Auto merge of #95548 - rcvalle:rust-cfi-2, r=nagisa

Add fine-grained LLVM CFI support to the Rust compiler

This PR improves the LLVM Control Flow Integrity (CFI) support in the Rust compiler by providing forward-edge control flow protection for Rust-compiled code only by aggregating function pointers in groups identified by their return and parameter types.

Forward-edge control flow protection for C or C++ and Rust -compiled code "mixed binaries" (i.e., for when C or C++ and Rust -compiled code share the same virtual address space) will be provided in later work as part of this project by identifying C char and integer type uses at the time types are encoded (see Type metadata in the design document in the tracking issue https://github.com/rust-lang/rust/issues/89653).

LLVM CFI can be enabled with -Zsanitizer=cfi and requires LTO (i.e., -Clto).

Thank you again, `@eddyb,` `@nagisa,` `@pcc,` and `@tmiasko` for all the help!

compiler/rustc_codegen_llvm/Cargo.toml

@@ -18,7 +18,6 @@ rustc_middle = { path = "../rustc_middle" }
 rustc-demangle = "0.1.21"
 rustc_attr = { path = "../rustc_attr" }
 rustc_codegen_ssa = { path = "../rustc_codegen_ssa" }
-rustc_symbol_mangling = { path = "../rustc_symbol_mangling" }
 rustc_data_structures = { path = "../rustc_data_structures" }
 rustc_errors = { path = "../rustc_errors" }
 rustc_fs_util = { path = "../rustc_fs_util" }
@@ -30,6 +29,7 @@ rustc_metadata = { path = "../rustc_metadata" }
 rustc_query_system = { path = "../rustc_query_system" }
 rustc_session = { path = "../rustc_session" }
 rustc_serialize = { path = "../rustc_serialize" }
+rustc_symbol_mangling = { path = "../rustc_symbol_mangling" }
 rustc_target = { path = "../rustc_target" }
 smallvec = { version = "1.8.1", features = ["union", "may_dangle"] }
 rustc_ast = { path = "../rustc_ast" }

compiler/rustc_codegen_llvm/src/builder.rs

@@ -626,32 +626,6 @@ impl<'a, 'll, 'tcx> BuilderMethods<'a, 'tcx> for Builder<'a, 'll, 'tcx> {
         }
     }
 
-    fn type_metadata(&mut self, function: &'ll Value, typeid: String) {
-        let typeid_metadata = self.typeid_metadata(typeid);
-        let v = [self.const_usize(0), typeid_metadata];
-        unsafe {
-            llvm::LLVMGlobalSetMetadata(
-                function,
-                llvm::MD_type as c_uint,
-                llvm::LLVMValueAsMetadata(llvm::LLVMMDNodeInContext(
-                    self.cx.llcx,
-                    v.as_ptr(),
-                    v.len() as c_uint,
-                )),
-            )
-        }
-    }
-
-    fn typeid_metadata(&mut self, typeid: String) -> Self::Value {
-        unsafe {
-            llvm::LLVMMDStringInContext(
-                self.cx.llcx,
-                typeid.as_ptr() as *const c_char,
-                typeid.as_bytes().len() as c_uint,
-            )
-        }
-    }
-
     fn store(&mut self, val: &'ll Value, ptr: &'ll Value, align: Align) -> &'ll Value {
         self.store_with_flags(val, ptr, align, MemFlags::empty())
     }

compiler/rustc_codegen_llvm/src/declare.rs

@@ -18,7 +18,9 @@ use crate::llvm;
 use crate::llvm::AttributePlace::Function;
 use crate::type_::Type;
 use crate::value::Value;
+use rustc_codegen_ssa::traits::TypeMembershipMethods;
 use rustc_middle::ty::Ty;
+use rustc_symbol_mangling::typeid::typeid_for_fnabi;
 use smallvec::SmallVec;
 use tracing::debug;
 
@@ -97,6 +99,12 @@ impl<'ll, 'tcx> CodegenCx<'ll, 'tcx> {
             fn_abi.llvm_type(self),
         );
         fn_abi.apply_attrs_llfn(self, llfn);
+
+        if self.tcx.sess.is_sanitizer_cfi_enabled() {
+            let typeid = typeid_for_fnabi(self.tcx, fn_abi);
+            self.set_type_metadata(llfn, typeid);
+        }
+
         llfn
     }
 

compiler/rustc_codegen_llvm/src/type_.rs

@@ -19,7 +19,7 @@ use rustc_target::abi::{AddressSpace, Align, Integer, Size};
 use std::fmt;
 use std::ptr;
 
-use libc::c_uint;
+use libc::{c_char, c_uint};
 
 impl PartialEq for Type {
     fn eq(&self, other: &Self) -> bool {
@@ -289,3 +289,31 @@ impl<'ll, 'tcx> LayoutTypeMethods<'tcx> for CodegenCx<'ll, 'tcx> {
         ty.llvm_type(self)
     }
 }
+
+impl<'ll, 'tcx> TypeMembershipMethods<'tcx> for CodegenCx<'ll, 'tcx> {
+    fn set_type_metadata(&self, function: &'ll Value, typeid: String) {
+        let typeid_metadata = self.typeid_metadata(typeid);
+        let v = [self.const_usize(0), typeid_metadata];
+        unsafe {
+            llvm::LLVMGlobalSetMetadata(
+                function,
+                llvm::MD_type as c_uint,
+                llvm::LLVMValueAsMetadata(llvm::LLVMMDNodeInContext(
+                    self.llcx,
+                    v.as_ptr(),
+                    v.len() as c_uint,
+                )),
+            )
+        }
+    }
+
+    fn typeid_metadata(&self, typeid: String) -> &'ll Value {
+        unsafe {
+            llvm::LLVMMDStringInContext(
+                self.llcx,
+                typeid.as_ptr() as *const c_char,
+                typeid.len() as c_uint,
+            )
+        }
+    }
+}