[dfsan] Record dfsan metadata in globals

This will allow identifying exactly how many shadow bytes were used
during compilation, for when fast8 mode is introduced.

Also, it will provide a consistent matching point for instrumentation
tests so that the exact llvm type used (i8 or i16) for the shadow can
be replaced by a pattern substitution. This is handy for tests with
multiple prefixes.

Reviewed by: stephan.yichao.zhao, morehouse

Differential Revision: https://reviews.llvm.org/D97409

Author: gbalats

llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp

@@ -450,6 +450,7 @@ class DataFlowSanitizer {
   Constant *getOrBuildTrampolineFunction(FunctionType *FT, StringRef FName);
   void initializeCallbackFunctions(Module &M);
   void initializeRuntimeFunctions(Module &M);
+  void injectMetadataGlobals(Module &M);
 
   bool init(Module &M);
 
@@ -1267,6 +1268,26 @@ void DataFlowSanitizer::initializeCallbackFunctions(Module &M) {
       Mod->getOrInsertFunction("__dfsan_cmp_callback", DFSanCmpCallbackFnTy);
 }
 
+void DataFlowSanitizer::injectMetadataGlobals(Module &M) {
+  // These variables can be used:
+  // - by the runtime (to discover what the shadow width was, during
+  //   compilation)
+  // - in testing (to avoid hardcoding the shadow width and type but instead
+  //   extract them by pattern matching)
+  Type *IntTy = Type::getInt32Ty(*Ctx);
+  (void)Mod->getOrInsertGlobal("__dfsan_shadow_width_bits", IntTy, [&] {
+    return new GlobalVariable(
+        M, IntTy, /*isConstant=*/true, GlobalValue::WeakODRLinkage,
+        ConstantInt::get(IntTy, ShadowWidthBits), "__dfsan_shadow_width_bits");
+  });
+  (void)Mod->getOrInsertGlobal("__dfsan_shadow_width_bytes", IntTy, [&] {
+    return new GlobalVariable(M, IntTy, /*isConstant=*/true,
+                              GlobalValue::WeakODRLinkage,
+                              ConstantInt::get(IntTy, ShadowWidthBytes),
+                              "__dfsan_shadow_width_bytes");
+  });
+}
+
 bool DataFlowSanitizer::runImpl(Module &M) {
   init(M);
 
@@ -1307,6 +1328,8 @@ bool DataFlowSanitizer::runImpl(Module &M) {
         "__dfsan_track_origins");
   });
 
+  injectMetadataGlobals(M);
+
   ExternalShadowMask =
       Mod->getOrInsertGlobal(kDFSanExternShadowPtrMask, IntptrTy);
 

llvm/test/Instrumentation/DataFlowSanitizer/basic.ll

@@ -9,34 +9,36 @@ target triple = "x86_64-unknown-linux-gnu"
 ; CHECK: @__dfsan_retval_origin_tls = external thread_local(initialexec) global i32
 ; CHECK_NO_ORIGIN: @__dfsan_track_origins = weak_odr constant i32 0
 ; CHECK_ORIGIN: @__dfsan_track_origins = weak_odr constant i32 1
+; CHECK: @__dfsan_shadow_width_bits = weak_odr constant i32 [[#SBITS:]]
+; CHECK: @__dfsan_shadow_width_bytes = weak_odr constant i32 [[#SBYTES:]]
 ; CHECK: @__dfsan_shadow_ptr_mask = external global i64
-; CHECK: declare void @__dfsan_load_callback(i16, i8*)
-; CHECK: declare void @__dfsan_store_callback(i16, i8*)
-; CHECK: declare void @__dfsan_mem_transfer_callback(i16*, i64)
-; CHECK: declare void @__dfsan_cmp_callback(i16)
+; CHECK: declare void @__dfsan_load_callback(i[[#SBITS]], i8*)
+; CHECK: declare void @__dfsan_store_callback(i[[#SBITS]], i8*)
+; CHECK: declare void @__dfsan_mem_transfer_callback(i[[#SBITS]]*, i64)
+; CHECK: declare void @__dfsan_cmp_callback(i[[#SBITS]])
 
 ; CHECK: ; Function Attrs: nounwind readnone
-; CHECK-NEXT: declare zeroext i16 @__dfsan_union(i16 zeroext, i16 zeroext) #0
+; CHECK-NEXT: declare zeroext i[[#SBITS]] @__dfsan_union(i[[#SBITS]] zeroext, i[[#SBITS]] zeroext) #0
 
 ; CHECK: ; Function Attrs: nounwind readnone
-; CHECK-NEXT: declare zeroext i16 @dfsan_union(i16 zeroext, i16 zeroext) #0
+; CHECK-NEXT: declare zeroext i[[#SBITS]] @dfsan_union(i[[#SBITS]] zeroext, i[[#SBITS]] zeroext) #0
 
 ; CHECK: ; Function Attrs: nounwind readonly
-; CHECK-NEXT: declare zeroext i16 @__dfsan_union_load(i16*, i64) #1
+; CHECK-NEXT: declare zeroext i[[#SBITS]] @__dfsan_union_load(i[[#SBITS]]*, i64) #1
 
 ; CHECK: ; Function Attrs: nounwind readonly
-; CHECK-NEXT: declare zeroext i16 @__dfsan_union_load_fast16labels(i16*, i64) #1
+; CHECK-NEXT: declare zeroext i[[#SBITS]] @__dfsan_union_load_fast16labels(i[[#SBITS]]*, i64) #1
 
 ; CHECK: ; Function Attrs: nounwind readonly
 ; CHECK-NEXT: declare zeroext i64 @__dfsan_load_label_and_origin(i8*, i64) #1
 
 ; CHECK: declare void @__dfsan_unimplemented(i8*)
-; CHECK: declare void @__dfsan_set_label(i16 zeroext, i32 zeroext, i8*, i64)
+; CHECK: declare void @__dfsan_set_label(i[[#SBITS]] zeroext, i32 zeroext, i8*, i64)
 ; CHECK: declare void @__dfsan_nonzero_label()
 ; CHECK: declare void @__dfsan_vararg_wrapper(i8*)
 ; CHECK: declare zeroext i32 @__dfsan_chain_origin(i32 zeroext)
 ; CHECK: declare void @__dfsan_mem_origin_transfer(i8*, i8*, i64)
-; CHECK: declare void @__dfsan_maybe_store_origin(i16 zeroext, i8*, i64, i32 zeroext)
+; CHECK: declare void @__dfsan_maybe_store_origin(i[[#SBITS]] zeroext, i8*, i64, i32 zeroext)
 
 define void @foo() {
   ret void