevice>>>> {
+        self.gic_device.as_ref()
+    }
 }
 
 impl InterruptController for Gic {
@@ -58,7 +70,7 @@ impl InterruptController for Gic {
         for i in IRQ_LEGACY_BASE..(IRQ_LEGACY_BASE + IRQ_LEGACY_COUNT) {
             let config = LegacyIrqSourceConfig {
                 irqchip: 0,
-                pin: i as u32,
+                pin: (i - IRQ_LEGACY_BASE) as u32,
             };
             self.interrupt_source_group
                 .update(

devices/src/ioapic.rs

@@ -14,6 +14,8 @@ use anyhow::anyhow;
 use byteorder::{ByteOrder, LittleEndian};
 use std::result;
 use std::sync::{Arc, Barrier};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::{
     InterruptIndex, InterruptManager, InterruptSourceConfig, InterruptSourceGroup,
     MsiIrqGroupConfig, MsiIrqSourceConfig,
@@ -21,15 +23,10 @@ use vm_device::interrupt::{
 use vm_device::BusDevice;
 use vm_memory::GuestAddress;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
-    Transportable,
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
 };
 use vmm_sys_util::eventfd::EventFd;
 
-#[derive(Serialize, Deserialize)]
-#[serde(remote = "GuestAddress")]
-pub struct GuestAddressDef(pub u64);
-
 type Result<T> = result::Result<T, Error>;
 
 // I/O REDIRECTION TABLE REGISTER
@@ -140,15 +137,15 @@ pub struct Ioapic {
     interrupt_source_group: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct IoapicState {
     id_reg: u32,
     reg_sel: u32,
     reg_entries: [RedirectionTableEntry; NUM_IOAPIC_PINS],
     used_entries: [bool; NUM_IOAPIC_PINS],
-    #[serde(with = "GuestAddressDef")]
-    apic_address: GuestAddress,
+    apic_address: u64,
 }
+impl VersionMapped for IoapicState {}
 
 impl BusDevice for Ioapic {
     fn read(&mut self, _base: u64, offset: u64, data: &mut [u8]) {
@@ -284,7 +281,7 @@ impl Ioapic {
             reg_sel: self.reg_sel,
             reg_entries: self.reg_entries,
             used_entries: self.used_entries,
-            apic_address: self.apic_address,
+            apic_address: self.apic_address.0,
         }
     }
 
@@ -293,7 +290,7 @@ impl Ioapic {
         self.reg_sel = state.reg_sel;
         self.reg_entries = state.reg_entries;
         self.used_entries = state.used_entries;
-        self.apic_address = state.apic_address;
+        self.apic_address = GuestAddress(state.apic_address);
         for (irq, entry) in self.used_entries.iter().enumerate() {
             if *entry {
                 self.update_entry(irq)?;
@@ -418,38 +415,18 @@ impl Snapshottable for Ioapic {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let snapshot =
-            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-        let mut ioapic_snapshot = Snapshot::new(self.id.as_str());
-        ioapic_snapshot.add_data_section(SnapshotDataSection {
-            id: format!("{}-section", self.id),
-            snapshot,
-        });
-
-        Ok(ioapic_snapshot)
+        Snapshot::new_from_versioned_state(&self.id, &self.state())
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        if let Some(ioapic_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
-            let ioapic_state = match serde_json::from_slice(&ioapic_section.snapshot) {
-                Ok(state) => state,
-                Err(error) => {
-                    return Err(MigratableError::Restore(anyhow!(
-                        "Could not deserialize IOAPIC {}",
-                        error
-                    )))
-                }
-            };
-
-            return self.set_state(&ioapic_state).map_err(|e| {
-                MigratableError::Restore(anyhow!("Could not restore IOAPIC state {:?}", e))
-            });
-        }
-
-        Err(MigratableError::Restore(anyhow!(
-            "Could not find IOAPIC snapshot section"
-        )))
+        self.set_state(&snapshot.to_versioned_state(&self.id)?)
+            .map_err(|e| {
+                MigratableError::Restore(anyhow!(
+                    "Could not restore state for {}: {:?}",
+                    self.id,
+                    e
+                ))
+            })
     }
 }
 

devices/src/legacy/gpio_pl061.rs

@@ -8,15 +8,15 @@
 //!
 
 use crate::{read_le_u32, write_le_u32};
-use anyhow::anyhow;
 use std::result;
 use std::sync::{Arc, Barrier};
 use std::{fmt, io};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
-    Transportable,
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
 };
 
 const OFS_DATA: u64 = 0x400; // Data Register
@@ -89,7 +89,7 @@ pub struct Gpio {
     interrupt: Arc<Box<dyn InterruptSourceGroup>>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct GpioState {
     data: u32,
     old_in_data: u32,
@@ -102,6 +102,8 @@ pub struct GpioState {
     afsel: u32,
 }
 
+impl VersionMapped for GpioState {}
+
 impl Gpio {
     /// Constructs an PL061 GPIO device.
     pub fn new(id: String, interrupt: Arc<Box<dyn InterruptSourceGroup>>) -> Self {
@@ -317,38 +319,12 @@ impl Snapshottable for Gpio {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let snapshot =
-            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-        let mut gpio_snapshot = Snapshot::new(self.id.as_str());
-        gpio_snapshot.add_data_section(SnapshotDataSection {
-            id: format!("{}-section", self.id),
-            snapshot,
-        });
-
-        Ok(gpio_snapshot)
+        Snapshot::new_from_versioned_state(&self.id, &self.state())
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        if let Some(gpio_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
-            let gpio_state = match serde_json::from_slice(&gpio_section.snapshot) {
-                Ok(state) => state,
-                Err(error) => {
-                    return Err(MigratableError::Restore(anyhow!(
-                        "Could not deserialize GPIO {}",
-                        error
-                    )))
-                }
-            };
-
-            self.set_state(&gpio_state);
-
-            return Ok(());
-        }
-
-        Err(MigratableError::Restore(anyhow!(
-            "Could not find the GPIO snapshot section"
-        )))
+        self.set_state(&snapshot.to_versioned_state(&self.id)?);
+        Ok(())
     }
 }
 

devices/src/legacy/serial.rs

@@ -5,15 +5,15 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE-BSD-3-Clause file.
 
-use anyhow::anyhow;
 use std::collections::VecDeque;
 use std::sync::{Arc, Barrier};
 use std::{io, result};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
-    Transportable,
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
 };
 use vmm_sys_util::errno::Result;
 
@@ -74,7 +74,7 @@ pub struct Serial {
     out: Option<Box<dyn io::Write + Send>>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct SerialState {
     interrupt_enable: u8,
     interrupt_identification: u8,
@@ -84,8 +84,9 @@ pub struct SerialState {
     modem_status: u8,
     scratch: u8,
     baud_divisor: u16,
-    in_buffer: VecDeque<u8>,
+    in_buffer: Vec<u8>,
 }
+impl VersionMapped for SerialState {}
 
 impl Serial {
     pub fn new(
@@ -227,7 +228,7 @@ impl Serial {
             modem_status: self.modem_status,
             scratch: self.scratch,
             baud_divisor: self.baud_divisor,
-            in_buffer: self.in_buffer.clone(),
+            in_buffer: self.in_buffer.clone().into(),
         }
     }
 
@@ -240,7 +241,7 @@ impl Serial {
         self.modem_status = state.modem_status;
         self.scratch = state.scratch;
         self.baud_divisor = state.baud_divisor;
-        self.in_buffer = state.in_buffer.clone();
+        self.in_buffer = state.in_buffer.clone().into();
     }
 }
 
@@ -292,38 +293,12 @@ impl Snapshottable for Serial {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let snapshot =
-            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-        let mut serial_snapshot = Snapshot::new(self.id.as_str());
-        serial_snapshot.add_data_section(SnapshotDataSection {
-            id: format!("{}-section", self.id),
-            snapshot,
-        });
-
-        Ok(serial_snapshot)
+        Snapshot::new_from_versioned_state(&self.id, &self.state())
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        if let Some(serial_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
-            let serial_state = match serde_json::from_slice(&serial_section.snapshot) {
-                Ok(state) => state,
-                Err(error) => {
-                    return Err(MigratableError::Restore(anyhow!(
-                        "Could not deserialize SERIAL {}",
-                        error
-                    )))
-                }
-            };
-
-            self.set_state(&serial_state);
-
-            return Ok(());
-        }
-
-        Err(MigratableError::Restore(anyhow!(
-            "Could not find the serial snapshot section"
-        )))
+        self.set_state(&snapshot.to_versioned_state(&self.id)?);
+        Ok(())
     }
 }
 

devices/src/legacy/uart_pl011.rs

@@ -7,16 +7,16 @@
 //!
 
 use crate::{read_le_u32, write_le_u32};
-use anyhow::anyhow;
 use std::collections::VecDeque;
 use std::fmt;
 use std::sync::{Arc, Barrier};
 use std::{io, result};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::InterruptSourceGroup;
 use vm_device::BusDevice;
 use vm_migration::{
-    Migratable, MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable,
-    Transportable,
+    Migratable, MigratableError, Pausable, Snapshot, Snapshottable, Transportable, VersionMapped,
 };
 
 /* Registers */
@@ -90,7 +90,7 @@ pub struct Pl011 {
     out: Option<Box<dyn io::Write + Send>>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 pub struct Pl011State {
     flags: u32,
     lcr: u32,
@@ -99,7 +99,7 @@ pub struct Pl011State {
     dmacr: u32,
     int_enabled: u32,
     int_level: u32,
-    read_fifo: VecDeque<u8>,
+    read_fifo: Vec<u8>,
     ilpr: u32,
     ibrd: u32,
     fbrd: u32,
@@ -108,6 +108,8 @@ pub struct Pl011State {
     read_trigger: u32,
 }
 
+impl VersionMapped for Pl011State {}
+
 impl Pl011 {
     /// Constructs an AMBA PL011 UART device.
     pub fn new(
@@ -145,7 +147,7 @@ impl Pl011 {
             dmacr: self.dmacr,
             int_enabled: self.int_enabled,
             int_level: self.int_level,
-            read_fifo: self.read_fifo.clone(),
+            read_fifo: self.read_fifo.clone().into(),
             ilpr: self.ilpr,
             ibrd: self.ibrd,
             fbrd: self.fbrd,
@@ -163,7 +165,7 @@ impl Pl011 {
         self.dmacr = state.dmacr;
         self.int_enabled = state.int_enabled;
         self.int_level = state.int_level;
-        self.read_fifo = state.read_fifo.clone();
+        self.read_fifo = state.read_fifo.clone().into();
         self.ilpr = state.ilpr;
         self.ibrd = state.ibrd;
         self.fbrd = state.fbrd;
@@ -361,38 +363,12 @@ impl Snapshottable for Pl011 {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let snapshot =
-            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-        let mut pl011_snapshot = Snapshot::new(self.id.as_str());
-        pl011_snapshot.add_data_section(SnapshotDataSection {
-            id: format!("{}-section", self.id),
-            snapshot,
-        });
-
-        Ok(pl011_snapshot)
+        Snapshot::new_from_versioned_state(&self.id, &self.state())
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        if let Some(pl011_section) = snapshot.snapshot_data.get(&format!("{}-section", self.id)) {
-            let pl011_state = match serde_json::from_slice(&pl011_section.snapshot) {
-                Ok(state) => state,
-                Err(error) => {
-                    return Err(MigratableError::Restore(anyhow!(
-                        "Could not deserialize PL011 {}",
-                        error
-                    )))
-                }
-            };
-
-            self.set_state(&pl011_state);
-
-            return Ok(());
-        }
-
-        Err(MigratableError::Restore(anyhow!(
-            "Could not find the PL011 snapshot section"
-        )))
+        self.set_state(&snapshot.to_versioned_state(&self.id)?);
+        Ok(())
     }
 }
 

devices/src/lib.rs

@@ -6,24 +6,11 @@
 // found in the LICENSE-BSD-3-Clause file.
 
 //! Emulates virtual and hardware devices.
-extern crate anyhow;
+
 #[macro_use]
 extern crate bitflags;
-extern crate byteorder;
-extern crate epoll;
-extern crate libc;
 #[macro_use]
 extern crate log;
-#[cfg(feature = "acpi")]
-extern crate acpi_tables;
-extern crate serde;
-extern crate vm_device;
-extern crate vm_memory;
-extern crate vm_migration;
-extern crate vmm_sys_util;
-#[macro_use]
-extern crate serde_derive;
-extern crate serde_json;
 
 #[cfg(feature = "acpi")]
 pub mod acpi;

docs/custom-image.md

@@ -78,7 +78,7 @@ Ubuntu distributions.
 
 ```bash
 apt update
-apt install fio iperf iperf3 socat
+apt install fio iperf iperf3 socat stress
 ```
 
 ### Remove counterproductive packages

docs/device_model.md

@@ -113,9 +113,8 @@ selecting `--serial tty --console off` from the command line.
 ### virtio-iommu
 
 As we want to improve our nested guests support, we added support for exposing
-a [paravirtualized IOMMU](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/iommu.md)
-device through virtio. This allows for a safer nested virtio and directly
-assigned devices support.
+a [paravirtualized IOMMU](iommu.md) device through virtio. This allows for a
+safer nested virtio and directly assigned devices support.
 
 This device is always built-in, and it is enabled based on the presence of the
 parameter `iommu=on` in any of the virtio or VFIO devices. If at least one of
@@ -184,8 +183,8 @@ This device is always built-in, and it is enabled when `vhost_user=true` and
 shared file system, allowing for an efficient and reliable way of sharing
 a filesystem between the host and the cloud-hypervisor guest.
 
-See our [filesystem sharing](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/fs.md)
-documentation for more details on how to use virtio-fs with cloud-hypervisor.
+See our [filesystem sharing](fs.md) documentation for more details on how to
+use virtio-fs with cloud-hypervisor.
 
 This device is always built-in, and it is enabled based on the presence of the
 flag `--fs`.
@@ -206,9 +205,8 @@ VFIO (Virtual Function I/O) is a kernel framework that exposes direct device
 access to userspace. `cloud-hypervisor` uses VFIO to directly assign host
 physical devices into its guest.
 
-See our [VFIO documentation](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/vfio.md)
-for more details on how to directly assign host devices to `cloud-hypervisor`
-guests.
+See our [VFIO documentation](vfio.md) for more details on how to directly
+assign host devices to `cloud-hypervisor` guests.
 
 Because VFIO implies `vfio-pci` in the `cloud-hypervisor` context, the VFIO
 support is built-in when the `pci` feature is selected. And because the `pci`

docs/fs.md

@@ -12,7 +12,7 @@ This virtual device relies on the _vhost-user_ protocol, which assumes the backe
 
 _Build virtiofsd_
 ```bash
-git clone --depth 1 "https://github.com/sboeuf/qemu.git" -b "virtio-fs" $VIRTIOFSD_DIR
+git clone --depth 1 "https://gitlab.com/virtio-fs/qemu.git" -b "qemu5.0-virtiofs-dax" $VIRTIOFSD_DIR
 cd $VIRTIOFSD_DIR
 ./configure --prefix=$PWD --target-list=x86_64-softmmu
 make virtiofsd -j `nproc`
@@ -35,45 +35,42 @@ The `cache=none` option should be the default when using `virtiofsd` with the __
 
 The `cache=always` option will allow for the guest page cache to be used, which will increase the memory footprint of the guest. This option should be used only for specific use cases where a single VM is going to be running on a host.
 
-### The kernel
+### Kernel support
 
-In order to leverage __virtio-fs__ support from within the guest, and because the code has not been merged in upstream Linux kernel yet, it is required to build a custom kernel embedding the patches.
-
-The following branch `virtio-fs-virtio-iommu` on the repository https://github.com/cloud-hypervisor/linux.git includes all the needed patches to support __virtio-fs__.
-
-Make sure to build a kernel out of this branch that can be then used to boot the VM.
+Modern Linux kernels starting (at least v5.10) have support for virtio-fs. Use
+of older kernels, with additional patches, are not supported.
 
 ## How to share directories with cloud-hypervisor
 
 ### Start the VM
 Once the daemon is running, the option `--fs` from __cloud-hypervisor__ needs to be used.
 
-Direct kernel boot option is preferred since we need to provide the custom kernel including the __virtio-fs__ patches. We could boot from `hypervisor-fw` if we had previously edited the image to replace the kernel binary.
+Direct kernel boot is the preferred option, but we can boot from an EFI cloud image if it contains a recent enough kernel.
 
-Because _vhost-user_ expects a dedicated process (__virtiofsd__ in this case) to be able to access the guest RAM to communicate through the _virtqueues_ with the driver running in the guest, `--memory` option needs to be slightly modified. It needs to specify a backing file for the memory so that an external process can access it.
+Because _vhost-user_ expects a dedicated process (__virtiofsd__ in this case) to be able to access the guest RAM to communicate through the _virtqueues_ with the driver running in the guest, `--memory` option needs to be slightly modified. It must specify `shared=on` to share the memory pages so that an external process can access them.
 
-Assuming you have `focal-server-cloudimg-amd64.raw` and `custom-vmlinux.bin` on your system, here is the __cloud-hypervisor__ command you need to run:
+Assuming you have `focal-server-cloudimg-amd64.raw` and `vmlinux` on your system, here is the __cloud-hypervisor__ command you need to run:
 ```bash
 ./cloud-hypervisor \
-    --cpus 4 \
-    --memory "size=512M,shared=on" \
+    --cpus boot=1 \
+    --memory size=1G,shared=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-vmlinux.bin \
-    --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
+    --kernel vmlinux \
+    --cmdline "console=hvc0 root=/dev/vda1 rw" \
     --fs tag=myfs,socket=/tmp/virtiofs,num_queues=1,queue_size=512
 ```
 
 By default, DAX is enabled with a cache window of 8GiB. You can specify a custom size (let's say 4GiB for this example) for the cache by explicitly setting DAX and the cache size:
 
 ```bash
---fs tag=virtiofs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=on,cache_size=4G
+--fs tag=myfs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=on,cache_size=4G
 
 ```
 
 In case you don't want to use a shared window of cache to pass the shared files content, this means you will have to explicitly disable DAX with `dax=off`. Note that in this case, the `cache_size` parameter will be ignored.
 
 ```bash
---fs tag=virtiofs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=off
+--fs tag=myfs,socket=/tmp/virtiofs,num_queues=1,queue_size=512,dax=off
 
 ```
 

docs/hotplug.md

@@ -31,7 +31,7 @@ $ ./cloud-hypervisor/target/release/cloud-hypervisor \
 $ popd
 ```
 
-Notice the addition of `--api-socket=/tmp/ch-socket` and a `max` parameter on `--cpus boot=4.max=8`.
+Notice the addition of `--api-socket=/tmp/ch-socket` and a `max` parameter on `--cpus boot=4,max=8`.
 
 To ask the VMM to add additional vCPUs then use the resize API:
 

docs/intel_sgx.md

@@ -19,7 +19,7 @@ following [instructions](https://github.com/intel/linux-sgx).
 
 ## Cloud-Hypervisor support
 
-Assuming the host exposes `/dev/sgx_virt_epc`, we can pass SGX enclaves through
+Assuming the host exposes `/dev/sgx_vepc`, we can pass SGX enclaves through
 the guest.
 
 In order to use SGX enclaves within a Cloud-Hypervisor VM, we must define one
@@ -32,7 +32,7 @@ memory, the second one being 32MiB with no pre-allocated memory.
     --cpus boot=1 \
     --memory size=1G \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel bzImage \
+    --kernel vmlinux \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
     --sgx-epc size=64M,prefault=on size=32M,prefault=off
 ```
@@ -43,7 +43,7 @@ have been correctly created under `/dev/sgx`:
 
 ```bash
 ls /dev/sgx*
-/dev/sgx_enclave  /dev/sgx_provision  /dev/sgx_virt_epc
+/dev/sgx_enclave  /dev/sgx_provision  /dev/sgx_vepc
 ```
 
 From this point, it is possible to run any SGX application from the guest, as
@@ -51,5 +51,5 @@ it will access `/dev/sgx_enclave` device to create dedicated SGX enclaves.
 
 Note: There is only one contiguous SGX EPC region, which contains all SGX EPC
 sections. This region is exposed through ACPI and marked as reserved through
-the e820 table. It is treated yet as another device, which means it should
+the e820 table. It is treated as yet another device, which means it should
 appear at the end of the guest address space.

docs/io_throttling.md

@@ -1,13 +1,16 @@
 # I/O Throttling
 
-Cloud Hypervisor now supports I/O throttling on virtio-block
+Cloud Hypervisor now supports I/O throttling on virtio-block and virtio-net
 devices. This support is based on the [`rate-limiter` module](https://github.com/firecracker-microvm/firecracker/tree/master/src/rate_limiter)
 from Firecracker. This document explains the user interface of this
 feature, and highlights some internal implementations that can help users
 better understand the expected behavior of I/O throttling in practice.
 
 Cloud Hypervisor allows to limit both the I/O bandwidth (e.g. bytes/s)
-and I/O operations (ops/s) independently. To limit the I/O bandwidth, it
+and I/O operations (ops/s) independently. For virtio-net devices, while
+sharing the same "rate limit" from user inputs (on both bandwidth and
+operations), the RX and TX queues are throttled independently.
+To limit the I/O bandwidth, Cloud Hypervisor
 provides three user options, i.e., `bw_size` (bytes), `bw_one_time_burst`
 (bytes), and `bw_refill_time` (ms). Both `bw_size` and `bw_refill_time`
 are required, while `bw_one_time_burst` is optional.
@@ -29,8 +32,8 @@ empty, it will stop I/O operations for a fixed amount of time
 (`cool_down_time`). The `cool_down_time` now is fixed at `100 ms`, it
 can have big implications to the actual rate limit (which can be a lot
 different the expected "refill-rate" derived from user inputs). For
-example, to have a 1000 IOPS limit, users should be able to provide
-either of the following two options:
+example, to have a 1000 IOPS limit on a virtio-blk device, users should
+be able to provide either of the following two options:
 `ops_size=1000,ops_refill_time=1000` or
 `ops_size=10,ops_refill_time=10`. However, the actual IOPS limits are
 likely to be ~1000 IOPS and ~100 IOPS respectively. The reason is the

docs/iommu.md

@@ -89,7 +89,7 @@ virtual IOMMU:
     --cpus boot=1 \
     --memory size=512M \
     --disk path=focal-server-cloudimg-amd64.raw,iommu=on \
-    --kernel custom-bzImage \
+    --kernel custom-vmlinux \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
 ```
 
@@ -166,7 +166,7 @@ be consumed.
     --cpus boot=1 \
     --memory size=8G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-bzImage \
+    --kernel custom-vmlinux \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw hugepagesz=2M hugepages=2048" \
     --net tap=,mac=,iommu=on
 ```
@@ -183,7 +183,7 @@ passing through is `0000:00:01.0`.
     --cpus boot=1 \
     --memory size=8G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-bzImage \
+    --kernel custom-vmlinux \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw kvm-intel.nested=1 vfio_iommu_type1.allow_unsafe_interrupts rw hugepagesz=2M hugepages=2048" \
     --device path=/sys/bus/pci/devices/0000:00:01.0,iommu=on
 ```
@@ -194,6 +194,7 @@ guest, and bind it to VFIO (it should appear as `0000:00:04.0`).
 ```bash
 echo 0000:00:04.0 > /sys/bus/pci/devices/0000\:00\:04.0/driver/unbind
 echo 8086 1502 > /sys/bus/pci/drivers/vfio-pci/new_id
+echo 0000:00:04.0 > /sys/bus/pci/drivers/vfio-pci/bind
 ```
 
 Last thing is to start the L2 guest with the huge pages memory backend.
@@ -203,7 +204,7 @@ Last thing is to start the L2 guest with the huge pages memory backend.
     --cpus boot=1 \
     --memory size=4G,hugepages=on \
     --disk path=focal-server-cloudimg-amd64.raw \
-    --kernel custom-bzImage \
+    --kernel custom-vmlinux \
     --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
     --device path=/sys/bus/pci/devices/0000:00:04.0
 ```

docs/live_migration.md

@@ -0,0 +1,139 @@
+# Live Migration
+
+This document gives two examples of how to use the live migration
+support in Cloud Hypervisor:
+
+1. local migration - migrating between two VMs running on the same
+   machine;
+1. nested-vm migration - migrating between two nested VMs whose host VMs
+   are running on the same machine.
+
+## Local Migration
+Launch the source VM (on the host machine):
+```bash
+$ target/release/cloud-hypervisor
+    --kernel ~/workloads/vmlinux \
+    --disk path=~/workloads/focal.raw \
+    --cpus boot=1 --memory size=1G \
+    --cmdline "root=/dev/vda1 console=ttyS0"  \
+    --serial tty --console off --api-socket=/tmp/api1
+```
+
+Launch the destination VM from the same directory (on the host machine):
+```bash
+$ target/release/cloud-hypervisor --api-socket=/tmp/api2
+```
+
+Get ready for receiving migration for the destination VM (on the host machine):
+```bash
+$ target/release/ch-remote --api-socket=/tmp/api2 receive-migration unix:/tmp/sock
+```
+
+Start to send migration for the source VM (on the host machine):
+```bash
+$ 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.
+
+## Nested-VM Migration
+
+Launch VM 1 (on the host machine) with an extra virtio-blk device for
+exposing a guest image for the nested source VM:
+> Note: the example below also attached an additional virtio-blk device
+> with a dummy image for testing purpose (which is optional).
+```bash
+$ head -c 1M < /dev/urandom > tmp.img # create a dummy image for testing
+$ sudo /target/release/cloud-hypervisor \
+        --serial tty --console off \
+        --cpus boot=1 --memory size=512M \
+        --kernel vmlinux \
+        --cmdline "root=/dev/vda1 console=ttyS0"  \
+        --disk path=focal-1.raw path=focal-nested.raw path=tmp.img\
+        --net ip=192.168.101.1
+```
+
+Launch VM 2 (on the host machine) with an extra virtio-blk device for
+exposing the same guest image for the nested destination VM:
+```bash
+$ sudo /target/release/cloud-hypervisor \
+        --serial tty --console off \
+        --cpus boot=1 --memory size=512M \
+        --kernel vmlinux \
+        --cmdline "root=/dev/vda1 console=ttyS0"  \
+        --disk path=focal-2.raw path=focal-nested.raw path=tmp.img\
+        --net ip=192.168.102.1
+```
+
+Launch the nested source VM (inside the guest OS of the VM 1) :
+```bash
+vm-1:~$ sudo ./cloud-hypervisor \
+        --serial tty --console off \
+        --memory size=128M \
+        --kernel vmlinux \
+        --cmdline "console=ttyS0 root=/dev/vda1" \
+        --disk path=/dev/vdb path=/dev/vdc \
+        --api-socket=/tmp/api1 \
+        --net ip=192.168.100.1
+vm-1:~$ # setup the guest network if needed
+vm-1:~$ sudo ip addr add 192.168.101.2/24 dev ens4
+vm-1:~$ sudo ip link set up dev ens4
+vm-1:~$ sudo ip r add default via 192.168.101.1
+```
+Optional: Run the guest workload below (on the guest OS of the nested source VM),
+which performs intensive virtio-blk operations. Now the console of the nested
+source VM should repeatedly print `"equal"`, and our goal is migrating
+this VM and the running workload without interruption.
+```bash
+#/bin/bash
+
+# On the guest OS of the nested source VM
+
+input="/dev/vdb"
+result=$(md5sum $input)
+tmp=$(md5sum $input)
+
+while  [[ "$result" == "$tmp" ]]
+do
+    echo "equal"
+    tmp=$(md5sum $input)
+done
+
+echo "not equal"
+echo "result = $result"
+echo "tmp = $tmp"
+```
+
+Launch the nested destination VM (inside the guest OS of the VM 2):
+```bash
+vm-2:~$ sudo ./cloud-hypervisor --api-socket=/tmp/api2
+vm-2:~$ # setup the guest network with the following commands if needed
+vm-2:~$ sudo ip addr add 192.168.102.2/24 dev ens4
+vm-2:~$ sudo ip link set up dev ens4
+vm-2:~$ sudo ip r add default via 192.168.102.1
+vm-2:~$ ping 192.168.101.2 # This should succeed
+```
+> Note: If the above ping failed, please check the iptables rule on the
+> host machine, e.g. whether the policy for the `FORWARD` chain is set
+> to `DROP` (which is the default setting configured by Docker).
+
+Get ready for receiving migration for the nested destination VM (inside
+the guest OS of the VM 2):
+```bash
+vm-2:~$ sudo ./ch-remote --api-socket=/tmp/api2 receive-migration unix:/tmp/sock2
+vm-2:~$ sudo socat TCP-LISTEN:6000,reuseaddr UNIX-CLIENT:/tmp/sock2
+```
+
+Start to send migration for the nested source VM (inside the guest OS of
+the VM 1):
+```bash
+vm-1:~$ sudo socat UNIX-LISTEN:/tmp/sock1,reuseaddr TCP:192.168.102.2:6000
+vm-1:~$ sudo ./ch-remote --api-socket=/tmp/api1 send-migration unix:/tmp/sock1
+```
+
+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.

docs/macvtap-bridge.md

@@ -1,6 +1,6 @@
 # Using MACVTAP to Bridge onto Host Network
 
-Cloud Hypervisor supports using a MACVTAP device which is derived from a MACVLAN. Full details of configuring MACVLAN or MACVTAP is out of scope of this document. However the example below indicates how to bridge the guest directly onto the the network the host is on. Due to the lack of hairpin mode it not usually possible to reach the guest directly from the host.
+Cloud Hypervisor supports using a MACVTAP device which is derived from a MACVLAN. Full details of configuring MACVLAN or MACVTAP is out of scope of this document. However the example below indicates how to bridge the guest directly onto the network the host is on. Due to the lack of hairpin mode it not usually possible to reach the guest directly from the host.
 
 ```bash
 # The MAC address must be attached to the macvtap and be used inside the guest

docs/networking.md

@@ -2,7 +2,7 @@
 
 cloud-hypervisor can emulate one or more virtual network interfaces, represented at the hypervisor host by [tap devices](https://www.kernel.org/doc/Documentation/networking/tuntap.txt). This guide briefly describes, in a manual and distribution neutral way, how to setup and use networking with cloud-hypervisor.
 
-## Multiple queue support for net devices ##
+## Multiple queue support for net devices
 
 While multiple vcpus defined for guest, to gain the benefit of vcpu scalable to improve performance, it suggests to define multiple queue pairs for net devices, one Tx/Rx queue pair per one vcpu, that means the number of queue pairs at least is equal to the vcpu count. In that case, after virtnet driver set cpu affinity for virtqueues in guest kernel, vcpus could handle interrupt from different virtqueue pairs in parallel.
 
@@ -23,7 +23,7 @@ Use one `--net` command-line argument from cloud-hypervisor to specify the emula
 
 ```bash
 ./cloud-hypervisor \
-    --cpus 4 \
+    --cpus boot=4 \
     --memory "size=512M" \
     --disk path=focal-server-cloudimg-amd64.raw \
     --kernel my-vmlinux.bin \
@@ -34,14 +34,14 @@ Use one `--net` command-line argument from cloud-hypervisor to specify the emula
 
 The `--net` argument takes 1 or more space-separated strings of key value pairs containing the following 4 keys or fields:
 
-| Name       | Purpose                    | Optional  |
-| -----------|----------------------------| ----------|
-| tap        | tap device name            | Yes       |
-| mac        | vNIC mac address           | Yes       |
-| ip         | tap IP IP address          | yes       |
-| mask       | tap IP netmask             | Yes       |
-| num_queues | the number of queues       | yes       |
-| queue_size | the size of each queue     | Yes       |
+| Name       | Purpose                | Optional |
+| ---------- | ---------------------- | -------- |
+| tap        | tap device name        | Yes      |
+| mac        | vNIC mac address       | Yes      |
+| ip         | tap IP IP address      | yes      |
+| mask       | tap IP netmask         | Yes      |
+| num_queues | the number of queues   | yes      |
+| queue_size | the size of each queue | Yes      |
 
 num_queues is the total number of tx and rx queues, the default value is 2, and it could be increased by multiples of 2. Additionally, num_queues is suggested to be as 2 times of vcpu count. The default value for queue_size is 256.
 
@@ -104,6 +104,7 @@ bridge name     bridge id               STP enabled     interfaces
 ich-dpl         8000.067afc1b9a67       no              ich1
 ich-int         8000.725412ffce6f       no              ich0
 ```
+
 This completes the layer 2 wiring: The cloud-hypervisor is now connected to the hypervisor host via the 2 linux bridges.
 
 ## IP (Layer 3) provisioning
@@ -116,6 +117,7 @@ On the hypervisor host add the network gateway IP address of each network to the
 root@host:~# ip addr add 192.168.4.1/24 dev ich-int
 root@host:~# ip addr add 10.0.1.1/24 dev ich-dpl
 ```
+
 The routing table of the hypervisor host should now also have corresponding routing entries:
 
 ```bash
@@ -127,9 +129,10 @@ Destination     Gateway         Genmask         Flags Metric Ref    Use Iface
 192.168.4.0     0.0.0.0         255.255.255.0   U     0      0        0 ich-int
 192.168.178.0   0.0.0.0         255.255.255.0   U     600    0        0 wlan1
 ```
+
 ### Virtual Machine
 
-Within the virtual machine set the vNIC's to up state and provision the corresponding IP addresses on the 2 vNIC's. The steps outlined below use the ip command as an example. Alternative distribution specific procedures can also apply.   
+Within the virtual machine set the vNIC's to up state and provision the corresponding IP addresses on the 2 vNIC's. The steps outlined below use the ip command as an example. Alternative distribution specific procedures can also apply.
 
 ```bash
 root@guest:~# ip link set up enp0s2
@@ -165,7 +168,7 @@ root@192.168.4.2's password:
 Linux cloud-hypervisor 5.2.0 #2 SMP Thu Jul 11 08:08:16 CEST 2019 x86_64
 
 Debian GNU/Linux comes with ABSOLUTELY NO WARRANTY, to the extent
-permitted by applicable law.                                                         
+permitted by applicable law.
 
 
 Last login: Fri Jul 12 13:27:56 2019 from 192.168.4.1
@@ -189,7 +192,7 @@ nameserver 192.168.178.1
 make sure that the default gateway of the hypervisor host (in this example host 192.168.178.1 which is an adsl router) has an entry in the routing table for the 192.168.4.0/24 network otherwise IP connectivity will not work.
 
 ```bash
-root@guest:~# nslookup  ftp.nl.debian.org       
+root@guest:~# nslookup  ftp.nl.debian.org
 Server:         192.168.178.1
 Address:        192.168.178.1#53
 

docs/profiling.md

@@ -1,6 +1,6 @@
 # Profiling
 
-`perf` can be used to profile the `cloud-hypervisor` binary but it is necessary to make some modifications to the the build in order to produce a binary that gives useful results.
+`perf` can be used to profile the `cloud-hypervisor` binary but it is necessary to make some modifications to the build in order to produce a binary that gives useful results.
 
 ## Building a suitable binary
 

docs/snapshot_restore.md

@@ -20,7 +20,7 @@ First thing, we must run a Cloud-Hypervisor VM:
     --api-socket /tmp/cloud-hypervisor.sock \
     --cpus boot=4 \
     --memory size=4G \
-    --kernel bzImage \
+    --kernel vmlinux \
     --cmdline "root=/dev/vda1 console=hvc0 rw" \
     --disk path=focal-server-cloudimg-amd64.raw
 ```

docs/vfio.md

@@ -11,7 +11,7 @@ by the VFIO kernel drivers. However, by default, a host device will be bound to
 its native driver, which is not the VFIO one.
 
 As a consequence, a device must be unbound from its native driver before passing
-it to `cloud-hypervisor` for assigning it to a guess.
+it to `cloud-hypervisor` for assigning it to a guest.
 
 ### Example
 
@@ -54,6 +54,7 @@ $ lspci -n -s 01:00.0
 01:00.0 ff00: 10ec:525a (rev 01)
 
 $ echo 10ec 525a > /sys/bus/pci/drivers/vfio-pci/new_id
+$ echo 0000:01:00.0 > /sys/bus/pci/drivers/vfio-pci/bind
 ```
 
 Now the device is managed by the VFIO framework.

docs/vhost-user-blk-testing.md

@@ -35,38 +35,52 @@ Here are some good references for detailing them.
 
 ## Test environment
 
-The below test environment is based on ubuntu release(16.04.1 LTS), as for other system, please check related document.
-The test runs with multiple queue (MQ) support enabled, using 4 queues defined for both SPDK and the virtual machine.
-Here are the details on how the test can be run.
+The below test environment is based on Ubuntu release (20.04.1 LTS), as for other system, please check related documents.
+This test runs with multiple queue (MQ) support enabled, using 4 queues defined for both SPDK and the virtual machine.
+Here are the detailed instructions.
 
-### The hugepages settings in host linux
-Add "default_hugepagesz=1G hugepagesz=1G hugepages=2" into host linux cmdline.
-As for how to change Ubuntu linux cmdline in grub file, please ref below link:
-https://www.ostechnix.com/configure-grub-2-boot-loader-settings-ubuntu-16-04/
-reboot Ubuntu
-sudo mount -t hugetlbfs -o pagesize=1G none /dev/hugepages
+### The hugepages settings on the host
+Allocate enough persistent huge pages (e.g. 2GiB) on the host:
+
+```bash
+# Assume the default hugepage size is 2MiB
+echo 1024 | sudo tee /proc/sys/vm/nr_hugepages
+# Confirm the value of "Hugepagesize" and "HugePages_Total"
+cat /proc/meminfo | grep -i huge
+```
 
 ### Download the SPDK code
+```bash
 git clone https://github.com/spdk/spdk
 cd spdk
 git submodule update --init
+```
 
 ### Create the build dep
-./scripts/pkgdep.sh
 
-### Build spdk
+```bash
+./scripts/pkgdep.sh
+```
+
+### Build SPDK
+```bash
 ./configure
 make
+```
 
-### Set the SPDk environment
+### Set the SPDK environment
+```bash
 sudo HUGEMEM=2048 scripts/setup.sh
-sudo ./app/vhost/vhost -S /var/tmp -s 1024 -m 0x3 &
+sudo ./build/bin/vhost -S /var/tmp -s 1024 -m 0x3 &
+```
 
 ### Create 512M block device
+```bash
 sudo scripts/rpc.py bdev_malloc_create 512 512 -b Malloc0
 sudo scripts/rpc.py vhost_create_blk_controller --cpumask 0x1 vhost.1 Malloc0
+```
 
-_Launch the VM_
+### Launch the VM
 
 VMs run in client mode. They connect to the socket created by the `dpdkvhostuser` in the SPDK backend.
 ```bash
@@ -89,9 +103,9 @@ login in guest
 # Use lsblk command to find out vhost-user-blk device
 lsblk
 NAME    MAJ:MIN RM  SIZE RO TYPE MOUNTPOINT
-vda     252:0    0  2.2G  0 disk 
+vda     252:0    0  2.2G  0 disk
 ├─vda1  252:1    0  2.1G  0 part /
-├─vda14 252:14   0    4M  0 part 
+├─vda14 252:14   0    4M  0 part
 └─vda15 252:15   0  106M  0 part /boot/efi
 vdb    253:16   0  512M  0 disk
 

docs/vhost-user-net-testing.md

@@ -1,27 +1,30 @@
 # How to test Vhost-user net with OpenVSwitch/DPDK
 
-The purpose of this document is to illustrate how to test vhost-user-net in cloud-hypervisor with OVS/DPDK as the backend.
+The purpose of this document is to illustrate how to test vhost-user-net
+in cloud-hypervisor with OVS/DPDK as the backend. This document was
+tested with Open vSwitch v2.13.1, DPDK v19.11.3, and Cloud Hypervisor
+v15.0 on Ubuntu 20.04.1 (host kernel v5.4.0).
 
 ## Framework
 
 It's a simple test to validate the communication between two virtual machine, connecting them to vhost-user ports respectively provided by `OVS/DPDK`.
 ```
-             +----+----------+          +-------------+-----------+-------------+          +----------+----+  
-             |    |          |          |             |           |             |          |          |    | 
-             |    |vhost-user|----------| vhost-user  |   ovs     | vhost-user  |----------|vhost-user|    |           
-             |    |net device|          | port 1      |           | port 2      |          |net device|    |           
-             |    |          |          |             |           |             |          |          |    |           
-             |    +----------+          +-------------+-----------+-------------+          +----------+    |           
-             |               |          |                                       |          |               |           
-             |vm1            |          |                  dpdk                 |          |           vm2 |           
-             |               |          |                                       |          |               |           
-          +--+---------------------------------------------------------------------------------------------+--+        
-          |  |                                       hugepages                                             |  |        
-          |  +---------------------------------------------------------------------------------------------+  |        
-          |                                                                                                   |        
-          |                                              host                                                 |        
-          |                                                                                                   |  
-          +---------------------------------------------------------------------------------------------------+        
+             +----+----------+          +-------------+-----------+-------------+          +----------+----+
+             |    |          |          |             |           |             |          |          |    |
+             |    |vhost-user|----------| vhost-user  |   ovs     | vhost-user  |----------|vhost-user|    |
+             |    |net device|          | port 1      |           | port 2      |          |net device|    |
+             |    |          |          |             |           |             |          |          |    |
+             |    +----------+          +-------------+-----------+-------------+          +----------+    |
+             |               |          |                                       |          |               |
+             |vm1            |          |                  dpdk                 |          |           vm2 |
+             |               |          |                                       |          |               |
+          +--+---------------------------------------------------------------------------------------------+--+
+          |  |                                       hugepages                                             |  |
+          |  +---------------------------------------------------------------------------------------------+  |
+          |                                                                                                   |
+          |                                              host                                                 |
+          |                                                                                                   |
+          +---------------------------------------------------------------------------------------------------+
 ```
 ## Prerequisites
 
@@ -30,44 +33,54 @@ Prior to running the test, the following steps need to be performed.
 - Install DPDK
 - Install OVS
 
-Here are some good references for detailing them.
-- Red Hat
-	* https://wiki.qemu.org/Documentation/vhost-user-ovs-dpdk
-- Ubuntu server
-	* https://help.ubuntu.com/lts/serverguide/DPDK.html
-	* https://software.intel.com/en-us/articles/set-up-open-vswitch-with-dpdk-on-ubuntu-server
+Here is a good reference for setting up OVS with DPDK from scratch:
+https://docs.openvswitch.org/en/latest/intro/install/dpdk/.
 
+On Ubuntu systems (18.04 or newer), the OpenVswitch-DPDK package can be
+easily installed with:
+```bash
+sudo apt-get update
+sudo apt-get install openvswitch-switch-dpdk
+sudo update-alternatives --set ovs-vswitchd /usr/lib/openvswitch-switch-dpdk/ovs-vswitchd-dpdk
+```
 ## Test
-The test runs with multiple queue (MQ) support enabled, using 2 pairs of TX/RX queues defined for both OVS and the virtual machine. Here are the details on how the test can be run.
+The test runs with multiple queue (MQ) support enabled, using 2 pairs of
+TX/RX queues defined for both OVS and the virtual machine. Here are the
+detailed instructions.
 
 _Setup OVS_
 
-`ovs_test.sh` is created to setup and start OVS. OVS will provide the `dpdkvhostuser` backend running in server mode.
+Here is an example how to configure a basic OpenVswitch using DPDK:
 ```bash
-mkdir -p /var/run/openvswitch
+# load the ovs kernel module
 modprobe openvswitch
-killall ovsdb-server ovs-vswitchd
-rm -f /var/run/openvswitch/vhost-user*
-rm -f /etc/openvswitch/conf.db
-export DB_SOCK=/var/run/openvswitch/db.sock
-ovsdb-tool create /etc/openvswitch/conf.db /usr/share/openvswitch/vswitch.ovsschema
-ovsdb-server --remote=punix:$DB_SOCK --remote=db:Open_vSwitch,Open_vSwitch,manager_options --pidfile --detach
-ovs-vsctl --no-wait init
-ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-lcore-mask=0xf
-ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-socket-mem=1024
-ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-init=true
-ovs-vsctl --no-wait set Open_vSwitch . other_config:pmd-cpu-mask=0xf
-ovs-vswitchd unix:$DB_SOCK --pidfile --detach --log-file=/var/log/openvswitch/ovs-vswitchd.log
+sudo service openvswitch-switch start
+ovs-vsctl init
+ovs-vsctl set Open_vSwitch . other_config:dpdk-init=true
+# run on core 0-3 only
+ovs-vsctl set Open_vSwitch . other_config:dpdk-lcore-mask=0xf
+# allocate 2G huge pages (to NUMA 0 only)
+ovs-vsctl set Open_vSwitch . other_config:dpdk-socket-mem=1024
+# run PMD (Pull Mode Driver) threads on core 0-3 only
+ovs-vsctl set Open_vSwitch . other_config:pmd-cpu-mask=0xf
+sudo service openvswitch-switch restart
+# double check the configurations
+ovs-vsctl list Open_vSwitch
+```
+
+Here is an example how to create a bridge and add two DPDK ports to it
+(for later use via Cloud Hypervisor):
+```bash
+# create a bridge
 ovs-vsctl add-br ovsbr0 -- set bridge ovsbr0 datapath_type=netdev
+# create two DPDK ports and add them to the bridge
 ovs-vsctl add-port ovsbr0 vhost-user1 -- set Interface vhost-user1 type=dpdkvhostuser
-ovs-vsctl add-port ovsbr0 vhost-user2 -- set Interface vhost-user2 type=dpdkvhostuser
+ovs-vsctl add-port ovsbr0 vhost-user2 -- set Interface vhost-user2
+type=dpdkvhostuser
+# set the number of rx queues
 ovs-vsctl set Interface vhost-user1 options:n_rxq=2
 ovs-vsctl set Interface vhost-user2 options:n_rxq=2
 ```
-_Run ovs_test.sh_
-```bash
-./ovs_test.sh
-```
 
 _Launch the VMs_
 
@@ -89,19 +102,21 @@ VMs run in client mode. They connect to the socket created by the `dpdkvhostuser
         --kernel vmlinux \
         --cmdline "console=ttyS0 console=hvc0 root=/dev/vda1 rw" \
         --disk path=focal-server-cloudimg-amd64.raw   \
-        --net "mac=52:54:20:11:C5:02,vhost_user=true,socket=/var/run/openvswitch/vhost-user2,num_queues=4"
+        --net mac=52:54:20:11:C5:02,vhost_user=true,socket=/var/run/openvswitch/vhost-user2,num_queues=4
 ```
 
 _Setup VM1_
 ```bash
 # From inside the guest
-sudo ip addr add 172.100.0.1/24 dev enp0s3
+sudo ip addr add 172.100.0.1/24 dev ens2
+sudo ip link set up dev ens2
 ```
 
 _Setup VM2_
 ```bash
 # From inside the guest
-sudo ip addr add 172.100.0.2/24 dev enp0s3
+sudo ip addr add 172.100.0.2/24 dev ens2
+sudo ip link set up dev ens2
 ```
 
 _Ping VM1 from VM2_
@@ -129,4 +144,3 @@ _Run VM2 as client_
 # From inside the guest
 iperf3 -c 172.100.0.1 -t 30 -p 4444 &
 ```
-

docs/windows.md

@@ -184,6 +184,16 @@ Set-Service -Name sshd -StartupType ‘Automatic’
 
 This allows for SSH login from a remote machine, for example through the `administrator` user: `ssh administrator@192.168.249.2`. For a more detailed OpenSSH guide, please follow the MSDN article from the [links](#links) section.
 
+## Hotplug capability
+
+CPU hotplug is supported. The VM operating system needs to support hotplug and be appropriately licensed. SKU limitations like constraints on the number of cores are to be taken into consideration. Note, that Windows doesn't support CPU hot-remove. When `ch-remote` is invoked to reduce the number of CPUs, the result will be visible after the OS reboot within the same hypervisor instance.
+
+RAM hotplug is supported. Note, that while the `pnpmem.sys` driver in use supports RAM hot-remove, the RAM being unplugged has to be not in use and have no reserved pages. In most cases it means, hot-remove won't work. Same as with the CPU hot-remove, when `ch-remote` is invoked to reduce the RAM size, the result will be visible after the OS reboot.
+
+Network device hotplug and hot-remove are supported.
+
+Disk hotplug and hot-remove are supported. After the device has been hotplugged, it will need to be onlined from within the guest. Among other tools, powershell applets `Get-Disk` and `Set-Disk` can be used for the disk configuration and activation.
+
 ## Debugging
 
 The Windows guest debugging process relies heavily on QEMU and [socat](http://www.dest-unreach.org/socat/). The procedure requires two Windows VMs:

event_monitor/Cargo.toml

@@ -5,7 +5,7 @@ authors = ["The Cloud Hypervisor Authors"]
 edition = "2018"
 
 [dependencies]
-libc = "0.2.91"
+libc = "0.2.96"
 serde = {version = ">=1.0.27", features = ["rc"] }
 serde_derive = ">=1.0.27"
 serde_json = ">=1.0.9"

fuzz/Cargo.lock

@@ -20,9 +20,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.39"
+version = "1.0.40"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "81cddc5f91628367664cc7c69714ff08deee8a3efc54623011c772544d7b2767"
+checksum = "28b2cd92db5cbd74e8e5028f7e27dd7aa3090e89e4f2a197cc7c8dfb69c7063b"
 
 [[package]]
 name = "api_client"
@@ -30,15 +30,15 @@ version = "0.1.0"
 
 [[package]]
 name = "arbitrary"
-version = "1.0.0"
+version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "698b65a961a9d730fb45b6b0327e20207810c9f61ee421b082b27ba003f49e2b"
+checksum = "237430fd6ed3740afe94eefcc278ae21e050285be882804e0d6e8695f0c94691"
 
 [[package]]
 name = "arc-swap"
-version = "1.2.0"
+version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d4d7d63395147b81a9e570bcc6243aaf71c017bd666d4909cfef0085bdda8d73"
+checksum = "e906254e445520903e7fc9da4f709886c84ae4bc4ddaf0e093188d66df4dc820"
 
 [[package]]
 name = "arch"
@@ -46,24 +46,20 @@ version = "0.1.0"
 dependencies = [
  "acpi_tables",
  "anyhow",
- "arch_gen",
  "byteorder",
  "hypervisor",
  "libc",
  "linux-loader",
  "log",
  "serde",
- "serde_derive",
- "serde_json",
  "thiserror",
+ "versionize",
+ "versionize_derive",
+ "vm-fdt",
  "vm-memory",
  "vm-migration",
 ]
 
-[[package]]
-name = "arch_gen"
-version = "0.1.0"
-
 [[package]]
 name = "atty"
 version = "0.2.14"
@@ -75,6 +71,15 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "bincode"
+version = "1.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "bitflags"
 version = "1.2.1"
@@ -89,10 +94,9 @@ dependencies = [
  "libc",
  "log",
  "qcow",
- "serde",
- "serde_derive",
- "serde_json",
  "thiserror",
+ "versionize",
+ "versionize_derive",
  "virtio-bindings",
  "vm-memory",
  "vm-virtio",
@@ -107,9 +111,9 @@ checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
 [[package]]
 name = "cc"
-version = "1.0.67"
+version = "1.0.68"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3c69b077ad434294d3ce9f1f6143a2a4b89a8a2d54ef813d85003a4fd1137fd"
+checksum = "4a72c244c1ff497a746a7e1fb3d14bd08420ecda70c8f25c7112f2781652d787"
 
 [[package]]
 name = "cfg-if"
@@ -135,7 +139,7 @@ dependencies = [
 
 [[package]]
 name = "cloud-hypervisor"
-version = "0.13.0"
+version = "15.0.0"
 dependencies = [
  "anyhow",
  "api_client",
@@ -171,20 +175,26 @@ dependencies = [
  "vmm-sys-util",
 ]
 
+[[package]]
+name = "crc64"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "55626594feae15d266d52440b26ff77de0e22230cf0c113abe619084c1ddc910"
+
 [[package]]
 name = "devices"
 version = "0.1.0"
 dependencies = [
  "acpi_tables",
  "anyhow",
+ "arch",
  "bitflags",
  "byteorder",
  "epoll",
  "libc",
  "log",
- "serde",
- "serde_derive",
- "serde_json",
+ "versionize",
+ "versionize_derive",
  "vm-device",
  "vm-memory",
  "vm-migration",
@@ -241,9 +251,9 @@ dependencies = [
 
 [[package]]
 name = "iced-x86"
-version = "1.11.0"
+version = "1.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4261b15a556aa9b83b976b7aa4613f5a3b80351683af14c5d8d7e62c00869d5a"
+checksum = "6d907dfc273d9ed0da940e8145ceb77759056a1fb2110b44b83d1b203cddb906"
 dependencies = [
  "lazy_static",
  "static_assertions",
@@ -277,9 +287,9 @@ dependencies = [
 
 [[package]]
 name = "kvm-ioctls"
-version = "0.8.0"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74058b16912c6723db02d4ca3ec919b73cd41512ccd3b6202cf91ae8d6c9dce5"
+checksum = "f2924454e22895c738e43331ae310459c74a11ded9c97dc250129ee10d2f9ca2"
 dependencies = [
  "kvm-bindings",
  "libc",
@@ -294,18 +304,19 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
-version = "0.2.91"
+version = "0.2.96"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8916b1f6ca17130ec6568feccee27c156ad12037880833a3b842a823236502e7"
+checksum = "5600b4e6efc5421841a2138a6b082e07fe12f9aaa12783d50e5d13325b26b4fc"
 
 [[package]]
 name = "libfuzzer-sys"
-version = "0.4.0"
+version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "86c975d637bc2a2f99440932b731491fc34c7f785d239e38af3addd3c2fd0e46"
+checksum = "36a9a84a6e8b55dfefb04235e55edb2b9a2a18488fcae777a6bdaa6f06f1deb3"
 dependencies = [
  "arbitrary",
  "cc",
+ "once_cell",
 ]
 
 [[package]]
@@ -329,9 +340,10 @@ dependencies = [
 [[package]]
 name = "micro_http"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/micro-http?branch=master#59ab64440a95f7b16253fef67b5201c2ec4adaf7"
+source = "git+https://github.com/firecracker-microvm/micro-http?branch=main#9b605a8b61df602cda62076d30d9f70307ea336f"
 dependencies = [
- "epoll",
+ "libc",
+ "vmm-sys-util",
 ]
 
 [[package]]
@@ -349,13 +361,22 @@ dependencies = [
  "libc",
  "log",
  "net_gen",
+ "rate_limiter",
  "serde",
+ "versionize",
+ "versionize_derive",
  "virtio-bindings",
  "vm-memory",
  "vm-virtio",
  "vmm-sys-util",
 ]
 
+[[package]]
+name = "once_cell"
+version = "1.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af8b08b04175473088b46763e51ee54da5f9a164bc162f615b91bc179dbf15a3"
+
 [[package]]
 name = "option_parser"
 version = "0.1.0"
@@ -369,9 +390,8 @@ dependencies = [
  "hypervisor",
  "libc",
  "log",
- "serde",
- "serde_derive",
- "serde_json",
+ "versionize",
+ "versionize_derive",
  "vfio-bindings",
  "vfio-ioctls",
  "vm-allocator",
@@ -383,9 +403,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.24"
+version = "1.0.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e0704ee1a7e00d7bb417d0770ea303c1bccbabf0ef1667dae92b5967f5f8a71"
+checksum = "f0d8caf72986c1a598726adc988bb5984792ef84f5ee5aa50209145ee8077038"
 dependencies = [
  "unicode-xid",
 ]
@@ -410,6 +430,15 @@ dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "rate_limiter"
+version = "0.1.0"
+dependencies = [
+ "libc",
+ "log",
+ "vmm-sys-util",
+]
+
 [[package]]
 name = "remain"
 version = "0.2.2"
@@ -430,22 +459,22 @@ checksum = "71d301d4193d031abdd79ff7e3dd721168a9572ef3fe51a1517aba235bd8f86e"
 [[package]]
 name = "seccomp"
 version = "0.1.0"
-source = "git+https://github.com/firecracker-microvm/firecracker?tag=v0.22.0#cc5387637c132e500b4857b80b5a239d8d732b77"
+source = "git+https://github.com/firecracker-microvm/firecracker?tag=v0.24.4#8f44986a0e956a77f2b2324c12f73bec16130c82"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "serde"
-version = "1.0.125"
+version = "1.0.126"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "558dc50e1a5a5fa7112ca2ce4effcb321b0300c0d4ccf0776a9f60cd89031171"
+checksum = "ec7505abeacaec74ae4778d9d9328fe5a5d04253220a85c4ee022239fc996d03"
 
 [[package]]
 name = "serde_derive"
-version = "1.0.125"
+version = "1.0.126"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b093b7a2bb58203b5da3056c05b4ec1fed827dcfdb37347a8841695263b3d06d"
+checksum = "963a7dbc9895aeac7ac90e74f34a5d5261828f79df35cbed41e10189d3804d43"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -465,9 +494,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook"
-version = "0.3.7"
+version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6aa894ef3fade0ee7243422f4fbbd6c2b48e6de767e621d37ef65f2310f53cea"
+checksum = "470c5a6397076fae0094aaf06a08e6ba6f37acb77d3b1b91ea92b4d6c8650c39"
 dependencies = [
  "libc",
  "signal-hook-registry",
@@ -475,9 +504,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook-registry"
-version = "1.3.0"
+version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "16f1d0fef1604ba8f7a073c7e701f213e056707210e9020af4528e0101ce11a6"
+checksum = "e51e73328dc4ac0c7ccbda3a494dfa03df1de2f46018127f60c693f2648455b0"
 dependencies = [
  "libc",
 ]
@@ -496,9 +525,9 @@ checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
 
 [[package]]
 name = "syn"
-version = "1.0.64"
+version = "1.0.73"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3fd9d1e9976102a03c542daa2eff1b43f9d72306342f3f8b3ed5fb8908195d6f"
+checksum = "f71489ff30030d2ae598524f61326b902466f72a0fb1a8564c001cc63425bcc7"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -527,18 +556,18 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "1.0.24"
+version = "1.0.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e0f4a65597094d4483ddaed134f409b2cb7c1beccf25201a9f73c719254fa98e"
+checksum = "fa6f76457f59514c7eeb4e59d891395fab0b2fd1d40723ae737d64153392e9c6"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.24"
+version = "1.0.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7765189610d8241a44529806d6fd1f2e0a08734313a35d5b3a556f92b381f3c0"
+checksum = "8a36768c0fbf1bb15eca10defa29526bda730a2376c2ab4393ccfa16fb1a318d"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -553,9 +582,15 @@ checksum = "9337591893a19b88d8d87f2cec1e73fad5cdfd10e5a6f349f498ad6ea2ffb1e3"
 
 [[package]]
 name = "unicode-xid"
-version = "0.2.1"
+version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7fe0bb3479651439c9112f72b6c505038574c9fbb575ed1bf3b797fa39dd564"
+checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"
+
+[[package]]
+name = "uuid"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bc5cf98d8186244414c848017f0e2676b3fcb46807f6668a97dfe67359a3c4b7"
 
 [[package]]
 name = "vec_map"
@@ -563,6 +598,34 @@ version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f1bddf1187be692e79c5ffeab891132dfb0f236ed36a43c7ed39f1165ee20191"
 
+[[package]]
+name = "versionize"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7429cf68de8f091b667d27323ed323afd39584a56d533995b12ddd748e5e6ca9"
+dependencies = [
+ "bincode",
+ "crc64",
+ "proc-macro2",
+ "quote",
+ "serde",
+ "serde_derive",
+ "syn",
+ "versionize_derive",
+ "vmm-sys-util",
+]
+
+[[package]]
+name = "versionize_derive"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "140aa9fd298f667ea50fa1cb0d8530076924079285c623b18b8f8a1c28386b4a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "vfio-bindings"
 version = "0.2.0"
@@ -575,7 +638,7 @@ dependencies = [
 [[package]]
 name = "vfio-ioctls"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=master#a87b13bdec026e8144b91f30f35451a966d8c1ca"
+source = "git+https://github.com/rust-vmm/vfio-ioctls?branch=master#5cb8550556620546e74b9fe6d1174e0d1fc83888"
 dependencies = [
  "byteorder",
  "kvm-bindings",
@@ -589,7 +652,7 @@ dependencies = [
 [[package]]
 name = "vhost"
 version = "0.1.0"
-source = "git+https://github.com/rust-vmm/vhost?branch=master#ee3e8722706c984b3dfe12d3a130e92101b78e8f"
+source = "git+https://github.com/rust-vmm/vhost?branch=master#e5b930b73a47cbdd79858e2e68bcb57123d1c1f3"
 dependencies = [
  "bitflags",
  "libc",
@@ -618,10 +681,13 @@ dependencies = [
  "net_gen",
  "net_util",
  "pci",
+ "rate_limiter",
  "seccomp",
  "serde",
  "serde_derive",
  "serde_json",
+ "versionize",
+ "versionize_derive",
  "vhost",
  "virtio-bindings",
  "vm-allocator",
@@ -655,11 +721,15 @@ dependencies = [
  "vmm-sys-util",
 ]
 
+[[package]]
+name = "vm-fdt"
+version = "0.1.0"
+source = "git+https://github.com/rust-vmm/vm-fdt?branch=master#13ab882e2f8387753064351c69fbe35c422b448b"
+
 [[package]]
 name = "vm-memory"
 version = "0.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "625f401b1b8b3ac3d43f53903cd138cfe840bd985f8581e553027b31d2bb8ae8"
+source = "git+https://github.com/rust-vmm/vm-memory?rev=5bd7138758183a73ac0da27ce40c004d95f1a7e9#5bd7138758183a73ac0da27ce40c004d95f1a7e9"
 dependencies = [
  "arc-swap",
  "libc",
@@ -675,6 +745,8 @@ dependencies = [
  "serde_derive",
  "serde_json",
  "thiserror",
+ "versionize",
+ "versionize_derive",
  "vm-memory",
 ]
 
@@ -683,9 +755,6 @@ name = "vm-virtio"
 version = "0.1.0"
 dependencies = [
  "log",
- "serde",
- "serde_derive",
- "serde_json",
  "virtio-bindings",
  "vm-memory",
 ]
@@ -720,6 +789,9 @@ dependencies = [
  "serde_json",
  "signal-hook",
  "thiserror",
+ "uuid",
+ "versionize",
+ "versionize_derive",
  "vfio-ioctls",
  "virtio-devices",
  "vm-allocator",

fuzz/Cargo.toml

@@ -10,21 +10,22 @@ cargo-fuzz = true
 
 [dependencies]
 block_util = { path = "../block_util" }
-libc = "0.2.90"
-libfuzzer-sys = "0.4"
+libc = "0.2.96"
+libfuzzer-sys = "0.4.2"
 qcow = { path = "../qcow" }
-seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.22.0" }
+seccomp = { git = "https://github.com/firecracker-microvm/firecracker", tag = "v0.24.4" }
 virtio-devices = { path = "../virtio-devices" }
 vmm-sys-util = "0.8.0"
 vm-virtio = { path = "../vm-virtio" }
 vm-memory = "0.5.0"
 
-[patch.crates-io]
-kvm-bindings = { git = "https://github.com/cloud-hypervisor/kvm-bindings", branch = "ch-v0.4.0", features = ["with-serde", "fam-wrappers"] }
-
 [dependencies.cloud-hypervisor]
 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"}
+
 # Prevent this from interfering with workspaces
 [workspace]
 members = ["."]

hypervisor/Cargo.toml

@@ -14,9 +14,9 @@ tdx = []
 anyhow = "1.0"
 epoll = ">=4.0.1"
 thiserror = "1.0"
-libc = "0.2.91"
+libc = "0.2.96"
 log = "0.4.14"
-kvm-ioctls = {  version = "0.8.0", 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}

hypervisor/src/arch/emulator/mod.rs

@@ -4,8 +4,6 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-extern crate thiserror;
-
 use core::fmt::Debug;
 use std::fmt::{self, Display};
 use thiserror::Error;

hypervisor/src/arch/x86/emulator/instructions/cmp.rs

@@ -10,8 +10,6 @@
 // CMP-Compare Two Operands
 //
 
-extern crate iced_x86;
-
 use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::regs::*;

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

@@ -4,8 +4,6 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-extern crate iced_x86;
-
 use crate::arch::emulator::{EmulationError, PlatformEmulator, PlatformError};
 use crate::arch::x86::emulator::CpuStateManager;
 use crate::arch::x86::Exception;
@@ -14,6 +12,7 @@ use iced_x86::*;
 pub mod cmp;
 pub mod mov;
 pub mod movs;
+pub mod or;
 
 fn get_op<T: CpuStateManager>(
     insn: &Instruction,

hypervisor/src/arch/x86/emulator/instructions/mov.rs

@@ -12,8 +12,6 @@
 //   Copies the second operand (source operand) to the first operand (destination operand).
 //
 
-extern crate iced_x86;
-
 use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::Exception;

hypervisor/src/arch/x86/emulator/instructions/movs.rs

@@ -10,8 +10,6 @@
 // MOVS - Move Data from String to String
 //
 
-extern crate iced_x86;
-
 use crate::arch::emulator::{EmulationError, PlatformEmulator};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::regs::DF;

hypervisor/src/arch/x86/emulator/instructions/or.rs

@@ -0,0 +1,83 @@
+//
+// Copyright © 2021 Microsoft
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+#![allow(non_camel_case_types)]
+
+//
+// OR - Logical inclusive OR
+//
+
+use crate::arch::emulator::{EmulationError, PlatformEmulator};
+use crate::arch::x86::emulator::instructions::*;
+use crate::arch::x86::Exception;
+
+macro_rules! or_rm_r {
+    ($bound:ty) => {
+        fn emulate(
+            &self,
+            insn: &Instruction,
+            state: &mut T,
+            platform: &mut dyn PlatformEmulator<CpuState = T>,
+        ) -> Result<(), EmulationError<Exception>> {
+            let src_reg_value = get_op(&insn, 1, std::mem::size_of::<$bound>(), state, platform)
+                .map_err(EmulationError::PlatformEmulationError)?;
+
+            let dst_value = get_op(&insn, 0, std::mem::size_of::<$bound>(), state, platform)
+                .map_err(EmulationError::PlatformEmulationError)?;
+
+            let result = src_reg_value | dst_value;
+
+            set_op(
+                &insn,
+                0,
+                std::mem::size_of::<$bound>(),
+                state,
+                platform,
+                result,
+            )
+            .map_err(EmulationError::PlatformEmulationError)?;
+
+            Ok(())
+        }
+    };
+}
+
+pub struct Or_rm8_r8;
+impl<T: CpuStateManager> InstructionHandler<T> for Or_rm8_r8 {
+    or_rm_r!(u8);
+}
+
+#[cfg(test)]
+mod tests {
+    #![allow(unused_mut)]
+    use super::*;
+
+    use crate::arch::x86::emulator::mock_vmm::*;
+
+    #[test]
+    // or byte ptr [rax+1h], sil
+    fn test_or_rm8_r8() {
+        let rax = 0;
+        let insn = [0x40, 0x08, 0x70, 0x1];
+        let cpu_id = 0;
+        let ip: u64 = 0x1000;
+        let sil = 0xaa;
+        let memory = [0x0, 0x55];
+
+        let mut vmm = MockVmm::new(
+            ip,
+            vec![(Register::SIL, sil), (Register::RAX, rax)],
+            Some((0, &memory)),
+        );
+
+        assert!(vmm.emulate_first_insn(cpu_id, &insn).is_ok());
+
+        let mut out: [u8; 1] = [0; 1];
+
+        vmm.read_memory(rax + 1, &mut out).unwrap();
+        assert_eq!(u8::from_le_bytes(out), 0xff);
+    }
+}

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

@@ -4,8 +4,6 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-extern crate iced_x86;
-
 use crate::arch::emulator::{EmulationError, EmulationResult, PlatformEmulator, PlatformError};
 use crate::arch::x86::emulator::instructions::*;
 use crate::arch::x86::regs::*;
@@ -526,7 +524,9 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
             (mov, Movzx_r32_rm16),
             (mov, Movzx_r64_rm16),
             // MOVS
-            (movs, Movsd_m32_m32)
+            (movs, Movsd_m32_m32),
+            // OR
+            (or, Or_rm8_r8)
         );
 
         handler
@@ -640,8 +640,6 @@ impl<'a, T: CpuStateManager> Emulator<'a, T> {
 mod mock_vmm {
     #![allow(unused_mut)]
 
-    extern crate env_logger;
-
     use super::*;
     use crate::arch::emulator::{EmulationError, PlatformEmulator};
     use crate::arch::x86::emulator::{Emulator, EmulatorCpuState as CpuState};
@@ -718,7 +716,7 @@ mod mock_vmm {
                 "Memory read {} bytes from [{:#x} -> {:#x}]",
                 data.len(),
                 gva,
-                gva
+                gva + data.len() as u64 - 1
             );
             data.copy_from_slice(&self.memory[gva as usize..gva as usize + data.len()]);
             Ok(())
@@ -729,7 +727,7 @@ mod mock_vmm {
                 "Memory write {} bytes at [{:#x} -> {:#x}]",
                 data.len(),
                 gva,
-                gva
+                gva + data.len() as u64 - 1
             );
             self.memory[gva as usize..gva as usize + data.len()].copy_from_slice(data);
 

hypervisor/src/hypervisor.rs

@@ -12,8 +12,6 @@ use crate::vm::Vm;
 use crate::x86_64::CpuId;
 #[cfg(target_arch = "x86_64")]
 use crate::x86_64::MsrList;
-#[cfg(all(feature = "kvm", target_arch = "x86_64"))]
-use kvm_ioctls::Cap;
 use std::sync::Arc;
 use thiserror::Error;
 
@@ -42,16 +40,6 @@ pub enum HypervisorError {
     #[error("Failed to get API Version: {0}")]
     GetApiVersion(#[source] anyhow::Error),
     ///
-    /// Vcpu mmap error
-    ///
-    #[error("Failed to get Vcpu Mmap: {0}")]
-    GetVcpuMmap(#[source] anyhow::Error),
-    ///
-    /// Max Vcpu error
-    ///
-    #[error("Failed to get number of max vcpus: {0}")]
-    GetMaxVcpu(#[source] anyhow::Error),
-    ///
     /// CpuId error
     ///
     #[error("Failed to get cpuid: {0}")]
@@ -66,6 +54,11 @@ pub enum HypervisorError {
     ///
     #[error("Incompatible API version")]
     IncompatibleApiVersion,
+    ///
+    /// Checking extensions failed
+    ///
+    #[error("Checking extensions:{0}")]
+    CheckExtensions(#[source] anyhow::Error),
 }
 
 ///
@@ -84,45 +77,32 @@ pub trait Hypervisor: Send + Sync {
     /// Return a hypervisor-agnostic Vm trait object
     ///
     fn create_vm(&self) -> Result<Arc<dyn Vm>>;
-    #[cfg(feature = "kvm")]
     ///
     /// Create a Vm of a specific type using the underlying hypervisor
     /// Return a hypervisor-agnostic Vm trait object
     ///
-    fn create_vm_with_type(&self, vm_type: u64) -> Result<Arc<dyn Vm>>;
-    #[cfg(feature = "kvm")]
-    ///
-    /// Returns the size of the memory mapping required to use the vcpu's structures
-    ///
-    fn get_vcpu_mmap_size(&self) -> Result<usize>;
-    #[cfg(feature = "kvm")]
-    ///
-    /// Gets the recommended maximum number of VCPUs per VM.
-    ///
-    fn get_max_vcpus(&self) -> Result<usize>;
-    #[cfg(feature = "kvm")]
-    ///
-    /// Gets the recommended number of VCPUs per VM.
-    ///
-    fn get_nr_vcpus(&self) -> Result<usize>;
-    #[cfg(all(feature = "kvm", target_arch = "x86_64"))]
-    ///
-    /// Checks if a particular `Cap` is available.
-    ///
-    fn check_capability(&self, c: Cap) -> bool;
+    fn create_vm_with_type(&self, _vm_type: u64) -> Result<Arc<dyn Vm>> {
+        unreachable!()
+    }
     #[cfg(target_arch = "x86_64")]
     ///
     /// Get the supported CpuID
     ///
     fn get_cpuid(&self) -> Result<CpuId>;
-    #[cfg(not(feature = "mshv"))]
     ///
     /// Check particular extensions if any
     ///
-    fn check_required_extensions(&self) -> Result<()>;
+    fn check_required_extensions(&self) -> Result<()> {
+        Ok(())
+    }
     #[cfg(target_arch = "x86_64")]
     ///
     /// Retrieve the list of MSRs supported by the hypervisor.
     ///
     fn get_msr_list(&self) -> Result<MsrList>;
+    #[cfg(target_arch = "aarch64")]
+    ///
+    /// Retrieve AArch64 host maximum IPA size supported by KVM.
+    ///
+    fn get_host_ipa_limit(&self) -> i32;
 }

hypervisor/src/kvm/aarch64/mod.rs

@@ -32,19 +32,17 @@ pub use {kvm_ioctls::Cap, kvm_ioctls::Kvm};
 
 // This macro gets the offset of a structure (i.e `str`) member (i.e `field`) without having
 // an instance of that structure.
-// It uses a null pointer to retrieve the offset to the field.
-// Inspired by C solution: `#define offsetof(str, f) ((size_t)(&((str *)0)->f))`.
-// Doing `offset__of!(user_pt_regs, pstate)` in our rust code will trigger the following:
-// unsafe { &(*(0 as *const user_pt_regs)).pstate as *const _ as usize }
-// The dereference expression produces an lvalue, but that lvalue is not actually read from,
-// we're just doing pointer math on it, so in theory, it should safe.
 #[macro_export]
 macro_rules! offset__of {
-    ($str:ty, $field:ident) => {
-        unsafe { &(*std::ptr::null::<$str>()).$field as *const _ as usize }
-    };
-}
+    ($str:ty, $($field:ident)+) => ({
+        let tmp: std::mem::MaybeUninit<$str> = std::mem::MaybeUninit::uninit();
+        let tmp = unsafe { tmp.assume_init() };
+        let base = &tmp as *const _ as usize;
+        let member =  &tmp.$($field)* as *const _ as usize;
 
+        member - base
+    });
+}
 // Get the ID of a core register
 #[macro_export]
 macro_rules! arm64_core_reg_id {

hypervisor/src/kvm/mod.rs

@@ -22,6 +22,8 @@ use crate::vm::{self, VmmOps};
 use crate::{arm64_core_reg_id, offset__of};
 use kvm_ioctls::{NoDatamatch, VcpuFd, VmFd};
 use serde_derive::{Deserialize, Serialize};
+#[cfg(target_arch = "aarch64")]
+use std::convert::TryInto;
 use std::os::unix::io::{AsRawFd, RawFd};
 use std::result;
 #[cfg(target_arch = "x86_64")]
@@ -70,9 +72,9 @@ pub use kvm_ioctls;
 pub use kvm_ioctls::{Cap, Kvm};
 #[cfg(target_arch = "aarch64")]
 use std::mem;
+use thiserror::Error;
 #[cfg(feature = "tdx")]
 use vmm_sys_util::{ioctl::ioctl_with_val, ioctl_expr, ioctl_ioc_nr, ioctl_iowr_nr};
-
 ///
 /// Export generically-named wrappers of kvm-bindings for Unix-based platforms
 ///
@@ -373,7 +375,7 @@ impl vm::Vm for KvmVm {
         let data = TdxInitVm {
             max_vcpus,
             reserved: 0,
-            attributes: 0,
+            attributes: 1, // TDX1_TD_ATTRIBUTE_DEBUG,
             cpuid: cpuid.as_fam_struct_ptr() as u64,
         };
 
@@ -465,8 +467,9 @@ pub struct KvmHypervisor {
     kvm: Kvm,
 }
 /// Enum for KVM related error
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum KvmError {
+    #[error("Capability missing: {0:?}")]
     CapabilityMissing(Cap),
 }
 pub type KvmResult<T> = result::Result<T, KvmError>;
@@ -557,41 +560,25 @@ impl hypervisor::Hypervisor for KvmHypervisor {
     /// let vm = hypervisor.create_vm().unwrap()
     ///
     fn create_vm(&self) -> hypervisor::Result<Arc<dyn vm::Vm>> {
-        self.create_vm_with_type(0) // Create with default platform type
+        #[allow(unused_mut)]
+        let mut vm_type: u64 = 0; // Create with default platform type
+
+        // When KVM supports Cap::ArmVmIPASize, it is better to get the IPA
+        // size from the host and use that when creating the VM, which may
+        // avoid unnecessary VM creation failures.
+        #[cfg(target_arch = "aarch64")]
+        if self.kvm.check_extension(Cap::ArmVmIPASize) {
+            vm_type = self.kvm.get_host_ipa_limit().try_into().unwrap();
+        }
+
+        self.create_vm_with_type(vm_type)
     }
 
     fn check_required_extensions(&self) -> hypervisor::Result<()> {
-        check_required_kvm_extensions(&self.kvm).expect("Missing KVM capabilities");
-        Ok(())
+        check_required_kvm_extensions(&self.kvm)
+            .map_err(|e| hypervisor::HypervisorError::CheckExtensions(e.into()))
     }
 
-    ///
-    ///  Returns the size of the memory mapping required to use the vcpu's `kvm_run` structure.
-    ///
-    fn get_vcpu_mmap_size(&self) -> hypervisor::Result<usize> {
-        self.kvm
-            .get_vcpu_mmap_size()
-            .map_err(|e| hypervisor::HypervisorError::GetVcpuMmap(e.into()))
-    }
-    ///
-    /// Gets the recommended maximum number of VCPUs per VM.
-    ///
-    fn get_max_vcpus(&self) -> hypervisor::Result<usize> {
-        Ok(self.kvm.get_max_vcpus())
-    }
-    ///
-    /// Gets the recommended number of VCPUs per VM.
-    ///
-    fn get_nr_vcpus(&self) -> hypervisor::Result<usize> {
-        Ok(self.kvm.get_nr_vcpus())
-    }
-    #[cfg(target_arch = "x86_64")]
-    ///
-    /// Checks if a particular `Cap` is available.
-    ///
-    fn check_capability(&self, c: Cap) -> bool {
-        self.kvm.check_extension(c)
-    }
     #[cfg(target_arch = "x86_64")]
     ///
     /// X86 specific call to get the system supported CPUID values.
@@ -601,6 +588,7 @@ impl hypervisor::Hypervisor for KvmHypervisor {
             .get_supported_cpuid(kvm_bindings::KVM_MAX_CPUID_ENTRIES)
             .map_err(|e| hypervisor::HypervisorError::GetCpuId(e.into()))
     }
+
     #[cfg(target_arch = "x86_64")]
     ///
     /// Retrieve the list of MSRs supported by KVM.
@@ -610,6 +598,13 @@ impl hypervisor::Hypervisor for KvmHypervisor {
             .get_msr_index_list()
             .map_err(|e| hypervisor::HypervisorError::GetMsrList(e.into()))
     }
+    #[cfg(target_arch = "aarch64")]
+    ///
+    /// Retrieve AArch64 host maximum IPA size supported by KVM.
+    ///
+    fn get_host_ipa_limit(&self) -> i32 {
+        self.kvm.get_host_ipa_limit()
+    }
 }
 /// Vcpu struct for KVM
 pub struct KvmVcpu {

hypervisor/src/lib.rs

@@ -23,10 +23,6 @@ extern crate anyhow;
 #[cfg(target_arch = "x86_64")]
 #[macro_use]
 extern crate log;
-extern crate serde;
-extern crate serde_derive;
-extern crate serde_json;
-extern crate thiserror;
 
 /// Architecture specific definitions
 #[macro_use]

hypervisor/src/mshv/mod.rs

@@ -473,7 +473,7 @@ impl cpu::Vcpu for MshvVcpu {
     ///
     fn set_xsave(&self, xsave: &Xsave) -> cpu::Result<()> {
         self.fd
-            .set_xsave(*xsave)
+            .set_xsave(xsave)
             .map_err(|e| cpu::HypervisorCpuError::SetXsaveState(e.into()))
     }
     ///

net_gen/Cargo.toml

@@ -2,6 +2,7 @@
 name = "net_gen"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
+edition = "2018"
 
 [dependencies]
 vmm-sys-util = ">=0.3.1"

net_gen/src/if_tun.rs

@@ -1,24 +1,27 @@
-// Copyright 2017 The Chromium OS Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the THIRD-PARTY file.
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
 
-/* automatically generated by rust-bindgen */
+// bindgen /usr/include/linux/if_tun.h --no-layout-tests
+
+/* automatically generated by rust-bindgen 0.58.1 */
 
 #[repr(C)]
 #[derive(Default)]
-pub struct __IncompleteArrayField<T>(::std::marker::PhantomData<T>);
+pub struct __IncompleteArrayField<T>(::std::marker::PhantomData<T>, [T; 0]);
 impl<T> __IncompleteArrayField<T> {
     #[inline]
-    pub fn new() -> Self {
-        __IncompleteArrayField(::std::marker::PhantomData)
+    pub const fn new() -> Self {
+        __IncompleteArrayField(::std::marker::PhantomData, [])
     }
     #[inline]
-    pub unsafe fn as_ptr(&self) -> *const T {
-        ::std::mem::transmute(self)
+    pub fn as_ptr(&self) -> *const T {
+        self as *const _ as *const T
     }
     #[inline]
-    pub unsafe fn as_mut_ptr(&mut self) -> *mut T {
-        ::std::mem::transmute(self)
+    pub fn as_mut_ptr(&mut self) -> *mut T {
+        self as *mut _ as *mut T
     }
     #[inline]
     pub unsafe fn as_slice(&self, len: usize) -> &[T] {
@@ -30,191 +33,203 @@ impl<T> __IncompleteArrayField<T> {
     }
 }
 impl<T> ::std::fmt::Debug for __IncompleteArrayField<T> {
-    fn fmt(&self, fmt: &mut ::std::fmt::Formatter) -> ::std::fmt::Result {
+    fn fmt(&self, fmt: &mut ::std::fmt::Formatter<'_>) -> ::std::fmt::Result {
         fmt.write_str("__IncompleteArrayField")
     }
 }
-impl<T> ::std::clone::Clone for __IncompleteArrayField<T> {
-    #[inline]
-    fn clone(&self) -> Self {
-        Self::new()
-    }
-}
-impl<T> ::std::marker::Copy for __IncompleteArrayField<T> {}
-pub const __BITS_PER_LONG: ::std::os::raw::c_uint = 64;
-pub const __FD_SETSIZE: ::std::os::raw::c_uint = 1024;
-pub const ETH_ALEN: ::std::os::raw::c_uint = 6;
-pub const ETH_HLEN: ::std::os::raw::c_uint = 14;
-pub const ETH_ZLEN: ::std::os::raw::c_uint = 60;
-pub const ETH_DATA_LEN: ::std::os::raw::c_uint = 1500;
-pub const ETH_FRAME_LEN: ::std::os::raw::c_uint = 1514;
-pub const ETH_FCS_LEN: ::std::os::raw::c_uint = 4;
-pub const ETH_P_LOOP: ::std::os::raw::c_uint = 96;
-pub const ETH_P_PUP: ::std::os::raw::c_uint = 512;
-pub const ETH_P_PUPAT: ::std::os::raw::c_uint = 513;
-pub const ETH_P_TSN: ::std::os::raw::c_uint = 8944;
-pub const ETH_P_IP: ::std::os::raw::c_uint = 2048;
-pub const ETH_P_X25: ::std::os::raw::c_uint = 2053;
-pub const ETH_P_ARP: ::std::os::raw::c_uint = 2054;
-pub const ETH_P_BPQ: ::std::os::raw::c_uint = 2303;
-pub const ETH_P_IEEEPUP: ::std::os::raw::c_uint = 2560;
-pub const ETH_P_IEEEPUPAT: ::std::os::raw::c_uint = 2561;
-pub const ETH_P_BATMAN: ::std::os::raw::c_uint = 17157;
-pub const ETH_P_DEC: ::std::os::raw::c_uint = 24576;
-pub const ETH_P_DNA_DL: ::std::os::raw::c_uint = 24577;
-pub const ETH_P_DNA_RC: ::std::os::raw::c_uint = 24578;
-pub const ETH_P_DNA_RT: ::std::os::raw::c_uint = 24579;
-pub const ETH_P_LAT: ::std::os::raw::c_uint = 24580;
-pub const ETH_P_DIAG: ::std::os::raw::c_uint = 24581;
-pub const ETH_P_CUST: ::std::os::raw::c_uint = 24582;
-pub const ETH_P_SCA: ::std::os::raw::c_uint = 24583;
-pub const ETH_P_TEB: ::std::os::raw::c_uint = 25944;
-pub const ETH_P_RARP: ::std::os::raw::c_uint = 32821;
-pub const ETH_P_ATALK: ::std::os::raw::c_uint = 32923;
-pub const ETH_P_AARP: ::std::os::raw::c_uint = 33011;
-pub const ETH_P_8021Q: ::std::os::raw::c_uint = 33024;
-pub const ETH_P_IPX: ::std::os::raw::c_uint = 33079;
-pub const ETH_P_IPV6: ::std::os::raw::c_uint = 34525;
-pub const ETH_P_PAUSE: ::std::os::raw::c_uint = 34824;
-pub const ETH_P_SLOW: ::std::os::raw::c_uint = 34825;
-pub const ETH_P_WCCP: ::std::os::raw::c_uint = 34878;
-pub const ETH_P_MPLS_UC: ::std::os::raw::c_uint = 34887;
-pub const ETH_P_MPLS_MC: ::std::os::raw::c_uint = 34888;
-pub const ETH_P_ATMMPOA: ::std::os::raw::c_uint = 34892;
-pub const ETH_P_PPP_DISC: ::std::os::raw::c_uint = 34915;
-pub const ETH_P_PPP_SES: ::std::os::raw::c_uint = 34916;
-pub const ETH_P_LINK_CTL: ::std::os::raw::c_uint = 34924;
-pub const ETH_P_ATMFATE: ::std::os::raw::c_uint = 34948;
-pub const ETH_P_PAE: ::std::os::raw::c_uint = 34958;
-pub const ETH_P_AOE: ::std::os::raw::c_uint = 34978;
-pub const ETH_P_8021AD: ::std::os::raw::c_uint = 34984;
-pub const ETH_P_802_EX1: ::std::os::raw::c_uint = 34997;
-pub const ETH_P_TIPC: ::std::os::raw::c_uint = 35018;
-pub const ETH_P_8021AH: ::std::os::raw::c_uint = 35047;
-pub const ETH_P_MVRP: ::std::os::raw::c_uint = 35061;
-pub const ETH_P_1588: ::std::os::raw::c_uint = 35063;
-pub const ETH_P_PRP: ::std::os::raw::c_uint = 35067;
-pub const ETH_P_FCOE: ::std::os::raw::c_uint = 35078;
-pub const ETH_P_TDLS: ::std::os::raw::c_uint = 35085;
-pub const ETH_P_FIP: ::std::os::raw::c_uint = 35092;
-pub const ETH_P_80221: ::std::os::raw::c_uint = 35095;
-pub const ETH_P_LOOPBACK: ::std::os::raw::c_uint = 36864;
-pub const ETH_P_QINQ1: ::std::os::raw::c_uint = 37120;
-pub const ETH_P_QINQ2: ::std::os::raw::c_uint = 37376;
-pub const ETH_P_QINQ3: ::std::os::raw::c_uint = 37632;
-pub const ETH_P_EDSA: ::std::os::raw::c_uint = 56026;
-pub const ETH_P_AF_IUCV: ::std::os::raw::c_uint = 64507;
-pub const ETH_P_802_3_MIN: ::std::os::raw::c_uint = 1536;
-pub const ETH_P_802_3: ::std::os::raw::c_uint = 1;
-pub const ETH_P_AX25: ::std::os::raw::c_uint = 2;
-pub const ETH_P_ALL: ::std::os::raw::c_uint = 3;
-pub const ETH_P_802_2: ::std::os::raw::c_uint = 4;
-pub const ETH_P_SNAP: ::std::os::raw::c_uint = 5;
-pub const ETH_P_DDCMP: ::std::os::raw::c_uint = 6;
-pub const ETH_P_WAN_PPP: ::std::os::raw::c_uint = 7;
-pub const ETH_P_PPP_MP: ::std::os::raw::c_uint = 8;
-pub const ETH_P_LOCALTALK: ::std::os::raw::c_uint = 9;
-pub const ETH_P_CAN: ::std::os::raw::c_uint = 12;
-pub const ETH_P_CANFD: ::std::os::raw::c_uint = 13;
-pub const ETH_P_PPPTALK: ::std::os::raw::c_uint = 16;
-pub const ETH_P_TR_802_2: ::std::os::raw::c_uint = 17;
-pub const ETH_P_MOBITEX: ::std::os::raw::c_uint = 21;
-pub const ETH_P_CONTROL: ::std::os::raw::c_uint = 22;
-pub const ETH_P_IRDA: ::std::os::raw::c_uint = 23;
-pub const ETH_P_ECONET: ::std::os::raw::c_uint = 24;
-pub const ETH_P_HDLC: ::std::os::raw::c_uint = 25;
-pub const ETH_P_ARCNET: ::std::os::raw::c_uint = 26;
-pub const ETH_P_DSA: ::std::os::raw::c_uint = 27;
-pub const ETH_P_TRAILER: ::std::os::raw::c_uint = 28;
-pub const ETH_P_PHONET: ::std::os::raw::c_uint = 245;
-pub const ETH_P_IEEE802154: ::std::os::raw::c_uint = 246;
-pub const ETH_P_CAIF: ::std::os::raw::c_uint = 247;
-pub const ETH_P_XDSA: ::std::os::raw::c_uint = 248;
-pub const BPF_LD: ::std::os::raw::c_uint = 0;
-pub const BPF_LDX: ::std::os::raw::c_uint = 1;
-pub const BPF_ST: ::std::os::raw::c_uint = 2;
-pub const BPF_STX: ::std::os::raw::c_uint = 3;
-pub const BPF_ALU: ::std::os::raw::c_uint = 4;
-pub const BPF_JMP: ::std::os::raw::c_uint = 5;
-pub const BPF_RET: ::std::os::raw::c_uint = 6;
-pub const BPF_MISC: ::std::os::raw::c_uint = 7;
-pub const BPF_W: ::std::os::raw::c_uint = 0;
-pub const BPF_H: ::std::os::raw::c_uint = 8;
-pub const BPF_B: ::std::os::raw::c_uint = 16;
-pub const BPF_IMM: ::std::os::raw::c_uint = 0;
-pub const BPF_ABS: ::std::os::raw::c_uint = 32;
-pub const BPF_IND: ::std::os::raw::c_uint = 64;
-pub const BPF_MEM: ::std::os::raw::c_uint = 96;
-pub const BPF_LEN: ::std::os::raw::c_uint = 128;
-pub const BPF_MSH: ::std::os::raw::c_uint = 160;
-pub const BPF_ADD: ::std::os::raw::c_uint = 0;
-pub const BPF_SUB: ::std::os::raw::c_uint = 16;
-pub const BPF_MUL: ::std::os::raw::c_uint = 32;
-pub const BPF_DIV: ::std::os::raw::c_uint = 48;
-pub const BPF_OR: ::std::os::raw::c_uint = 64;
-pub const BPF_AND: ::std::os::raw::c_uint = 80;
-pub const BPF_LSH: ::std::os::raw::c_uint = 96;
-pub const BPF_RSH: ::std::os::raw::c_uint = 112;
-pub const BPF_NEG: ::std::os::raw::c_uint = 128;
-pub const BPF_MOD: ::std::os::raw::c_uint = 144;
-pub const BPF_XOR: ::std::os::raw::c_uint = 160;
-pub const BPF_JA: ::std::os::raw::c_uint = 0;
-pub const BPF_JEQ: ::std::os::raw::c_uint = 16;
-pub const BPF_JGT: ::std::os::raw::c_uint = 32;
-pub const BPF_JGE: ::std::os::raw::c_uint = 48;
-pub const BPF_JSET: ::std::os::raw::c_uint = 64;
-pub const BPF_K: ::std::os::raw::c_uint = 0;
-pub const BPF_X: ::std::os::raw::c_uint = 8;
-pub const BPF_MAXINSNS: ::std::os::raw::c_uint = 4096;
-pub const BPF_MAJOR_VERSION: ::std::os::raw::c_uint = 1;
-pub const BPF_MINOR_VERSION: ::std::os::raw::c_uint = 1;
-pub const BPF_A: ::std::os::raw::c_uint = 16;
-pub const BPF_TAX: ::std::os::raw::c_uint = 0;
-pub const BPF_TXA: ::std::os::raw::c_uint = 128;
-pub const BPF_MEMWORDS: ::std::os::raw::c_uint = 16;
-pub const SKF_AD_OFF: ::std::os::raw::c_int = -4096;
-pub const SKF_AD_PROTOCOL: ::std::os::raw::c_uint = 0;
-pub const SKF_AD_PKTTYPE: ::std::os::raw::c_uint = 4;
-pub const SKF_AD_IFINDEX: ::std::os::raw::c_uint = 8;
-pub const SKF_AD_NLATTR: ::std::os::raw::c_uint = 12;
-pub const SKF_AD_NLATTR_NEST: ::std::os::raw::c_uint = 16;
-pub const SKF_AD_MARK: ::std::os::raw::c_uint = 20;
-pub const SKF_AD_QUEUE: ::std::os::raw::c_uint = 24;
-pub const SKF_AD_HATYPE: ::std::os::raw::c_uint = 28;
-pub const SKF_AD_RXHASH: ::std::os::raw::c_uint = 32;
-pub const SKF_AD_CPU: ::std::os::raw::c_uint = 36;
-pub const SKF_AD_ALU_XOR_X: ::std::os::raw::c_uint = 40;
-pub const SKF_AD_VLAN_TAG: ::std::os::raw::c_uint = 44;
-pub const SKF_AD_VLAN_TAG_PRESENT: ::std::os::raw::c_uint = 48;
-pub const SKF_AD_PAY_OFFSET: ::std::os::raw::c_uint = 52;
-pub const SKF_AD_RANDOM: ::std::os::raw::c_uint = 56;
-pub const SKF_AD_VLAN_TPID: ::std::os::raw::c_uint = 60;
-pub const SKF_AD_MAX: ::std::os::raw::c_uint = 64;
-pub const SKF_NET_OFF: ::std::os::raw::c_int = -1048576;
-pub const SKF_LL_OFF: ::std::os::raw::c_int = -2097152;
-pub const BPF_NET_OFF: ::std::os::raw::c_int = -1048576;
-pub const BPF_LL_OFF: ::std::os::raw::c_int = -2097152;
-pub const TUN_READQ_SIZE: ::std::os::raw::c_uint = 500;
-pub const TUN_TYPE_MASK: ::std::os::raw::c_uint = 15;
-pub const IFF_TUN: ::std::os::raw::c_uint = 1;
-pub const IFF_TAP: ::std::os::raw::c_uint = 2;
-pub const IFF_NO_PI: ::std::os::raw::c_uint = 4096;
-pub const IFF_ONE_QUEUE: ::std::os::raw::c_uint = 8192;
-pub const IFF_VNET_HDR: ::std::os::raw::c_uint = 16384;
-pub const IFF_TUN_EXCL: ::std::os::raw::c_uint = 32768;
-pub const IFF_MULTI_QUEUE: ::std::os::raw::c_uint = 256;
-pub const IFF_ATTACH_QUEUE: ::std::os::raw::c_uint = 512;
-pub const IFF_DETACH_QUEUE: ::std::os::raw::c_uint = 1024;
-pub const IFF_PERSIST: ::std::os::raw::c_uint = 2048;
-pub const IFF_NOFILTER: ::std::os::raw::c_uint = 4096;
-pub const TUN_TX_TIMESTAMP: ::std::os::raw::c_uint = 1;
-pub const TUN_F_CSUM: ::std::os::raw::c_uint = 1;
-pub const TUN_F_TSO4: ::std::os::raw::c_uint = 2;
-pub const TUN_F_TSO6: ::std::os::raw::c_uint = 4;
-pub const TUN_F_TSO_ECN: ::std::os::raw::c_uint = 8;
-pub const TUN_F_UFO: ::std::os::raw::c_uint = 16;
-pub const TUN_PKT_STRIP: ::std::os::raw::c_uint = 1;
-pub const TUN_FLT_ALLMULTI: ::std::os::raw::c_uint = 1;
+pub const __BITS_PER_LONG: u32 = 64;
+pub const __FD_SETSIZE: u32 = 1024;
+pub const ETH_ALEN: u32 = 6;
+pub const ETH_TLEN: u32 = 2;
+pub const ETH_HLEN: u32 = 14;
+pub const ETH_ZLEN: u32 = 60;
+pub const ETH_DATA_LEN: u32 = 1500;
+pub const ETH_FRAME_LEN: u32 = 1514;
+pub const ETH_FCS_LEN: u32 = 4;
+pub const ETH_MIN_MTU: u32 = 68;
+pub const ETH_MAX_MTU: u32 = 65535;
+pub const ETH_P_LOOP: u32 = 96;
+pub const ETH_P_PUP: u32 = 512;
+pub const ETH_P_PUPAT: u32 = 513;
+pub const ETH_P_TSN: u32 = 8944;
+pub const ETH_P_ERSPAN2: u32 = 8939;
+pub const ETH_P_IP: u32 = 2048;
+pub const ETH_P_X25: u32 = 2053;
+pub const ETH_P_ARP: u32 = 2054;
+pub const ETH_P_BPQ: u32 = 2303;
+pub const ETH_P_IEEEPUP: u32 = 2560;
+pub const ETH_P_IEEEPUPAT: u32 = 2561;
+pub const ETH_P_BATMAN: u32 = 17157;
+pub const ETH_P_DEC: u32 = 24576;
+pub const ETH_P_DNA_DL: u32 = 24577;
+pub const ETH_P_DNA_RC: u32 = 24578;
+pub const ETH_P_DNA_RT: u32 = 24579;
+pub const ETH_P_LAT: u32 = 24580;
+pub const ETH_P_DIAG: u32 = 24581;
+pub const ETH_P_CUST: u32 = 24582;
+pub const ETH_P_SCA: u32 = 24583;
+pub const ETH_P_TEB: u32 = 25944;
+pub const ETH_P_RARP: u32 = 32821;
+pub const ETH_P_ATALK: u32 = 32923;
+pub const ETH_P_AARP: u32 = 33011;
+pub const ETH_P_8021Q: u32 = 33024;
+pub const ETH_P_ERSPAN: u32 = 35006;
+pub const ETH_P_IPX: u32 = 33079;
+pub const ETH_P_IPV6: u32 = 34525;
+pub const ETH_P_PAUSE: u32 = 34824;
+pub const ETH_P_SLOW: u32 = 34825;
+pub const ETH_P_WCCP: u32 = 34878;
+pub const ETH_P_MPLS_UC: u32 = 34887;
+pub const ETH_P_MPLS_MC: u32 = 34888;
+pub const ETH_P_ATMMPOA: u32 = 34892;
+pub const ETH_P_PPP_DISC: u32 = 34915;
+pub const ETH_P_PPP_SES: u32 = 34916;
+pub const ETH_P_LINK_CTL: u32 = 34924;
+pub const ETH_P_ATMFATE: u32 = 34948;
+pub const ETH_P_PAE: u32 = 34958;
+pub const ETH_P_AOE: u32 = 34978;
+pub const ETH_P_8021AD: u32 = 34984;
+pub const ETH_P_802_EX1: u32 = 34997;
+pub const ETH_P_PREAUTH: u32 = 35015;
+pub const ETH_P_TIPC: u32 = 35018;
+pub const ETH_P_LLDP: u32 = 35020;
+pub const ETH_P_MRP: u32 = 35043;
+pub const ETH_P_MACSEC: u32 = 35045;
+pub const ETH_P_8021AH: u32 = 35047;
+pub const ETH_P_MVRP: u32 = 35061;
+pub const ETH_P_1588: u32 = 35063;
+pub const ETH_P_NCSI: u32 = 35064;
+pub const ETH_P_PRP: u32 = 35067;
+pub const ETH_P_FCOE: u32 = 35078;
+pub const ETH_P_IBOE: u32 = 35093;
+pub const ETH_P_TDLS: u32 = 35085;
+pub const ETH_P_FIP: u32 = 35092;
+pub const ETH_P_80221: u32 = 35095;
+pub const ETH_P_HSR: u32 = 35119;
+pub const ETH_P_NSH: u32 = 35151;
+pub const ETH_P_LOOPBACK: u32 = 36864;
+pub const ETH_P_QINQ1: u32 = 37120;
+pub const ETH_P_QINQ2: u32 = 37376;
+pub const ETH_P_QINQ3: u32 = 37632;
+pub const ETH_P_EDSA: u32 = 56026;
+pub const ETH_P_DSA_8021Q: u32 = 56027;
+pub const ETH_P_IFE: u32 = 60734;
+pub const ETH_P_AF_IUCV: u32 = 64507;
+pub const ETH_P_802_3_MIN: u32 = 1536;
+pub const ETH_P_802_3: u32 = 1;
+pub const ETH_P_AX25: u32 = 2;
+pub const ETH_P_ALL: u32 = 3;
+pub const ETH_P_802_2: u32 = 4;
+pub const ETH_P_SNAP: u32 = 5;
+pub const ETH_P_DDCMP: u32 = 6;
+pub const ETH_P_WAN_PPP: u32 = 7;
+pub const ETH_P_PPP_MP: u32 = 8;
+pub const ETH_P_LOCALTALK: u32 = 9;
+pub const ETH_P_CAN: u32 = 12;
+pub const ETH_P_CANFD: u32 = 13;
+pub const ETH_P_PPPTALK: u32 = 16;
+pub const ETH_P_TR_802_2: u32 = 17;
+pub const ETH_P_MOBITEX: u32 = 21;
+pub const ETH_P_CONTROL: u32 = 22;
+pub const ETH_P_IRDA: u32 = 23;
+pub const ETH_P_ECONET: u32 = 24;
+pub const ETH_P_HDLC: u32 = 25;
+pub const ETH_P_ARCNET: u32 = 26;
+pub const ETH_P_DSA: u32 = 27;
+pub const ETH_P_TRAILER: u32 = 28;
+pub const ETH_P_PHONET: u32 = 245;
+pub const ETH_P_IEEE802154: u32 = 246;
+pub const ETH_P_CAIF: u32 = 247;
+pub const ETH_P_XDSA: u32 = 248;
+pub const ETH_P_MAP: u32 = 249;
+pub const __UAPI_DEF_ETHHDR: u32 = 1;
+pub const BPF_LD: u32 = 0;
+pub const BPF_LDX: u32 = 1;
+pub const BPF_ST: u32 = 2;
+pub const BPF_STX: u32 = 3;
+pub const BPF_ALU: u32 = 4;
+pub const BPF_JMP: u32 = 5;
+pub const BPF_RET: u32 = 6;
+pub const BPF_MISC: u32 = 7;
+pub const BPF_W: u32 = 0;
+pub const BPF_H: u32 = 8;
+pub const BPF_B: u32 = 16;
+pub const BPF_IMM: u32 = 0;
+pub const BPF_ABS: u32 = 32;
+pub const BPF_IND: u32 = 64;
+pub const BPF_MEM: u32 = 96;
+pub const BPF_LEN: u32 = 128;
+pub const BPF_MSH: u32 = 160;
+pub const BPF_ADD: u32 = 0;
+pub const BPF_SUB: u32 = 16;
+pub const BPF_MUL: u32 = 32;
+pub const BPF_DIV: u32 = 48;
+pub const BPF_OR: u32 = 64;
+pub const BPF_AND: u32 = 80;
+pub const BPF_LSH: u32 = 96;
+pub const BPF_RSH: u32 = 112;
+pub const BPF_NEG: u32 = 128;
+pub const BPF_MOD: u32 = 144;
+pub const BPF_XOR: u32 = 160;
+pub const BPF_JA: u32 = 0;
+pub const BPF_JEQ: u32 = 16;
+pub const BPF_JGT: u32 = 32;
+pub const BPF_JGE: u32 = 48;
+pub const BPF_JSET: u32 = 64;
+pub const BPF_K: u32 = 0;
+pub const BPF_X: u32 = 8;
+pub const BPF_MAXINSNS: u32 = 4096;
+pub const BPF_MAJOR_VERSION: u32 = 1;
+pub const BPF_MINOR_VERSION: u32 = 1;
+pub const BPF_A: u32 = 16;
+pub const BPF_TAX: u32 = 0;
+pub const BPF_TXA: u32 = 128;
+pub const BPF_MEMWORDS: u32 = 16;
+pub const SKF_AD_OFF: i32 = -4096;
+pub const SKF_AD_PROTOCOL: u32 = 0;
+pub const SKF_AD_PKTTYPE: u32 = 4;
+pub const SKF_AD_IFINDEX: u32 = 8;
+pub const SKF_AD_NLATTR: u32 = 12;
+pub const SKF_AD_NLATTR_NEST: u32 = 16;
+pub const SKF_AD_MARK: u32 = 20;
+pub const SKF_AD_QUEUE: u32 = 24;
+pub const SKF_AD_HATYPE: u32 = 28;
+pub const SKF_AD_RXHASH: u32 = 32;
+pub const SKF_AD_CPU: u32 = 36;
+pub const SKF_AD_ALU_XOR_X: u32 = 40;
+pub const SKF_AD_VLAN_TAG: u32 = 44;
+pub const SKF_AD_VLAN_TAG_PRESENT: u32 = 48;
+pub const SKF_AD_PAY_OFFSET: u32 = 52;
+pub const SKF_AD_RANDOM: u32 = 56;
+pub const SKF_AD_VLAN_TPID: u32 = 60;
+pub const SKF_AD_MAX: u32 = 64;
+pub const SKF_NET_OFF: i32 = -1048576;
+pub const SKF_LL_OFF: i32 = -2097152;
+pub const BPF_NET_OFF: i32 = -1048576;
+pub const BPF_LL_OFF: i32 = -2097152;
+pub const TUN_READQ_SIZE: u32 = 500;
+pub const TUN_TYPE_MASK: u32 = 15;
+pub const IFF_TUN: u32 = 1;
+pub const IFF_TAP: u32 = 2;
+pub const IFF_NAPI: u32 = 16;
+pub const IFF_NAPI_FRAGS: u32 = 32;
+pub const IFF_NO_PI: u32 = 4096;
+pub const IFF_ONE_QUEUE: u32 = 8192;
+pub const IFF_VNET_HDR: u32 = 16384;
+pub const IFF_TUN_EXCL: u32 = 32768;
+pub const IFF_MULTI_QUEUE: u32 = 256;
+pub const IFF_ATTACH_QUEUE: u32 = 512;
+pub const IFF_DETACH_QUEUE: u32 = 1024;
+pub const IFF_PERSIST: u32 = 2048;
+pub const IFF_NOFILTER: u32 = 4096;
+pub const TUN_TX_TIMESTAMP: u32 = 1;
+pub const TUN_F_CSUM: u32 = 1;
+pub const TUN_F_TSO4: u32 = 2;
+pub const TUN_F_TSO6: u32 = 4;
+pub const TUN_F_TSO_ECN: u32 = 8;
+pub const TUN_F_UFO: u32 = 16;
+pub const TUN_PKT_STRIP: u32 = 1;
+pub const TUN_FLT_ALLMULTI: u32 = 1;
 pub type __s8 = ::std::os::raw::c_schar;
 pub type __u8 = ::std::os::raw::c_uchar;
 pub type __s16 = ::std::os::raw::c_short;
@@ -224,38 +239,10 @@ pub type __u32 = ::std::os::raw::c_uint;
 pub type __s64 = ::std::os::raw::c_longlong;
 pub type __u64 = ::std::os::raw::c_ulonglong;
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct __kernel_fd_set {
     pub fds_bits: [::std::os::raw::c_ulong; 16usize],
 }
-#[test]
-fn bindgen_test_layout___kernel_fd_set() {
-    assert_eq!(
-        ::std::mem::size_of::<__kernel_fd_set>(),
-        128usize,
-        concat!("Size of: ", stringify!(__kernel_fd_set))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<__kernel_fd_set>(),
-        8usize,
-        concat!("Alignment of ", stringify!(__kernel_fd_set))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const __kernel_fd_set)).fds_bits as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(__kernel_fd_set),
-            "::",
-            stringify!(fds_bits)
-        )
-    );
-}
-impl Clone for __kernel_fd_set {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 pub type __kernel_sighandler_t =
     ::std::option::Option<unsafe extern "C" fn(arg1: ::std::os::raw::c_int)>;
 pub type __kernel_key_t = ::std::os::raw::c_int;
@@ -279,41 +266,15 @@ pub type __kernel_size_t = __kernel_ulong_t;
 pub type __kernel_ssize_t = __kernel_long_t;
 pub type __kernel_ptrdiff_t = __kernel_long_t;
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct __kernel_fsid_t {
     pub val: [::std::os::raw::c_int; 2usize],
 }
-#[test]
-fn bindgen_test_layout___kernel_fsid_t() {
-    assert_eq!(
-        ::std::mem::size_of::<__kernel_fsid_t>(),
-        8usize,
-        concat!("Size of: ", stringify!(__kernel_fsid_t))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<__kernel_fsid_t>(),
-        4usize,
-        concat!("Alignment of ", stringify!(__kernel_fsid_t))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const __kernel_fsid_t)).val as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(__kernel_fsid_t),
-            "::",
-            stringify!(val)
-        )
-    );
-}
-impl Clone for __kernel_fsid_t {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 pub type __kernel_off_t = __kernel_long_t;
 pub type __kernel_loff_t = ::std::os::raw::c_longlong;
+pub type __kernel_old_time_t = __kernel_long_t;
 pub type __kernel_time_t = __kernel_long_t;
+pub type __kernel_time64_t = ::std::os::raw::c_longlong;
 pub type __kernel_clock_t = __kernel_long_t;
 pub type __kernel_timer_t = ::std::os::raw::c_int;
 pub type __kernel_clockid_t = ::std::os::raw::c_int;
@@ -328,272 +289,38 @@ pub type __le64 = __u64;
 pub type __be64 = __u64;
 pub type __sum16 = __u16;
 pub type __wsum = __u32;
+pub type __poll_t = ::std::os::raw::c_uint;
 #[repr(C, packed)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct ethhdr {
     pub h_dest: [::std::os::raw::c_uchar; 6usize],
     pub h_source: [::std::os::raw::c_uchar; 6usize],
     pub h_proto: __be16,
 }
-#[test]
-fn bindgen_test_layout_ethhdr() {
-    assert_eq!(
-        ::std::mem::size_of::<ethhdr>(),
-        14usize,
-        concat!("Size of: ", stringify!(ethhdr))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<ethhdr>(),
-        1usize,
-        concat!("Alignment of ", stringify!(ethhdr))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ethhdr)).h_dest as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ethhdr),
-            "::",
-            stringify!(h_dest)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ethhdr)).h_source as *const _ as usize },
-        6usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ethhdr),
-            "::",
-            stringify!(h_source)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ethhdr)).h_proto as *const _ as usize },
-        12usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ethhdr),
-            "::",
-            stringify!(h_proto)
-        )
-    );
-}
-impl Clone for ethhdr {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct sock_filter {
     pub code: __u16,
     pub jt: __u8,
     pub jf: __u8,
     pub k: __u32,
 }
-#[test]
-fn bindgen_test_layout_sock_filter() {
-    assert_eq!(
-        ::std::mem::size_of::<sock_filter>(),
-        8usize,
-        concat!("Size of: ", stringify!(sock_filter))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<sock_filter>(),
-        4usize,
-        concat!("Alignment of ", stringify!(sock_filter))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sock_filter)).code as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sock_filter),
-            "::",
-            stringify!(code)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sock_filter)).jt as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sock_filter),
-            "::",
-            stringify!(jt)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sock_filter)).jf as *const _ as usize },
-        3usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sock_filter),
-            "::",
-            stringify!(jf)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sock_filter)).k as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sock_filter),
-            "::",
-            stringify!(k)
-        )
-    );
-}
-impl Clone for sock_filter {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct sock_fprog {
     pub len: ::std::os::raw::c_ushort,
     pub filter: *mut sock_filter,
 }
-#[test]
-fn bindgen_test_layout_sock_fprog() {
-    assert_eq!(
-        ::std::mem::size_of::<sock_fprog>(),
-        16usize,
-        concat!("Size of: ", stringify!(sock_fprog))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<sock_fprog>(),
-        8usize,
-        concat!("Alignment of ", stringify!(sock_fprog))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sock_fprog)).len as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sock_fprog),
-            "::",
-            stringify!(len)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sock_fprog)).filter as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sock_fprog),
-            "::",
-            stringify!(filter)
-        )
-    );
-}
-impl Clone for sock_fprog {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-impl Default for sock_fprog {
-    fn default() -> Self {
-        unsafe { ::std::mem::zeroed() }
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct tun_pi {
     pub flags: __u16,
     pub proto: __be16,
 }
-#[test]
-fn bindgen_test_layout_tun_pi() {
-    assert_eq!(
-        ::std::mem::size_of::<tun_pi>(),
-        4usize,
-        concat!("Size of: ", stringify!(tun_pi))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<tun_pi>(),
-        2usize,
-        concat!("Alignment of ", stringify!(tun_pi))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const tun_pi)).flags as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(tun_pi),
-            "::",
-            stringify!(flags)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const tun_pi)).proto as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(tun_pi),
-            "::",
-            stringify!(proto)
-        )
-    );
-}
-impl Clone for tun_pi {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug)]
 pub struct tun_filter {
     pub flags: __u16,
     pub count: __u16,
     pub addr: __IncompleteArrayField<[__u8; 6usize]>,
 }
-#[test]
-fn bindgen_test_layout_tun_filter() {
-    assert_eq!(
-        ::std::mem::size_of::<tun_filter>(),
-        4usize,
-        concat!("Size of: ", stringify!(tun_filter))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<tun_filter>(),
-        2usize,
-        concat!("Alignment of ", stringify!(tun_filter))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const tun_filter)).flags as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(tun_filter),
-            "::",
-            stringify!(flags)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const tun_filter)).count as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(tun_filter),
-            "::",
-            stringify!(count)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const tun_filter)).addr as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(tun_filter),
-            "::",
-            stringify!(addr)
-        )
-    );
-}
-impl Clone for tun_filter {
-    fn clone(&self) -> Self {
-        *self
-    }
-}

net_gen/src/inn.rs

@@ -1,103 +1,119 @@
-// Copyright 2017 The Chromium OS Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the THIRD-PARTY file.
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
 
-/* automatically generated by rust-bindgen */
+// bindgen /usr/include/linux/in.h --no-layout-tests
 
-pub const __BITS_PER_LONG: ::std::os::raw::c_uint = 64;
-pub const __FD_SETSIZE: ::std::os::raw::c_uint = 1024;
-pub const __UAPI_DEF_IN_ADDR: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IN_IPPROTO: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IN_PKTINFO: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IP_MREQ: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_SOCKADDR_IN: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IN_CLASS: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IN6_ADDR: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IN6_ADDR_ALT: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_SOCKADDR_IN6: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IPV6_MREQ: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IPPROTO_V6: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IPV6_OPTIONS: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IN6_PKTINFO: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_IP6_MTUINFO: ::std::os::raw::c_uint = 1;
-pub const __UAPI_DEF_XATTR: ::std::os::raw::c_uint = 1;
-pub const _K_SS_MAXSIZE: ::std::os::raw::c_uint = 128;
-pub const IP_TOS: ::std::os::raw::c_uint = 1;
-pub const IP_TTL: ::std::os::raw::c_uint = 2;
-pub const IP_HDRINCL: ::std::os::raw::c_uint = 3;
-pub const IP_OPTIONS: ::std::os::raw::c_uint = 4;
-pub const IP_ROUTER_ALERT: ::std::os::raw::c_uint = 5;
-pub const IP_RECVOPTS: ::std::os::raw::c_uint = 6;
-pub const IP_RETOPTS: ::std::os::raw::c_uint = 7;
-pub const IP_PKTINFO: ::std::os::raw::c_uint = 8;
-pub const IP_PKTOPTIONS: ::std::os::raw::c_uint = 9;
-pub const IP_MTU_DISCOVER: ::std::os::raw::c_uint = 10;
-pub const IP_RECVERR: ::std::os::raw::c_uint = 11;
-pub const IP_RECVTTL: ::std::os::raw::c_uint = 12;
-pub const IP_RECVTOS: ::std::os::raw::c_uint = 13;
-pub const IP_MTU: ::std::os::raw::c_uint = 14;
-pub const IP_FREEBIND: ::std::os::raw::c_uint = 15;
-pub const IP_IPSEC_POLICY: ::std::os::raw::c_uint = 16;
-pub const IP_XFRM_POLICY: ::std::os::raw::c_uint = 17;
-pub const IP_PASSSEC: ::std::os::raw::c_uint = 18;
-pub const IP_TRANSPARENT: ::std::os::raw::c_uint = 19;
-pub const IP_RECVRETOPTS: ::std::os::raw::c_uint = 7;
-pub const IP_ORIGDSTADDR: ::std::os::raw::c_uint = 20;
-pub const IP_RECVORIGDSTADDR: ::std::os::raw::c_uint = 20;
-pub const IP_MINTTL: ::std::os::raw::c_uint = 21;
-pub const IP_NODEFRAG: ::std::os::raw::c_uint = 22;
-pub const IP_CHECKSUM: ::std::os::raw::c_uint = 23;
-pub const IP_BIND_ADDRESS_NO_PORT: ::std::os::raw::c_uint = 24;
-pub const IP_RECVFRAGSIZE: ::std::os::raw::c_uint = 25;
-pub const IP_PMTUDISC_DONT: ::std::os::raw::c_uint = 0;
-pub const IP_PMTUDISC_WANT: ::std::os::raw::c_uint = 1;
-pub const IP_PMTUDISC_DO: ::std::os::raw::c_uint = 2;
-pub const IP_PMTUDISC_PROBE: ::std::os::raw::c_uint = 3;
-pub const IP_PMTUDISC_INTERFACE: ::std::os::raw::c_uint = 4;
-pub const IP_PMTUDISC_OMIT: ::std::os::raw::c_uint = 5;
-pub const IP_MULTICAST_IF: ::std::os::raw::c_uint = 32;
-pub const IP_MULTICAST_TTL: ::std::os::raw::c_uint = 33;
-pub const IP_MULTICAST_LOOP: ::std::os::raw::c_uint = 34;
-pub const IP_ADD_MEMBERSHIP: ::std::os::raw::c_uint = 35;
-pub const IP_DROP_MEMBERSHIP: ::std::os::raw::c_uint = 36;
-pub const IP_UNBLOCK_SOURCE: ::std::os::raw::c_uint = 37;
-pub const IP_BLOCK_SOURCE: ::std::os::raw::c_uint = 38;
-pub const IP_ADD_SOURCE_MEMBERSHIP: ::std::os::raw::c_uint = 39;
-pub const IP_DROP_SOURCE_MEMBERSHIP: ::std::os::raw::c_uint = 40;
-pub const IP_MSFILTER: ::std::os::raw::c_uint = 41;
-pub const MCAST_JOIN_GROUP: ::std::os::raw::c_uint = 42;
-pub const MCAST_BLOCK_SOURCE: ::std::os::raw::c_uint = 43;
-pub const MCAST_UNBLOCK_SOURCE: ::std::os::raw::c_uint = 44;
-pub const MCAST_LEAVE_GROUP: ::std::os::raw::c_uint = 45;
-pub const MCAST_JOIN_SOURCE_GROUP: ::std::os::raw::c_uint = 46;
-pub const MCAST_LEAVE_SOURCE_GROUP: ::std::os::raw::c_uint = 47;
-pub const MCAST_MSFILTER: ::std::os::raw::c_uint = 48;
-pub const IP_MULTICAST_ALL: ::std::os::raw::c_uint = 49;
-pub const IP_UNICAST_IF: ::std::os::raw::c_uint = 50;
-pub const MCAST_EXCLUDE: ::std::os::raw::c_uint = 0;
-pub const MCAST_INCLUDE: ::std::os::raw::c_uint = 1;
-pub const IP_DEFAULT_MULTICAST_TTL: ::std::os::raw::c_uint = 1;
-pub const IP_DEFAULT_MULTICAST_LOOP: ::std::os::raw::c_uint = 1;
-pub const __SOCK_SIZE__: ::std::os::raw::c_uint = 16;
-pub const IN_CLASSA_NET: ::std::os::raw::c_uint = 4278190080;
-pub const IN_CLASSA_NSHIFT: ::std::os::raw::c_uint = 24;
-pub const IN_CLASSA_HOST: ::std::os::raw::c_uint = 16777215;
-pub const IN_CLASSA_MAX: ::std::os::raw::c_uint = 128;
-pub const IN_CLASSB_NET: ::std::os::raw::c_uint = 4294901760;
-pub const IN_CLASSB_NSHIFT: ::std::os::raw::c_uint = 16;
-pub const IN_CLASSB_HOST: ::std::os::raw::c_uint = 65535;
-pub const IN_CLASSB_MAX: ::std::os::raw::c_uint = 65536;
-pub const IN_CLASSC_NET: ::std::os::raw::c_uint = 4294967040;
-pub const IN_CLASSC_NSHIFT: ::std::os::raw::c_uint = 8;
-pub const IN_CLASSC_HOST: ::std::os::raw::c_uint = 255;
-pub const IN_MULTICAST_NET: ::std::os::raw::c_uint = 4026531840;
-pub const IN_LOOPBACKNET: ::std::os::raw::c_uint = 127;
-pub const INADDR_LOOPBACK: ::std::os::raw::c_uint = 2130706433;
-pub const INADDR_UNSPEC_GROUP: ::std::os::raw::c_uint = 3758096384;
-pub const INADDR_ALLHOSTS_GROUP: ::std::os::raw::c_uint = 3758096385;
-pub const INADDR_ALLRTRS_GROUP: ::std::os::raw::c_uint = 3758096386;
-pub const INADDR_MAX_LOCAL_GROUP: ::std::os::raw::c_uint = 3758096639;
-pub const __LITTLE_ENDIAN: ::std::os::raw::c_uint = 1234;
+/* automatically generated by rust-bindgen 0.58.1 */
+
+pub const __BITS_PER_LONG: u32 = 64;
+pub const __FD_SETSIZE: u32 = 1024;
+pub const __UAPI_DEF_IF_IFCONF: u32 = 1;
+pub const __UAPI_DEF_IF_IFMAP: u32 = 1;
+pub const __UAPI_DEF_IF_IFNAMSIZ: u32 = 1;
+pub const __UAPI_DEF_IF_IFREQ: u32 = 1;
+pub const __UAPI_DEF_IF_NET_DEVICE_FLAGS: u32 = 1;
+pub const __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO: u32 = 1;
+pub const __UAPI_DEF_IN_ADDR: u32 = 1;
+pub const __UAPI_DEF_IN_IPPROTO: u32 = 1;
+pub const __UAPI_DEF_IN_PKTINFO: u32 = 1;
+pub const __UAPI_DEF_IP_MREQ: u32 = 1;
+pub const __UAPI_DEF_SOCKADDR_IN: u32 = 1;
+pub const __UAPI_DEF_IN_CLASS: u32 = 1;
+pub const __UAPI_DEF_IN6_ADDR: u32 = 1;
+pub const __UAPI_DEF_IN6_ADDR_ALT: u32 = 1;
+pub const __UAPI_DEF_SOCKADDR_IN6: u32 = 1;
+pub const __UAPI_DEF_IPV6_MREQ: u32 = 1;
+pub const __UAPI_DEF_IPPROTO_V6: u32 = 1;
+pub const __UAPI_DEF_IPV6_OPTIONS: u32 = 1;
+pub const __UAPI_DEF_IN6_PKTINFO: u32 = 1;
+pub const __UAPI_DEF_IP6_MTUINFO: u32 = 1;
+pub const __UAPI_DEF_SOCKADDR_IPX: u32 = 1;
+pub const __UAPI_DEF_IPX_ROUTE_DEFINITION: u32 = 1;
+pub const __UAPI_DEF_IPX_INTERFACE_DEFINITION: u32 = 1;
+pub const __UAPI_DEF_IPX_CONFIG_DATA: u32 = 1;
+pub const __UAPI_DEF_IPX_ROUTE_DEF: u32 = 1;
+pub const __UAPI_DEF_XATTR: u32 = 1;
+pub const _K_SS_MAXSIZE: u32 = 128;
+pub const IP_TOS: u32 = 1;
+pub const IP_TTL: u32 = 2;
+pub const IP_HDRINCL: u32 = 3;
+pub const IP_OPTIONS: u32 = 4;
+pub const IP_ROUTER_ALERT: u32 = 5;
+pub const IP_RECVOPTS: u32 = 6;
+pub const IP_RETOPTS: u32 = 7;
+pub const IP_PKTINFO: u32 = 8;
+pub const IP_PKTOPTIONS: u32 = 9;
+pub const IP_MTU_DISCOVER: u32 = 10;
+pub const IP_RECVERR: u32 = 11;
+pub const IP_RECVTTL: u32 = 12;
+pub const IP_RECVTOS: u32 = 13;
+pub const IP_MTU: u32 = 14;
+pub const IP_FREEBIND: u32 = 15;
+pub const IP_IPSEC_POLICY: u32 = 16;
+pub const IP_XFRM_POLICY: u32 = 17;
+pub const IP_PASSSEC: u32 = 18;
+pub const IP_TRANSPARENT: u32 = 19;
+pub const IP_RECVRETOPTS: u32 = 7;
+pub const IP_ORIGDSTADDR: u32 = 20;
+pub const IP_RECVORIGDSTADDR: u32 = 20;
+pub const IP_MINTTL: u32 = 21;
+pub const IP_NODEFRAG: u32 = 22;
+pub const IP_CHECKSUM: u32 = 23;
+pub const IP_BIND_ADDRESS_NO_PORT: u32 = 24;
+pub const IP_RECVFRAGSIZE: u32 = 25;
+pub const IP_PMTUDISC_DONT: u32 = 0;
+pub const IP_PMTUDISC_WANT: u32 = 1;
+pub const IP_PMTUDISC_DO: u32 = 2;
+pub const IP_PMTUDISC_PROBE: u32 = 3;
+pub const IP_PMTUDISC_INTERFACE: u32 = 4;
+pub const IP_PMTUDISC_OMIT: u32 = 5;
+pub const IP_MULTICAST_IF: u32 = 32;
+pub const IP_MULTICAST_TTL: u32 = 33;
+pub const IP_MULTICAST_LOOP: u32 = 34;
+pub const IP_ADD_MEMBERSHIP: u32 = 35;
+pub const IP_DROP_MEMBERSHIP: u32 = 36;
+pub const IP_UNBLOCK_SOURCE: u32 = 37;
+pub const IP_BLOCK_SOURCE: u32 = 38;
+pub const IP_ADD_SOURCE_MEMBERSHIP: u32 = 39;
+pub const IP_DROP_SOURCE_MEMBERSHIP: u32 = 40;
+pub const IP_MSFILTER: u32 = 41;
+pub const MCAST_JOIN_GROUP: u32 = 42;
+pub const MCAST_BLOCK_SOURCE: u32 = 43;
+pub const MCAST_UNBLOCK_SOURCE: u32 = 44;
+pub const MCAST_LEAVE_GROUP: u32 = 45;
+pub const MCAST_JOIN_SOURCE_GROUP: u32 = 46;
+pub const MCAST_LEAVE_SOURCE_GROUP: u32 = 47;
+pub const MCAST_MSFILTER: u32 = 48;
+pub const IP_MULTICAST_ALL: u32 = 49;
+pub const IP_UNICAST_IF: u32 = 50;
+pub const MCAST_EXCLUDE: u32 = 0;
+pub const MCAST_INCLUDE: u32 = 1;
+pub const IP_DEFAULT_MULTICAST_TTL: u32 = 1;
+pub const IP_DEFAULT_MULTICAST_LOOP: u32 = 1;
+pub const __SOCK_SIZE__: u32 = 16;
+pub const IN_CLASSA_NET: u32 = 4278190080;
+pub const IN_CLASSA_NSHIFT: u32 = 24;
+pub const IN_CLASSA_HOST: u32 = 16777215;
+pub const IN_CLASSA_MAX: u32 = 128;
+pub const IN_CLASSB_NET: u32 = 4294901760;
+pub const IN_CLASSB_NSHIFT: u32 = 16;
+pub const IN_CLASSB_HOST: u32 = 65535;
+pub const IN_CLASSB_MAX: u32 = 65536;
+pub const IN_CLASSC_NET: u32 = 4294967040;
+pub const IN_CLASSC_NSHIFT: u32 = 8;
+pub const IN_CLASSC_HOST: u32 = 255;
+pub const IN_MULTICAST_NET: u32 = 3758096384;
+pub const IN_CLASSE_NET: u32 = 4294967295;
+pub const IN_CLASSE_NSHIFT: u32 = 0;
+pub const IN_LOOPBACKNET: u32 = 127;
+pub const INADDR_LOOPBACK: u32 = 2130706433;
+pub const INADDR_UNSPEC_GROUP: u32 = 3758096384;
+pub const INADDR_ALLHOSTS_GROUP: u32 = 3758096385;
+pub const INADDR_ALLRTRS_GROUP: u32 = 3758096386;
+pub const INADDR_ALLSNOOPERS_GROUP: u32 = 3758096490;
+pub const INADDR_MAX_LOCAL_GROUP: u32 = 3758096639;
+pub const __LITTLE_ENDIAN: u32 = 1234;
 pub type __s8 = ::std::os::raw::c_schar;
 pub type __u8 = ::std::os::raw::c_uchar;
 pub type __s16 = ::std::os::raw::c_short;
@@ -107,38 +123,10 @@ pub type __u32 = ::std::os::raw::c_uint;
 pub type __s64 = ::std::os::raw::c_longlong;
 pub type __u64 = ::std::os::raw::c_ulonglong;
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct __kernel_fd_set {
     pub fds_bits: [::std::os::raw::c_ulong; 16usize],
 }
-#[test]
-fn bindgen_test_layout___kernel_fd_set() {
-    assert_eq!(
-        ::std::mem::size_of::<__kernel_fd_set>(),
-        128usize,
-        concat!("Size of: ", stringify!(__kernel_fd_set))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<__kernel_fd_set>(),
-        8usize,
-        concat!("Alignment of ", stringify!(__kernel_fd_set))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const __kernel_fd_set)).fds_bits as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(__kernel_fd_set),
-            "::",
-            stringify!(fds_bits)
-        )
-    );
-}
-impl Clone for __kernel_fd_set {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 pub type __kernel_sighandler_t =
     ::std::option::Option<unsafe extern "C" fn(arg1: ::std::os::raw::c_int)>;
 pub type __kernel_key_t = ::std::os::raw::c_int;
@@ -162,41 +150,15 @@ pub type __kernel_size_t = __kernel_ulong_t;
 pub type __kernel_ssize_t = __kernel_long_t;
 pub type __kernel_ptrdiff_t = __kernel_long_t;
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct __kernel_fsid_t {
     pub val: [::std::os::raw::c_int; 2usize],
 }
-#[test]
-fn bindgen_test_layout___kernel_fsid_t() {
-    assert_eq!(
-        ::std::mem::size_of::<__kernel_fsid_t>(),
-        8usize,
-        concat!("Size of: ", stringify!(__kernel_fsid_t))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<__kernel_fsid_t>(),
-        4usize,
-        concat!("Alignment of ", stringify!(__kernel_fsid_t))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const __kernel_fsid_t)).val as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(__kernel_fsid_t),
-            "::",
-            stringify!(val)
-        )
-    );
-}
-impl Clone for __kernel_fsid_t {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 pub type __kernel_off_t = __kernel_long_t;
 pub type __kernel_loff_t = ::std::os::raw::c_longlong;
+pub type __kernel_old_time_t = __kernel_long_t;
 pub type __kernel_time_t = __kernel_long_t;
+pub type __kernel_time64_t = ::std::os::raw::c_longlong;
 pub type __kernel_clock_t = __kernel_long_t;
 pub type __kernel_timer_t = ::std::os::raw::c_int;
 pub type __kernel_clockid_t = ::std::os::raw::c_int;
@@ -211,267 +173,81 @@ pub type __le64 = __u64;
 pub type __be64 = __u64;
 pub type __sum16 = __u16;
 pub type __wsum = __u32;
+pub type __poll_t = ::std::os::raw::c_uint;
 pub type __kernel_sa_family_t = ::std::os::raw::c_ushort;
 #[repr(C)]
+#[derive(Copy, Clone)]
 pub struct __kernel_sockaddr_storage {
+    pub __bindgen_anon_1: __kernel_sockaddr_storage__bindgen_ty_1,
+}
+#[repr(C)]
+#[derive(Copy, Clone)]
+pub union __kernel_sockaddr_storage__bindgen_ty_1 {
+    pub __bindgen_anon_1: __kernel_sockaddr_storage__bindgen_ty_1__bindgen_ty_1,
+    pub __align: *mut ::std::os::raw::c_void,
+}
+#[repr(C)]
+#[derive(Copy, Clone)]
+pub struct __kernel_sockaddr_storage__bindgen_ty_1__bindgen_ty_1 {
     pub ss_family: __kernel_sa_family_t,
     pub __data: [::std::os::raw::c_char; 126usize],
-    pub __bindgen_align: [u64; 0usize],
 }
-#[test]
-fn bindgen_test_layout___kernel_sockaddr_storage() {
-    assert_eq!(
-        ::std::mem::size_of::<__kernel_sockaddr_storage>(),
-        128usize,
-        concat!("Size of: ", stringify!(__kernel_sockaddr_storage))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<__kernel_sockaddr_storage>(),
-        8usize,
-        concat!("Alignment of ", stringify!(__kernel_sockaddr_storage))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const __kernel_sockaddr_storage)).ss_family as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(__kernel_sockaddr_storage),
-            "::",
-            stringify!(ss_family)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const __kernel_sockaddr_storage)).__data as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(__kernel_sockaddr_storage),
-            "::",
-            stringify!(__data)
-        )
-    );
-}
-impl Default for __kernel_sockaddr_storage {
-    fn default() -> Self {
-        unsafe { ::std::mem::zeroed() }
-    }
-}
-pub const IPPROTO_IP: _bindgen_ty_1 = 0;
-pub const IPPROTO_ICMP: _bindgen_ty_1 = 1;
-pub const IPPROTO_IGMP: _bindgen_ty_1 = 2;
-pub const IPPROTO_IPIP: _bindgen_ty_1 = 4;
-pub const IPPROTO_TCP: _bindgen_ty_1 = 6;
-pub const IPPROTO_EGP: _bindgen_ty_1 = 8;
-pub const IPPROTO_PUP: _bindgen_ty_1 = 12;
-pub const IPPROTO_UDP: _bindgen_ty_1 = 17;
-pub const IPPROTO_IDP: _bindgen_ty_1 = 22;
-pub const IPPROTO_TP: _bindgen_ty_1 = 29;
-pub const IPPROTO_DCCP: _bindgen_ty_1 = 33;
-pub const IPPROTO_IPV6: _bindgen_ty_1 = 41;
-pub const IPPROTO_RSVP: _bindgen_ty_1 = 46;
-pub const IPPROTO_GRE: _bindgen_ty_1 = 47;
-pub const IPPROTO_ESP: _bindgen_ty_1 = 50;
-pub const IPPROTO_AH: _bindgen_ty_1 = 51;
-pub const IPPROTO_MTP: _bindgen_ty_1 = 92;
-pub const IPPROTO_BEETPH: _bindgen_ty_1 = 94;
-pub const IPPROTO_ENCAP: _bindgen_ty_1 = 98;
-pub const IPPROTO_PIM: _bindgen_ty_1 = 103;
-pub const IPPROTO_COMP: _bindgen_ty_1 = 108;
-pub const IPPROTO_SCTP: _bindgen_ty_1 = 132;
-pub const IPPROTO_UDPLITE: _bindgen_ty_1 = 136;
-pub const IPPROTO_MPLS: _bindgen_ty_1 = 137;
-pub const IPPROTO_RAW: _bindgen_ty_1 = 255;
-pub const IPPROTO_MAX: _bindgen_ty_1 = 256;
+pub const IPPROTO_IP: ::std::os::raw::c_uint = 0;
+pub const IPPROTO_ICMP: ::std::os::raw::c_uint = 1;
+pub const IPPROTO_IGMP: ::std::os::raw::c_uint = 2;
+pub const IPPROTO_IPIP: ::std::os::raw::c_uint = 4;
+pub const IPPROTO_TCP: ::std::os::raw::c_uint = 6;
+pub const IPPROTO_EGP: ::std::os::raw::c_uint = 8;
+pub const IPPROTO_PUP: ::std::os::raw::c_uint = 12;
+pub const IPPROTO_UDP: ::std::os::raw::c_uint = 17;
+pub const IPPROTO_IDP: ::std::os::raw::c_uint = 22;
+pub const IPPROTO_TP: ::std::os::raw::c_uint = 29;
+pub const IPPROTO_DCCP: ::std::os::raw::c_uint = 33;
+pub const IPPROTO_IPV6: ::std::os::raw::c_uint = 41;
+pub const IPPROTO_RSVP: ::std::os::raw::c_uint = 46;
+pub const IPPROTO_GRE: ::std::os::raw::c_uint = 47;
+pub const IPPROTO_ESP: ::std::os::raw::c_uint = 50;
+pub const IPPROTO_AH: ::std::os::raw::c_uint = 51;
+pub const IPPROTO_MTP: ::std::os::raw::c_uint = 92;
+pub const IPPROTO_BEETPH: ::std::os::raw::c_uint = 94;
+pub const IPPROTO_ENCAP: ::std::os::raw::c_uint = 98;
+pub const IPPROTO_PIM: ::std::os::raw::c_uint = 103;
+pub const IPPROTO_COMP: ::std::os::raw::c_uint = 108;
+pub const IPPROTO_SCTP: ::std::os::raw::c_uint = 132;
+pub const IPPROTO_UDPLITE: ::std::os::raw::c_uint = 136;
+pub const IPPROTO_MPLS: ::std::os::raw::c_uint = 137;
+pub const IPPROTO_ETHERNET: ::std::os::raw::c_uint = 143;
+pub const IPPROTO_RAW: ::std::os::raw::c_uint = 255;
+pub const IPPROTO_MPTCP: ::std::os::raw::c_uint = 262;
+pub const IPPROTO_MAX: ::std::os::raw::c_uint = 263;
 pub type _bindgen_ty_1 = ::std::os::raw::c_uint;
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct in_addr {
     pub s_addr: __be32,
 }
-#[test]
-fn bindgen_test_layout_in_addr() {
-    assert_eq!(
-        ::std::mem::size_of::<in_addr>(),
-        4usize,
-        concat!("Size of: ", stringify!(in_addr))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<in_addr>(),
-        4usize,
-        concat!("Alignment of ", stringify!(in_addr))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const in_addr)).s_addr as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(in_addr),
-            "::",
-            stringify!(s_addr)
-        )
-    );
-}
-impl Clone for in_addr {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct ip_mreq {
     pub imr_multiaddr: in_addr,
     pub imr_interface: in_addr,
 }
-#[test]
-fn bindgen_test_layout_ip_mreq() {
-    assert_eq!(
-        ::std::mem::size_of::<ip_mreq>(),
-        8usize,
-        concat!("Size of: ", stringify!(ip_mreq))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<ip_mreq>(),
-        4usize,
-        concat!("Alignment of ", stringify!(ip_mreq))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreq)).imr_multiaddr as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreq),
-            "::",
-            stringify!(imr_multiaddr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreq)).imr_interface as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreq),
-            "::",
-            stringify!(imr_interface)
-        )
-    );
-}
-impl Clone for ip_mreq {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct ip_mreqn {
     pub imr_multiaddr: in_addr,
     pub imr_address: in_addr,
     pub imr_ifindex: ::std::os::raw::c_int,
 }
-#[test]
-fn bindgen_test_layout_ip_mreqn() {
-    assert_eq!(
-        ::std::mem::size_of::<ip_mreqn>(),
-        12usize,
-        concat!("Size of: ", stringify!(ip_mreqn))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<ip_mreqn>(),
-        4usize,
-        concat!("Alignment of ", stringify!(ip_mreqn))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreqn)).imr_multiaddr as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreqn),
-            "::",
-            stringify!(imr_multiaddr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreqn)).imr_address as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreqn),
-            "::",
-            stringify!(imr_address)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreqn)).imr_ifindex as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreqn),
-            "::",
-            stringify!(imr_ifindex)
-        )
-    );
-}
-impl Clone for ip_mreqn {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct ip_mreq_source {
     pub imr_multiaddr: __be32,
     pub imr_interface: __be32,
     pub imr_sourceaddr: __be32,
 }
-#[test]
-fn bindgen_test_layout_ip_mreq_source() {
-    assert_eq!(
-        ::std::mem::size_of::<ip_mreq_source>(),
-        12usize,
-        concat!("Size of: ", stringify!(ip_mreq_source))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<ip_mreq_source>(),
-        4usize,
-        concat!("Alignment of ", stringify!(ip_mreq_source))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreq_source)).imr_multiaddr as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreq_source),
-            "::",
-            stringify!(imr_multiaddr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreq_source)).imr_interface as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreq_source),
-            "::",
-            stringify!(imr_interface)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_mreq_source)).imr_sourceaddr as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_mreq_source),
-            "::",
-            stringify!(imr_sourceaddr)
-        )
-    );
-}
-impl Clone for ip_mreq_source {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct ip_msfilter {
     pub imsf_multiaddr: __be32,
     pub imsf_interface: __be32,
@@ -479,172 +255,21 @@ pub struct ip_msfilter {
     pub imsf_numsrc: __u32,
     pub imsf_slist: [__be32; 1usize],
 }
-#[test]
-fn bindgen_test_layout_ip_msfilter() {
-    assert_eq!(
-        ::std::mem::size_of::<ip_msfilter>(),
-        20usize,
-        concat!("Size of: ", stringify!(ip_msfilter))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<ip_msfilter>(),
-        4usize,
-        concat!("Alignment of ", stringify!(ip_msfilter))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_msfilter)).imsf_multiaddr as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_msfilter),
-            "::",
-            stringify!(imsf_multiaddr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_msfilter)).imsf_interface as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_msfilter),
-            "::",
-            stringify!(imsf_interface)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_msfilter)).imsf_fmode as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_msfilter),
-            "::",
-            stringify!(imsf_fmode)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_msfilter)).imsf_numsrc as *const _ as usize },
-        12usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_msfilter),
-            "::",
-            stringify!(imsf_numsrc)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const ip_msfilter)).imsf_slist as *const _ as usize },
-        16usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(ip_msfilter),
-            "::",
-            stringify!(imsf_slist)
-        )
-    );
-}
-impl Clone for ip_msfilter {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
+#[derive(Copy, Clone)]
 pub struct group_req {
     pub gr_interface: __u32,
     pub gr_group: __kernel_sockaddr_storage,
 }
-#[test]
-fn bindgen_test_layout_group_req() {
-    assert_eq!(
-        ::std::mem::size_of::<group_req>(),
-        136usize,
-        concat!("Size of: ", stringify!(group_req))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<group_req>(),
-        8usize,
-        concat!("Alignment of ", stringify!(group_req))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_req)).gr_interface as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_req),
-            "::",
-            stringify!(gr_interface)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_req)).gr_group as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_req),
-            "::",
-            stringify!(gr_group)
-        )
-    );
-}
-impl Default for group_req {
-    fn default() -> Self {
-        unsafe { ::std::mem::zeroed() }
-    }
-}
 #[repr(C)]
+#[derive(Copy, Clone)]
 pub struct group_source_req {
     pub gsr_interface: __u32,
     pub gsr_group: __kernel_sockaddr_storage,
     pub gsr_source: __kernel_sockaddr_storage,
 }
-#[test]
-fn bindgen_test_layout_group_source_req() {
-    assert_eq!(
-        ::std::mem::size_of::<group_source_req>(),
-        264usize,
-        concat!("Size of: ", stringify!(group_source_req))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<group_source_req>(),
-        8usize,
-        concat!("Alignment of ", stringify!(group_source_req))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_source_req)).gsr_interface as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_source_req),
-            "::",
-            stringify!(gsr_interface)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_source_req)).gsr_group as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_source_req),
-            "::",
-            stringify!(gsr_group)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_source_req)).gsr_source as *const _ as usize },
-        136usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_source_req),
-            "::",
-            stringify!(gsr_source)
-        )
-    );
-}
-impl Default for group_source_req {
-    fn default() -> Self {
-        unsafe { ::std::mem::zeroed() }
-    }
-}
 #[repr(C)]
+#[derive(Copy, Clone)]
 pub struct group_filter {
     pub gf_interface: __u32,
     pub gf_group: __kernel_sockaddr_storage,
@@ -652,192 +277,18 @@ pub struct group_filter {
     pub gf_numsrc: __u32,
     pub gf_slist: [__kernel_sockaddr_storage; 1usize],
 }
-#[test]
-fn bindgen_test_layout_group_filter() {
-    assert_eq!(
-        ::std::mem::size_of::<group_filter>(),
-        272usize,
-        concat!("Size of: ", stringify!(group_filter))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<group_filter>(),
-        8usize,
-        concat!("Alignment of ", stringify!(group_filter))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_filter)).gf_interface as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_filter),
-            "::",
-            stringify!(gf_interface)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_filter)).gf_group as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_filter),
-            "::",
-            stringify!(gf_group)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_filter)).gf_fmode as *const _ as usize },
-        136usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_filter),
-            "::",
-            stringify!(gf_fmode)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_filter)).gf_numsrc as *const _ as usize },
-        140usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_filter),
-            "::",
-            stringify!(gf_numsrc)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const group_filter)).gf_slist as *const _ as usize },
-        144usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(group_filter),
-            "::",
-            stringify!(gf_slist)
-        )
-    );
-}
-impl Default for group_filter {
-    fn default() -> Self {
-        unsafe { ::std::mem::zeroed() }
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct in_pktinfo {
     pub ipi_ifindex: ::std::os::raw::c_int,
     pub ipi_spec_dst: in_addr,
     pub ipi_addr: in_addr,
 }
-#[test]
-fn bindgen_test_layout_in_pktinfo() {
-    assert_eq!(
-        ::std::mem::size_of::<in_pktinfo>(),
-        12usize,
-        concat!("Size of: ", stringify!(in_pktinfo))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<in_pktinfo>(),
-        4usize,
-        concat!("Alignment of ", stringify!(in_pktinfo))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const in_pktinfo)).ipi_ifindex as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(in_pktinfo),
-            "::",
-            stringify!(ipi_ifindex)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const in_pktinfo)).ipi_spec_dst as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(in_pktinfo),
-            "::",
-            stringify!(ipi_spec_dst)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const in_pktinfo)).ipi_addr as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(in_pktinfo),
-            "::",
-            stringify!(ipi_addr)
-        )
-    );
-}
-impl Clone for in_pktinfo {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
 #[repr(C)]
-#[derive(Debug, Default, Copy)]
+#[derive(Debug, Copy, Clone)]
 pub struct sockaddr_in {
     pub sin_family: __kernel_sa_family_t,
     pub sin_port: __be16,
     pub sin_addr: in_addr,
     pub __pad: [::std::os::raw::c_uchar; 8usize],
 }
-#[test]
-fn bindgen_test_layout_sockaddr_in() {
-    assert_eq!(
-        ::std::mem::size_of::<sockaddr_in>(),
-        16usize,
-        concat!("Size of: ", stringify!(sockaddr_in))
-    );
-    assert_eq!(
-        ::std::mem::align_of::<sockaddr_in>(),
-        4usize,
-        concat!("Alignment of ", stringify!(sockaddr_in))
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sockaddr_in)).sin_family as *const _ as usize },
-        0usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sockaddr_in),
-            "::",
-            stringify!(sin_family)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sockaddr_in)).sin_port as *const _ as usize },
-        2usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sockaddr_in),
-            "::",
-            stringify!(sin_port)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sockaddr_in)).sin_addr as *const _ as usize },
-        4usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sockaddr_in),
-            "::",
-            stringify!(sin_addr)
-        )
-    );
-    assert_eq!(
-        unsafe { &(*(0 as *const sockaddr_in)).__pad as *const _ as usize },
-        8usize,
-        concat!(
-            "Alignment of field: ",
-            stringify!(sockaddr_in),
-            "::",
-            stringify!(__pad)
-        )
-    );
-}
-impl Clone for sockaddr_in {
-    fn clone(&self) -> Self {
-        *self
-    }
-}

net_gen/src/sockios.rs

@@ -1,89 +1,95 @@
-// Copyright 2017 The Chromium OS Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the THIRD-PARTY file.
+// Copyright © 2021 Intel Corporation
+//
+// SPDX-License-Identifier: Apache-2.0
+//
 
-/* automatically generated by rust-bindgen */
+// bindgen /usr/include/linux/sockios.h --no-layout-tests
 
-pub const FIOSETOWN: ::std::os::raw::c_uint = 35073;
-pub const SIOCSPGRP: ::std::os::raw::c_uint = 35074;
-pub const FIOGETOWN: ::std::os::raw::c_uint = 35075;
-pub const SIOCGPGRP: ::std::os::raw::c_uint = 35076;
-pub const SIOCATMARK: ::std::os::raw::c_uint = 35077;
-pub const SIOCGSTAMP: ::std::os::raw::c_uint = 35078;
-pub const SIOCGSTAMPNS: ::std::os::raw::c_uint = 35079;
-pub const SOCK_IOC_TYPE: ::std::os::raw::c_uint = 137;
-pub const SIOCADDRT: ::std::os::raw::c_uint = 35083;
-pub const SIOCDELRT: ::std::os::raw::c_uint = 35084;
-pub const SIOCRTMSG: ::std::os::raw::c_uint = 35085;
-pub const SIOCGIFNAME: ::std::os::raw::c_uint = 35088;
-pub const SIOCSIFLINK: ::std::os::raw::c_uint = 35089;
-pub const SIOCGIFCONF: ::std::os::raw::c_uint = 35090;
-pub const SIOCGIFFLAGS: ::std::os::raw::c_uint = 35091;
-pub const SIOCSIFFLAGS: ::std::os::raw::c_uint = 35092;
-pub const SIOCGIFADDR: ::std::os::raw::c_uint = 35093;
-pub const SIOCSIFADDR: ::std::os::raw::c_uint = 35094;
-pub const SIOCGIFDSTADDR: ::std::os::raw::c_uint = 35095;
-pub const SIOCSIFDSTADDR: ::std::os::raw::c_uint = 35096;
-pub const SIOCGIFBRDADDR: ::std::os::raw::c_uint = 35097;
-pub const SIOCSIFBRDADDR: ::std::os::raw::c_uint = 35098;
-pub const SIOCGIFNETMASK: ::std::os::raw::c_uint = 35099;
-pub const SIOCSIFNETMASK: ::std::os::raw::c_uint = 35100;
-pub const SIOCGIFMETRIC: ::std::os::raw::c_uint = 35101;
-pub const SIOCSIFMETRIC: ::std::os::raw::c_uint = 35102;
-pub const SIOCGIFMEM: ::std::os::raw::c_uint = 35103;
-pub const SIOCSIFMEM: ::std::os::raw::c_uint = 35104;
-pub const SIOCGIFMTU: ::std::os::raw::c_uint = 35105;
-pub const SIOCSIFMTU: ::std::os::raw::c_uint = 35106;
-pub const SIOCSIFNAME: ::std::os::raw::c_uint = 35107;
-pub const SIOCSIFHWADDR: ::std::os::raw::c_uint = 35108;
-pub const SIOCGIFENCAP: ::std::os::raw::c_uint = 35109;
-pub const SIOCSIFENCAP: ::std::os::raw::c_uint = 35110;
-pub const SIOCGIFHWADDR: ::std::os::raw::c_uint = 35111;
-pub const SIOCGIFSLAVE: ::std::os::raw::c_uint = 35113;
-pub const SIOCSIFSLAVE: ::std::os::raw::c_uint = 35120;
-pub const SIOCADDMULTI: ::std::os::raw::c_uint = 35121;
-pub const SIOCDELMULTI: ::std::os::raw::c_uint = 35122;
-pub const SIOCGIFINDEX: ::std::os::raw::c_uint = 35123;
-pub const SIOGIFINDEX: ::std::os::raw::c_uint = 35123;
-pub const SIOCSIFPFLAGS: ::std::os::raw::c_uint = 35124;
-pub const SIOCGIFPFLAGS: ::std::os::raw::c_uint = 35125;
-pub const SIOCDIFADDR: ::std::os::raw::c_uint = 35126;
-pub const SIOCSIFHWBROADCAST: ::std::os::raw::c_uint = 35127;
-pub const SIOCGIFCOUNT: ::std::os::raw::c_uint = 35128;
-pub const SIOCGIFBR: ::std::os::raw::c_uint = 35136;
-pub const SIOCSIFBR: ::std::os::raw::c_uint = 35137;
-pub const SIOCGIFTXQLEN: ::std::os::raw::c_uint = 35138;
-pub const SIOCSIFTXQLEN: ::std::os::raw::c_uint = 35139;
-pub const SIOCETHTOOL: ::std::os::raw::c_uint = 35142;
-pub const SIOCGMIIPHY: ::std::os::raw::c_uint = 35143;
-pub const SIOCGMIIREG: ::std::os::raw::c_uint = 35144;
-pub const SIOCSMIIREG: ::std::os::raw::c_uint = 35145;
-pub const SIOCWANDEV: ::std::os::raw::c_uint = 35146;
-pub const SIOCOUTQNSD: ::std::os::raw::c_uint = 35147;
-pub const SIOCGSKNS: ::std::os::raw::c_uint = 35148;
-pub const SIOCDARP: ::std::os::raw::c_uint = 35155;
-pub const SIOCGARP: ::std::os::raw::c_uint = 35156;
-pub const SIOCSARP: ::std::os::raw::c_uint = 35157;
-pub const SIOCDRARP: ::std::os::raw::c_uint = 35168;
-pub const SIOCGRARP: ::std::os::raw::c_uint = 35169;
-pub const SIOCSRARP: ::std::os::raw::c_uint = 35170;
-pub const SIOCGIFMAP: ::std::os::raw::c_uint = 35184;
-pub const SIOCSIFMAP: ::std::os::raw::c_uint = 35185;
-pub const SIOCADDDLCI: ::std::os::raw::c_uint = 35200;
-pub const SIOCDELDLCI: ::std::os::raw::c_uint = 35201;
-pub const SIOCGIFVLAN: ::std::os::raw::c_uint = 35202;
-pub const SIOCSIFVLAN: ::std::os::raw::c_uint = 35203;
-pub const SIOCBONDENSLAVE: ::std::os::raw::c_uint = 35216;
-pub const SIOCBONDRELEASE: ::std::os::raw::c_uint = 35217;
-pub const SIOCBONDSETHWADDR: ::std::os::raw::c_uint = 35218;
-pub const SIOCBONDSLAVEINFOQUERY: ::std::os::raw::c_uint = 35219;
-pub const SIOCBONDINFOQUERY: ::std::os::raw::c_uint = 35220;
-pub const SIOCBONDCHANGEACTIVE: ::std::os::raw::c_uint = 35221;
-pub const SIOCBRADDBR: ::std::os::raw::c_uint = 35232;
-pub const SIOCBRDELBR: ::std::os::raw::c_uint = 35233;
-pub const SIOCBRADDIF: ::std::os::raw::c_uint = 35234;
-pub const SIOCBRDELIF: ::std::os::raw::c_uint = 35235;
-pub const SIOCSHWTSTAMP: ::std::os::raw::c_uint = 35248;
-pub const SIOCGHWTSTAMP: ::std::os::raw::c_uint = 35249;
-pub const SIOCDEVPRIVATE: ::std::os::raw::c_uint = 35312;
-pub const SIOCPROTOPRIVATE: ::std::os::raw::c_uint = 35296;
+/* automatically generated by rust-bindgen 0.58.1 */
+
+pub const __BITS_PER_LONG: u32 = 64;
+pub const FIOSETOWN: u32 = 35073;
+pub const SIOCSPGRP: u32 = 35074;
+pub const FIOGETOWN: u32 = 35075;
+pub const SIOCGPGRP: u32 = 35076;
+pub const SIOCATMARK: u32 = 35077;
+pub const SIOCGSTAMP_OLD: u32 = 35078;
+pub const SIOCGSTAMPNS_OLD: u32 = 35079;
+pub const SOCK_IOC_TYPE: u32 = 137;
+pub const SIOCGSTAMP: u32 = 35078;
+pub const SIOCGSTAMPNS: u32 = 35079;
+pub const SIOCADDRT: u32 = 35083;
+pub const SIOCDELRT: u32 = 35084;
+pub const SIOCRTMSG: u32 = 35085;
+pub const SIOCGIFNAME: u32 = 35088;
+pub const SIOCSIFLINK: u32 = 35089;
+pub const SIOCGIFCONF: u32 = 35090;
+pub const SIOCGIFFLAGS: u32 = 35091;
+pub const SIOCSIFFLAGS: u32 = 35092;
+pub const SIOCGIFADDR: u32 = 35093;
+pub const SIOCSIFADDR: u32 = 35094;
+pub const SIOCGIFDSTADDR: u32 = 35095;
+pub const SIOCSIFDSTADDR: u32 = 35096;
+pub const SIOCGIFBRDADDR: u32 = 35097;
+pub const SIOCSIFBRDADDR: u32 = 35098;
+pub const SIOCGIFNETMASK: u32 = 35099;
+pub const SIOCSIFNETMASK: u32 = 35100;
+pub const SIOCGIFMETRIC: u32 = 35101;
+pub const SIOCSIFMETRIC: u32 = 35102;
+pub const SIOCGIFMEM: u32 = 35103;
+pub const SIOCSIFMEM: u32 = 35104;
+pub const SIOCGIFMTU: u32 = 35105;
+pub const SIOCSIFMTU: u32 = 35106;
+pub const SIOCSIFNAME: u32 = 35107;
+pub const SIOCSIFHWADDR: u32 = 35108;
+pub const SIOCGIFENCAP: u32 = 35109;
+pub const SIOCSIFENCAP: u32 = 35110;
+pub const SIOCGIFHWADDR: u32 = 35111;
+pub const SIOCGIFSLAVE: u32 = 35113;
+pub const SIOCSIFSLAVE: u32 = 35120;
+pub const SIOCADDMULTI: u32 = 35121;
+pub const SIOCDELMULTI: u32 = 35122;
+pub const SIOCGIFINDEX: u32 = 35123;
+pub const SIOGIFINDEX: u32 = 35123;
+pub const SIOCSIFPFLAGS: u32 = 35124;
+pub const SIOCGIFPFLAGS: u32 = 35125;
+pub const SIOCDIFADDR: u32 = 35126;
+pub const SIOCSIFHWBROADCAST: u32 = 35127;
+pub const SIOCGIFCOUNT: u32 = 35128;
+pub const SIOCGIFBR: u32 = 35136;
+pub const SIOCSIFBR: u32 = 35137;
+pub const SIOCGIFTXQLEN: u32 = 35138;
+pub const SIOCSIFTXQLEN: u32 = 35139;
+pub const SIOCETHTOOL: u32 = 35142;
+pub const SIOCGMIIPHY: u32 = 35143;
+pub const SIOCGMIIREG: u32 = 35144;
+pub const SIOCSMIIREG: u32 = 35145;
+pub const SIOCWANDEV: u32 = 35146;
+pub const SIOCOUTQNSD: u32 = 35147;
+pub const SIOCGSKNS: u32 = 35148;
+pub const SIOCDARP: u32 = 35155;
+pub const SIOCGARP: u32 = 35156;
+pub const SIOCSARP: u32 = 35157;
+pub const SIOCDRARP: u32 = 35168;
+pub const SIOCGRARP: u32 = 35169;
+pub const SIOCSRARP: u32 = 35170;
+pub const SIOCGIFMAP: u32 = 35184;
+pub const SIOCSIFMAP: u32 = 35185;
+pub const SIOCADDDLCI: u32 = 35200;
+pub const SIOCDELDLCI: u32 = 35201;
+pub const SIOCGIFVLAN: u32 = 35202;
+pub const SIOCSIFVLAN: u32 = 35203;
+pub const SIOCBONDENSLAVE: u32 = 35216;
+pub const SIOCBONDRELEASE: u32 = 35217;
+pub const SIOCBONDSETHWADDR: u32 = 35218;
+pub const SIOCBONDSLAVEINFOQUERY: u32 = 35219;
+pub const SIOCBONDINFOQUERY: u32 = 35220;
+pub const SIOCBONDCHANGEACTIVE: u32 = 35221;
+pub const SIOCBRADDBR: u32 = 35232;
+pub const SIOCBRDELBR: u32 = 35233;
+pub const SIOCBRADDIF: u32 = 35234;
+pub const SIOCBRDELIF: u32 = 35235;
+pub const SIOCSHWTSTAMP: u32 = 35248;
+pub const SIOCGHWTSTAMP: u32 = 35249;
+pub const SIOCDEVPRIVATE: u32 = 35312;
+pub const SIOCPROTOPRIVATE: u32 = 35296;

net_util/Cargo.toml

@@ -2,19 +2,23 @@
 name = "net_util"
 version = "0.1.0"
 authors = ["The Chromium OS Authors"]
+edition = "2018"
 
 [dependencies]
 epoll = ">=4.0.1"
-libc = "0.2.91"
+libc = "0.2.96"
 log = "0.4.14"
 net_gen = { path = "../net_gen" }
-serde = "1.0.125"
+rate_limiter = { path = "../rate_limiter" }
+serde = "1.0.126"
+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"] }
+vm-memory = { version = "0.5.0", features = ["backend-mmap", "backend-atomic", "backend-bitmap"] }
 vm-virtio = { path = "../vm-virtio" }
 vmm-sys-util = ">=0.3.1"
 
 [dev-dependencies]
 lazy_static = "1.3.0"
-pnet = "0.27.2"
+pnet = "0.28.0"
 serde_json = "1.0.64"

net_util/src/ctrl_queue.rs

@@ -0,0 +1,141 @@
+// Copyright (c) 2021 Intel Corporation. All rights reserved.
+//
+// SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
+
+use crate::GuestMemoryMmap;
+use crate::Tap;
+use libc::c_uint;
+use virtio_bindings::bindings::virtio_net::{
+    VIRTIO_NET_CTRL_GUEST_OFFLOADS, VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, VIRTIO_NET_CTRL_MQ,
+    VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN,
+    VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, VIRTIO_NET_ERR, VIRTIO_NET_F_GUEST_CSUM,
+    VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
+    VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_OK,
+};
+use vm_memory::{ByteValued, Bytes, GuestMemoryError};
+use vm_virtio::Queue;
+
+#[derive(Debug)]
+pub enum Error {
+    /// Read queue failed.
+    GuestMemory(GuestMemoryError),
+    /// No queue pairs number.
+    NoQueuePairsDescriptor,
+    /// No status descriptor
+    NoStatusDescriptor,
+}
+
+type Result<T> = std::result::Result<T, Error>;
+
+#[repr(C, packed)]
+#[derive(Debug, Clone, Copy, Default)]
+pub struct ControlHeader {
+    pub class: u8,
+    pub cmd: u8,
+}
+
+unsafe impl ByteValued for ControlHeader {}
+
+pub struct CtrlQueue {
+    pub taps: Vec<Tap>,
+}
+
+impl CtrlQueue {
+    pub fn new(taps: Vec<Tap>) -> Self {
+        CtrlQueue { taps }
+    }
+
+    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) {
+            let ctrl_hdr: ControlHeader =
+                mem.read_obj(avail_desc.addr).map_err(Error::GuestMemory)?;
+            let data_desc = avail_desc
+                .next_descriptor()
+                .ok_or(Error::NoQueuePairsDescriptor)?;
+            let status_desc = data_desc
+                .next_descriptor()
+                .ok_or(Error::NoStatusDescriptor)?;
+
+            let ok = match u32::from(ctrl_hdr.class) {
+                VIRTIO_NET_CTRL_MQ => {
+                    let queue_pairs = mem
+                        .read_obj::<u16>(data_desc.addr)
+                        .map_err(Error::GuestMemory)?;
+                    if u32::from(ctrl_hdr.cmd) != VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET {
+                        warn!("Unsupported command: {}", ctrl_hdr.cmd);
+                        false
+                    } else if (queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN as u16)
+                        || (queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX as u16)
+                    {
+                        warn!("Number of MQ pairs out of range: {}", queue_pairs);
+                        false
+                    } else {
+                        info!("Number of MQ pairs requested: {}", queue_pairs);
+                        true
+                    }
+                }
+                VIRTIO_NET_CTRL_GUEST_OFFLOADS => {
+                    let features = mem
+                        .read_obj::<u64>(data_desc.addr)
+                        .map_err(Error::GuestMemory)?;
+                    if u32::from(ctrl_hdr.cmd) != VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET {
+                        warn!("Unsupported command: {}", ctrl_hdr.cmd);
+                        false
+                    } else {
+                        let mut ok = true;
+                        for tap in self.taps.iter_mut() {
+                            info!("Reprogramming tap offload with features: {}", features);
+                            tap.set_offload(virtio_features_to_tap_offload(features))
+                                .map_err(|e| {
+                                    error!("Error programming tap offload: {:?}", e);
+                                    ok = false
+                                })
+                                .ok();
+                        }
+                        ok
+                    }
+                }
+                _ => {
+                    warn!("Unsupported command {:?}", ctrl_hdr);
+                    false
+                }
+            };
+
+            mem.write_obj(
+                if ok { VIRTIO_NET_OK } else { VIRTIO_NET_ERR } as u8,
+                status_desc.addr,
+            )
+            .map_err(Error::GuestMemory)?;
+            used_desc_heads.push((avail_desc.index, avail_desc.len));
+        }
+
+        for (desc_index, len) in used_desc_heads.iter() {
+            queue.add_used(&mem, *desc_index, *len);
+            queue.update_avail_event(&mem);
+        }
+
+        Ok(!used_desc_heads.is_empty())
+    }
+}
+
+pub fn virtio_features_to_tap_offload(features: u64) -> c_uint {
+    let mut tap_offloads: c_uint = 0;
+    if features & (1 << VIRTIO_NET_F_GUEST_CSUM) != 0 {
+        tap_offloads |= net_gen::TUN_F_CSUM;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_TSO4) != 0 {
+        tap_offloads |= net_gen::TUN_F_TSO4;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_TSO6) != 0 {
+        tap_offloads |= net_gen::TUN_F_TSO6;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_ECN) != 0 {
+        tap_offloads |= net_gen::TUN_F_TSO_ECN;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_UFO) != 0 {
+        tap_offloads |= net_gen::TUN_F_UFO;
+    }
+
+    tap_offloads
+}

net_util/src/lib.rs

@@ -10,25 +10,31 @@
 #[cfg(test)]
 #[macro_use]
 extern crate lazy_static;
-extern crate libc;
 #[macro_use]
 extern crate log;
-extern crate net_gen;
-extern crate serde;
-extern crate virtio_bindings;
-extern crate vm_memory;
-extern crate vm_virtio;
-extern crate vmm_sys_util;
 
+mod ctrl_queue;
 mod mac;
 mod open_tap;
 mod queue_pair;
 mod tap;
 
 use std::io::Error as IoError;
+use std::os::raw::c_uint;
 use std::os::unix::io::{FromRawFd, RawFd};
 use std::{io, mem, net};
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
+use virtio_bindings::bindings::virtio_net::{
+    virtio_net_hdr_v1, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN,
+    VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_TSO4,
+    VIRTIO_NET_F_GUEST_TSO6, VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_MAC, VIRTIO_NET_F_MQ,
+};
+use vm_memory::{bitmap::AtomicBitmap, ByteValued};
 
+type GuestMemoryMmap = vm_memory::GuestMemoryMmap<AtomicBitmap>;
+
+pub use ctrl_queue::{CtrlQueue, Error as CtrlQueueError};
 pub use mac::{MacAddr, MAC_ADDR_LEN};
 pub use open_tap::{open_tap, Error as OpenTapError};
 pub use queue_pair::{NetCounters, NetQueuePair, NetQueuePairError, RxVirtio, TxVirtio};
@@ -42,6 +48,20 @@ pub enum Error {
 
 pub type Result<T> = std::result::Result<T, Error>;
 
+#[repr(C, packed)]
+#[derive(Copy, Clone, Debug, Default, Versionize)]
+pub struct VirtioNetConfig {
+    pub mac: [u8; 6],
+    pub status: u16,
+    pub max_virtqueue_pairs: u16,
+    pub mtu: u16,
+    pub speed: u32,
+    pub duplex: u8,
+}
+
+// Safe because it only has data and has no implicit padding.
+unsafe impl ByteValued for VirtioNetConfig {}
+
 /// Create a sockaddr_in from an IPv4 address, and expose it as
 /// an opaque sockaddr suitable for usage by socket ioctls.
 fn create_sockaddr(ip_addr: net::Ipv4Addr) -> net_gen::sockaddr {
@@ -69,7 +89,6 @@ fn create_socket() -> Result<net::UdpSocket> {
 }
 
 fn vnet_hdr_len() -> usize {
-    use virtio_bindings::bindings::virtio_net::virtio_net_hdr_v1;
     std::mem::size_of::<virtio_net_hdr_v1>()
 }
 
@@ -101,6 +120,53 @@ pub fn unregister_listener(
     )
 }
 
+pub fn build_net_config_space(
+    mut config: &mut VirtioNetConfig,
+    mac: MacAddr,
+    num_queues: usize,
+    avail_features: &mut u64,
+) {
+    config.mac.copy_from_slice(mac.get_bytes());
+    *avail_features |= 1 << VIRTIO_NET_F_MAC;
+
+    build_net_config_space_with_mq(&mut config, num_queues, avail_features);
+}
+
+pub fn build_net_config_space_with_mq(
+    config: &mut VirtioNetConfig,
+    num_queues: usize,
+    avail_features: &mut u64,
+) {
+    let num_queue_pairs = (num_queues / 2) as u16;
+    if (num_queue_pairs >= VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN as u16)
+        && (num_queue_pairs <= VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX as u16)
+    {
+        config.max_virtqueue_pairs = num_queue_pairs;
+        *avail_features |= 1 << VIRTIO_NET_F_MQ;
+    }
+}
+
+pub fn virtio_features_to_tap_offload(features: u64) -> c_uint {
+    let mut tap_offloads: c_uint = 0;
+    if features & (1 << VIRTIO_NET_F_GUEST_CSUM) != 0 {
+        tap_offloads |= net_gen::TUN_F_CSUM;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_TSO4) != 0 {
+        tap_offloads |= net_gen::TUN_F_TSO4;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_TSO6) != 0 {
+        tap_offloads |= net_gen::TUN_F_TSO6;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_ECN) != 0 {
+        tap_offloads |= net_gen::TUN_F_TSO_ECN;
+    }
+    if features & (1 << VIRTIO_NET_F_GUEST_UFO) != 0 {
+        tap_offloads |= net_gen::TUN_F_UFO;
+    }
+
+    tap_offloads
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;

net_util/src/mac.rs

@@ -152,8 +152,6 @@ impl FromStr for MacAddr {
 
 #[cfg(test)]
 mod tests {
-    extern crate serde_json;
-
     use super::*;
 
     #[test]

net_util/src/open_tap.rs

@@ -27,8 +27,6 @@ pub enum Error {
     TapSetMac(TapError),
     /// Getting MAC address failed
     TapGetMac(TapError),
-    /// Setting tap interface offload flags failed.
-    TapSetOffload(TapError),
     /// Setting vnet header size failed.
     TapSetVnetHdrSize(TapError),
     /// Enabling tap interface failed.
@@ -70,7 +68,6 @@ pub fn open_tap(
     let mut taps: Vec<Tap> = Vec::new();
     let mut ifname: String = String::new();
     let vnet_hdr_size = vnet_hdr_len() as i32;
-    let flag = net_gen::TUN_F_CSUM | net_gen::TUN_F_UFO | net_gen::TUN_F_TSO4 | net_gen::TUN_F_TSO6;
 
     // In case the tap interface already exists, check if the number of
     // queues is appropriate. The tap might not support multiqueue while
@@ -98,7 +95,6 @@ pub fn open_tap(
                 *host_mac = Some(tap.get_mac_addr().map_err(Error::TapGetMac)?)
             }
             tap.enable().map_err(Error::TapEnable)?;
-            tap.set_offload(flag).map_err(Error::TapSetOffload)?;
 
             tap.set_vnet_hdr_size(vnet_hdr_size)
                 .map_err(Error::TapSetVnetHdrSize)?;
@@ -106,7 +102,6 @@ pub fn open_tap(
             ifname = String::from_utf8(tap.get_if_name()).unwrap();
         } else {
             tap = Tap::open_named(ifname.as_str(), num_rx_q, flags).map_err(Error::TapOpen)?;
-            tap.set_offload(flag).map_err(Error::TapSetOffload)?;
 
             tap.set_vnet_hdr_size(vnet_hdr_size)
                 .map_err(Error::TapSetVnetHdrSize)?;

net_util/src/queue_pair.rs

@@ -3,12 +3,14 @@
 // SPDX-License-Identifier: Apache-2.0 AND BSD-3-Clause
 
 use super::{unregister_listener, vnet_hdr_len, Tap};
+use crate::GuestMemoryMmap;
+use rate_limiter::{RateLimiter, TokenType};
 use std::io;
 use std::num::Wrapping;
 use std::os::unix::io::{AsRawFd, RawFd};
 use std::sync::atomic::{AtomicU64, Ordering};
 use std::sync::Arc;
-use vm_memory::{Bytes, GuestAddressSpace, GuestMemory, GuestMemoryAtomic, GuestMemoryMmap};
+use vm_memory::{Bytes, GuestAddressSpace, GuestMemory, GuestMemoryAtomic};
 use vm_virtio::Queue;
 
 #[derive(Clone)]
@@ -36,11 +38,35 @@ impl TxVirtio {
         mem: &GuestMemoryMmap,
         tap: &mut Tap,
         queue: &mut Queue,
+        rate_limiter: &mut Option<RateLimiter>,
     ) -> Result<(), NetQueuePairError> {
         while let Some(avail_desc) = queue.iter(&mem).next() {
             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 {
@@ -67,8 +93,14 @@ impl TxVirtio {
                 };
                 if result < 0 {
                     let e = std::io::Error::last_os_error();
-                    error!("net: tx: failed writing to tap: {}", e);
                     queue.go_to_previous_position();
+
+                    /* EAGAIN */
+                    if e.kind() == std::io::ErrorKind::WouldBlock {
+                        warn!("net: tx: (recoverable) failed writing to tap: {}", e);
+                        break;
+                    }
+                    error!("net: tx: failed writing to tap: {}", e);
                     return Err(NetQueuePairError::WriteTap(e));
                 }
 
@@ -109,9 +141,18 @@ impl RxVirtio {
         mem: &GuestMemoryMmap,
         tap: &mut Tap,
         queue: &mut Queue,
+        rate_limiter: &mut Option<RateLimiter>,
     ) -> Result<bool, NetQueuePairError> {
         let mut exhausted_descs = true;
+        let mut rate_limit_reached = false;
+
         while let Some(avail_desc) = queue.iter(&mem).next() {
+            if rate_limit_reached {
+                exhausted_descs = false;
+                queue.go_to_previous_position();
+                break;
+            }
+
             let head_index = avail_desc.index;
             let num_buffers_addr = mem.checked_offset(avail_desc.addr, 10).unwrap();
             let mut next_desc = Some(avail_desc);
@@ -145,10 +186,9 @@ impl RxVirtio {
                     exhausted_descs = false;
                     queue.go_to_previous_position();
 
-                    if let Some(raw_err) = e.raw_os_error() {
-                        if raw_err == libc::EAGAIN {
-                            break;
-                        }
+                    /* EAGAIN */
+                    if e.kind() == std::io::ErrorKind::WouldBlock {
+                        break;
                     }
 
                     error!("net: rx: failed reading from tap: {}", e);
@@ -170,6 +210,15 @@ impl RxVirtio {
 
             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
+            // 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(exhausted_descs)
@@ -209,6 +258,9 @@ pub struct NetQueuePair {
     pub rx_tap_listening: bool,
     pub counters: NetCounters,
     pub tap_event_id: u16,
+    pub rx_desc_avail: bool,
+    pub rx_rate_limiter: Option<RateLimiter>,
+    pub tx_rate_limiter: Option<RateLimiter>,
 }
 
 impl NetQueuePair {
@@ -220,7 +272,7 @@ impl NetQueuePair {
             .map(|m| m.memory())?;
 
         self.tx
-            .process_desc_chain(&mem, &mut self.tap, &mut queue)?;
+            .process_desc_chain(&mem, &mut self.tap, &mut queue, &mut self.tx_rate_limiter)?;
 
         self.counters
             .tx_bytes
@@ -241,11 +293,21 @@ impl NetQueuePair {
             .ok_or(NetQueuePairError::NoMemoryConfigured)
             .map(|m| m.memory())?;
 
-        if self
-            .rx
-            .process_desc_chain(&mem, &mut self.tap, &mut queue)?
-            && self.rx_tap_listening
-        {
+        self.rx_desc_avail = !self.rx.process_desc_chain(
+            &mem,
+            &mut self.tap,
+            &mut queue,
+            &mut self.rx_rate_limiter,
+        )?;
+        let rate_limit_reached = self
+            .rx_rate_limiter
+            .as_ref()
+            .map_or(false, |r| r.is_blocked());
+
+        // Stop listening on the `RX_TAP_EVENT` when:
+        // 1) there is no available describles, or
+        // 2) the RX rate limit is reached.
+        if self.rx_tap_listening && (!self.rx_desc_avail || rate_limit_reached) {
             unregister_listener(
                 self.epoll_fd.unwrap(),
                 self.tap.as_raw_fd(),

net_util/src/tap.rs

@@ -6,8 +6,7 @@
 // found in the THIRD-PARTY file.
 
 use super::{create_sockaddr, create_socket, vnet_hdr_len, Error as NetUtilError, MacAddr};
-use mac::MAC_ADDR_LEN;
-use net_gen;
+use crate::mac::MAC_ADDR_LEN;
 use std::fs::File;
 use std::io::{Error as IoError, Read, Result as IoResult, Write};
 use std::net;
@@ -121,13 +120,12 @@ impl Tap {
         let mut ifreq: net_gen::ifreq = Default::default();
         unsafe {
             let ifrn_name = ifreq.ifr_ifrn.ifrn_name.as_mut();
-            let ifru_flags = ifreq.ifr_ifru.ifru_flags.as_mut();
             let name_slice = &mut ifrn_name[..terminated_if_name.len()];
             name_slice.copy_from_slice(terminated_if_name.as_slice());
-            *ifru_flags =
+            ifreq.ifr_ifru.ifru_flags =
                 (net_gen::IFF_TAP | net_gen::IFF_NO_PI | net_gen::IFF_VNET_HDR) as c_short;
             if num_queue_pairs > 1 {
-                *ifru_flags |= net_gen::IFF_MULTI_QUEUE as c_short;
+                ifreq.ifr_ifru.ifru_flags |= net_gen::IFF_MULTI_QUEUE as c_short;
             }
         }
 
@@ -138,8 +136,7 @@ impl Tap {
             return Err(Error::ConfigureTap(IoError::last_os_error()));
         }
 
-        let if_name_temp = unsafe { *ifreq.ifr_ifrn.ifrn_name.as_ref() };
-        let mut if_name = if_name_temp.to_vec();
+        let mut if_name = unsafe { ifreq.ifr_ifrn.ifrn_name }.to_vec();
         if_name.truncate(terminated_if_name.len() - 1);
         // Safe since only the name is accessed, and it's cloned out.
         Ok(Tap {
@@ -173,16 +170,16 @@ impl Tap {
         if ret < 0 {
             return Err(Error::IoctlError(IoError::last_os_error()));
         }
-        let if_name = unsafe { *ifreq.ifr_ifrn.ifrn_name.as_ref() }.to_vec();
+        // We only access one field of the ifru union, hence this is safe.
+        let if_name = unsafe { ifreq.ifr_ifrn.ifrn_name }.to_vec();
 
         // Try and update flags. Depending on how the tap was created (macvtap
         // or via open_named()) this might return -EEXIST so we just ignore that.
         unsafe {
-            let ifru_flags = ifreq.ifr_ifru.ifru_flags.as_mut();
-            *ifru_flags =
+            ifreq.ifr_ifru.ifru_flags =
                 (net_gen::IFF_TAP | net_gen::IFF_NO_PI | net_gen::IFF_VNET_HDR) as c_short;
             if num_queue_pairs > 1 {
-                *ifru_flags |= net_gen::IFF_MULTI_QUEUE as c_short;
+                ifreq.ifr_ifru.ifru_flags |= net_gen::IFF_MULTI_QUEUE as c_short;
             }
         }
         let ret = unsafe { ioctl_with_mut_ref(&tap_file, net_gen::TUNSETIFF(), &mut ifreq) };
@@ -190,11 +187,8 @@ impl Tap {
             return Err(Error::ConfigureTap(IoError::last_os_error()));
         }
 
-        let tap = Tap { if_name, tap_file };
-        let offload_flags =
-            net_gen::TUN_F_CSUM | net_gen::TUN_F_UFO | net_gen::TUN_F_TSO4 | net_gen::TUN_F_TSO6;
+        let tap = Tap { tap_file, if_name };
         let vnet_hdr_size = vnet_hdr_len() as i32;
-        tap.set_offload(offload_flags)?;
         tap.set_vnet_hdr_size(vnet_hdr_size)?;
 
         Ok(tap)
@@ -207,11 +201,7 @@ impl Tap {
 
         let mut ifreq = self.get_ifreq();
 
-        // We only access one field of the ifru union, hence this is safe.
-        unsafe {
-            let ifru_addr = ifreq.ifr_ifru.ifru_addr.as_mut();
-            *ifru_addr = addr;
-        }
+        ifreq.ifr_ifru.ifru_addr = addr;
 
         // ioctl is safe. Called with a valid sock fd, and we check the return.
         #[allow(clippy::cast_lossless)]
@@ -248,9 +238,9 @@ impl Tap {
         }
         // We only access one field of the ifru union, hence this is safe.
         unsafe {
-            let ifru_hwaddr = ifreq.ifr_ifru.ifru_hwaddr.as_mut();
+            let ifru_hwaddr = &mut ifreq.ifr_ifru.ifru_hwaddr;
             for (i, v) in addr.get_bytes().iter().enumerate() {
-                ifru_hwaddr.sa_data[i] = *v as c_char;
+                ifru_hwaddr.sa_data[i] = *v as c_uchar;
             }
         }
 
@@ -281,11 +271,8 @@ impl Tap {
 
         // We only access one field of the ifru union, hence this is safe.
         let addr = unsafe {
-            let ifru_hwaddr = ifreq.ifr_ifru.ifru_hwaddr.as_ref();
-            MacAddr::from_bytes(
-                &*(&ifru_hwaddr.sa_data[0..MAC_ADDR_LEN] as *const _ as *const [u8]),
-            )
-            .map_err(Error::MacParsing)?
+            MacAddr::from_bytes(&ifreq.ifr_ifru.ifru_hwaddr.sa_data[0..MAC_ADDR_LEN])
+                .map_err(Error::MacParsing)?
         };
         Ok(addr)
     }
@@ -297,11 +284,7 @@ impl Tap {
 
         let mut ifreq = self.get_ifreq();
 
-        // We only access one field of the ifru union, hence this is safe.
-        unsafe {
-            let ifru_addr = ifreq.ifr_ifru.ifru_addr.as_mut();
-            *ifru_addr = addr;
-        }
+        ifreq.ifr_ifru.ifru_addr = addr;
 
         // ioctl is safe. Called with a valid sock fd, and we check the return.
         #[allow(clippy::cast_lossless)]
@@ -341,7 +324,7 @@ impl Tap {
         }
 
         // If TAP device is already up don't try and enable it
-        let ifru_flags = unsafe { ifreq.ifr_ifru.ifru_flags.as_ref() };
+        let ifru_flags = unsafe { ifreq.ifr_ifru.ifru_flags };
         if ifru_flags
             & (net_gen::net_device_flags_IFF_UP | net_gen::net_device_flags_IFF_RUNNING) as i16
             == (net_gen::net_device_flags_IFF_UP | net_gen::net_device_flags_IFF_RUNNING) as i16
@@ -349,13 +332,8 @@ impl Tap {
             return Ok(());
         }
 
-        // We only access one field of the ifru union, hence this is safe.
-        unsafe {
-            let ifru_flags = ifreq.ifr_ifru.ifru_flags.as_mut();
-
-            *ifru_flags =
-                (net_gen::net_device_flags_IFF_UP | net_gen::net_device_flags_IFF_RUNNING) as i16;
-        }
+        ifreq.ifr_ifru.ifru_flags =
+            (net_gen::net_device_flags_IFF_UP | net_gen::net_device_flags_IFF_RUNNING) as i16;
 
         // ioctl is safe. Called with a valid sock fd, and we check the return.
         #[allow(clippy::cast_lossless)]
@@ -634,18 +612,6 @@ mod tests {
         assert!(ret.is_ok());
     }
 
-    #[test]
-    fn test_tap_get_ifreq() {
-        let _tap_ip_guard = TAP_IP_LOCK.lock().unwrap();
-
-        let tap = Tap::new(1).unwrap();
-        let ret = tap.get_ifreq();
-        assert_eq!(
-            "__BindgenUnionField",
-            format!("{:?}", ret.ifr_ifrn.ifrn_name)
-        );
-    }
-
     #[test]
     fn test_raw_fd() {
         let _tap_ip_guard = TAP_IP_LOCK.lock().unwrap();

pci/Cargo.toml

@@ -10,11 +10,10 @@ 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 = "0.2.91"
+libc = "0.2.96"
 log = "0.4.14"
-serde = {version = ">=1.0.27", features = ["rc"] }
-serde_derive = ">=1.0.27"
-serde_json = ">=1.0.9"
+versionize = "0.1.6"
+versionize_derive = "0.1.4"
 vm-allocator = { path = "../vm-allocator" }
 vm-device = { path = "../vm-device" }
 vm-memory = "0.5.0"

pci/src/configuration.rs

@@ -4,11 +4,12 @@
 
 use crate::device::BarReprogrammingParams;
 use crate::{MsixConfig, PciInterruptPin};
-use anyhow::anyhow;
 use byteorder::{ByteOrder, LittleEndian};
 use std::fmt::{self, Display};
 use std::sync::{Arc, Mutex};
-use vm_migration::{MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable};
+use versionize::{VersionMap, Versionize, VersionizeError, VersionizeResult};
+use versionize_derive::Versionize;
+use vm_migration::{MigratableError, Pausable, Snapshot, Snapshottable, VersionMapped};
 
 // The number of 32bit registers in the config space, 4096 bytes.
 const NUM_CONFIGURATION_REGISTERS: usize = 1024;
@@ -277,7 +278,7 @@ fn decode_64_bits_bar_size(bar_size_hi: u32, bar_size_lo: u32) -> Option<u64> {
     None
 }
 
-#[derive(Serialize, Deserialize, Default, Clone, Copy)]
+#[derive(Default, Clone, Copy, Versionize)]
 struct PciBar {
     addr: u32,
     size: u32,
@@ -285,7 +286,7 @@ struct PciBar {
     r#type: Option<PciBarRegionType>,
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 struct PciConfigurationState {
     registers: Vec<u32>,
     writable_bits: Vec<u32>,
@@ -297,6 +298,8 @@ struct PciConfigurationState {
     msix_cap_reg_idx: Option<usize>,
 }
 
+impl VersionMapped for PciConfigurationState {}
+
 /// Contains the configuration space of a PCI node.
 /// See the [specification](https://en.wikipedia.org/wiki/PCI_configuration_space).
 /// The configuration space is accessed with DWORD reads and writes from the guest.
@@ -314,7 +317,7 @@ pub struct PciConfiguration {
 }
 
 /// See pci_regs.h in kernel
-#[derive(Copy, Clone, PartialEq, Serialize, Deserialize)]
+#[derive(Copy, Clone, PartialEq, Versionize)]
 pub enum PciBarRegionType {
     Memory32BitRegion = 0,
     IoRegion = 0x01,
@@ -769,85 +772,77 @@ impl PciConfiguration {
 
         let mask = self.writable_bits[reg_idx];
         if (BAR0_REG..BAR0_REG + NUM_BAR_REGS).contains(&reg_idx) {
+            // Ignore the case where the BAR size is being asked for.
+            if value == 0xffff_ffff {
+                return None;
+            }
+
             let bar_idx = reg_idx - 4;
-            if (value & mask) != (self.bars[bar_idx].addr & mask) {
-                // Handle special case where the address being written is
-                // different from the address initially provided. This is a
-                // BAR reprogramming case which needs to be properly caught.
-                if let Some(bar_type) = self.bars[bar_idx].r#type {
-                    match bar_type {
-                        PciBarRegionType::Memory64BitRegion => {}
-                        _ => {
-                            // Ignore the case where the BAR size is being
-                            // asked for.
-                            if value == 0xffff_ffff {
-                                return None;
-                            }
-
-                            debug!(
-                                "DETECT BAR REPROG: current 0x{:x}, new 0x{:x}",
-                                self.registers[reg_idx], value
-                            );
-                            let old_base = u64::from(self.bars[bar_idx].addr & mask);
-                            let new_base = u64::from(value & mask);
-                            let len = u64::from(
-                                decode_32_bits_bar_size(self.bars[bar_idx].size)
-                                    .ok_or(Error::Decode32BarSize)
-                                    .unwrap(),
-                            );
-                            let region_type = bar_type;
-
-                            self.bars[bar_idx].addr = value;
-
-                            return Some(BarReprogrammingParams {
-                                old_base,
-                                new_base,
-                                len,
-                                region_type,
-                            });
-                        }
-                    }
-                } else if (reg_idx > BAR0_REG)
-                    && (self.registers[reg_idx - 1] & self.writable_bits[reg_idx - 1])
-                        != (self.bars[bar_idx - 1].addr & self.writable_bits[reg_idx - 1])
-                {
-                    // Ignore the case where the BAR size is being asked for.
-                    // Because we are in the 64bits case here, we have to check
-                    // if the lower 32bits of the current BAR have already been
-                    // asked for the BAR size too.
-                    if value == 0xffff_ffff
-                        && self.registers[reg_idx - 1] & self.writable_bits[reg_idx - 1]
-                            == self.bars[bar_idx - 1].size & self.writable_bits[reg_idx - 1]
-                    {
-                        return None;
-                    }
-
-                    debug!(
-                        "DETECT BAR REPROG: current 0x{:x}, new 0x{:x}",
-                        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]);
-                    let new_base = u64::from(value & mask) << 32
-                        | u64::from(self.registers[reg_idx - 1] & self.writable_bits[reg_idx - 1]);
-                    let len = decode_64_bits_bar_size(
-                        self.bars[bar_idx].size,
-                        self.bars[bar_idx - 1].size,
-                    )
-                    .ok_or(Error::Decode64BarSize)
-                    .unwrap();
-                    let region_type = PciBarRegionType::Memory64BitRegion;
-
-                    self.bars[bar_idx].addr = value;
-                    self.bars[bar_idx - 1].addr = self.registers[reg_idx - 1];
-
-                    return Some(BarReprogrammingParams {
-                        old_base,
-                        new_base,
-                        len,
-                        region_type,
-                    });
+            // Handle special case where the address being written is
+            // different from the address initially provided. This is a
+            // BAR reprogramming case which needs to be properly caught.
+            if let Some(bar_type) = self.bars[bar_idx].r#type {
+                // In case of 64 bits memory BAR, we don't do anything until
+                // the upper BAR is modified, otherwise we would be moving the
+                // BAR to a wrong location in memory.
+                if bar_type == PciBarRegionType::Memory64BitRegion {
+                    return None;
                 }
+
+                // Ignore the case where the value is unchanged.
+                if (value & mask) == (self.bars[bar_idx].addr & mask) {
+                    return None;
+                }
+
+                debug!(
+                    "DETECT BAR REPROG: current 0x{:x}, new 0x{:x}",
+                    self.registers[reg_idx], value
+                );
+                let old_base = u64::from(self.bars[bar_idx].addr & mask);
+                let new_base = u64::from(value & mask);
+                let len = u64::from(
+                    decode_32_bits_bar_size(self.bars[bar_idx].size)
+                        .ok_or(Error::Decode32BarSize)
+                        .unwrap(),
+                );
+                let region_type = bar_type;
+
+                self.bars[bar_idx].addr = value;
+
+                return Some(BarReprogrammingParams {
+                    old_base,
+                    new_base,
+                    len,
+                    region_type,
+                });
+            } else if (reg_idx > BAR0_REG)
+                && ((self.registers[reg_idx - 1] & self.writable_bits[reg_idx - 1])
+                    != (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
+                );
+                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]);
+                let new_base = u64::from(value & mask) << 32
+                    | u64::from(self.registers[reg_idx - 1] & self.writable_bits[reg_idx - 1]);
+                let len =
+                    decode_64_bits_bar_size(self.bars[bar_idx].size, self.bars[bar_idx - 1].size)
+                        .ok_or(Error::Decode64BarSize)
+                        .unwrap();
+                let region_type = PciBarRegionType::Memory64BitRegion;
+
+                self.bars[bar_idx].addr = value;
+                self.bars[bar_idx - 1].addr = self.registers[reg_idx - 1];
+
+                return Some(BarReprogrammingParams {
+                    old_base,
+                    new_base,
+                    len,
+                    region_type,
+                });
             }
         } else if reg_idx == ROM_BAR_REG && (value & mask) != (self.rom_bar_addr & mask) {
             // Ignore the case where the BAR size is being asked for.
@@ -890,43 +885,12 @@ impl Snapshottable for PciConfiguration {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let snapshot =
-            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-        let mut config_snapshot = Snapshot::new(self.id().as_str());
-        config_snapshot.add_data_section(SnapshotDataSection {
-            id: format!("{}-section", self.id()),
-            snapshot,
-        });
-
-        Ok(config_snapshot)
+        Snapshot::new_from_versioned_state(&self.id(), &self.state())
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        if let Some(config_section) = snapshot
-            .snapshot_data
-            .get(&format!("{}-section", self.id()))
-        {
-            let config_state = match serde_json::from_slice(&config_section.snapshot) {
-                Ok(state) => state,
-                Err(error) => {
-                    return Err(MigratableError::Restore(anyhow!(
-                        "Could not deserialize {}: {}",
-                        self.id(),
-                        error
-                    )))
-                }
-            };
-
-            self.set_state(&config_state);
-
-            return Ok(());
-        }
-
-        Err(MigratableError::Restore(anyhow!(
-            "Could not find {} snapshot section",
-            self.id()
-        )))
+        self.set_state(&snapshot.to_versioned_state(&self.id())?);
+        Ok(())
     }
 }
 

pci/src/lib.rs

@@ -5,12 +5,6 @@
 //! Implements pci devices and busses.
 #[macro_use]
 extern crate log;
-extern crate hypervisor;
-extern crate serde;
-#[macro_use]
-extern crate serde_derive;
-extern crate serde_json;
-extern crate vm_memory;
 
 mod bus;
 mod configuration;

pci/src/msi.rs

@@ -3,9 +3,6 @@
 // SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause
 //
 
-extern crate byteorder;
-extern crate vm_memory;
-
 use byteorder::{ByteOrder, LittleEndian};
 use std::sync::Arc;
 use vm_device::interrupt::{

pci/src/msix.rs

@@ -3,20 +3,19 @@
 // SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause
 //
 
-extern crate byteorder;
-extern crate vm_memory;
-
 use crate::{PciCapability, PciCapabilityId};
 use anyhow::anyhow;
 use byteorder::{ByteOrder, LittleEndian};
 use std::io;
 use std::result;
 use std::sync::Arc;
+use versionize::{VersionMap, Versionize, VersionizeResult};
+use versionize_derive::Versionize;
 use vm_device::interrupt::{
     InterruptIndex, InterruptSourceConfig, InterruptSourceGroup, MsiIrqSourceConfig,
 };
 use vm_memory::ByteValued;
-use vm_migration::{MigratableError, Pausable, Snapshot, SnapshotDataSection, Snapshottable};
+use vm_migration::{MigratableError, Pausable, Snapshot, Snapshottable, VersionMapped};
 
 const MAX_MSIX_VECTORS_PER_DEVICE: u16 = 2048;
 const MSIX_TABLE_ENTRIES_MODULO: u64 = 16;
@@ -36,7 +35,7 @@ enum Error {
     UpdateInterruptRoute(io::Error),
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Versionize)]
 pub struct MsixTableEntry {
     pub msg_addr_lo: u32,
     pub msg_addr_hi: u32,
@@ -61,7 +60,7 @@ impl Default for MsixTableEntry {
     }
 }
 
-#[derive(Serialize, Deserialize)]
+#[derive(Versionize)]
 struct MsixConfigState {
     table_entries: Vec<MsixTableEntry>,
     pba_entries: Vec<u64>,
@@ -69,6 +68,8 @@ struct MsixConfigState {
     enabled: bool,
 }
 
+impl VersionMapped for MsixConfigState {}
+
 pub struct MsixConfig {
     pub table_entries: Vec<MsixTableEntry>,
     pub pba_entries: Vec<u64>,
@@ -432,41 +433,18 @@ impl Snapshottable for MsixConfig {
     }
 
     fn snapshot(&mut self) -> std::result::Result<Snapshot, MigratableError> {
-        let snapshot =
-            serde_json::to_vec(&self.state()).map_err(|e| MigratableError::Snapshot(e.into()))?;
-
-        let mut msix_snapshot = Snapshot::new(self.id().as_str());
-        msix_snapshot.add_data_section(SnapshotDataSection {
-            id: format!("{}-section", self.id()),
-            snapshot,
-        });
-
-        Ok(msix_snapshot)
+        Snapshot::new_from_versioned_state(&self.id(), &self.state())
     }
 
     fn restore(&mut self, snapshot: Snapshot) -> std::result::Result<(), MigratableError> {
-        if let Some(msix_section) = snapshot
-            .snapshot_data
-            .get(&format!("{}-section", self.id()))
-        {
-            let msix_state = match serde_json::from_slice(&msix_section.snapshot) {
-                Ok(state) => state,
-                Err(error) => {
-                    return Err(MigratableError::Restore(anyhow!(
-                        "Could not deserialize MSI-X {}",
-                        error
-                    )))
-                }
-            };
-
-            return self.set_state(&msix_state).map_err(|e| {
-                MigratableError::Restore(anyhow!("Could not restore MSI-X state {:?}", e))
-            });
-        }
-
-        Err(MigratableError::Restore(anyhow!(
-            "Could not find MSI-X snapshot section"
-        )))
+        self.set_state(&snapshot.to_versioned_state(&self.id())?)
+            .map_err(|e| {
+                MigratableError::Restore(anyhow!(
+                    "Could not restore state for {}: {:?}",
+                    self.id(),
+                    e
+                ))
+            })
     }
 }
 

pci/src/vfio.rs

@@ -3,8 +3,6 @@
 // SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause
 //
 
-extern crate vm_allocator;
-
 use crate::{
     msi_num_enabled_vectors, BarReprogrammingParams, MsiConfig, MsixCap, MsixConfig,
     PciBarConfiguration, PciBarRegionType, PciCapabilityId, PciClassCode, PciConfiguration,
@@ -910,26 +908,14 @@ impl PciDevice for VfioPciDevice {
                 let first_bit = region_size.trailing_zeros();
                 region_size = 2u64.pow(first_bit);
 
-                // We need to allocate a guest MMIO address range for that BAR.
-                // In case the BAR is mappable directly, this means it might be
-                // set as user memory region, which expects to deal with 4K
-                // pages. Therefore, the alignment has to be set accordingly.
-                let bar_alignment = if (bar_id == VFIO_PCI_ROM_REGION_INDEX)
-                    || (self.device.get_region_flags(bar_id) & VFIO_REGION_INFO_FLAG_MMAP != 0)
-                {
-                    // 4K alignment
-                    0x1000
-                } else {
-                    // Default 16 bytes alignment
-                    0x10
-                };
+                // BAR allocation needs to be naturally aligned
                 if is_64bit_bar {
                     bar_addr = allocator
-                        .allocate_mmio_addresses(None, region_size, Some(bar_alignment))
+                        .allocate_mmio_addresses(None, region_size, Some(region_size))
                         .ok_or(PciDeviceError::IoAllocationFailed(region_size))?;
                 } else {
                     bar_addr = allocator
-                        .allocate_mmio_hole_addresses(None, region_size, Some(bar_alignment))
+                        .allocate_mmio_hole_addresses(None, region_size, Some(region_size))
                         .ok_or(PciDeviceError::IoAllocationFailed(region_size))?;
                 }
             }

qcow/Cargo.toml

@@ -10,7 +10,7 @@ path = "src/qcow.rs"
 
 [dependencies]
 byteorder = "1.4.3"
-libc = "0.2.91"
+libc = "0.2.96"
 log = "0.4.14"
 remain = "0.2.2"
 vmm-sys-util = ">=0.3.1"

rate_limiter/Cargo.toml

@@ -0,0 +1,9 @@
+[package]
+name = "rate_limiter"
+version = "0.1.0"
+edition = "2018"
+
+[dependencies]
+libc = "0.2.96"
+log = "0.4.14"
+vmm-sys-util = "0.8.0"

rate_limiter/src/lib.rs

@@ -43,6 +43,9 @@
 //! It is meant to be used in an external event loop and thus implements the `AsRawFd`
 //! trait and provides an *event-handler* as part of its API. This *event-handler*
 //! needs to be called by the user on every event on the rate limiter's `AsRawFd` FD.
+#[macro_use]
+extern crate log;
+
 use std::os::unix::io::{AsRawFd, RawFd};
 use std::time::{Duration, Instant};
 use std::{fmt, io};

release-notes.md

@@ -1,3 +1,19 @@
+- [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)
+    - [Removed functionality](#removed-functionality)
+    - [Contributors](#contributors)
+- [v15.0](#v150)
+    - [Version numbering and stability guarantees](#version-numbering-and-stability-guarantees)
+    - [Network device rate limiting](#network-device-rate-limiting)
+    - [Support for runtime control of `virtio-net` guest offload](#support-for-runtime-control-of-virtio-net-guest-offload)
+    - [`--api-socket` supports file descriptor parameter](#--api-socket-supports-file-descriptor-parameter)
+    - [Bug fixes](#bug-fixes)
+    - [Deprecations](#deprecations)
+    - [Contributors](#contributors-1)
+- [v0.14.1](#v0141)
 - [v0.14.0](#v0140)
     - [Structured event monitoring](#structured-event-monitoring)
     - [MSHV improvements](#mshv-improvements)
@@ -5,8 +21,8 @@
     - [Updated hotplug documentation](#updated-hotplug-documentation)
     - [PTY control for serial and `virtio-console`](#pty-control-for-serial-and-virtio-console)
     - [Block device rate limiting](#block-device-rate-limiting)
-    - [Deprecations](#deprecations)
-    - [Contributors](#contributors)
+    - [Deprecations](#deprecations-1)
+    - [Contributors](#contributors-2)
 - [v0.13.0](#v0130)
     - [Wider VFIO device support](#wider-vfio-device-support)
     - [Improved huge page support](#improved-huge-page-support)
@@ -14,13 +30,13 @@
     - [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-1)
+    - [Contributors](#contributors-3)
 - [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-2)
+    - [Contributors](#contributors-4)
 - [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)
@@ -32,15 +48,15 @@
     - [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)
-    - [Contributors](#contributors-3)
+    - [Notable Bug Fixes](#notable-bug-fixes-1)
+    - [Contributors](#contributors-5)
 - [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-1)
-    - [Contributors](#contributors-4)
+    - [Notable Bug Fixes](#notable-bug-fixes-2)
+    - [Contributors](#contributors-6)
 - [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)
@@ -53,17 +69,17 @@
     - [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-2)
-    - [Contributors](#contributors-5)
+    - [Notable Bug Fixes](#notable-bug-fixes-3)
+    - [Contributors](#contributors-7)
 - [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-3)
+    - [Notable Bug Fixes](#notable-bug-fixes-4)
     - [Command Line and API Changes](#command-line-and-api-changes)
-    - [Contributors](#contributors-6)
+    - [Contributors](#contributors-8)
 - [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)
@@ -73,14 +89,14 @@
     - [`Seccomp` Sandboxing](#seccomp-sandboxing)
     - [Updated Distribution Support](#updated-distribution-support)
     - [Command Line and API Changes](#command-line-and-api-changes-1)
-    - [Contributors](#contributors-7)
+    - [Contributors](#contributors-9)
 - [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-8)
+    - [Contributors](#contributors-10)
 - [v0.5.1](#v051)
 - [v0.5.0](#v050)
     - [Virtual Machine Dynamic Resizing](#virtual-machine-dynamic-resizing)
@@ -88,7 +104,7 @@
     - [New Interrupt Management Framework](#new-interrupt-management-framework)
     - [Development Tools](#development-tools)
     - [Kata Containers Integration](#kata-containers-integration)
-    - [Contributors](#contributors-9)
+    - [Contributors](#contributors-11)
 - [v0.4.0](#v040)
     - [Dynamic virtual CPUs addition](#dynamic-virtual-cpus-addition)
     - [Programmatic firmware tables generation](#programmatic-firmware-tables-generation)
@@ -97,7 +113,7 @@
     - [Userspace IOAPIC by default](#userspace-ioapic-by-default)
     - [PCI BAR reprogramming](#pci-bar-reprogramming)
     - [New `cloud-hypervisor` organization](#new-cloud-hypervisor-organization)
-    - [Contributors](#contributors-10)
+    - [Contributors](#contributors-12)
 - [v0.3.0](#v030)
     - [Block device offloading](#block-device-offloading)
     - [Network device backend](#network-device-backend)
@@ -124,6 +140,135 @@
     - [Unit testing](#unit-testing)
     - [Integration tests parallelization](#integration-tests-parallelization)
 
+# v16.0
+
+This release has been tracked through the [v16.0 project](https://github.com/cloud-hypervisor/cloud-hypervisor/projects/19).
+
+### Improved live migration support
+
+The live migration support inside Cloud Hypervisor has been improved with the addition of the tracking of dirty pages written by the VMM to complement the tracking of dirty pages made by the guest itself. Further the internal state of the VMM now is versioned which allows the safe migration of VMs from one version of the VMM to a newer one. However further testing is required so this should be done with care. See the [live migration documentation](docs/live_migration.md) for more details.
+
+### Improved `vhost-user` support
+
+When using `vhost-user` to access devices implemented in different processes there is now support for reconnection of those devices in the case of a restart of the backend. In addition it is now possible to operate with the direction of the `vhost-user-net` connection reversed with the server in the VMM and the client in the backend. This is aligns with the default approach recommended by Open vSwitch.
+
+### ARM64 ACPI and UEFI support
+
+Cloud Hypervisor now supports using ACPI and booting from a UEFI image on ARM64. This allows the use of stock OS images without direct kernel boot.
+
+### Notable bug fixes
+
+* Activating fewer `virtio-net` queues than advertised is now supported. This appeared when using OVMF with an MQ enabled device (#2578).
+* When using MQ with `virtio` devices Cloud Hypervisor now enforces a minimum vCPU count which ensures that the user will not see adverse guest performance (#2563).
+* The KVM clock is now correctly handled during live migration / snapshot & restore.
+
+### Removed functionality
+
+The following formerly deprecated features have been removed:
+
+* Support for booting with the "LinuxBoot" protocol for ELF and `bzImage`
+  binaries has been deprecated. When using direct boot users should configure
+  their kernel with `CONFIG_PVH=y`.
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release including some new faces.
+
+* Anatol Belski <anbelski@linux.microsoft.com>
+* Bo Chen <chen.bo@intel.com>
+* Dayu Liu <liu.dayu@zte.com.cn>
+* Henry Wang <Henry.Wang@arm.com>
+* Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
+* Jianyong Wu <jianyong.wu@arm.com>
+* Michael Zhao <michael.zhao@arm.com>
+* Mikko Ylinen <mikko.ylinen@intel.com>
+* Muminul Islam <muislam@microsoft.com>
+* Ren Lei <ren.lei4@zte.com.cn>
+* Rob Bradford <robert.bradford@intel.com>
+* Sebastien Boeuf <sebastien.boeuf@intel.com>
+* Wei Liu <liuwe@microsoft.com>
+* Yi Wang <wang.yi59@zte.com.cn>
+
+# v15.0
+
+This release has been tracked through the [v15.0 project](https://github.com/cloud-hypervisor/cloud-hypervisor/projects/18).
+
+Highlights for `cloud-hypervisor` version v15.0 include:
+
+### Version numbering and stability guarantees
+
+This release is the first in a new version numbering scheme to represent that
+we believe Cloud Hypervisor is maturing and entering a period of stability.
+With this new release we are beginning our new stability guarantees:
+
+* The API (including command line options) will not be removed or changed in a
+  breaking way without a minimum of 2 releases notice. Where possible warnings
+  will be given about the use of deprecated functionality and the deprecations
+  will be documented in the release notes.
+* Point releases will be made between individual releases where there are
+  substantial bug fixes or security issues that need to be fixed.
+
+Currently the following items are **not** guaranteed across updates:
+
+* Snapshot/restore is not supported across different versions
+* Live migration is not supported across different versions
+* The following features are considered experimental and may change
+  substantially between releases: TDX, SGX.
+
+### Network device rate limiting
+
+Building on our existing support for rate limiting block activity the network
+device also now supports rate limiting. Full details of the controls are in the
+[IO throttling documentation.](docs/io_throttling.md)
+
+### Support for runtime control of `virtio-net` guest offload
+
+The guest is now able to change the offload settings for the `virtio-net`
+device. As well as providing a useful control this mitigates an issue in the
+Linux kernel where the guest will attempt to reprogram the offload settings
+even if they are not advertised as configurable (#2528).
+
+### `--api-socket` supports file descriptor parameter
+
+The `--api-socket` can now take an `fd=` parameter to specify an existing file
+descriptor to use. This is particularly beneficial for frameworks that need to
+programmatically control Cloud Hypervisor.
+
+### Bug fixes
+
+* A workaround has been put in place to mitigate a Linux kernel issues that
+  results in the CPU thread spinning at 100% when using `virtio-pmem` (#2277).
+* PCI BARs are now correctly aligned removing the need for the guest to
+  reprogram them (#1797,#1798)
+* Handle TAP interface not being writable within virtio-net (due to the buffer
+  exhaustion on the host) (#2517)
+* The recommended Linux kernel is now v5.12.0 as it contains a fix that
+  prevents snapshot & restore working (#2535)
+
+### Deprecations
+
+Deprecated features will be removed in a subsequent release and users should plan to use alternatives
+
+* Support for booting with the "LinuxBoot" protocol for ELF and `bzImage`
+  binaries has been deprecated. When using direct boot users should configure
+  their kernel with `CONFIG_PVH=y`. Will be removed in v16.0.
+
+### Contributors
+
+Many thanks to everyone who has contributed to our release including some new faces.
+
+* Alyssa Ross <hi@alyssa.is>
+* Anatol Belski <anbelski@linux.microsoft.com>
+* Bo Chen <chen.bo@intel.com>
+* Gaelan Steele <gbs@canishe.com>
+* Jianyong Wu <jianyong.wu@arm.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>
+* William Douglas <william.douglas@intel.com>
+
 # v0.14.1
 
 Bug fix release branched off the v0.14.0 release. The following bugs were fixed
@@ -176,7 +321,7 @@ PTY subsystem.
 
 The block device performance can now be constrained as part of the VM
 configuration allowing rate limiting. Full details of the controls are in the
-[IO throttling doumentation.](docs/io_throttling.md)
+[IO throttling documentation.](docs/io_throttling.md)
 
 
 ### Deprecations
@@ -764,11 +909,11 @@ to run their guest I/O into separate executions contexts.
 ### Command Line Interface
 
 More and more Cloud Hypervisor services are exposed through the
-[Rest API](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/vmm/src/api/openapi/cloud-hypervisor.yaml)
-and thus only accessible via relatively cumbersome HTTP calls. In order
-to abstract those calls into a more user friendly tool, we created a Cloud
-Hypervisor Command Line Interface (CLI) called `ch-remote`.
-The `ch-remote` binary is created with each build and available e.g. at
+[Rest API](vmm/src/api/openapi/cloud-hypervisor.yaml) and thus only
+accessible via relatively cumbersome HTTP calls. In order to abstract
+those calls into a more user friendly tool, we created a Cloud Hypervisor
+Command Line Interface (CLI) called `ch-remote`.  The `ch-remote` binary
+is created with each build and available e.g. at
 `cloud-hypervisor/target/debug/ch-remote` when doing a debug build.
 
 Please check `ch-remote --help` for a complete description of all available
@@ -844,7 +989,7 @@ In order to provide a better developer experience, we worked on improving our
 build, development and testing tools.
 Somehow similar to the excellent
 [Firecracker's devtool](https://github.com/firecracker-microvm/firecracker/blob/master/tools/devtool),
-we now provide a [dev_cli script](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/scripts/dev_cli.sh).
+we now provide a [dev_cli script](scripts/dev_cli.sh).
 
 With this new tool, our users and contributors will be able to build and test
 Cloud Hypervisor through a containerized environment.
@@ -881,7 +1026,7 @@ As a way to vertically scale Cloud-Hypervisor guests, we now support dynamically
 adding virtual CPUs to the guests, a mechanism also known as CPU hot plug.
 Through hardware-reduced ACPI notifications, Cloud Hypervisor can now add CPUs
 to an already running guest and the high level operations for that process are
-documented [here](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/hotplug.md)
+documented [here](docs/hotplug.md)
 
 During the next release cycles we are planning to extend Cloud Hypervisor
 hot plug framework to other resources, namely PCI devices and memory.
@@ -997,9 +1142,8 @@ configurations that do not require a PCI bus emulation.
 ### Paravirtualized IOMMU
 
 As we want to improve our nested guests support, we added support for exposing
-a [paravirtualized IOMMU](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/iommu.md)
-device through virtio. This allows for a safer nested virtio and directly
-assigned devices support.
+a [paravirtualized IOMMU](docs/iommu.md) device through virtio. This allows
+for a safer nested virtio and directly assigned devices support.
 
 To add the IOMMU support, we had to make some CLI changes for Cloud Hypervisor
 users to be able to specify if devices had to be handled through this virtual
@@ -1048,8 +1192,8 @@ Based on the Firecracker idea of using a dedicated I/O port to measure guest
 boot times, we added support for logging guest events through the
 [0x80](https://www.intel.com/content/www/us/en/support/articles/000005500/boards-and-kits.html)
 PC debug port. This allows, among other things, for granular guest boot time
-measurements. See our [debug port documentation](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/debug-port.md)
-for more details.
+measurements. See our [debug port documentation](docs/debug-port.md) for more
+details.
 
 ### Improved direct device assignment
 
@@ -1084,8 +1228,8 @@ We added support for the [virtio-fs](https://virtio-fs.gitlab.io/) shared file
 system, allowing for an efficient and reliable way of sharing a filesystem
 between the host and the `cloud-hypervisor` guest.
 
-See our [filesystem sharing](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/fs.md)
-documentation for more details on how to use virtio-fs with `cloud-hypervisor`.
+See our [filesystem sharing](docs/fs.md) documentation for more details on how
+to use virtio-fs with `cloud-hypervisor`.
 
 ### Initial direct device assignment support
 
@@ -1093,9 +1237,8 @@ VFIO (Virtual Function I/O) is a kernel framework that exposes direct device
 access to userspace. `cloud-hypervisor` uses VFIO to directly assign host
 physical devices into its guest.
 
-See our [VFIO](https://github.com/cloud-hypervisor/cloud-hypervisor/blob/master/docs/vfio.md)
-documentation for more detail on how to directly assign host devices to
-`cloud-hypervisor` guests.
+See our [VFIO](docs/vfio.md) documentation for more detail on how to directly
+assign host devices to `cloud-hypervisor` guests.
 
 ### Userspace IOAPIC
 

resources/Dockerfile

@@ -1,7 +1,7 @@
-FROM ubuntu:18.04 as dev
+FROM ubuntu:20.04 as dev
 
 ARG TARGETARCH
-ARG RUST_TOOLCHAIN="1.49.0"
+ARG RUST_TOOLCHAIN="1.52.1"
 ARG CLH_SRC_DIR="/cloud-hypervisor"
 ARG CLH_BUILD_DIR="$CLH_SRC_DIR/build"
 ARG CARGO_REGISTRY_DIR="$CLH_BUILD_DIR/cargo_registry"
@@ -37,12 +37,18 @@ RUN apt-get update \
 	socat \
 	dosfstools \
 	cpio \
-	bsdtar \
-	libfdt-dev \
+	python \
+	python3 \
 	python3-setuptools \
+	ntfs-3g \
+	openvswitch-switch-dpdk \
+	python3-distutils \
+	uuid-dev \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
+RUN update-alternatives --set ovs-vswitchd /usr/lib/openvswitch-switch-dpdk/ovs-vswitchd-dpdk
+
 RUN if [ "$TARGETARCH" = "amd64" ]; then \
 	apt-get update \
 	&& apt-get -yq upgrade \
@@ -57,14 +63,7 @@ RUN if [ "$TARGETARCH" = "arm64" ]; then \
         && apt-get -yq upgrade \
         && DEBIAN_FRONTEND=noninteractive apt-get install -yq libcap2-bin \
         && apt-get clean \
-        && rm -rf /var/lib/apt/lists/* \
-        # Build and install the musl-gcc version of libfdt. This is to ensure
-        # the cloud-hypervisor binary can be built and linked using musl toolchain.
-        && git clone https://github.com/dgibson/dtc.git && cd dtc \
-        && sed -i 's/$(LIBFDT_archive) $(LIBFDT_lib)/$(LIBFDT_archive)/g' Makefile \
-        && export CC=musl-gcc && make libfdt \
-        && cp libfdt/libfdt.a /usr/lib/aarch64-linux-musl \
-        && rm -rf /dtc;	fi
+        && rm -rf /var/lib/apt/lists/*;	fi
 
 # Fix the libssl-dev install
 RUN export ARCH="$(uname -m)" \