[clang][UBSan] Sanitization for alignment assumptions.

Summary:
UB isn't nice. It's cool and powerful, but not nice.
Having a way to detect it is nice though.
[[ https://wg21.link/p1007r3 | P1007R3: std::assume_aligned ]] / http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2018/p1007r2.pdf says:
```
We propose to add this functionality via a library function instead of a core language attribute.
...
If the pointer passed in is not aligned to at least N bytes, calling assume_aligned results in undefined behaviour.
```

This differential teaches clang to sanitize all the various variants of this assume-aligned attribute.

Requires D54588 for LLVM IRBuilder changes.
The compiler-rt part is D54590.

Reviewers: ABataev, craig.topper, vsk, rsmith, rnk, #sanitizers, erichkeane, filcab, rjmccall

Reviewed By: rjmccall

Subscribers: chandlerc, ldionne, EricWF, mclow.lists, cfe-commits, bkramer

Tags: #sanitizers

Differential Revision: https://reviews.llvm.org/D54589

llvm-svn: 351105

6 files changed, 145 insertions, 25 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 4c17602314e5..a718f2f19aa6 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -1904,15 +1904,17 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     return RValue::get(Result);
   }
   case Builtin::BI__builtin_assume_aligned: {
-    Value *PtrValue = EmitScalarExpr(E->getArg(0));
+    const Expr *Ptr = E->getArg(0);
+    Value *PtrValue = EmitScalarExpr(Ptr);
     Value *OffsetValue =
       (E->getNumArgs() > 2) ? EmitScalarExpr(E->getArg(2)) : nullptr;
 
     Value *AlignmentValue = EmitScalarExpr(E->getArg(1));
     ConstantInt *AlignmentCI = cast<ConstantInt>(AlignmentValue);
-    unsigned Alignment = (unsigned) AlignmentCI->getZExtValue();
+    unsigned Alignment = (unsigned)AlignmentCI->getZExtValue();
 
-    EmitAlignmentAssumption(PtrValue, Alignment, OffsetValue);
+    EmitAlignmentAssumption(PtrValue, Ptr, /*The expr loc is sufficient.*/ SourceLocation(),
+                            Alignment, OffsetValue);
     return RValue::get(PtrValue);
   }
   case Builtin::BI__assume:
diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
index 455a25434ffb..7d494bb1f1c7 100644
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -2410,7 +2410,10 @@ void CodeGenFunction::EmitFunctionProlog(const CGFunctionInfo &FI,
           if (!AVAttr)
             if (const auto *TOTy = dyn_cast<TypedefType>(OTy))
               AVAttr = TOTy->getDecl()->getAttr<AlignValueAttr>();
-          if (AVAttr) {
+          if (AVAttr && !SanOpts.has(SanitizerKind::Alignment)) {
+            // If alignment-assumption sanitizer is enabled, we do *not* add
+            // alignment attribute here, but emit normal alignment assumption,
+            // so the UBSAN check could function.
             llvm::Value *AlignmentValue =
               EmitScalarExpr(AVAttr->getAlignment());
             llvm::ConstantInt *AlignmentCI =
@@ -4535,13 +4538,14 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
 
       llvm::Value *Alignment = EmitScalarExpr(AA->getAlignment());
       llvm::ConstantInt *AlignmentCI = cast<llvm::ConstantInt>(Alignment);
-      EmitAlignmentAssumption(Ret.getScalarVal(), AlignmentCI->getZExtValue(),
-                              OffsetValue);
+      EmitAlignmentAssumption(Ret.getScalarVal(), RetTy, Loc, AA->getLocation(),
+                              AlignmentCI->getZExtValue(), OffsetValue);
     } else if (const auto *AA = TargetDecl->getAttr<AllocAlignAttr>()) {
-      llvm::Value *ParamVal =
-          CallArgs[AA->getParamIndex().getLLVMIndex()].getRValue(
-              *this).getScalarVal();
-      EmitAlignmentAssumption(Ret.getScalarVal(), ParamVal);
+      llvm::Value *AlignmentVal = CallArgs[AA->getParamIndex().getLLVMIndex()]
+                                      .getRValue(*this)
+                                      .getScalarVal();
+      EmitAlignmentAssumption(Ret.getScalarVal(), RetTy, Loc, AA->getLocation(),
+                              AlignmentVal);
     }
   }
 
diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
index f53bb33e463a..1c14d4c99a23 100644
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -258,8 +258,11 @@ public:
           AVAttr = TTy->getDecl()->getAttr<AlignValueAttr>();
       } else {
         // Assumptions for function parameters are emitted at the start of the
-        // function, so there is no need to repeat that here.
-        if (isa<ParmVarDecl>(VD))
+        // function, so there is no need to repeat that here,
+        // unless the alignment-assumption sanitizer is enabled,
+        // then we prefer the assumption over alignment attribute
+        // on IR function param.
+        if (isa<ParmVarDecl>(VD) && !CGF.SanOpts.has(SanitizerKind::Alignment))
           return;
 
         AVAttr = VD->getAttr<AlignValueAttr>();
@@ -276,7 +279,8 @@ public:
 
     Value *AlignmentValue = CGF.EmitScalarExpr(AVAttr->getAlignment());
     llvm::ConstantInt *AlignmentCI = cast<llvm::ConstantInt>(AlignmentValue);
-    CGF.EmitAlignmentAssumption(V, AlignmentCI->getZExtValue());
+    CGF.EmitAlignmentAssumption(V, E, AVAttr->getLocation(),
+                                AlignmentCI->getZExtValue());
   }
 
   /// EmitLoadOfLValue - Given an expression with complex type that represents a
diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index 650f4e8b91aa..eb1304d89345 100644
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -1472,7 +1472,8 @@ static void emitAlignedClause(CodeGenFunction &CGF,
              "alignment is not power of 2");
       if (Alignment != 0) {
         llvm::Value *PtrValue = CGF.EmitScalarExpr(E);
-        CGF.EmitAlignmentAssumption(PtrValue, Alignment);
+        CGF.EmitAlignmentAssumption(
+            PtrValue, E, /*No second loc needed*/ SourceLocation(), Alignment);
       }
     }
   }
diff --git a/clang/lib/CodeGen/CodeGenFunction.cpp b/clang/lib/CodeGen/CodeGenFunction.cpp
index 2b25fb469d75..1713e40c312b 100644
--- a/clang/lib/CodeGen/CodeGenFunction.cpp
+++ b/clang/lib/CodeGen/CodeGenFunction.cpp
@@ -2207,6 +2207,49 @@ void CodeGenFunction::unprotectFromPeepholes(PeepholeProtection protection) {
   protection.Inst->eraseFromParent();
 }
 
+void CodeGenFunction::EmitAlignmentAssumption(llvm::Value *PtrValue,
+                                              QualType Ty, SourceLocation Loc,
+                                              SourceLocation AssumptionLoc,
+                                              llvm::Value *Alignment,
+                                              llvm::Value *OffsetValue) {
+  llvm::Value *TheCheck;
+  llvm::Instruction *Assumption = Builder.CreateAlignmentAssumption(
+      CGM.getDataLayout(), PtrValue, Alignment, OffsetValue, &TheCheck);
+  if (SanOpts.has(SanitizerKind::Alignment)) {
+    EmitAlignmentAssumptionCheck(PtrValue, Ty, Loc, AssumptionLoc, Alignment,
+                                 OffsetValue, TheCheck, Assumption);
+  }
+}
+
+void CodeGenFunction::EmitAlignmentAssumption(llvm::Value *PtrValue,
+                                              QualType Ty, SourceLocation Loc,
+                                              SourceLocation AssumptionLoc,
+                                              unsigned Alignment,
+                                              llvm::Value *OffsetValue) {
+  llvm::Value *TheCheck;
+  llvm::Instruction *Assumption = Builder.CreateAlignmentAssumption(
+      CGM.getDataLayout(), PtrValue, Alignment, OffsetValue, &TheCheck);
+  if (SanOpts.has(SanitizerKind::Alignment)) {
+    llvm::Value *AlignmentVal = llvm::ConstantInt::get(IntPtrTy, Alignment);
+    EmitAlignmentAssumptionCheck(PtrValue, Ty, Loc, AssumptionLoc, AlignmentVal,
+                                 OffsetValue, TheCheck, Assumption);
+  }
+}
+
+void CodeGenFunction::EmitAlignmentAssumption(llvm::Value *PtrValue,
+                                              const Expr *E,
+                                              SourceLocation AssumptionLoc,
+                                              unsigned Alignment,
+                                              llvm::Value *OffsetValue) {
+  if (auto *CE = dyn_cast<CastExpr>(E))
+    E = CE->getSubExprAsWritten();
+  QualType Ty = E->getType();
+  SourceLocation Loc = E->getExprLoc();
+
+  EmitAlignmentAssumption(PtrValue, Ty, Loc, AssumptionLoc, Alignment,
+                          OffsetValue);
+}
+
 llvm::Value *CodeGenFunction::EmitAnnotationCall(llvm::Value *AnnotationFn,
                                                  llvm::Value *AnnotatedVal,
                                                  StringRef AnnotationStr,
@@ -2459,6 +2502,61 @@ void CodeGenFunction::EmitMultiVersionResolver(
   Builder.ClearInsertionPoint();
 }
 
+// Loc - where the diagnostic will point, where in the source code this
+//  alignment has failed.
+// SecondaryLoc - if present (will be present if sufficiently different from
+//  Loc), the diagnostic will additionally point a "Note:" to this location.
+//  It should be the location where the __attribute__((assume_aligned))
+//  was written e.g.
+void CodeGenFunction::EmitAlignmentAssumptionCheck(
+    llvm::Value *Ptr, QualType Ty, SourceLocation Loc,
+    SourceLocation SecondaryLoc, llvm::Value *Alignment,
+    llvm::Value *OffsetValue, llvm::Value *TheCheck,
+    llvm::Instruction *Assumption) {
+  assert(Assumption && isa<llvm::CallInst>(Assumption) &&
+         cast<llvm::CallInst>(Assumption)->getCalledValue() ==
+             llvm::Intrinsic::getDeclaration(
+                 Builder.GetInsertBlock()->getParent()->getParent(),
+                 llvm::Intrinsic::assume) &&
+         "Assumption should be a call to llvm.assume().");
+  assert(&(Builder.GetInsertBlock()->back()) == Assumption &&
+         "Assumption should be the last instruction of the basic block, "
+         "since the basic block is still being generated.");
+
+  if (!SanOpts.has(SanitizerKind::Alignment))
+    return;
+
+  // Don't check pointers to volatile data. The behavior here is implementation-
+  // defined.
+  if (Ty->getPointeeType().isVolatileQualified())
+    return;
+
+  // We need to temorairly remove the assumption so we can insert the
+  // sanitizer check before it, else the check will be dropped by optimizations.
+  Assumption->removeFromParent();
+
+  {
+    SanitizerScope SanScope(this);
+
+    if (!OffsetValue)
+      OffsetValue = Builder.getInt1(0); // no offset.
+
+    llvm::Constant *StaticData[] = {EmitCheckSourceLocation(Loc),
+                                    EmitCheckSourceLocation(SecondaryLoc),
+                                    EmitCheckTypeDescriptor(Ty)};
+    llvm::Value *DynamicData[] = {EmitCheckValue(Ptr),
+                                  EmitCheckValue(Alignment),
+                                  EmitCheckValue(OffsetValue)};
+    EmitCheck({std::make_pair(TheCheck, SanitizerKind::Alignment)},
+              SanitizerHandler::AlignmentAssumption, StaticData, DynamicData);
+  }
+
+  // We are now in the (new, empty) "cont" basic block.
+  // Reintroduce the assumption.
+  Builder.Insert(Assumption);
+  // FIXME: Assumption still has it's original basic block as it's Parent.
+}
+
 llvm::DebugLoc CodeGenFunction::SourceLocToDebugLoc(SourceLocation Location) {
   if (CGDebugInfo *DI = getDebugInfo())
     return DI->SourceLocToDebugLoc(Location);
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index c8b300236f45..89cb850ab1b1 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -131,6 +131,7 @@ enum TypeEvaluationKind {
   SANITIZER_CHECK(ShiftOutOfBounds, shift_out_of_bounds, 0)                    \
   SANITIZER_CHECK(SubOverflow, sub_overflow, 0)                                \
   SANITIZER_CHECK(TypeMismatch, type_mismatch, 1)                              \
+  SANITIZER_CHECK(AlignmentAssumption, alignment_assumption, 0)                \
   SANITIZER_CHECK(VLABoundNotPositive, vla_bound_not_positive, 0)
 
 enum SanitizerHandler {
@@ -2633,12 +2634,6 @@ public:
   ComplexPairTy EmitComplexPrePostIncDec(const UnaryOperator *E, LValue LV,
                                          bool isInc, bool isPre);
 
-  void EmitAlignmentAssumption(llvm::Value *PtrValue, unsigned Alignment,
-                               llvm::Value *OffsetValue = nullptr) {
-    Builder.CreateAlignmentAssumption(CGM.getDataLayout(), PtrValue, Alignment,
-                                      OffsetValue);
-  }
-
   /// Converts Location to a DebugLoc, if debug information is enabled.
   llvm::DebugLoc SourceLocToDebugLoc(SourceLocation Location);
 
@@ -2802,11 +2797,27 @@ public:
   PeepholeProtection protectFromPeepholes(RValue rvalue);
   void unprotectFromPeepholes(PeepholeProtection protection);
 
-  void EmitAlignmentAssumption(llvm::Value *PtrValue, llvm::Value *Alignment,
-                               llvm::Value *OffsetValue = nullptr) {
-    Builder.CreateAlignmentAssumption(CGM.getDataLayout(), PtrValue, Alignment,
-                                      OffsetValue);
-  }
+  void EmitAlignmentAssumptionCheck(llvm::Value *Ptr, QualType Ty,
+                                    SourceLocation Loc,
+                                    SourceLocation AssumptionLoc,
+                                    llvm::Value *Alignment,
+                                    llvm::Value *OffsetValue,
+                                    llvm::Value *TheCheck,
+                                    llvm::Instruction *Assumption);
+
+  void EmitAlignmentAssumption(llvm::Value *PtrValue, QualType Ty,
+                               SourceLocation Loc, SourceLocation AssumptionLoc,
+                               llvm::Value *Alignment,
+                               llvm::Value *OffsetValue = nullptr);
+
+  void EmitAlignmentAssumption(llvm::Value *PtrValue, QualType Ty,
+                               SourceLocation Loc, SourceLocation AssumptionLoc,
+                               unsigned Alignment,
+                               llvm::Value *OffsetValue = nullptr);
+
+  void EmitAlignmentAssumption(llvm::Value *PtrValue, const Expr *E,
+                               SourceLocation AssumptionLoc, unsigned Alignment,
+                               llvm::Value *OffsetValue = nullptr);
 
   //===--------------------------------------------------------------------===//
   //                             Statement Emission