[asan] Prevent folding of globals with redzones

[vitalybuka]

Summary

ICF prevented by removing unnamed_addr and local_unnamed_addr for all sanitized
globals. Also in general unnamed_addr is not valid here as address now is important for
ODR violation detector and redzone poisoning.

ICF on globals causes:

1. false ODR reports when we register global on the same address more than once
2. globals buffer overflow if we fold variables of smaller type inside of large

type. Then the smaller one will poison redzone which overlaps with the larger one.

Both can be avoided with private aliases and ODR-indicators, however they
increase size more than just disabling ICF on sanitized globals.

[pcc]

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

2151 ↗

(On Diff #178797)

The comment should say that asan's ODR violation detector and redzone poisoning implicitly creates a dependence on the global's address, so it is no longer valid for it to be marked unnamed_addr.

2203 ↗

(On Diff #178797)

Can we remove the linkonce_odr and weak_odr checks from here now?

[vitalybuka]

updated comment

[vitalybuka]

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

2203 ↗

(On Diff #178797)

D55899

[pcc]

LGTM

llvm/trunk/lib/Transforms/Instrumentation/AddressSanitizer.cpp

for (size_t i = 0; i < n; i++) {
     if (G->isConstant() && Linkage == GlobalValue::PrivateLinkage)
       Linkage = GlobalValue::InternalLinkage;
     GlobalVariable *NewGlobal =
         new GlobalVariable(M, NewTy, G->isConstant(), Linkage, NewInitializer,
                            "", G, G->getThreadLocalMode());
     NewGlobal->copyAttributesFrom(G);
     NewGlobal->setComdat(G->getComdat());
     NewGlobal->setAlignment(MinRZ);
+    // Don't fold globals with redzones. ODR violation detector and redzone
+    // poisoning implicitly creates a dependence on the global's address, so it
+    // is no longer valid for it to be marked unnamed_addr.
+    NewGlobal->setUnnamedAddr(GlobalValue::UnnamedAddr::None);
 
     // Move null-terminated C strings to "__asan_cstring" section on Darwin.
     if (TargetTriple.isOSBinFormatMachO() && !G->hasSection() &&
         G->isConstant()) {
       auto Seq = dyn_cast<ConstantDataSequential>(G->getInitializer());
       if (Seq && Seq->isCString())
         NewGlobal->setSection("__TEXT,__asan_cstring,regular");
     }

llvm/trunk/test/Instrumentation/AddressSanitizer/global_cstring_darwin.ll

 ; This test checks that instrumented global C (null terminated) strings are put into a special section on Darwin.
 ; 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-apple-macosx10.10.0"
 
 ; Should be put into __asan_cstring section:
 @.str.1 = private unnamed_addr constant [13 x i8] c"Hello world.\00", align 1
 @.str.2 = private unnamed_addr constant [4 x i8] c"%s\0A\00", align 1
 
-; CHECK: @.str.1 = internal unnamed_addr constant { [13 x i8], [51 x i8] } { [13 x i8] c"Hello world.\00", [51 x i8] zeroinitializer }, section "__TEXT,__asan_cstring,regular", align 32
-; CHECK: @.str.2 = internal unnamed_addr constant { [4 x i8], [60 x i8] } { [4 x i8] c"%s\0A\00", [60 x i8] zeroinitializer }, section "__TEXT,__asan_cstring,regular", align 32
+; CHECK: @.str.1 = internal constant { [13 x i8], [51 x i8] } { [13 x i8] c"Hello world.\00", [51 x i8] zeroinitializer }, section "__TEXT,__asan_cstring,regular", align 32
+; CHECK: @.str.2 = internal constant { [4 x i8], [60 x i8] } { [4 x i8] c"%s\0A\00", [60 x i8] zeroinitializer }, section "__TEXT,__asan_cstring,regular", align 32
 
 ; Shouldn't be put into special section:
 @.str.3 = private unnamed_addr constant [4 x i8] c"\00\01\02\03", align 1
 @.str.4 = private unnamed_addr global [7 x i8] c"Hello.\00", align 1
 @.str.5 = private unnamed_addr constant [8 x i8] c"Hello.\00\00", align 1
 
-; CHECK: @.str.3 = internal unnamed_addr constant { [4 x i8], [60 x i8] } { [4 x i8] c"\00\01\02\03", [60 x i8] zeroinitializer }, align 32
-; CHECK: @.str.4 = private unnamed_addr global { [7 x i8], [57 x i8] } { [7 x i8] c"Hello.\00", [57 x i8] zeroinitializer }, align 32
-; CHECK: @.str.5 = internal unnamed_addr constant { [8 x i8], [56 x i8] } { [8 x i8] c"Hello.\00\00", [56 x i8] zeroinitializer }, align 32
+; CHECK: @.str.3 = internal constant { [4 x i8], [60 x i8] } { [4 x i8] c"\00\01\02\03", [60 x i8] zeroinitializer }, align 32
+; CHECK: @.str.4 = private global { [7 x i8], [57 x i8] } { [7 x i8] c"Hello.\00", [57 x i8] zeroinitializer }, align 32
+; CHECK: @.str.5 = internal constant { [8 x i8], [56 x i8] } { [8 x i8] c"Hello.\00\00", [56 x i8] zeroinitializer }, align 32

llvm/trunk/test/Instrumentation/AddressSanitizer/global_metadata.ll

 @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 }]
 
 ; Check that globals were instrumented:
 
 ; CHECK: @global = global { i32, [60 x i8] } zeroinitializer, comdat, 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 }, comdat($".str${{[01-9a-f]+}}"), align 32
+; CHECK: @.str = internal constant { [14 x i8], [50 x i8] } { [14 x i8] c"Hello, world!\00", [50 x i8] zeroinitializer }, comdat($".str${{[01-9a-f]+}}"), align 32
 
 ; Check emitted location descriptions:
 ; CHECK: [[VARNAME:@___asan_gen_.[0-9]+]] = private unnamed_addr constant [7 x i8] c"global\00", align 1
 ; CHECK: [[FILENAME:@___asan_gen_.[0-9]+]] = private unnamed_addr constant [22 x i8] c"/tmp/asan-globals.cpp\00", align 1
 ; CHECK: [[LOCDESCR:@___asan_gen_.[0-9]+]] = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* [[FILENAME]], i32 5, i32 5 }
 ; CHECK: @__asan_global_global = {{.*}}i64 ptrtoint ({ i32, [60 x i8] }* @global to i64){{.*}} section "asan_globals"{{.*}}, !associated
 ; CHECK: @__asan_global_.str = {{.*}}i64 ptrtoint ({ [14 x i8], [50 x i8] }* @{{.str|1}} to i64){{.*}} section "asan_globals"{{.*}}, !associated
 

llvm/trunk/test/Instrumentation/AddressSanitizer/global_metadata_array.ll

 @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 }]
 
 ; Check that globals were instrumented:
 ; 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: @.str = internal constant { [14 x i8], [50 x i8] } { [14 x i8] c"Hello, world!\00", [50 x i8] zeroinitializer }{{.*}}, align 32
 
 ; Check emitted location descriptions:
 ; CHECK: [[VARNAME:@___asan_gen_.[0-9]+]] = private unnamed_addr constant [7 x i8] c"global\00", align 1
 ; CHECK: [[FILENAME:@___asan_gen_.[0-9]+]] = private unnamed_addr constant [22 x i8] c"/tmp/asan-globals.cpp\00", align 1
 ; CHECK: [[LOCDESCR:@___asan_gen_.[0-9]+]] = private unnamed_addr constant { [22 x i8]*, i32, i32 } { [22 x i8]* [[FILENAME]], i32 5, i32 5 }
 
 ; Check that location descriptors and global names were passed into __asan_register_globals:
 ; CHECK: i64 ptrtoint ([7 x i8]* [[VARNAME]] to i64)

llvm/trunk/test/Instrumentation/AddressSanitizer/global_metadata_windows.ll

 ; Test that global metadata is placed in a separate section on Windows, and that
 ; it is in the same comdat group as the instrumented global. This ensures that
 ; linker dead stripping (/OPT:REF) works as intended.
 
 ; FIXME: Later we can use this to instrument linkonce odr string literals.
 
 ; RUN: opt < %s -asan -asan-module -asan-globals-live-support=1 -S | FileCheck %s
 
 target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-pc-windows-msvc19.0.24215"
 
 $mystr = comdat any
 
 ; CHECK: $dead_global = comdat noduplicates
 ; CHECK: $private_str = comdat noduplicates
 
-; CHECK: @dead_global = local_unnamed_addr global { i32, [60 x i8] } { i32 42, [60 x i8] zeroinitializer }, comdat, align 32
-; CHECK: @private_str = internal unnamed_addr constant { [8 x i8], [56 x i8] } { [8 x i8] c"private\00", [56 x i8] zeroinitializer }, comdat, align 32
+; CHECK: @dead_global = global { i32, [60 x i8] } { i32 42, [60 x i8] zeroinitializer }, comdat, align 32
+; CHECK: @private_str = internal constant { [8 x i8], [56 x i8] } { [8 x i8] c"private\00", [56 x i8] zeroinitializer }, comdat, align 32
 
 ; CHECK: @__asan_global_dead_global = private global { {{.*}} }, section ".ASAN$GL", comdat($dead_global), align 64
 ; CHECK: @__asan_global_private_str = private global { {{.*}} }, section ".ASAN$GL", comdat($private_str), align 64
 
 @dead_global = local_unnamed_addr global i32 42, align 4
 @mystr = linkonce_odr unnamed_addr constant [5 x i8] c"main\00", comdat, align 1
 
 ; Private globals will get upgraded to internal linkage.

llvm/trunk/test/Instrumentation/AddressSanitizer/win-string-literal.ll

 ; RUN: opt < %s -asan -asan-module -S | FileCheck %s
 
 ; Generated like so:
 ; $ clang -S -emit-llvm -Xclang -disable-llvm-passes -fsanitize=address -O1 t.cpp -o t.ll
 ; const char *getstr() { return "asdf"; }
 
 ; CHECK: $"??_C@_04JIHMPGLA@asdf?$AA@" = comdat any
 
 ; CHECK: @"??_C@_04JIHMPGLA@asdf?$AA@" =
-; CHECK-SAME: linkonce_odr dso_local unnamed_addr constant { [5 x i8], [59 x i8] }
+; CHECK-SAME: linkonce_odr dso_local constant { [5 x i8], [59 x i8] }
 ; CHECK-SAME: { [5 x i8] c"asdf\00", [59 x i8] zeroinitializer }, comdat, align 32
 
 ; CHECK: @"__asan_global_??_C@_04JIHMPGLA@asdf?$AA@" =
 ; CHECK-SAME: private global { i64, i64, i64, i64, i64, i64, i64, i64 }
 ; CHECK-SAME: { i64 ptrtoint ({ [5 x i8], [59 x i8] }* @"??_C@_04JIHMPGLA@asdf?$AA@" to i64),
 ; CHECK-SAME:   i64 5, i64 64, i64 ptrtoint ([17 x i8]* @___asan_gen_.1 to i64),
 ; CHECK-SAME:   i64 ptrtoint ([8 x i8]* @___asan_gen_ to i64), i64 0,
 ; CHECK-SAME:   i64 ptrtoint ({ [6 x i8]*, i32, i32 }* @___asan_gen_.3 to i64), i64 -1 },