[PATCH v3 1/3] rust: macros: add `decl_generics` to `parse_generics()`

[Benno Lossin]

The generic parameters on a type definition can specify default values.
Currently `parse_generics()` cannot handle this though. For example when
parsing the following generics:

    <T: Clone, const N: usize = 0>

The `impl_generics` will be set to `T: Clone, const N: usize = 0` and
`ty_generics` will be set to `T, N`. Now using the `impl_generics` on an
impl block:

    impl<$($impl_generics)*> Foo {}

will result in invalid Rust code, because default values are only
available on type definitions.

Therefore add parsing support for generic parameter default values using
a new kind of generics called `decl_generics` and change the old
behavior of `impl_generics` to not contain the generic parameter default
values.

Now `Generics` has three fields:
- `impl_generics`: the generics with bounds
  (e.g. `T: Clone, const N: usize`)
- `decl_generics`: the generics with bounds and default values
  (e.g. `T: Clone, const N: usize = 0`)
- `ty_generics`:  contains the generics without bounds and without
  default values (e.g. `T, N`)

`impl_generics` is designed to be used on `impl<$impl_generics>`,
`decl_generics` for the type definition, so `struct Foo<$decl_generics>`
and `ty_generics` whenever you use the type, so `Foo<$ty_generics>`.

Here is an example that uses all three different types of generics:

    let (Generics { decl_generics, impl_generics, ty_generics }, rest) = parse_generics(input);
    quote! {
        struct Foo<$($decl_generics)*> {
            // ...
        }

        impl<$impl_generics> Foo<$ty_generics> {
            fn foo() {
                // ...
            }
        }
    }

The next commit contains a fix to the `#[pin_data]` macro making it
compatible with generic parameter default values by relying on this new
behavior.

Signed-off-by: Benno Lossin <benno.lossin@xxxxxxxxx>
---
v2 -> v3:
- addressed Gary's nits
- add #[allow(dead_code)] to remove warning
- rebase onto rust-next

v1 -> v2:
- improve documentation and commit message explanation
- add motivation to commit message


v1: https://lore.kernel.org/rust-for-linux/20231125125024.1235933-1-benno.lossin@xxxxxxxxx/
v2: https://lore.kernel.org/rust-for-linux/20231213220447.3613500-1-benno.lossin@xxxxxxxxx/

 rust/macros/helpers.rs  | 123 ++++++++++++++++++++++++++++++----------
 rust/macros/pin_data.rs |   1 +
 rust/macros/zeroable.rs |   1 +
 3 files changed, 95 insertions(+), 30 deletions(-)

diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs
index afb0f2e3a36a..2497d6519f2f 100644
--- a/rust/macros/helpers.rs
+++ b/rust/macros/helpers.rs
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-use proc_macro::{token_stream, Group, Punct, Spacing, TokenStream, TokenTree};
+use proc_macro::{token_stream, Group, TokenStream, TokenTree};
 
 pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option<String> {
     if let Some(TokenTree::Ident(ident)) = it.next() {
@@ -70,8 +70,41 @@ pub(crate) fn expect_end(it: &mut token_stream::IntoIter) {
     }
 }
 
+/// Parsed generics.
+///
+/// See the field documentation for an explanation what each of the fields represents.
+///
+/// # Examples
+///
+/// ```rust,ignore
+/// # let input = todo!();
+/// let (Generics { decl_generics, impl_generics, ty_generics }, rest) = parse_generics(input);
+/// quote! {
+///     struct Foo<$($decl_generics)*> {
+///         // ...
+///     }
+///
+///     impl<$impl_generics> Foo<$ty_generics> {
+///         fn foo() {
+///             // ...
+///         }
+///     }
+/// }
+/// ```
 pub(crate) struct Generics {
+    /// The generics with bounds and default values (e.g. `T: Clone, const N: usize = 0`).
+    ///
+    /// Use this on type definitions e.g. `struct Foo<$decl_generics> ...` (or `union`/`enum`).
+    #[allow(dead_code)]
+    pub(crate) decl_generics: Vec<TokenTree>,
+    /// The generics with bounds (e.g. `T: Clone, const N: usize`).
+    ///
+    /// Use this on `impl` blocks e.g. `impl<$impl_generics> Trait for ...`.
     pub(crate) impl_generics: Vec<TokenTree>,
+    /// The generics without bounds and without default values (e.g. `T, N`).
+    ///
+    /// Use this when you use the type that is declared with these generics e.g.
+    /// `Foo<$ty_generics>`.
     pub(crate) ty_generics: Vec<TokenTree>,
 }
 
@@ -79,6 +112,8 @@ pub(crate) struct Generics {
 ///
 /// The generics are not present in the rest, but a where clause might remain.
 pub(crate) fn parse_generics(input: TokenStream) -> (Generics, Vec<TokenTree>) {
+    // The generics with bounds and default values.
+    let mut decl_generics = vec![];
     // `impl_generics`, the declared generics with their bounds.
     let mut impl_generics = vec![];
     // Only the names of the generics, without any bounds.
@@ -90,10 +125,17 @@ pub(crate) fn parse_generics(input: TokenStream) -> (Generics, Vec<TokenTree>) {
     let mut toks = input.into_iter();
     // If we are at the beginning of a generic parameter.
     let mut at_start = true;
-    for tt in &mut toks {
+    let mut skip_until_comma = false;
+    while let Some(tt) = toks.next() {
+        if nesting == 1 && matches!(&tt, TokenTree::Punct(p) if p.as_char() == '>') {
+            // Found the end of the generics.
+            break;
+        } else if nesting >= 1 {
+            decl_generics.push(tt.clone());
+        }
         match tt.clone() {
             TokenTree::Punct(p) if p.as_char() == '<' => {
-                if nesting >= 1 {
+                if nesting >= 1 && !skip_until_comma {
                     // This is inside of the generics and part of some bound.
                     impl_generics.push(tt);
                 }
@@ -105,49 +147,70 @@ pub(crate) fn parse_generics(input: TokenStream) -> (Generics, Vec<TokenTree>) {
                     break;
                 } else {
                     nesting -= 1;
-                    if nesting >= 1 {
+                    if nesting >= 1 && !skip_until_comma {
                         // We are still inside of the generics and part of some bound.
                         impl_generics.push(tt);
                     }
-                    if nesting == 0 {
-                        break;
-                    }
                 }
             }
-            tt => {
+            TokenTree::Punct(p) if skip_until_comma && p.as_char() == ',' => {
                 if nesting == 1 {
-                    // Here depending on the token, it might be a generic variable name.
-                    match &tt {
-                        // Ignore const.
-                        TokenTree::Ident(i) if i.to_string() == "const" => {}
-                        TokenTree::Ident(_) if at_start => {
-                            ty_generics.push(tt.clone());
-                            // We also already push the `,` token, this makes it easier to append
-                            // generics.
-                            ty_generics.push(TokenTree::Punct(Punct::new(',', Spacing::Alone)));
-                            at_start = false;
-                        }
-                        TokenTree::Punct(p) if p.as_char() == ',' => at_start = true,
-                        // Lifetimes begin with `'`.
-                        TokenTree::Punct(p) if p.as_char() == '\'' && at_start => {
-                            ty_generics.push(tt.clone());
-                        }
-                        _ => {}
-                    }
-                }
-                if nesting >= 1 {
+                    impl_generics.push(tt.clone());
                     impl_generics.push(tt);
-                } else if nesting == 0 {
+                    skip_until_comma = false;
+                }
+            }
+            _ if !skip_until_comma => {
+                match nesting {
                     // If we haven't entered the generics yet, we still want to keep these tokens.
-                    rest.push(tt);
+                    0 => rest.push(tt),
+                    1 => {
+                        // Here depending on the token, it might be a generic variable name.
+                        match tt.clone() {
+                            TokenTree::Ident(i) if at_start && i.to_string() == "const" => {
+                                let Some(name) = toks.next() else {
+                                    // Parsing error.
+                                    break;
+                                };
+                                impl_generics.push(tt);
+                                impl_generics.push(name.clone());
+                                ty_generics.push(name.clone());
+                                decl_generics.push(name);
+                                at_start = false;
+                            }
+                            TokenTree::Ident(_) if at_start => {
+                                impl_generics.push(tt.clone());
+                                ty_generics.push(tt);
+                                at_start = false;
+                            }
+                            TokenTree::Punct(p) if p.as_char() == ',' => {
+                                impl_generics.push(tt.clone());
+                                ty_generics.push(tt);
+                                at_start = true;
+                            }
+                            // Lifetimes begin with `'`.
+                            TokenTree::Punct(p) if p.as_char() == '\'' && at_start => {
+                                impl_generics.push(tt.clone());
+                                ty_generics.push(tt);
+                            }
+                            // Generics can have default values, we skip these.
+                            TokenTree::Punct(p) if p.as_char() == '=' => {
+                                skip_until_comma = true;
+                            }
+                            _ => impl_generics.push(tt),
+                        }
+                    }
+                    _ => impl_generics.push(tt),
                 }
             }
+            _ => {}
         }
     }
     rest.extend(toks);
     (
         Generics {
             impl_generics,
+            decl_generics,
             ty_generics,
         },
         rest,
diff --git a/rust/macros/pin_data.rs b/rust/macros/pin_data.rs
index 6d58cfda9872..022e68e9720d 100644
--- a/rust/macros/pin_data.rs
+++ b/rust/macros/pin_data.rs
@@ -10,6 +10,7 @@ pub(crate) fn pin_data(args: TokenStream, input: TokenStream) -> TokenStream {
     let (
         Generics {
             impl_generics,
+            decl_generics: _,
             ty_generics,
         },
         rest,
diff --git a/rust/macros/zeroable.rs b/rust/macros/zeroable.rs
index 0d605c46ab3b..cfee2cec18d5 100644
--- a/rust/macros/zeroable.rs
+++ b/rust/macros/zeroable.rs
@@ -7,6 +7,7 @@ pub(crate) fn derive(input: TokenStream) -> TokenStream {
     let (
         Generics {
             impl_generics,
+            decl_generics: _,
             ty_generics,
         },
         mut rest,

base-commit: 768409cff6cc89fe1194da880537a09857b6e4db
-- 
2.42.0