[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.

llvm-svn: 212188

13 files changed, 334 insertions, 60 deletions

diff --git a/clang/lib/CodeGen/CGDecl.cpp b/clang/lib/CodeGen/CGDecl.cpp
index a28e7213771..9bd61d7164f 100644
--- a/clang/lib/CodeGen/CGDecl.cpp
+++ b/clang/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/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index d172b45c682..e088bd4e4fe 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/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/clang/lib/CodeGen/CodeGenModule.h b/clang/lib/CodeGen/CodeGenModule.h
index a4d398a2fa7..88f5faf7093 100644
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/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/clang/test/CodeGen/asan-globals.cpp b/clang/test/CodeGen/asan-globals.cpp
new file mode 100644
index 00000000000..996be2b95a2
--- /dev/null
+++ b/clang/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/clang/test/CodeGen/sanitize-init-order.cpp b/clang/test/CodeGen/sanitize-init-order.cpp
index dc8e8e2f9fa..8c662dbe034 100644
--- a/clang/test/CodeGen/sanitize-init-order.cpp
+++ b/clang/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}
diff --git a/compiler-rt/lib/asan/asan_dll_thunk.cc b/compiler-rt/lib/asan/asan_dll_thunk.cc
index aa27c404f4d..7b6ccc6a645 100644
--- a/compiler-rt/lib/asan/asan_dll_thunk.cc
+++ b/compiler-rt/lib/asan/asan_dll_thunk.cc
@@ -203,13 +203,13 @@ extern "C" {
 
   // Manually wrap __asan_init as we need to initialize
   // __asan_option_detect_stack_use_after_return afterwards.
-  void __asan_init_v3() {
+  void __asan_init_v4() {
     typedef void (*fntype)();
     static fntype fn = 0;
-    // __asan_init_v3 is expected to be called by only one thread.
+    // __asan_init_v4 is expected to be called by only one thread.
     if (fn) return;
 
-    fn = (fntype)getRealProcAddressOrDie("__asan_init_v3");
+    fn = (fntype)getRealProcAddressOrDie("__asan_init_v4");
     fn();
     __asan_option_detect_stack_use_after_return =
         (__asan_should_detect_stack_use_after_return() != 0);
@@ -339,7 +339,7 @@ void InterceptHooks() {
 // In DLLs, the callbacks are expected to return 0,
 // otherwise CRT initialization fails.
 static int call_asan_init() {
-  __asan_init_v3();
+  __asan_init_v4();
   return 0;
 }
 #pragma section(".CRT$XIB", long, read)  // NOLINT
diff --git a/compiler-rt/lib/asan/asan_interface_internal.h b/compiler-rt/lib/asan/asan_interface_internal.h
index 84525d090ac..6d95ad8199a 100644
--- a/compiler-rt/lib/asan/asan_interface_internal.h
+++ b/compiler-rt/lib/asan/asan_interface_internal.h
@@ -30,8 +30,17 @@ extern "C" {
   // v2=>v3: stack frame description (created by the compiler)
   //         contains the function PC as the 3-rd field (see
   //         DescribeAddressIfStack).
-  SANITIZER_INTERFACE_ATTRIBUTE void __asan_init_v3();
-  #define __asan_init __asan_init_v3
+  // v3=>v4: added '__asan_global_source_location' to __asan_global.
+  SANITIZER_INTERFACE_ATTRIBUTE void __asan_init_v4();
+  #define __asan_init __asan_init_v4
+
+  // This structure is used to describe the source location of a place where
+  // global was defined.
+  struct __asan_global_source_location {
+    const char *filename;
+    int line_no;
+    int column_no;
+  };
 
   // This structure describes an instrumented global variable.
   struct __asan_global {
@@ -42,6 +51,8 @@ extern "C" {
     const char *module_name; // Module name as a C string. This pointer is a
                              // unique identifier of a module.
     uptr has_dynamic_init;   // Non-zero if the global has dynamic initializer.
+    __asan_global_source_location *location;  // Source location of a global,
+                                              // or NULL if it is unknown.
   };
 
   // These two functions should be called by the instrumented code.
diff --git a/compiler-rt/lib/asan/asan_report.cc b/compiler-rt/lib/asan/asan_report.cc
index 3b8fa3e800a..66329c07819 100644
--- a/compiler-rt/lib/asan/asan_report.cc
+++ b/compiler-rt/lib/asan/asan_report.cc
@@ -212,6 +212,26 @@ static void PrintGlobalNameIfASCII(InternalScopedString *str,
               (char *)g.beg);
 }
 
+static const char *GlobalFilename(const __asan_global &g) {
+  const char *res = g.module_name;
+  // Prefer the filename from source location, if is available.
+  if (g.location)
+    res = g.location->filename;
+  CHECK(res);
+  return res;
+}
+
+static void PrintGlobalLocation(InternalScopedString *str,
+                                const __asan_global &g) {
+  str->append("%s", GlobalFilename(g));
+  if (!g.location)
+    return;
+  if (g.location->line_no)
+    str->append(":%d", g.location->line_no);
+  if (g.location->column_no)
+    str->append(":%d", g.location->column_no);
+}
+
 bool DescribeAddressRelativeToGlobal(uptr addr, uptr size,
                                      const __asan_global &g) {
   static const uptr kMinimalDistanceFromAnotherGlobal = 64;
@@ -232,8 +252,10 @@ bool DescribeAddressRelativeToGlobal(uptr addr, uptr size,
     // Can it happen?
     str.append("%p is located %zd bytes inside", (void *)addr, addr - g.beg);
   }
-  str.append(" of global variable '%s' from '%s' (0x%zx) of size %zu\n",
-             MaybeDemangleGlobalName(g.name), g.module_name, g.beg, g.size);
+  str.append(" of global variable '%s' defined in '",
+             MaybeDemangleGlobalName(g.name));
+  PrintGlobalLocation(&str, g);
+  str.append("' (0x%zx) of size %zu\n", g.beg, g.size);
   str.append("%s", d.EndLocation());
   PrintGlobalNameIfASCII(&str, g);
   Printf("%s", str.data());
@@ -742,8 +764,11 @@ void ReportODRViolation(const __asan_global *g1, u32 stack_id1,
   Printf("%s", d.Warning());
   Report("ERROR: AddressSanitizer: odr-violation (%p):\n", g1->beg);
   Printf("%s", d.EndWarning());
-  Printf("  [1] size=%zd %s %s\n", g1->size, g1->name, g1->module_name);
-  Printf("  [2] size=%zd %s %s\n", g2->size, g2->name, g2->module_name);
+  InternalScopedString g1_loc(256), g2_loc(256);
+  PrintGlobalLocation(&g1_loc, *g1);
+  PrintGlobalLocation(&g2_loc, *g2);
+  Printf("  [1] size=%zd %s %s\n", g1->size, g1->name, g1_loc.data());
+  Printf("  [2] size=%zd %s %s\n", g2->size, g2->name, g2_loc.data());
   if (stack_id1 && stack_id2) {
     Printf("These globals were registered at these points:\n");
     Printf("  [1]:\n");
@@ -756,7 +781,7 @@ void ReportODRViolation(const __asan_global *g1, u32 stack_id1,
   }
   Report("HINT: if you don't care about these warnings you may set "
          "ASAN_OPTIONS=detect_odr_violation=0\n");
-  ReportErrorSummary("odr-violation", g1->module_name, 0, g1->name);
+  ReportErrorSummary("odr-violation", g1_loc.data(), 0, g1->name);
 }
 
 // ----------------------- CheckForInvalidPointerPair ----------- {{{1
diff --git a/compiler-rt/test/asan/TestCases/global-location.cc b/compiler-rt/test/asan/TestCases/global-location.cc
new file mode 100644
index 00000000000..4e386c98866
--- /dev/null
+++ b/compiler-rt/test/asan/TestCases/global-location.cc
@@ -0,0 +1,38 @@
+// RUN: %clangxx_asan -O2 %s -o %t
+// RUN: not %run %t g 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=GLOB
+// RUN: not %run %t c 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=CLASS_STATIC
+// RUN: not %run %t f 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=FUNC_STATIC
+// RUN: not %run %t l 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=LITERAL
+
+// CHECK: AddressSanitizer: global-buffer-overflow
+
+#include <string.h>
+
+struct C {
+  static int array[10];
+};
+
+int global[10];
+// GLOB: 0x{{.*}} is located 4 bytes to the right of global variable 'global' defined in '{{.*}}global-location.cc:[[@LINE-1]]:5' {{.*}} of size 40
+int C::array[10];
+// CLASS_STATIC: 0x{{.*}} is located 4 bytes to the right of global variable 'C::array' defined in '{{.*}}global-location.cc:[[@LINE-1]]:8' {{.*}} of size 40
+
+int main(int argc, char **argv) {
+  int one = argc - 1;
+  switch (argv[1][0]) {
+  case 'g': return global[one * 11];
+  case 'c': return C::array[one * 11];
+  case 'f':
+    static int array[10];
+    // FUNC_STATIC: 0x{{.*}} is located 4 bytes to the right of global variable 'main::array' defined in '{{.*}}global-location.cc:[[@LINE-1]]:16' {{.*}} of size 40
+    memset(array, 0, 10);
+    return array[one * 11];
+  case 'l':
+    const char *str = "0123456789";
+    // LITERAL: 0x{{.*}} is located 0 bytes to the right of global variable {{.*}} defined in '{{.*}}global-location.cc:[[@LINE-1]]:23' {{.*}} of size 11
+    return str[one * 11];
+  }
+  return 0;
+}
+
+// CHECK: SUMMARY: AddressSanitizer: global-buffer-overflow
diff --git a/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp b/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
index 6dbcde03cf2..290efe2ec00 100644
--- a/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
@@ -16,6 +16,7 @@
 #include "llvm/Transforms/Instrumentation.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallString.h"
@@ -79,7 +80,7 @@ static const char *const kAsanUnregisterGlobalsName =
     "__asan_unregister_globals";
 static const char *const kAsanPoisonGlobalsName = "__asan_before_dynamic_init";
 static const char *const kAsanUnpoisonGlobalsName = "__asan_after_dynamic_init";
-static const char *const kAsanInitName = "__asan_init_v3";
+static const char *const kAsanInitName = "__asan_init_v4";
 static const char *const kAsanCovModuleInitName = "__sanitizer_cov_module_init";
 static const char *const kAsanCovName = "__sanitizer_cov";
 static const char *const kAsanPtrCmp = "__sanitizer_ptr_cmp";
@@ -215,28 +216,86 @@ STATISTIC(NumOptimizedAccessesToGlobalVar,
           "Number of optimized accesses to global vars");
 
 namespace {
-/// A set of dynamically initialized globals extracted from metadata.
-class SetOfDynamicallyInitializedGlobals {
+/// Frontend-provided metadata for global variables.
+class GlobalsMetadata {
  public:
-  void Init(Module& M) {
-    // Clang generates metadata identifying all dynamically initialized globals.
-    NamedMDNode *DynamicGlobals =
-        M.getNamedMetadata("llvm.asan.dynamically_initialized_globals");
-    if (!DynamicGlobals)
+  void init(Module& M) {
+    assert(!inited_);
+    inited_ = true;
+    NamedMDNode *Globals = M.getNamedMetadata("llvm.asan.globals");
+    if (!Globals)
       return;
-    for (const auto MDN : DynamicGlobals->operands()) {
-      assert(MDN->getNumOperands() == 1);
-      Value *VG = MDN->getOperand(0);
-      // The optimizer may optimize away a global entirely, in which case we
-      // cannot instrument access to it.
-      if (!VG)
+    for (auto MDN : Globals->operands()) {
+      // Format of the metadata node for the global:
+      // {
+      //   global,
+      //   source_location,
+      //   i1 is_dynamically_initialized,
+      //   i1 is_blacklisted
+      // }
+      assert(MDN->getNumOperands() == 4);
+      Value *V = MDN->getOperand(0);
+      // The optimizer may optimize away a global entirely.
+      if (!V)
         continue;
-      DynInitGlobals.insert(cast<GlobalVariable>(VG));
+      GlobalVariable *GV = cast<GlobalVariable>(V);
+      if (Value *Loc = MDN->getOperand(1)) {
+        GlobalVariable *GVLoc = cast<GlobalVariable>(Loc);
+        // We may already know the source location for GV, if it was merged
+        // with another global.
+        if (SourceLocation.insert(std::make_pair(GV, GVLoc)).second)
+          addSourceLocationGlobal(GVLoc);
+      }
+      ConstantInt *IsDynInit = cast<ConstantInt>(MDN->getOperand(2));
+      if (IsDynInit->isOne())
+        DynInitGlobals.insert(GV);
+      ConstantInt *IsBlacklisted = cast<ConstantInt>(MDN->getOperand(3));
+      if (IsBlacklisted->isOne())
+        BlacklistedGlobals.insert(GV);
     }
   }
-  bool Contains(GlobalVariable *G) { return DynInitGlobals.count(G) != 0; }
+
+  GlobalVariable *getSourceLocation(GlobalVariable *G) const {
+    auto Pos = SourceLocation.find(G);
+    return (Pos != SourceLocation.end()) ? Pos->second : nullptr;
+  }
+
+  /// Check if the global is dynamically initialized.
+  bool isDynInit(GlobalVariable *G) const {
+    return DynInitGlobals.count(G);
+  }
+
+  /// Check if the global was blacklisted.
+  bool isBlacklisted(GlobalVariable *G) const {
+    return BlacklistedGlobals.count(G);
+  }
+
+  /// Check if the global was generated to describe source location of another
+  /// global (we don't want to instrument them).
+  bool isSourceLocationGlobal(GlobalVariable *G) const {
+    return LocationGlobals.count(G);
+  }
+
  private:
-  SmallSet<GlobalValue*, 32> DynInitGlobals;
+  bool inited_ = false;
+  DenseMap<GlobalVariable*, GlobalVariable*> SourceLocation;
+  DenseSet<GlobalVariable*> DynInitGlobals;
+  DenseSet<GlobalVariable*> BlacklistedGlobals;
+  DenseSet<GlobalVariable*> LocationGlobals;
+
+  void addSourceLocationGlobal(GlobalVariable *SourceLocGV) {
+    // Source location global is a struct with layout:
+    // {
+    //    filename,
+    //    i32 line_number,
+    //    i32 column_number,
+    // }
+    LocationGlobals.insert(SourceLocGV);
+    ConstantStruct *Contents =
+        cast<ConstantStruct>(SourceLocGV->getInitializer());
+    GlobalVariable *FilenameGV = cast<GlobalVariable>(Contents->getOperand(0));
+    LocationGlobals.insert(FilenameGV);
+  }
 };
 
 /// This struct defines the shadow mapping using the rule:
@@ -351,7 +410,7 @@ struct AddressSanitizer : public FunctionPass {
            *AsanMemoryAccessCallbackSized[2];
   Function *AsanMemmove, *AsanMemcpy, *AsanMemset;
   InlineAsm *EmptyAsm;
-  SetOfDynamicallyInitializedGlobals DynamicallyInitializedGlobals;
+  GlobalsMetadata GlobalsMD;
 
   friend struct FunctionStackPoisoner;
 };
@@ -381,7 +440,7 @@ class AddressSanitizerModule : public ModulePass {
   SmallString<64> BlacklistFile;
 
   std::unique_ptr<SpecialCaseList> BL;
-  SetOfDynamicallyInitializedGlobals DynamicallyInitializedGlobals;
+  GlobalsMetadata GlobalsMD;
   Type *IntptrTy;
   LLVMContext *C;
   const DataLayout *DL;
@@ -659,7 +718,7 @@ bool AddressSanitizer::GlobalIsLinkerInitialized(GlobalVariable *G) {
   // If a global variable does not have dynamic initialization we don't
   // have to instrument it.  However, if a global does not have initializer
   // at all, we assume it has dynamic initializer (in other TU).
-  return G->hasInitializer() && !DynamicallyInitializedGlobals.Contains(G);
+  return G->hasInitializer() && !GlobalsMD.isDynInit(G);
 }
 
 void
@@ -866,7 +925,11 @@ bool AddressSanitizerModule::ShouldInstrumentGlobal(GlobalVariable *G) {
   Type *Ty = cast<PointerType>(G->getType())->getElementType();
   DEBUG(dbgs() << "GLOBAL: " << *G << "\n");
 
+  // FIXME: Don't use the blacklist here, all the data should be collected
+  // by the frontend and passed in globals metadata.
   if (BL->isIn(*G)) return false;
+  if (GlobalsMD.isBlacklisted(G)) return false;
+  if (GlobalsMD.isSourceLocationGlobal(G)) return false;
   if (!Ty->isSized()) return false;
   if (!G->hasInitializer()) return false;
   if (GlobalWasGeneratedByAsan(G)) return false;  // Our own global.
@@ -967,7 +1030,7 @@ void AddressSanitizerModule::initializeCallbacks(Module &M) {
 // trailing redzones. It also creates a function that poisons
 // redzones and inserts this function into llvm.global_ctors.
 bool AddressSanitizerModule::InstrumentGlobals(IRBuilder<> &IRB, Module &M) {
-  DynamicallyInitializedGlobals.Init(M);
+  GlobalsMD.init(M);
 
   SmallVector<GlobalVariable *, 16> GlobalsToChange;
 
@@ -986,10 +1049,11 @@ bool AddressSanitizerModule::InstrumentGlobals(IRBuilder<> &IRB, Module &M) {
   //   const char *name;
   //   const char *module_name;
   //   size_t has_dynamic_init;
+  //   void *source_location;
   // We initialize an array of such structures and pass it to a run-time call.
-  StructType *GlobalStructTy = StructType::get(IntptrTy, IntptrTy,
-                                               IntptrTy, IntptrTy,
-                                               IntptrTy, IntptrTy, NULL);
+  StructType *GlobalStructTy =
+      StructType::get(IntptrTy, IntptrTy, IntptrTy, IntptrTy, IntptrTy,
+                      IntptrTy, IntptrTy, NULL);
   SmallVector<Constant *, 16> Initializers(n);
 
   bool HasDynamicallyInitializedGlobals = false;
@@ -1017,9 +1081,6 @@ bool AddressSanitizerModule::InstrumentGlobals(IRBuilder<> &IRB, Module &M) {
       RightRedzoneSize += MinRZ - (SizeInBytes % MinRZ);
     assert(((RightRedzoneSize + SizeInBytes) % MinRZ) == 0);
     Type *RightRedZoneTy = ArrayType::get(IRB.getInt8Ty(), RightRedzoneSize);
-    // Determine whether this global should be poisoned in initialization.
-    bool GlobalHasDynamicInitializer =
-        DynamicallyInitializedGlobals.Contains(G);
 
     StructType *NewTy = StructType::get(Ty, RightRedZoneTy, NULL);
     Constant *NewInitializer = ConstantStruct::get(
@@ -1048,17 +1109,20 @@ bool AddressSanitizerModule::InstrumentGlobals(IRBuilder<> &IRB, Module &M) {
     NewGlobal->takeName(G);
     G->eraseFromParent();
 
+    bool GlobalHasDynamicInitializer = GlobalsMD.isDynInit(G);
+    GlobalVariable *SourceLoc = GlobalsMD.getSourceLocation(G);
+
     Initializers[i] = ConstantStruct::get(
-        GlobalStructTy,
-        ConstantExpr::getPointerCast(NewGlobal, IntptrTy),
+        GlobalStructTy, ConstantExpr::getPointerCast(NewGlobal, IntptrTy),
         ConstantInt::get(IntptrTy, SizeInBytes),
         ConstantInt::get(IntptrTy, SizeInBytes + RightRedzoneSize),
         ConstantExpr::getPointerCast(Name, IntptrTy),
         ConstantExpr::getPointerCast(ModuleName, IntptrTy),
         ConstantInt::get(IntptrTy, GlobalHasDynamicInitializer),
+        SourceLoc ? ConstantExpr::getPointerCast(SourceLoc, IntptrTy)
+                  : ConstantInt::get(IntptrTy, 0),
         NULL);
 
-    // Populate the first and last globals declared in this TU.
     if (ClInitializers && GlobalHasDynamicInitializer)
       HasDynamicallyInitializedGlobals = true;
 
@@ -1186,7 +1250,7 @@ bool AddressSanitizer::doInitialization(Module &M) {
     report_fatal_error("data layout missing");
   DL = &DLP->getDataLayout();
 
-  DynamicallyInitializedGlobals.Init(M);
+  GlobalsMD.init(M);
 
   C = &(M.getContext());
   LongSize = DL->getPointerSizeInBits();
diff --git a/llvm/test/Instrumentation/AddressSanitizer/global_metadata.ll b/llvm/test/Instrumentation/AddressSanitizer/global_metadata.ll
new file mode 100644
index 00000000000..9641c3ed4d7
--- /dev/null
+++ b/llvm/test/Instrumentation/AddressSanitizer/global_metadata.ll
@@ -0,0 +1,63 @@
+; RUN: opt < %s -asan -asan-module -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Globals:
+@global = global i32 0, align 4
+@dyn_init_global = global i32 0, align 4
+@blacklisted_global = global i32 0, align 4
+@_ZZ4funcvE10static_var = internal global i32 0, align 4
+@.str = private unnamed_addr constant [14 x i8] c"Hello, world!\00", align 1
+@llvm.global_ctors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 65535, void ()* @_GLOBAL__sub_I_asan_globals.cpp, i8* null }]
+
+; Sanitizer location descriptors:
+@.str1 = private unnamed_addr constant [22 x i8] c"/tmp/asan-globals.cpp\00", align 1
+@.asan_loc_descr = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* @.str1, i32 5, i32 5 }
+@.asan_loc_descr1 = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* @.str1, i32 7, i32 5 }
+@.asan_loc_descr2 = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* @.str1, i32 12, i32 14 }
+@.asan_loc_descr4 = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* @.str1, i32 14, i32 25 }
+
+; Check that globals were instrumented, but sanitizer location descriptors weren't:
+; CHECK: @global = global { i32, [60 x i8] } zeroinitializer, align 32
+; CHECK: @.str = internal unnamed_addr constant { [14 x i8], [50 x i8] } { [14 x i8] c"Hello, world!\00", [50 x i8] zeroinitializer }, align 32
+; CHECK: @.asan_loc_descr = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* @.str1, i32 5, i32 5 }
+
+; Check that location decriptors were passed into __asan_register_globals:
+; CHECK: i64 ptrtoint ({ [22 x i8]*, i32, i32 }* @.asan_loc_descr to i64)
+
+; Function Attrs: nounwind sanitize_address
+define internal void @__cxx_global_var_init() #0 section ".text.startup" {
+entry:
+  %0 = load i32* @global, align 4
+  store i32 %0, i32* @dyn_init_global, align 4
+  ret void
+}
+
+; Function Attrs: nounwind sanitize_address
+define void @_Z4funcv() #1 {
+entry:
+  %literal = alloca i8*, align 8
+  store i8* getelementptr inbounds ([14 x i8]* @.str, i32 0, i32 0), i8** %literal, align 8
+  ret void
+}
+
+; Function Attrs: nounwind sanitize_address
+define internal void @_GLOBAL__sub_I_asan_globals.cpp() #0 section ".text.startup" {
+entry:
+  call void @__cxx_global_var_init()
+  ret void
+}
+
+attributes #0 = { nounwind sanitize_address }
+attributes #1 = { nounwind sanitize_address "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-realign-stack" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.asan.globals = !{!0, !1, !2, !3, !4}
+!llvm.ident = !{!5}
+
+!0 = metadata !{i32* @global, { [22 x i8]*, i32, i32 }* @.asan_loc_descr, i1 false, i1 false}
+!1 = metadata !{i32* @dyn_init_global, { [22 x i8]*, i32, i32 }* @.asan_loc_descr1, i1 true, i1 false}
+!2 = metadata !{i32* @blacklisted_global, null, i1 false, i1 true}
+!3 = metadata !{i32* @_ZZ4funcvE10static_var, { [22 x i8]*, i32, i32 }* @.asan_loc_descr2, i1 false, i1 false}
+!4 = metadata !{[14 x i8]* @.str, { [22 x i8]*, i32, i32 }* @.asan_loc_descr4, i1 false, i1 false}
+!5 = metadata !{metadata !"clang version 3.5.0 (211282)"}
diff --git a/llvm/test/Instrumentation/AddressSanitizer/instrument_global.ll b/llvm/test/Instrumentation/AddressSanitizer/instrument_global.ll
index 7945e816ca3..816ab291566 100644
--- a/llvm/test/Instrumentation/AddressSanitizer/instrument_global.ll
+++ b/llvm/test/Instrumentation/AddressSanitizer/instrument_global.ll
@@ -68,8 +68,8 @@ entry:
 }
 
 
-!llvm.asan.dynamically_initialized_globals = !{!0}
-!0 = metadata !{[10 x i32]* @GlobDy}
+!llvm.asan.globals = !{!0}
+!0 = metadata !{[10 x i32]* @GlobDy, null, i1 true, i1 false}
 
 ; CHECK-LABEL: define internal void @asan.module_ctor
 ; CHECK-NOT: ret
diff --git a/llvm/test/Instrumentation/AddressSanitizer/instrument_initializer_metadata.ll b/llvm/test/Instrumentation/AddressSanitizer/instrument_initializer_metadata.ll
index 05e18b5a01b..83ff53f6f51 100644
--- a/llvm/test/Instrumentation/AddressSanitizer/instrument_initializer_metadata.ll
+++ b/llvm/test/Instrumentation/AddressSanitizer/instrument_initializer_metadata.ll
@@ -7,9 +7,11 @@ target triple = "x86_64-unknown-linux-gnu"
 @YYY = global i32 0, align 4           ; W/o dynamic initializer.
 ; Clang will emit the following metadata identifying @xxx as dynamically
 ; initialized.
-!0 = metadata !{i32* @xxx}
-!1 = metadata !{i32* @XXX}
-!llvm.asan.dynamically_initialized_globals = !{!0, !1}
+!0 = metadata !{i32* @xxx, null, i1 true, i1 false}
+!1 = metadata !{i32* @XXX, null, i1 true, i1 false}
+!2 = metadata !{i32* @yyy, null, i1 false, i1 false}
+!3 = metadata !{i32* @YYY, null, i1 false, i1 false}
+!llvm.asan.globals = !{!0, !1, !2, !3}
 
 define i32 @initializer() uwtable {
 entry: