rust: introduce alternative implementation of offset_of!

offset_of! was stabilized in Rust 1.77.0.  Use an alternative implemenation
that was found on the Rust forums, and whose author agreed to license as
MIT for use in QEMU.

The alternative allows only one level of field access, but apart
from this can be used just by replacing core::mem::offset_of! with
qemu_api::offset_of!.

The actual implementation of offset_of! is done in a declarative macro,
but for simplicity and to avoid introducing an extra level of indentation,
the trigger is a procedural macro #[derive(offsets)].

The procedural macro is perhaps a bit overengineered, but it helps
introducing some idioms that will be useful in the future as well.

Signed-off-by: Junjie Mao <[email protected]>
Co-developed-by: Paolo Bonzini <[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

rust/hw/char/pl011/src/device.rs

@@ -55,7 +55,7 @@ impl DeviceId {
 }
 
 #[repr(C)]
-#[derive(Debug, qemu_api_macros::Object)]
+#[derive(Debug, qemu_api_macros::Object, qemu_api_macros::offsets)]
 /// PL011 Device Model in QEMU
 pub struct PL011State {
     pub parent_obj: SysBusDevice,

rust/qemu-api-macros/Cargo.toml

@@ -19,4 +19,4 @@ proc-macro = true
 [dependencies]
 proc-macro2 = "1"
 quote = "1"
-syn = "2"
+syn = { version = "2", features = ["extra-traits"] }

rust/qemu-api-macros/src/lib.rs

@@ -3,8 +3,34 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 use proc_macro::TokenStream;
-use quote::quote;
-use syn::{parse_macro_input, DeriveInput};
+use proc_macro2::Span;
+use quote::{quote, quote_spanned};
+use syn::{
+    parse_macro_input, parse_quote, punctuated::Punctuated, token::Comma, Data, DeriveInput, Field,
+    Fields, Ident, Type, Visibility,
+};
+
+struct CompileError(String, Span);
+
+impl From<CompileError> for proc_macro2::TokenStream {
+    fn from(err: CompileError) -> Self {
+        let CompileError(msg, span) = err;
+        quote_spanned! { span => compile_error!(#msg); }
+    }
+}
+
+fn is_c_repr(input: &DeriveInput, msg: &str) -> Result<(), CompileError> {
+    let expected = parse_quote! { #[repr(C)] };
+
+    if input.attrs.iter().any(|attr| attr == &expected) {
+        Ok(())
+    } else {
+        Err(CompileError(
+            format!("#[repr(C)] required for {}", msg),
+            input.ident.span(),
+        ))
+    }
+}
 
 #[proc_macro_derive(Object)]
 pub fn derive_object(input: TokenStream) -> TokenStream {
@@ -21,3 +47,48 @@ pub fn derive_object(input: TokenStream) -> TokenStream {
 
     TokenStream::from(expanded)
 }
+
+fn get_fields(input: &DeriveInput) -> Result<&Punctuated<Field, Comma>, CompileError> {
+    if let Data::Struct(s) = &input.data {
+        if let Fields::Named(fs) = &s.fields {
+            Ok(&fs.named)
+        } else {
+            Err(CompileError(
+                "Cannot generate offsets for unnamed fields.".to_string(),
+                input.ident.span(),
+            ))
+        }
+    } else {
+        Err(CompileError(
+            "Cannot generate offsets for union or enum.".to_string(),
+            input.ident.span(),
+        ))
+    }
+}
+
+#[rustfmt::skip::macros(quote)]
+fn derive_offsets_or_error(input: DeriveInput) -> Result<proc_macro2::TokenStream, CompileError> {
+    is_c_repr(&input, "#[derive(offsets)]")?;
+
+    let name = &input.ident;
+    let fields = get_fields(&input)?;
+    let field_names: Vec<&Ident> = fields.iter().map(|f| f.ident.as_ref().unwrap()).collect();
+    let field_types: Vec<&Type> = fields.iter().map(|f| &f.ty).collect();
+    let field_vis: Vec<&Visibility> = fields.iter().map(|f| &f.vis).collect();
+
+    Ok(quote! {
+	::qemu_api::with_offsets! {
+	    struct #name {
+		#(#field_vis #field_names: #field_types,)*
+	    }
+	}
+    })
+}
+
+#[proc_macro_derive(offsets)]
+pub fn derive_offsets(input: TokenStream) -> TokenStream {
+    let input = parse_macro_input!(input as DeriveInput);
+    let expanded = derive_offsets_or_error(input).unwrap_or_else(Into::into);
+
+    TokenStream::from(expanded)
+}

rust/qemu-api/Cargo.toml

@@ -16,9 +16,13 @@ categories = []
 [dependencies]
 qemu_api_macros = { path = "../qemu-api-macros" }
 
+[build-dependencies]
+version_check = "~0.9"
+
 [features]
 default = []
 allocator = []
 
 [lints.rust]
-unexpected_cfgs = { level = "warn", check-cfg = ['cfg(MESON)', 'cfg(HAVE_GLIB_WITH_ALIGNED_ALLOC)'] }
+unexpected_cfgs = { level = "warn", check-cfg = ['cfg(MESON)', 'cfg(HAVE_GLIB_WITH_ALIGNED_ALLOC)',
+                                                 'cfg(has_offset_of)'] }

rust/qemu-api/build.rs

@@ -4,11 +4,20 @@
 
 use std::path::Path;
 
+use version_check as rustc;
+
 fn main() {
     if !Path::new("src/bindings.rs").exists() {
         panic!(
             "No generated C bindings found! Either build them manually with bindgen or with meson \
              (`ninja bindings.rs`) and copy them to src/bindings.rs, or build through meson."
         );
     }
+
+    // Check for available rustc features
+    if rustc::is_min_version("1.77.0").unwrap_or(false) {
+        println!("cargo:rustc-cfg=has_offset_of");
+    }
+
+    println!("cargo:rerun-if-changed=build.rs");
 }

rust/qemu-api/meson.build

@@ -1,3 +1,9 @@
+_qemu_api_cfg = ['--cfg', 'MESON']
+# _qemu_api_cfg += ['--cfg', 'feature="allocator"']
+if rustc.version().version_compare('>=1.77.0')
+  _qemu_api_cfg += ['--cfg', 'has_offset_of']
+endif
+
 _qemu_api_rs = static_library(
   'qemu_api',
   structured_sources(
@@ -6,17 +12,15 @@ _qemu_api_rs = static_library(
       'src/c_str.rs',
       'src/definitions.rs',
       'src/device_class.rs',
+      'src/offset_of.rs',
       'src/vmstate.rs',
       'src/zeroable.rs',
     ],
     {'.' : bindings_rs},
   ),
   override_options: ['rust_std=2021', 'build.rust_std=2021'],
   rust_abi: 'rust',
-  rust_args: [
-    '--cfg', 'MESON',
-    # '--cfg', 'feature="allocator"',
-  ],
+  rust_args: _qemu_api_cfg,
 )
 
 rust.test('rust-qemu-api-tests', _qemu_api_rs,

rust/qemu-api/src/device_class.rs

@@ -23,23 +23,23 @@ macro_rules! device_class_init {
 
 #[macro_export]
 macro_rules! define_property {
-    ($name:expr, $state:ty, $field:expr, $prop:expr, $type:expr, default = $defval:expr$(,)*) => {
+    ($name:expr, $state:ty, $field:ident, $prop:expr, $type:expr, default = $defval:expr$(,)*) => {
         $crate::bindings::Property {
             // use associated function syntax for type checking
             name: ::std::ffi::CStr::as_ptr($name),
             info: $prop,
-            offset: ::core::mem::offset_of!($state, $field) as isize,
+            offset: $crate::offset_of!($state, $field) as isize,
             set_default: true,
             defval: $crate::bindings::Property__bindgen_ty_1 { u: $defval as u64 },
             ..$crate::zeroable::Zeroable::ZERO
         }
     };
-    ($name:expr, $state:ty, $field:expr, $prop:expr, $type:expr$(,)*) => {
+    ($name:expr, $state:ty, $field:ident, $prop:expr, $type:expr$(,)*) => {
         $crate::bindings::Property {
             // use associated function syntax for type checking
             name: ::std::ffi::CStr::as_ptr($name),
             info: $prop,
-            offset: ::core::mem::offset_of!($state, $field) as isize,
+            offset: $crate::offset_of!($state, $field) as isize,
             set_default: false,
             ..$crate::zeroable::Zeroable::ZERO
         }

rust/qemu-api/src/lib.rs

@@ -32,6 +32,7 @@ unsafe impl Sync for bindings::VMStateInfo {}
 pub mod c_str;
 pub mod definitions;
 pub mod device_class;
+pub mod offset_of;
 pub mod vmstate;
 pub mod zeroable;
 
@@ -169,3 +170,6 @@ unsafe impl GlobalAlloc for QemuAllocator {
         }
     }
 }
+
+#[cfg(has_offset_of)]
+pub use core::mem::offset_of;

rust/qemu-api/src/offset_of.rs

@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: MIT
+
+/// This macro provides the same functionality as `core::mem::offset_of`,
+/// except that only one level of field access is supported.  The declaration
+/// of the struct must be wrapped with `with_offsets! { }`.
+///
+/// It is needed because `offset_of!` was only stabilized in Rust 1.77.
+#[cfg(not(has_offset_of))]
+#[macro_export]
+macro_rules! offset_of {
+    ($Container:ty, $field:ident) => {
+        <$Container>::OFFSET_TO__.$field
+    };
+}
+
+/// A wrapper for struct declarations, that allows using `offset_of!` in
+/// versions of Rust prior to 1.77
+#[macro_export]
+macro_rules! with_offsets {
+    // This method to generate field offset constants comes from:
+    //
+    //     https://play.rust-lang.org/?version=stable&mode=debug&edition=2018&gist=10a22a9b8393abd7b541d8fc844bc0df
+    //
+    // used under MIT license with permission of Yandros aka Daniel Henry-Mantilla
+    (
+        $(#[$struct_meta:meta])*
+        $struct_vis:vis
+        struct $StructName:ident {
+            $(
+                $(#[$field_meta:meta])*
+                $field_vis:vis
+                $field_name:ident : $field_ty:ty
+            ),*
+            $(,)?
+        }
+    ) => (
+        #[cfg(not(has_offset_of))]
+        const _: () = {
+            struct StructOffsetsHelper<T>(std::marker::PhantomData<T>);
+            const END_OF_PREV_FIELD: usize = 0;
+
+            // populate StructOffsetsHelper<T> with associated consts,
+            // one for each field
+            $crate::with_offsets! {
+                @struct $StructName
+                @names [ $($field_name)* ]
+                @tys [ $($field_ty ,)*]
+            }
+
+            // now turn StructOffsetsHelper<T>'s consts into a single struct,
+            // applying field visibility.  This provides better error messages
+            // than if offset_of! used StructOffsetsHelper::<T> directly.
+            pub
+            struct StructOffsets {
+                $(
+                    $field_vis
+                    $field_name: usize,
+                )*
+            }
+            impl $StructName {
+                pub
+                const OFFSET_TO__: StructOffsets = StructOffsets {
+                    $(
+                        $field_name: StructOffsetsHelper::<$StructName>::$field_name,
+                    )*
+                };
+            }
+        };
+    );
+
+    (
+        @struct $StructName:ident
+        @names []
+        @tys []
+    ) => ();
+
+    (
+        @struct $StructName:ident
+        @names [$field_name:ident $($other_names:tt)*]
+        @tys [$field_ty:ty , $($other_tys:tt)*]
+    ) => (
+        #[allow(non_local_definitions)]
+        #[allow(clippy::modulo_one)]
+        impl StructOffsetsHelper<$StructName> {
+            #[allow(nonstandard_style)]
+            const $field_name: usize = {
+                const ALIGN: usize = std::mem::align_of::<$field_ty>();
+                const TRAIL: usize = END_OF_PREV_FIELD % ALIGN;
+                END_OF_PREV_FIELD + (if TRAIL == 0 { 0usize } else { ALIGN - TRAIL })
+            };
+        }
+        const _: () = {
+            const END_OF_PREV_FIELD: usize =
+                StructOffsetsHelper::<$StructName>::$field_name +
+                std::mem::size_of::<$field_ty>()
+            ;
+            $crate::with_offsets! {
+                @struct $StructName
+                @names [$($other_names)*]
+                @tys [$($other_tys)*]
+            }
+        };
+    );
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::offset_of;
+
+    #[repr(C)]
+    struct Foo {
+        a: u16,
+        b: u32,
+        c: u64,
+        d: u16,
+    }
+
+    #[repr(C)]
+    struct Bar {
+        pub a: u16,
+        pub b: u64,
+        c: Foo,
+        d: u64,
+    }
+
+    crate::with_offsets! {
+        #[repr(C)]
+        struct Bar {
+            pub a: u16,
+            pub b: u64,
+            c: Foo,
+            d: u64,
+        }
+    }
+
+    #[repr(C)]
+    pub struct Baz {
+        b: u32,
+        a: u8,
+    }
+    crate::with_offsets! {
+        #[repr(C)]
+        pub struct Baz {
+            b: u32,
+            a: u8,
+        }
+    }
+
+    #[test]
+    fn test_offset_of() {
+        const OFFSET_TO_C: usize = offset_of!(Bar, c);
+
+        assert_eq!(offset_of!(Bar, a), 0);
+        assert_eq!(offset_of!(Bar, b), 8);
+        assert_eq!(OFFSET_TO_C, 16);
+        assert_eq!(offset_of!(Bar, d), 40);
+
+        assert_eq!(offset_of!(Baz, b), 0);
+        assert_eq!(offset_of!(Baz, a), 4);
+    }
+}