[ASan] Print exact source location of global variables in error reports.

See https://code.google.com/p/address-sanitizer/issues/detail?id=299 for the
original feature request.

Introduce llvm.asan.globals metadata, which Clang (or any other frontend)
may use to report extra information about global variables to ASan
instrumentation pass in the backend. This metadata replaces
llvm.asan.dynamically_initialized_globals that was used to detect init-order
bugs. llvm.asan.globals contains the following data for each global:
  1) source location (file/line/column info);
  2) whether it is dynamically initialized;
  3) whether it is blacklisted (shouldn't be instrumented).

Source location data is then emitted in the binary and can be picked up
by ASan runtime in case it needs to print error report involving some global.
For example:

  0x... is located 4 bytes to the right of global variable 'C::array' defined in '/path/to/file:17:8' (0x...) of size 40

These source locations are printed even if the binary doesn't have any
debug info.

This is an ABI-breaking change. ASan initialization is renamed to
__asan_init_v4(). Pre-built libraries compiled with older Clang will not work
with the fresh runtime.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@212188 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGDecl.cpp b/lib/CodeGen/CGDecl.cpp
index a28e721377125ea9f26fbc37606ba6bbd82e2a3f..9bd61d7164f5811d9db31a396ee5e341e05929fc 100644 (file)
--- a/lib/CodeGen/CGDecl.cpp
+++ b/lib/CodeGen/CGDecl.cpp
@@ -345,6 +345,8 @@ void CodeGenFunction::EmitStaticVarDecl(const VarDecl &D,
   DMEntry = castedAddr;
   CGM.setStaticLocalDeclAddress(&D, castedAddr);
 
+  CGM.reportGlobalToASan(var, D.getLocation());
+
   // Emit global variable debug descriptor for static vars.
   CGDebugInfo *DI = getDebugInfo();
   if (DI &&

diff --git a/lib/CodeGen/CodeGenModule.cpp b/lib/CodeGen/CodeGenModule.cpp
index d172b45c682a5797e9f9c17c9bab294d96cbc0be..e088bd4e4fe9d89ce6f4ea2a23be84b6a531baf5 100644 (file)
--- a/lib/CodeGen/CodeGenModule.cpp
+++ b/lib/CodeGen/CodeGenModule.cpp
@@ -1958,16 +1958,7 @@ void CodeGenModule::EmitGlobalVarDefinition(const VarDecl *D) {
   if (NeedsGlobalCtor || NeedsGlobalDtor)
     EmitCXXGlobalVarDeclInitFunc(D, GV, NeedsGlobalCtor);
 
-  // If we are compiling with ASan, add metadata indicating dynamically
-  // initialized (and not blacklisted) globals.
-  if (SanOpts.Address && NeedsGlobalCtor &&
-      !SanitizerBlacklist->isIn(*GV, "init")) {
-    llvm::NamedMDNode *DynamicInitializers = TheModule.getOrInsertNamedMetadata(
-        "llvm.asan.dynamically_initialized_globals");
-    llvm::Value *GlobalToAdd[] = { GV };
-    llvm::MDNode *ThisGlobal = llvm::MDNode::get(VMContext, GlobalToAdd);
-    DynamicInitializers->addOperand(ThisGlobal);
-  }
+  reportGlobalToASan(GV, D->getLocation(), NeedsGlobalCtor);
 
   // Emit global variable debug information.
   if (CGDebugInfo *DI = getModuleDebugInfo())
@@ -1975,6 +1966,51 @@ void CodeGenModule::EmitGlobalVarDefinition(const VarDecl *D) {
       DI->EmitGlobalVariable(GV, D);
 }
 
+void CodeGenModule::reportGlobalToASan(llvm::GlobalVariable *GV,
+                                       SourceLocation Loc, bool IsDynInit) {
+  if (!SanOpts.Address)
+    return;
+  IsDynInit &= !SanitizerBlacklist->isIn(*GV, "init");
+  bool IsBlacklisted = SanitizerBlacklist->isIn(*GV);
+
+  llvm::LLVMContext &LLVMCtx = TheModule.getContext();
+
+  llvm::GlobalVariable *LocDescr = nullptr;
+  if (!IsBlacklisted) {
+    // Don't generate source location if a global is blacklisted - it won't
+    // be instrumented anyway.
+    PresumedLoc PLoc = Context.getSourceManager().getPresumedLoc(Loc);
+    if (PLoc.isValid()) {
+      llvm::Constant *LocData[] = {
+          GetAddrOfConstantCString(PLoc.getFilename()),
+          llvm::ConstantInt::get(llvm::Type::getInt32Ty(LLVMCtx), PLoc.getLine()),
+          llvm::ConstantInt::get(llvm::Type::getInt32Ty(LLVMCtx),
+                                 PLoc.getColumn()),
+      };
+      auto LocStruct = llvm::ConstantStruct::getAnon(LocData);
+      LocDescr = new llvm::GlobalVariable(TheModule, LocStruct->getType(), true,
+                                          llvm::GlobalValue::PrivateLinkage,
+                                          LocStruct, ".asan_loc_descr");
+      LocDescr->setUnnamedAddr(true);
+      // Add LocDescr to llvm.compiler.used, so that it won't be removed by
+      // the optimizer before the ASan instrumentation pass.
+      addCompilerUsedGlobal(LocDescr);
+    }
+  }
+
+  llvm::Value *GlobalMetadata[] = {
+      GV,
+      LocDescr,
+      llvm::ConstantInt::get(llvm::Type::getInt1Ty(LLVMCtx), IsDynInit),
+      llvm::ConstantInt::get(llvm::Type::getInt1Ty(LLVMCtx), IsBlacklisted)
+  };
+
+  llvm::MDNode *ThisGlobal = llvm::MDNode::get(VMContext, GlobalMetadata);
+  llvm::NamedMDNode *AsanGlobals =
+      TheModule.getOrInsertNamedMetadata("llvm.asan.globals");
+  AsanGlobals->addOperand(ThisGlobal);
+}
+
 static bool isVarDeclStrongDefinition(const VarDecl *D, bool NoCommon) {
   // Don't give variables common linkage if -fno-common was specified unless it
   // was overridden by a NoCommon attribute.
@@ -2779,6 +2815,8 @@ CodeGenModule::GetAddrOfConstantStringFromLiteral(const StringLiteral *S) {
   auto GV = GenerateStringLiteral(C, LT, *this, GlobalVariableName, Alignment);
   if (Entry)
     Entry->setValue(GV);
+
+  reportGlobalToASan(GV, S->getStrTokenLoc(0));
   return GV;
 }
 

diff --git a/lib/CodeGen/CodeGenModule.h b/lib/CodeGen/CodeGenModule.h
index a4d398a2fa74a06d32d4bd5bfa436537688f4acd..88f5faf7093d72d159f23b6c505dea22d124054f 100644 (file)
--- a/lib/CodeGen/CodeGenModule.h
+++ b/lib/CodeGen/CodeGenModule.h
@@ -1025,6 +1025,9 @@ public:
 
   const SanitizerOptions &getSanOpts() const { return SanOpts; }
 
+  void reportGlobalToASan(llvm::GlobalVariable *GV, SourceLocation Loc,
+                          bool IsDynInit = false);
+
   void addDeferredVTable(const CXXRecordDecl *RD) {
     DeferredVTables.push_back(RD);
   }

diff --git a/test/CodeGen/asan-globals.cpp b/test/CodeGen/asan-globals.cpp
new file mode 100644 (file)
index 0000000..996be2b
--- /dev/null
+++ b/test/CodeGen/asan-globals.cpp
@@ -0,0 +1,23 @@
+// RUN: echo "global:*blacklisted_global*" > %t.blacklist
+// RUN: %clang_cc1 -fsanitize=address -fsanitize-blacklist=%t.blacklist -emit-llvm -o - %s | FileCheck %s
+// REQUIRES: shell
+
+int global;
+// CHECK: [[GLOBAL_LOC:@.asan_loc_descr[0-9]*]] = private unnamed_addr constant {{.*}} i32 [[@LINE-1]], i32 5
+int dyn_init_global = global;
+// CHECK: [[DYN_INIT_LOC:@.asan_loc_descr[0-9]*]] = {{.*}} i32 [[@LINE-1]], i32 5
+int blacklisted_global;
+
+void func() {
+  static int static_var = 0;
+  // CHECK: [[STATIC_LOC:@.asan_loc_descr[0-9]*]] = {{.*}} i32 [[@LINE-1]], i32 14
+  const char *literal = "Hello, world!";
+  // CHECK: [[LITERAL_LOC:@.asan_loc_descr[0-9]*]] = {{.*}} i32 [[@LINE-1]], i32 25
+}
+
+// CHECK: !llvm.asan.globals = !{![[GLOBAL:[0-9]+]], ![[DYN_INIT_GLOBAL:[0-9]+]], ![[BLACKLISTED_GLOBAL:[0-9]+]], ![[STATIC_VAR:[0-9]+]], ![[LITERAL:[0-9]+]]}
+// CHECK: ![[GLOBAL]] = metadata !{{{.*}} [[GLOBAL_LOC]], i1 false, i1 false}
+// CHECK: ![[DYN_INIT_GLOBAL]] = metadata !{{{.*}} [[DYN_INIT_LOC]], i1 true, i1 false}
+// CHECK: ![[BLACKLISTED_GLOBAL]] = metadata !{{{.*}}, null, i1 false, i1 true}
+// CHECK: ![[STATIC_VAR]] = metadata !{{{.*}} [[STATIC_LOC]], i1 false, i1 false}
+// CHECK: ![[LITERAL]] = metadata !{{{.*}} [[LITERAL_LOC]], i1 false, i1 false}

diff --git a/test/CodeGen/sanitize-init-order.cpp b/test/CodeGen/sanitize-init-order.cpp
index dc8e8e2f9faeb52681a641aceb671a7f4983da44..8c662dbe03439539300f754c581a6b03679259bc 100644 (file)
--- a/test/CodeGen/sanitize-init-order.cpp
+++ b/test/CodeGen/sanitize-init-order.cpp
@@ -27,7 +27,12 @@ PODWithCtorAndDtor s3;
 
 // Check that ASan init-order checking ignores structs with trivial default
 // constructor.
-// CHECK: !llvm.asan.dynamically_initialized_globals = !{[[GLOB:![0-9]+]]}
-// CHECK: [[GLOB]] = metadata !{%struct.PODWithCtorAndDtor
+// CHECK: !llvm.asan.globals = !{![[GLOB_1:[0-9]+]], ![[GLOB_2:[0-9]+]], ![[GLOB_3:[0-9]]]}
+// CHECK: ![[GLOB_1]] = metadata !{%struct.PODStruct* {{.*}}, i1 false, i1 false}
+// CHECK: ![[GLOB_2]] = metadata !{%struct.PODWithDtor* {{.*}}, i1 false, i1 false}
+// CHECK: ![[GLOB_3]] = metadata !{%struct.PODWithCtorAndDtor* {{.*}}, i1 true, i1 false}
 
-// BLACKLIST-NOT: llvm.asan.dynamically_initialized_globals
+// BLACKLIST: !llvm.asan.globals = !{![[GLOB_1:[0-9]+]], ![[GLOB_2:[0-9]+]], ![[GLOB_3:[0-9]]]}
+// BLACKLIST: ![[GLOB_1]] = metadata !{%struct.PODStruct* {{.*}}, i1 false, i1 false}
+// BLACKLIST: ![[GLOB_2]] = metadata !{%struct.PODWithDtor* {{.*}}, i1 false, i1 false}
+// BLACKLIST: ![[GLOB_3]] = metadata !{%struct.PODWithCtorAndDtor* {{.*}}, i1 false, i1 false}