[PATCH v2] rust: macros: fix soundness issue in `module!` macro

[Benno Lossin]

The `module!` macro creates glue code that are called by C to initialize
the Rust modules using the `Module::init` function. Part of this glue
code are the local functions `__init` and `__exit` that are used to
initialize/destroy the Rust module.
These functions are safe and also visible to the Rust mod in which the
`module!` macro is invoked. This means that they can be called by other
safe Rust code. But since they contain `unsafe` blocks that rely on only
being called at the right time, this is a soundness issue.

Wrap these generated functions inside of two private modules, this
guarantees that the public functions cannot be called from the outside.
Make the safe functions `unsafe` and add SAFETY comments.

Cc: stable@xxxxxxxxxxxxxxx
Closes: https://github.com/Rust-for-Linux/linux/issues/629
Fixes: 1fbde52bde73 ("rust: add `macros` crate")
Signed-off-by: Benno Lossin <benno.lossin@xxxxxxxxx>
---
v1: https://lore.kernel.org/rust-for-linux/20240327160346.22442-1-benno.lossin@xxxxxxxxx/
v1 -> v2:
- wrapped `__init` and `__exit` calls in `unsafe` blocks and added
  SAFETY comments,
- fixed safety requirement on `__exit` and `__init`,
- rebased onto rust-next.

 rust/macros/module.rs | 213 +++++++++++++++++++++++++-----------------
 1 file changed, 127 insertions(+), 86 deletions(-)

diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index 27979e582e4b..293beca0a583 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -199,103 +199,144 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
             /// Used by the printing macros, e.g. [`info!`].
             const __LOG_PREFIX: &[u8] = b\"{name}\\0\";
 
-            /// The \"Rust loadable module\" mark.
-            //
-            // This may be best done another way later on, e.g. as a new modinfo
-            // key or a new section. For the moment, keep it simple.
-            #[cfg(MODULE)]
-            #[doc(hidden)]
-            #[used]
-            static __IS_RUST_MODULE: () = ();
-
-            static mut __MOD: Option<{type_}> = None;
-
-            // SAFETY: `__this_module` is constructed by the kernel at load time and will not be
-            // freed until the module is unloaded.
-            #[cfg(MODULE)]
-            static THIS_MODULE: kernel::ThisModule = unsafe {{
-                kernel::ThisModule::from_ptr(&kernel::bindings::__this_module as *const _ as *mut _)
-            }};
-            #[cfg(not(MODULE))]
-            static THIS_MODULE: kernel::ThisModule = unsafe {{
-                kernel::ThisModule::from_ptr(core::ptr::null_mut())
-            }};
-
-            // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
-            /// # Safety
-            ///
-            /// This function must not be called after module initialization, because it may be
-            /// freed after that completes.
-            #[cfg(MODULE)]
-            #[doc(hidden)]
-            #[no_mangle]
-            #[link_section = \".init.text\"]
-            pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
-                __init()
-            }}
+            // Double nested modules, since then nobody can access the public items inside.
+            mod __module_init {{
+                mod __module_init {{
+                    use super::super::{type_};
+
+                    /// The \"Rust loadable module\" mark.
+                    //
+                    // This may be best done another way later on, e.g. as a new modinfo
+                    // key or a new section. For the moment, keep it simple.
+                    #[cfg(MODULE)]
+                    #[doc(hidden)]
+                    #[used]
+                    static __IS_RUST_MODULE: () = ();
+
+                    static mut __MOD: Option<{type_}> = None;
+
+                    // SAFETY: `__this_module` is constructed by the kernel at load time and will not be
+                    // freed until the module is unloaded.
+                    #[cfg(MODULE)]
+                    static THIS_MODULE: kernel::ThisModule = unsafe {{
+                        kernel::ThisModule::from_ptr(&kernel::bindings::__this_module as *const _ as *mut _)
+                    }};
+                    #[cfg(not(MODULE))]
+                    static THIS_MODULE: kernel::ThisModule = unsafe {{
+                        kernel::ThisModule::from_ptr(core::ptr::null_mut())
+                    }};
+
+                    // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
+                    /// # Safety
+                    ///
+                    /// This function must not be called after module initialization, because it may be
+                    /// freed after that completes.
+                    #[cfg(MODULE)]
+                    #[doc(hidden)]
+                    #[no_mangle]
+                    #[link_section = \".init.text\"]
+                    pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
+                        // SAFETY: this function is inaccessible to the outside due to the double
+                        // module wrapping it. It is called exactly once by the C side via its
+                        // unique name.
+                        unsafe {{ __init() }}
+                    }}
 
-            #[cfg(MODULE)]
-            #[doc(hidden)]
-            #[no_mangle]
-            pub extern \"C\" fn cleanup_module() {{
-                __exit()
-            }}
+                    #[cfg(MODULE)]
+                    #[doc(hidden)]
+                    #[no_mangle]
+                    pub extern \"C\" fn cleanup_module() {{
+                        // SAFETY:
+                        // - this function is inaccessible to the outside due to the double
+                        //   module wrapping it. It is called exactly once by the C side via its
+                        //   unique name,
+                        // - furthermore it is only called after `init_module` has returned `0`
+                        //   (which delegates to `__init`).
+                        unsafe {{ __exit() }}
+                    }}
 
-            // Built-in modules are initialized through an initcall pointer
-            // and the identifiers need to be unique.
-            #[cfg(not(MODULE))]
-            #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))]
-            #[doc(hidden)]
-            #[link_section = \"{initcall_section}\"]
-            #[used]
-            pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init;
-
-            #[cfg(not(MODULE))]
-            #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
-            core::arch::global_asm!(
-                r#\".section \"{initcall_section}\", \"a\"
-                __{name}_initcall:
-                    .long   __{name}_init - .
-                    .previous
-                \"#
-            );
+                    // Built-in modules are initialized through an initcall pointer
+                    // and the identifiers need to be unique.
+                    #[cfg(not(MODULE))]
+                    #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))]
+                    #[doc(hidden)]
+                    #[link_section = \"{initcall_section}\"]
+                    #[used]
+                    pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init;
+
+                    #[cfg(not(MODULE))]
+                    #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
+                    core::arch::global_asm!(
+                        r#\".section \"{initcall_section}\", \"a\"
+                        __{name}_initcall:
+                            .long   __{name}_init - .
+                            .previous
+                        \"#
+                    );
+
+                    #[cfg(not(MODULE))]
+                    #[doc(hidden)]
+                    #[no_mangle]
+                    pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{
+                        // SAFETY: this function is inaccessible to the outside due to the double
+                        // module wrapping it. It is called exactly once by the C side via its
+                        // placement above in the initcall section.
+                        unsafe {{ __init() }}
+                    }}
 
-            #[cfg(not(MODULE))]
-            #[doc(hidden)]
-            #[no_mangle]
-            pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{
-                __init()
-            }}
+                    #[cfg(not(MODULE))]
+                    #[doc(hidden)]
+                    #[no_mangle]
+                    pub extern \"C\" fn __{name}_exit() {{
+                        // SAFETY:
+                        // - this function is inaccessible to the outside due to the double
+                        //   module wrapping it. It is called exactly once by the C side via its
+                        //   unique name,
+                        // - furthermore it is only called after `__{name}_init` has returned `0`
+                        //   (which delegates to `__init`).
+                        unsafe {{ __exit() }}
+                    }}
 
-            #[cfg(not(MODULE))]
-            #[doc(hidden)]
-            #[no_mangle]
-            pub extern \"C\" fn __{name}_exit() {{
-                __exit()
-            }}
+                    /// # Safety
+                    ///
+                    /// This function must only be called once.
+                    unsafe fn __init() -> core::ffi::c_int {{
+                        match <{type_} as kernel::Module>::init(&THIS_MODULE) {{
+                            Ok(m) => {{
+                                // SAFETY:
+                                // no data race, since `__MOD` can only be accessed by this module and
+                                // there only `__init` and `__exit` access it. These functions are only
+                                // called once and `__exit` cannot be called before or during `__init`.
+                                unsafe {{
+                                    __MOD = Some(m);
+                                }}
+                                return 0;
+                            }}
+                            Err(e) => {{
+                                return e.to_errno();
+                            }}
+                        }}
+                    }}
 
-            fn __init() -> core::ffi::c_int {{
-                match <{type_} as kernel::Module>::init(&THIS_MODULE) {{
-                    Ok(m) => {{
+                    /// # Safety
+                    ///
+                    /// This function must
+                    /// - only be called once,
+                    /// - be called after `__init` has been called and returned `0`.
+                    unsafe fn __exit() {{
+                        // SAFETY:
+                        // no data race, since `__MOD` can only be accessed by this module and there
+                        // only `__init` and `__exit` access it. These functions are only called once
+                        // and `__init` was already called.
                         unsafe {{
-                            __MOD = Some(m);
+                            // Invokes `drop()` on `__MOD`, which should be used for cleanup.
+                            __MOD = None;
                         }}
-                        return 0;
                     }}
-                    Err(e) => {{
-                        return e.to_errno();
-                    }}
-                }}
-            }}
 
-            fn __exit() {{
-                unsafe {{
-                    // Invokes `drop()` on `__MOD`, which should be used for cleanup.
-                    __MOD = None;
+                    {modinfo}
                 }}
             }}
-
-            {modinfo}
         ",
         type_ = info.type_,
         name = info.name,

base-commit: 9ffe2a730313f27cebd0859ea856247ac59c576c
-- 
2.44.0