From 1030297d77ae5110b7873530f645aeec3a4264ba Mon Sep 17 00:00:00 2001
From: Yuanfang Chen <yuanfang.chen@sony.com>
Date: Mon, 27 Jun 2022 11:33:45 -0700
Subject: [PATCH] [ubsan] Using metadata instead of prologue data for function
sanitizer
Information in the function `Prologue Data` is intentionally opaque.
When a function with `Prologue Data` is duplicated. The self (global
value) references inside `Prologue Data` is still pointing to the
original function. This may cause errors like `fatal error: error in backend: Cannot represent a difference across sections`.
This patch detaches the information from function `Prologue Data`
and attaches it to a function metadata node.
This and D116130 fix https://github.com/llvm/llvm-project/issues/49689.
Reviewed By: pcc
Differential Revision: https://reviews.llvm.org/D115844
(cherry picked from commit 6678f8e505b19069a9dbdc3e3ee088d543752412)
---
clang/lib/CodeGen/CodeGenFunction.cpp | 36 ++++--------------
clang/lib/CodeGen/CodeGenFunction.h | 4 --
clang/lib/CodeGen/CodeGenModule.cpp | 16 ++++++++
clang/lib/CodeGen/CodeGenModule.h | 5 +++
clang/lib/Driver/SanitizerArgs.cpp | 13 +++++++
clang/test/CodeGen/ubsan-function.cpp | 5 ++-
.../test/CodeGenCXX/catch-undef-behavior.cpp | 37 +++++++++----------
.../CodeGenCXX/ubsan-function-noexcept.cpp | 6 ++-
clang/test/Driver/fsanitize.c | 3 ++
9 files changed, 69 insertions(+), 56 deletions(-)
diff --git a/clang/lib/CodeGen/CodeGenFunction.cpp b/clang/lib/CodeGen/CodeGenFunction.cpp
index 50e1638924d1..d7393526bb2c 100644
--- a/clang/lib/CodeGen/CodeGenFunction.cpp
+++ b/clang/lib/CodeGen/CodeGenFunction.cpp
@@ -560,29 +560,6 @@ bool CodeGenFunction::AlwaysEmitXRayTypedEvents() const {
XRayInstrKind::Typed);
}
-llvm::Constant *
-CodeGenFunction::EncodeAddrForUseInPrologue(llvm::Function *F,
- llvm::Constant *Addr) {
- // Addresses stored in prologue data can't require run-time fixups and must
- // be PC-relative. Run-time fixups are undesirable because they necessitate
- // writable text segments, which are unsafe. And absolute addresses are
- // undesirable because they break PIE mode.
-
- // Add a layer of indirection through a private global. Taking its address
- // won't result in a run-time fixup, even if Addr has linkonce_odr linkage.
- auto *GV = new llvm::GlobalVariable(CGM.getModule(), Addr->getType(),
- /*isConstant=*/true,
- llvm::GlobalValue::PrivateLinkage, Addr);
-
- // Create a PC-relative address.
- auto *GOTAsInt = llvm::ConstantExpr::getPtrToInt(GV, IntPtrTy);
- auto *FuncAsInt = llvm::ConstantExpr::getPtrToInt(F, IntPtrTy);
- auto *PCRelAsInt = llvm::ConstantExpr::getSub(GOTAsInt, FuncAsInt);
- return (IntPtrTy == Int32Ty)
- ? PCRelAsInt
- : llvm::ConstantExpr::getTrunc(PCRelAsInt, Int32Ty);
-}
-
llvm::Value *
CodeGenFunction::DecodeAddrUsedInPrologue(llvm::Value *F,
llvm::Value *EncodedAddr) {
@@ -926,12 +903,13 @@ void CodeGenFunction::StartFunction(GlobalDecl GD, QualType RetTy,
FD->getType(), EST_None);
llvm::Constant *FTRTTIConst =
CGM.GetAddrOfRTTIDescriptor(ProtoTy, /*ForEH=*/true);
- llvm::Constant *FTRTTIConstEncoded =
- EncodeAddrForUseInPrologue(Fn, FTRTTIConst);
- llvm::Constant *PrologueStructElems[] = {PrologueSig, FTRTTIConstEncoded};
- llvm::Constant *PrologueStructConst =
- llvm::ConstantStruct::getAnon(PrologueStructElems, /*Packed=*/true);
- Fn->setPrologueData(PrologueStructConst);
+ llvm::GlobalVariable *FTRTTIProxy =
+ CGM.GetOrCreateRTTIProxyGlobalVariable(FTRTTIConst);
+ llvm::LLVMContext &Ctx = Fn->getContext();
+ llvm::MDBuilder MDB(Ctx);
+ Fn->setMetadata(llvm::LLVMContext::MD_func_sanitize,
+ MDB.createRTTIPointerPrologue(PrologueSig, FTRTTIProxy));
+ CGM.addCompilerUsedGlobal(FTRTTIProxy);
}
}
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index df99cd9a1b79..046b249b1aac 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -2351,10 +2351,6 @@ public:
/// XRay typed event handling calls.
bool AlwaysEmitXRayTypedEvents() const;
- /// Encode an address into a form suitable for use in a function prologue.
- llvm::Constant *EncodeAddrForUseInPrologue(llvm::Function *F,
- llvm::Constant *Addr);
-
/// Decode an address used in a function prologue, encoded by \c
/// EncodeAddrForUseInPrologue.
llvm::Value *DecodeAddrUsedInPrologue(llvm::Value *F,
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index 2777fc22600d..58eef1b0fdca 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -1826,6 +1826,22 @@ CodeGenModule::getMostBaseClasses(const CXXRecordDecl *RD) {
return MostBases.takeVector();
}
+llvm::GlobalVariable *
+CodeGenModule::GetOrCreateRTTIProxyGlobalVariable(llvm::Constant *Addr) {
+ auto It = RTTIProxyMap.find(Addr);
+ if (It != RTTIProxyMap.end())
+ return It->second;
+
+ auto *FTRTTIProxy = new llvm::GlobalVariable(
+ TheModule, Addr->getType(),
+ /*isConstant=*/true, llvm::GlobalValue::PrivateLinkage, Addr,
+ "__llvm_rtti_proxy");
+ FTRTTIProxy->setUnnamedAddr(llvm::GlobalValue::UnnamedAddr::Global);
+
+ RTTIProxyMap[Addr] = FTRTTIProxy;
+ return FTRTTIProxy;
+}
+
void CodeGenModule::SetLLVMFunctionAttributesForDefinition(const Decl *D,
llvm::Function *F) {
llvm::AttrBuilder B(F->getContext());
diff --git a/clang/lib/CodeGen/CodeGenModule.h b/clang/lib/CodeGen/CodeGenModule.h
index a8a63c8da57f..3a9d542eb2e0 100644
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/lib/CodeGen/CodeGenModule.h
@@ -561,6 +561,8 @@ private:
MetadataTypeMap VirtualMetadataIdMap;
MetadataTypeMap GeneralizedMetadataIdMap;
+ llvm::DenseMap<const llvm::Constant *, llvm::GlobalVariable *> RTTIProxyMap;
+
public:
CodeGenModule(ASTContext &C, const HeaderSearchOptions &headersearchopts,
const PreprocessorOptions &ppopts,
@@ -1411,6 +1413,9 @@ public:
std::vector<const CXXRecordDecl *>
getMostBaseClasses(const CXXRecordDecl *RD);
+ llvm::GlobalVariable *
+ GetOrCreateRTTIProxyGlobalVariable(llvm::Constant *Addr);
+
/// Get the declaration of std::terminate for the platform.
llvm::FunctionCallee getTerminateFn();
diff --git a/clang/lib/Driver/SanitizerArgs.cpp b/clang/lib/Driver/SanitizerArgs.cpp
index 403fac76f060..96cef9eb80b8 100644
--- a/clang/lib/Driver/SanitizerArgs.cpp
+++ b/clang/lib/Driver/SanitizerArgs.cpp
@@ -367,6 +367,19 @@ SanitizerArgs::SanitizerArgs(const ToolChain &TC,
Add &= ~NotAllowedWithMinimalRuntime;
}
+ if (llvm::opt::Arg *A = Args.getLastArg(options::OPT_mcmodel_EQ)) {
+ StringRef CM = A->getValue();
+ if (CM != "small" &&
+ (Add & SanitizerKind::Function & ~DiagnosedKinds)) {
+ if (DiagnoseErrors)
+ D.Diag(diag::err_drv_argument_only_allowed_with)
+ << "-fsanitize=function"
+ << "-mcmodel=small";
+ Add &= ~SanitizerKind::Function;
+ DiagnosedKinds |= SanitizerKind::Function;
+ }
+ }
+
// FIXME: Make CFI on member function calls compatible with cross-DSO CFI.
// There are currently two problems:
// - Virtual function call checks need to pass a pointer to the function
diff --git a/clang/test/CodeGen/ubsan-function.cpp b/clang/test/CodeGen/ubsan-function.cpp
index 2466d8a2645d..8a16dfdf5da1 100644
--- a/clang/test/CodeGen/ubsan-function.cpp
+++ b/clang/test/CodeGen/ubsan-function.cpp
@@ -1,6 +1,7 @@
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm -o - %s -fsanitize=function -fno-sanitize-recover=all | FileCheck %s
-// CHECK-LABEL: define{{.*}} void @_Z3funv() #0 prologue <{ i32, i32 }> <{ i32 846595819, i32 trunc (i64 sub (i64 ptrtoint (i8** @0 to i64), i64 ptrtoint (void ()* @_Z3funv to i64)) to i32) }> {
+// CHECK: @[[PROXY:.*]] = private unnamed_addr constant i8* bitcast ({ i8*, i8* }* @_ZTIFvvE to i8*)
+// CHECK: define{{.*}} void @_Z3funv() #0 !func_sanitize ![[FUNCSAN:.*]] {
void fun() {}
// CHECK-LABEL: define{{.*}} void @_Z6callerPFvvE(void ()* noundef %f)
@@ -20,3 +21,5 @@ void fun() {}
// CHECK: [[LABEL3]]:
// CHECK: br label %[[LABEL4]], !nosanitize
void caller(void (*f)()) { f(); }
+
+// CHECK: ![[FUNCSAN]] = !{i32 846595819, i8** @[[PROXY]]}
diff --git a/clang/test/CodeGenCXX/catch-undef-behavior.cpp b/clang/test/CodeGenCXX/catch-undef-behavior.cpp
index d6b094cb5b82..ade29797f5a0 100644
--- a/clang/test/CodeGenCXX/catch-undef-behavior.cpp
+++ b/clang/test/CodeGenCXX/catch-undef-behavior.cpp
@@ -1,8 +1,8 @@
-// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=signed-integer-overflow,integer-divide-by-zero,float-divide-by-zero,shift-base,shift-exponent,unreachable,return,vla-bound,alignment,null,vptr,object-size,float-cast-overflow,bool,enum,array-bounds,function -fsanitize-recover=signed-integer-overflow,integer-divide-by-zero,float-divide-by-zero,shift-base,shift-exponent,vla-bound,alignment,null,vptr,object-size,float-cast-overflow,bool,enum,array-bounds,function -emit-llvm %s -o - -triple x86_64-linux-gnu | opt -instnamer -S | FileCheck %s
+// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=signed-integer-overflow,integer-divide-by-zero,float-divide-by-zero,shift-base,shift-exponent,unreachable,return,vla-bound,alignment,null,vptr,object-size,float-cast-overflow,bool,enum,array-bounds,function -fsanitize-recover=signed-integer-overflow,integer-divide-by-zero,float-divide-by-zero,shift-base,shift-exponent,vla-bound,alignment,null,vptr,object-size,float-cast-overflow,bool,enum,array-bounds,function -emit-llvm %s -o - -triple x86_64-linux-gnu | opt -instnamer -S | FileCheck %s --check-prefixes=CHECK,CHECK-FUNCSAN
// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=vptr,address -fsanitize-recover=vptr,address -emit-llvm %s -o - -triple x86_64-linux-gnu | FileCheck %s --check-prefix=CHECK-ASAN
// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=vptr -fsanitize-recover=vptr -emit-llvm %s -o - -triple x86_64-linux-gnu | FileCheck %s --check-prefix=DOWNCAST-NULL
-// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=function -emit-llvm %s -o - -triple x86_64-linux-gnux32 | FileCheck %s --check-prefix=CHECK-X32
-// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=function -emit-llvm %s -o - -triple i386-linux-gnu | FileCheck %s --check-prefix=CHECK-X86
+// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=function -emit-llvm %s -o - -triple x86_64-linux-gnux32 | FileCheck %s --check-prefix=CHECK-FUNCSAN
+// RUN: %clang_cc1 -disable-noundef-analysis -std=c++11 -fsanitize=function -emit-llvm %s -o - -triple i386-linux-gnu | FileCheck %s --check-prefix=CHECK-FUNCSAN
struct S {
double d;
@@ -16,9 +16,7 @@ struct S {
// Check that type mismatch handler is not modified by ASan.
// CHECK-ASAN: private unnamed_addr global { { [{{.*}} x i8]*, i32, i32 }, { i16, i16, [4 x i8] }*, i8*, i8 } { {{.*}}, { i16, i16, [4 x i8] }* [[TYPE_DESCR]], {{.*}} }
-// CHECK: [[IndirectRTTI_ZTIFvPFviEE:@.+]] = private constant i8* bitcast ({ i8*, i8* }* @_ZTIFvPFviEE to i8*)
-// CHECK-X86: [[IndirectRTTI_ZTIFvPFviEE:@.+]] = private constant i8* bitcast ({ i8*, i8* }* @_ZTIFvPFviEE to i8*)
-// CHECK-X32: [[IndirectRTTI_ZTIFvPFviEE:@.+]] = private constant i8* bitcast ({ i8*, i8* }* @_ZTIFvPFviEE to i8*)
+// CHECK-FUNCSAN: [[PROXY:@.+]] = private unnamed_addr constant i8* bitcast ({ i8*, i8* }* @_ZTIFvPFviEE to i8*)
struct T : S {};
@@ -399,10 +397,7 @@ void downcast_reference(B &b) {
// CHECK-NEXT: br i1 [[AND]]
}
-//
-// CHECK-LABEL: @_Z22indirect_function_callPFviE({{.*}} prologue <{ i32, i32 }> <{ i32 846595819, i32 trunc (i64 sub (i64 ptrtoint (i8** {{.*}} to i64), i64 ptrtoint (void (void (i32)*)* @_Z22indirect_function_callPFviE to i64)) to i32) }>
-// CHECK-X32: @_Z22indirect_function_callPFviE({{.*}} prologue <{ i32, i32 }> <{ i32 846595819, i32 sub (i32 ptrtoint (i8** [[IndirectRTTI_ZTIFvPFviEE]] to i32), i32 ptrtoint (void (void (i32)*)* @_Z22indirect_function_callPFviE to i32)) }>
-// CHECK-X86: @_Z22indirect_function_callPFviE({{.*}} prologue <{ i32, i32 }> <{ i32 846595819, i32 sub (i32 ptrtoint (i8** [[IndirectRTTI_ZTIFvPFviEE]] to i32), i32 ptrtoint (void (void (i32)*)* @_Z22indirect_function_callPFviE to i32)) }>
+// CHECK-FUNCSAN: @_Z22indirect_function_callPFviE({{.*}} !func_sanitize ![[FUNCSAN:.*]] {
void indirect_function_call(void (*p)(int)) {
// CHECK: [[PTR:%.+]] = bitcast void (i32)* {{.*}} to <{ i32, i32 }>*
@@ -483,34 +478,34 @@ void force_irgen() {
}
// CHECK-LABEL: define{{.*}} void @_ZN29FunctionSanitizerVirtualCalls1B1fEv
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define{{.*}} void @_ZTv0_n24_N29FunctionSanitizerVirtualCalls1B1fEv
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define{{.*}} void @_ZN29FunctionSanitizerVirtualCalls11force_irgenEv()
-// CHECK: prologue
+// CHECK: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1AC1Ev
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1A1gEv
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1A1hEv
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1BC1Ev
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1B1bEv
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1B1gEv
-// CHECK-NOT: prologue
+// CHECK-NOT: !func_sanitize
//
// CHECK-LABEL: define linkonce_odr void @_ZN29FunctionSanitizerVirtualCalls1B1qEv
-// CHECK: prologue
+// CHECK: !func_sanitize
}
@@ -754,3 +749,5 @@ void ThisAlign::this_align_lambda_2() {
}
// CHECK: attributes [[NR_NUW]] = { noreturn nounwind }
+
+// CHECK-FUNCSAN: ![[FUNCSAN]] = !{i32 846595819, i8** [[PROXY]]}
diff --git a/clang/test/CodeGenCXX/ubsan-function-noexcept.cpp b/clang/test/CodeGenCXX/ubsan-function-noexcept.cpp
index 3c0c0e8be91f..9d5eb1edefe5 100644
--- a/clang/test/CodeGenCXX/ubsan-function-noexcept.cpp
+++ b/clang/test/CodeGenCXX/ubsan-function-noexcept.cpp
@@ -2,8 +2,8 @@
// Check that typeinfo recorded in function prolog doesn't have "Do" noexcept
// qualifier in its mangled name.
-// CHECK: @[[RTTI:[0-9]+]] = private constant i8* bitcast ({ i8*, i8* }* @_ZTIFvvE to i8*)
-// CHECK: define{{.*}} void @_Z1fv() #{{.*}} prologue <{ i32, i32 }> <{ i32 {{.*}}, i32 trunc (i64 sub (i64 ptrtoint (i8** @[[RTTI]] to i64), i64 ptrtoint (void ()* @_Z1fv to i64)) to i32) }>
+// CHECK: [[PROXY:@.*]] = private unnamed_addr constant i8* bitcast ({ i8*, i8* }* @_ZTIFvvE to i8*)
+// CHECK: define{{.*}} void @_Z1fv() #{{.*}} !func_sanitize ![[FUNCSAN:.*]] {
void f() noexcept {}
// CHECK: define{{.*}} void @_Z1gPDoFvvE
@@ -13,3 +13,5 @@ void g(void (*p)() noexcept) {
// CHECK: icmp eq i8* %{{.*}}, bitcast ({ i8*, i8* }* @_ZTIFvvE to i8*), !nosanitize
p();
}
+
+// CHECK: ![[FUNCSAN]] = !{i32 846595819, i8** [[PROXY]]}
diff --git a/clang/test/Driver/fsanitize.c b/clang/test/Driver/fsanitize.c
index 17fce1981eea..624dc98478ec 100644
--- a/clang/test/Driver/fsanitize.c
+++ b/clang/test/Driver/fsanitize.c
@@ -915,3 +915,6 @@
// RUN: %clang -fsanitize=undefined,float-divide-by-zero %s -### 2>&1 | FileCheck %s --check-prefix=CHECK-DIVBYZERO-UBSAN
// CHECK-DIVBYZERO-UBSAN: "-fsanitize={{.*}},float-divide-by-zero,{{.*}}"
+
+// RUN: %clang -target x86_64-linux-gnu -fsanitize=undefined,function -mcmodel=large %s -### 2>&1 | FileCheck %s --check-prefix=CHECK-UBSAN-FUNCTION-CODE-MODEL
+// CHECK-UBSAN-FUNCTION-CODE-MODEL: error: invalid argument '-fsanitize=function' only allowed with '-mcmodel=small'