Rollup merge of #145965 - bjorn3:sanitize_symbol_export_improvements, r=lqd

Move exporting of profiler and sanitizer symbols to the LLVM backend

Only the LLVM backend needs those specific symbols exported and it only needs them to be exported for LTO, not from cdylibs in general.

Author: GuillaumeGomez

compiler/rustc_codegen_llvm/src/back/lto.rs

@@ -15,6 +15,7 @@ use rustc_codegen_ssa::{ModuleCodegen, ModuleKind, looks_like_rust_object_file};
 use rustc_data_structures::fx::FxHashMap;
 use rustc_data_structures::memmap::Mmap;
 use rustc_errors::DiagCtxtHandle;
+use rustc_hir::attrs::SanitizerSet;
 use rustc_middle::bug;
 use rustc_middle::dep_graph::WorkProduct;
 use rustc_session::config::{self, Lto};
@@ -42,6 +43,37 @@ fn prepare_lto(
         .map(|symbol| CString::new(symbol.to_owned()).unwrap())
         .collect::<Vec<CString>>();
 
+    if cgcx.regular_module_config.instrument_coverage
+        || cgcx.regular_module_config.pgo_gen.enabled()
+    {
+        // These are weak symbols that point to the profile version and the
+        // profile name, which need to be treated as exported so LTO doesn't nix
+        // them.
+        const PROFILER_WEAK_SYMBOLS: [&CStr; 2] =
+            [c"__llvm_profile_raw_version", c"__llvm_profile_filename"];
+
+        symbols_below_threshold.extend(PROFILER_WEAK_SYMBOLS.iter().map(|&sym| sym.to_owned()));
+    }
+
+    if cgcx.regular_module_config.sanitizer.contains(SanitizerSet::MEMORY) {
+        let mut msan_weak_symbols = Vec::new();
+
+        // Similar to profiling, preserve weak msan symbol during LTO.
+        if cgcx.regular_module_config.sanitizer_recover.contains(SanitizerSet::MEMORY) {
+            msan_weak_symbols.push(c"__msan_keep_going");
+        }
+
+        if cgcx.regular_module_config.sanitizer_memory_track_origins != 0 {
+            msan_weak_symbols.push(c"__msan_track_origins");
+        }
+
+        symbols_below_threshold.extend(msan_weak_symbols.into_iter().map(|sym| sym.to_owned()));
+    }
+
+    // Preserve LLVM-injected, ASAN-related symbols.
+    // See also https://github.com/rust-lang/rust/issues/113404.
+    symbols_below_threshold.push(c"___asan_globals_registered".to_owned());
+
     // __llvm_profile_counter_bias is pulled in at link time by an undefined reference to
     // __llvm_profile_runtime, therefore we won't know until link time if this symbol
     // should have default visibility.

compiler/rustc_codegen_ssa/src/back/symbol_export.rs

@@ -15,7 +15,7 @@ use rustc_middle::ty::{self, GenericArgKind, GenericArgsRef, Instance, SymbolNam
 use rustc_middle::util::Providers;
 use rustc_session::config::{CrateType, OomStrategy};
 use rustc_symbol_mangling::mangle_internal_symbol;
-use rustc_target::spec::{SanitizerSet, TlsModel};
+use rustc_target::spec::TlsModel;
 use tracing::debug;
 
 use crate::base::allocator_kind_for_codegen;
@@ -242,53 +242,6 @@ fn exported_non_generic_symbols_provider_local<'tcx>(
         }
     }
 
-    if tcx.sess.instrument_coverage() || tcx.sess.opts.cg.profile_generate.enabled() {
-        // These are weak symbols that point to the profile version and the
-        // profile name, which need to be treated as exported so LTO doesn't nix
-        // them.
-        const PROFILER_WEAK_SYMBOLS: [&str; 2] =
-            ["__llvm_profile_raw_version", "__llvm_profile_filename"];
-
-        symbols.extend(PROFILER_WEAK_SYMBOLS.iter().map(|sym| {
-            let exported_symbol = ExportedSymbol::NoDefId(SymbolName::new(tcx, sym));
-            (
-                exported_symbol,
-                SymbolExportInfo {
-                    level: SymbolExportLevel::C,
-                    kind: SymbolExportKind::Data,
-                    used: false,
-                    rustc_std_internal_symbol: false,
-                },
-            )
-        }));
-    }
-
-    if tcx.sess.opts.unstable_opts.sanitizer.contains(SanitizerSet::MEMORY) {
-        let mut msan_weak_symbols = Vec::new();
-
-        // Similar to profiling, preserve weak msan symbol during LTO.
-        if tcx.sess.opts.unstable_opts.sanitizer_recover.contains(SanitizerSet::MEMORY) {
-            msan_weak_symbols.push("__msan_keep_going");
-        }
-
-        if tcx.sess.opts.unstable_opts.sanitizer_memory_track_origins != 0 {
-            msan_weak_symbols.push("__msan_track_origins");
-        }
-
-        symbols.extend(msan_weak_symbols.into_iter().map(|sym| {
-            let exported_symbol = ExportedSymbol::NoDefId(SymbolName::new(tcx, sym));
-            (
-                exported_symbol,
-                SymbolExportInfo {
-                    level: SymbolExportLevel::C,
-                    kind: SymbolExportKind::Data,
-                    used: false,
-                    rustc_std_internal_symbol: false,
-                },
-            )
-        }));
-    }
-
     // Sort so we get a stable incr. comp. hash.
     symbols.sort_by_cached_key(|s| s.0.symbol_name_for_local_instance(tcx));
 

compiler/rustc_llvm/llvm-wrapper/PassWrapper.cpp

@@ -1226,12 +1226,6 @@ extern "C" void LLVMRustPrintPasses() {
 extern "C" void LLVMRustRunRestrictionPass(LLVMModuleRef M, char **Symbols,
                                            size_t Len) {
   auto PreserveFunctions = [=](const GlobalValue &GV) {
-    // Preserve LLVM-injected, ASAN-related symbols.
-    // See also https://github.com/rust-lang/rust/issues/113404.
-    if (GV.getName() == "___asan_globals_registered") {
-      return true;
-    }
-
     // Preserve symbols exported from Rust modules.
     for (size_t I = 0; I < Len; I++) {
       if (GV.getName() == Symbols[I]) {