Take alignment into account in isSafeToSpeculativelyExecute and isSafeToLoadUnconditionally.

Reviewed By: hfinkel, sanjoy, MatzeB

Differential Revision: http://reviews.llvm.org/D9791


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245223 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Analysis/ValueTracking.h

@@ -228,6 +228,16 @@ namespace llvm {
                                 const Instruction *CtxI = nullptr,
                                 const DominatorTree *DT = nullptr,
                                 const TargetLibraryInfo *TLI = nullptr);
+
+  /// Returns true if V is always a dereferenceable pointer with alignment
+  /// greater or equal than requested. If the context instruction is specified
+  /// performs context-sensitive analysis and returns true if the pointer is
+  /// dereferenceable at the specified instruction.
+  bool isDereferenceableAndAlignedPointer(const Value *V, unsigned Align,
+                                          const DataLayout &DL,
+                                          const Instruction *CtxI = nullptr,
+                                          const DominatorTree *DT = nullptr,
+                                          const TargetLibraryInfo *TLI = nullptr);
   
   /// isSafeToSpeculativelyExecute - Return true if the instruction does not
   /// have any effects besides calculating the result and does not have

lib/Analysis/MemDerefPrinter.cpp

@@ -22,7 +22,8 @@ using namespace llvm;
 
 namespace {
   struct MemDerefPrinter : public FunctionPass {
-    SmallVector<Value *, 4> Vec;
+    SmallVector<Value *, 4> Deref;
+    SmallPtrSet<Value *, 4> DerefAndAligned;
 
     static char ID; // Pass identification, replacement for typeid
     MemDerefPrinter() : FunctionPass(ID) {
@@ -34,7 +35,8 @@ namespace {
     bool runOnFunction(Function &F) override;
     void print(raw_ostream &OS, const Module * = nullptr) const override;
     void releaseMemory() override {
-      Vec.clear();
+      Deref.clear();
+      DerefAndAligned.clear();
     }
   };
 }
@@ -55,7 +57,9 @@ bool MemDerefPrinter::runOnFunction(Function &F) {
     if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
       Value *PO = LI->getPointerOperand();
       if (isDereferenceablePointer(PO, DL))
-        Vec.push_back(PO);
+        Deref.push_back(PO);
+      if (isDereferenceableAndAlignedPointer(PO, LI->getAlignment(), DL))
+        DerefAndAligned.insert(PO);
     }
   }
   return false;
@@ -63,8 +67,12 @@ bool MemDerefPrinter::runOnFunction(Function &F) {
 
 void MemDerefPrinter::print(raw_ostream &OS, const Module *M) const {
   OS << "The following are dereferenceable:\n";
-  for (auto &V: Vec) {
+  for (Value *V: Deref) {
     V->print(OS);
+    if (DerefAndAligned.count(V))
+      OS << "\t(aligned)";
+    else
+      OS << "\t(unaligned)";
     OS << "\n\n";
   }
 }

lib/Analysis/ValueTracking.cpp

@@ -2935,20 +2935,44 @@ static bool isDereferenceableFromAttribute(const Value *V, const DataLayout &DL,
   return isDereferenceableFromAttribute(V, Offset, Ty, DL, CtxI, DT, TLI);
 }
 
-/// Return true if Value is always a dereferenceable pointer.
+static bool isAligned(const Value *Base, APInt Offset, unsigned Align,
-///
+                      const DataLayout &DL) {
+  APInt BaseAlign(Offset.getBitWidth(), 0);
+  if (const AllocaInst *AI = dyn_cast<AllocaInst>(Base))
+    BaseAlign = AI->getAlignment();
+  else if (const GlobalVariable *GV = dyn_cast<GlobalVariable>(Base))
+    BaseAlign = GV->getAlignment();
+  else if (const Argument *A = dyn_cast<Argument>(Base))
+    BaseAlign = A->getParamAlignment();
+
+  if (!BaseAlign) {
+    Type *Ty = Base->getType()->getPointerElementType();
+    BaseAlign = DL.getABITypeAlignment(Ty);
+  }
+
+  APInt Alignment(Offset.getBitWidth(), Align);
+
+  assert(Alignment.isPowerOf2() && "must be a power of 2!");
+  return BaseAlign.uge(Alignment) && !(Offset & (Alignment-1));
+}
+
+static bool isAligned(const Value *Base, unsigned Align, const DataLayout &DL) {
+  APInt Offset(DL.getTypeStoreSizeInBits(Base->getType()), 0);
+  return isAligned(Base, Offset, Align, DL);
+}
+
 /// Test if V is always a pointer to allocated and suitably aligned memory for
 /// a simple load or store.
-static bool isDereferenceablePointer(const Value *V, const DataLayout &DL,
+static bool isDereferenceableAndAlignedPointer(
-                                     const Instruction *CtxI,
+    const Value *V, unsigned Align, const DataLayout &DL,
-                                     const DominatorTree *DT,
+    const Instruction *CtxI, const DominatorTree *DT,
-                                     const TargetLibraryInfo *TLI,
+    const TargetLibraryInfo *TLI, SmallPtrSetImpl<const Value *> &Visited) {
-                                     SmallPtrSetImpl<const Value *> &Visited) {
   // Note that it is not safe to speculate into a malloc'd region because
   // malloc may return null.
 
-  // These are obviously ok.
+  // These are obviously ok if aligned.
-  if (isa<AllocaInst>(V)) return true;
+  if (isa<AllocaInst>(V))
+    return isAligned(V, Align, DL);
 
   // It's not always safe to follow a bitcast, for example:
   //   bitcast i8* (alloca i8) to i32*
@@ -2963,21 +2987,22 @@ static bool isDereferenceablePointer(const Value *V, const DataLayout &DL,
     if (STy->isSized() && DTy->isSized() &&
         (DL.getTypeStoreSize(STy) >= DL.getTypeStoreSize(DTy)) &&
         (DL.getABITypeAlignment(STy) >= DL.getABITypeAlignment(DTy)))
-      return isDereferenceablePointer(BC->getOperand(0), DL, CtxI,
+      return isDereferenceableAndAlignedPointer(BC->getOperand(0), Align, DL,
-                                      DT, TLI, Visited);
+                                                CtxI, DT, TLI, Visited);
   }
 
   // Global variables which can't collapse to null are ok.
   if (const GlobalVariable *GV = dyn_cast<GlobalVariable>(V))
-    return !GV->hasExternalWeakLinkage();
+    if (!GV->hasExternalWeakLinkage())
+      return isAligned(V, Align, DL);
 
   // byval arguments are okay.
   if (const Argument *A = dyn_cast<Argument>(V))
     if (A->hasByValAttr())
-      return true;
+      return isAligned(V, Align, DL);
-    
+
   if (isDereferenceableFromAttribute(V, DL, CtxI, DT, TLI))
-    return true;
+    return isAligned(V, Align, DL);
 
   // For GEPs, determine if the indexing lands within the allocated object.
   if (const GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {
@@ -2985,61 +3010,79 @@ static bool isDereferenceablePointer(const Value *V, const DataLayout &DL,
     Type *Ty = VTy->getPointerElementType();
     const Value *Base = GEP->getPointerOperand();
 
-    // Conservatively require that the base pointer be fully dereferenceable.
+    // Conservatively require that the base pointer be fully dereferenceable
+    // and aligned.
     if (!Visited.insert(Base).second)
       return false;
-    if (!isDereferenceablePointer(Base, DL, CtxI,
+    if (!isDereferenceableAndAlignedPointer(Base, Align, DL, CtxI, DT, TLI,
-                                  DT, TLI, Visited))
+                                            Visited))
       return false;
-    
+
     APInt Offset(DL.getPointerTypeSizeInBits(VTy), 0);
     if (!GEP->accumulateConstantOffset(DL, Offset))
       return false;
-    
+
-    // Check if the load is within the bounds of the underlying object.
+    // Check if the load is within the bounds of the underlying object
+    // and offset is aligned.
     uint64_t LoadSize = DL.getTypeStoreSize(Ty);
     Type *BaseType = Base->getType()->getPointerElementType();
-    return (Offset + LoadSize).ule(DL.getTypeAllocSize(BaseType));
+    assert(isPowerOf2_32(Align) && "must be a power of 2!");
+    return (Offset + LoadSize).ule(DL.getTypeAllocSize(BaseType)) && 
+           !(Offset & APInt(Offset.getBitWidth(), Align-1));
   }
 
   // For gc.relocate, look through relocations
   if (const IntrinsicInst *I = dyn_cast<IntrinsicInst>(V))
     if (I->getIntrinsicID() == Intrinsic::experimental_gc_relocate) {
       GCRelocateOperands RelocateInst(I);
-      return isDereferenceablePointer(RelocateInst.getDerivedPtr(), DL, CtxI,
+      return isDereferenceableAndAlignedPointer(
-                                      DT, TLI, Visited);
+          RelocateInst.getDerivedPtr(), Align, DL, CtxI, DT, TLI, Visited);
     }
 
   if (const AddrSpaceCastInst *ASC = dyn_cast<AddrSpaceCastInst>(V))
-    return isDereferenceablePointer(ASC->getOperand(0), DL, CtxI,
+    return isDereferenceableAndAlignedPointer(ASC->getOperand(0), Align, DL,
-                                    DT, TLI, Visited);
+                                              CtxI, DT, TLI, Visited);
 
   // If we don't know, assume the worst.
   return false;
 }
 
-bool llvm::isDereferenceablePointer(const Value *V, const DataLayout &DL,
+bool llvm::isDereferenceableAndAlignedPointer(const Value *V, unsigned Align,
-                                    const Instruction *CtxI,
+                                              const DataLayout &DL,
-                                    const DominatorTree *DT,
+                                              const Instruction *CtxI,
-                                    const TargetLibraryInfo *TLI) {
+                                              const DominatorTree *DT,
+                                              const TargetLibraryInfo *TLI) {
   // When dereferenceability information is provided by a dereferenceable
   // attribute, we know exactly how many bytes are dereferenceable. If we can
   // determine the exact offset to the attributed variable, we can use that
   // information here.
   Type *VTy = V->getType();
   Type *Ty = VTy->getPointerElementType();
+
+  // Require ABI alignment for loads without alignment specification
+  if (Align == 0)
+    Align = DL.getABITypeAlignment(Ty);
+
   if (Ty->isSized()) {
     APInt Offset(DL.getTypeStoreSizeInBits(VTy), 0);
     const Value *BV = V->stripAndAccumulateInBoundsConstantOffsets(DL, Offset);
-    
+
     if (Offset.isNonNegative())
-      if (isDereferenceableFromAttribute(BV, Offset, Ty, DL,
+      if (isDereferenceableFromAttribute(BV, Offset, Ty, DL, CtxI, DT, TLI) &&
-                                         CtxI, DT, TLI))
+          isAligned(BV, Offset, Align, DL))
         return true;
   }
 
   SmallPtrSet<const Value *, 32> Visited;
-  return ::isDereferenceablePointer(V, DL, CtxI, DT, TLI, Visited);
+  return ::isDereferenceableAndAlignedPointer(V, Align, DL, CtxI, DT, TLI,
+                                              Visited);
+}
+
+bool llvm::isDereferenceablePointer(const Value *V, const DataLayout &DL,
+                                    const Instruction *CtxI,
+                                    const DominatorTree *DT,
+                                    const TargetLibraryInfo *TLI) {
+  return isDereferenceableAndAlignedPointer(V, 1, DL, CtxI, DT, TLI);
 }
 
 bool llvm::isSafeToSpeculativelyExecute(const Value *V,
@@ -3092,7 +3135,8 @@ bool llvm::isSafeToSpeculativelyExecute(const Value *V,
         LI->getParent()->getParent()->hasFnAttribute(Attribute::SanitizeThread))
       return false;
     const DataLayout &DL = LI->getModule()->getDataLayout();
-    return isDereferenceablePointer(LI->getPointerOperand(), DL, CtxI, DT, TLI);
+    return isDereferenceableAndAlignedPointer(
+        LI->getPointerOperand(), LI->getAlignment(), DL, CtxI, DT, TLI);
   }
   case Instruction::Call: {
     if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst)) {

test/Analysis/ValueTracking/memory-dereferenceable.ll

@@ -13,60 +13,104 @@ declare zeroext i1 @return_i1()
 %struct.A = type { [8 x i8], [5 x i8] }
 @globalstruct = external global %struct.A
 
-define void @test(i32 addrspace(1)* dereferenceable(8) %dparam) gc "statepoint-example" {
+@globalptr.align1 = external global i8, align 1
+@globalptr.align16 = external global i8, align 16
+
+define void @test(i32 addrspace(1)* dereferenceable(8) %dparam,
+                  i8 addrspace(1)* dereferenceable(32) align 1 %dparam.align1,
+                  i8 addrspace(1)* dereferenceable(32) align 16 %dparam.align16)
+    gc "statepoint-example" {
 ; CHECK: The following are dereferenceable:
-; CHECK: %globalptr
-; CHECK: %alloca
-; CHECK: %dparam
-; CHECK: %relocate
-; CHECK-NOT: %nparam
-; CHECK-NOT: %nd_load
-; CHECK: %d4_load
-; CHECK-NOT: %d2_load
-; CHECK-NOT: %d_or_null_load
-; CHECK: %d_or_null_non_null_load
-; CHECK: %within_allocation
-; CHECK-NOT: %outside_allocation
 entry:
+; CHECK: %globalptr{{.*}}(aligned)
     %globalptr = getelementptr inbounds [6 x i8], [6 x i8]* @globalstr, i32 0, i32 0
     %load1 = load i8, i8* %globalptr
+
+; CHECK: %alloca{{.*}}(aligned)
     %alloca = alloca i1
     %load2 = load i1, i1* %alloca
+
+; CHECK: %dparam{{.*}}(aligned)
     %load3 = load i32, i32 addrspace(1)* %dparam
+
+; CHECK: %relocate{{.*}}(aligned)
     %tok = tail call i32 (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 0, i1 ()* @return_i1, i32 0, i32 0, i32 0, i32 0, i32 addrspace(1)* %dparam)
     %relocate = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %tok, i32 7, i32 7)
     %load4 = load i32, i32 addrspace(1)* %relocate
+
+; CHECK-NOT: %nparam
     %nparam = getelementptr i32, i32 addrspace(1)* %dparam, i32 5
     %load5 = load i32, i32 addrspace(1)* %nparam
 
     ; Load from a non-dereferenceable load
+; CHECK-NOT: %nd_load
     %nd_load = load i32*, i32** @globali32ptr
     %load6 = load i32, i32* %nd_load
 
     ; Load from a dereferenceable load
+; CHECK: %d4_load{{.*}}(aligned)
     %d4_load = load i32*, i32** @globali32ptr, !dereferenceable !0
     %load7 = load i32, i32* %d4_load
 
     ; Load from an offset not covered by the dereferenceable portion
+; CHECK-NOT: %d2_load
     %d2_load = load i32*, i32** @globali32ptr, !dereferenceable !1
     %load8 = load i32, i32* %d2_load
 
     ; Load from a potentially null pointer with dereferenceable_or_null
+; CHECK-NOT: %d_or_null_load
     %d_or_null_load = load i32*, i32** @globali32ptr, !dereferenceable_or_null !0
     %load9 = load i32, i32* %d_or_null_load
 
     ; Load from a non-null pointer with dereferenceable_or_null
+; CHECK: %d_or_null_non_null_load{{.*}}(aligned)
     %d_or_null_non_null_load = load i32*, i32** @globali32ptr, !nonnull !2, !dereferenceable_or_null !0
     %load10 = load i32, i32* %d_or_null_non_null_load
 
     ; It's OK to overrun static array size as long as we stay within underlying object size
+; CHECK: %within_allocation{{.*}}(aligned)
     %within_allocation = getelementptr inbounds %struct.A, %struct.A* @globalstruct, i64 0, i32 0, i64 10
     %load11 = load i8, i8* %within_allocation
 
     ; GEP is outside the underlying object size
+; CHECK-NOT: %outside_allocation
     %outside_allocation = getelementptr inbounds %struct.A, %struct.A* @globalstruct, i64 0, i32 1, i64 10
     %load12 = load i8, i8* %outside_allocation
 
+    ; Loads from aligned globals
+; CHECK: @globalptr.align1{{.*}}(unaligned)
+; CHECK: @globalptr.align16{{.*}}(aligned)
+    %load13 = load i8, i8* @globalptr.align1, align 16
+    %load14 = load i8, i8* @globalptr.align16, align 16
+
+    ; Loads from aligned arguments
+; CHECK: %dparam.align1{{.*}}(unaligned)
+; CHECK: %dparam.align16{{.*}}(aligned)
+    %load15 = load i8, i8 addrspace(1)* %dparam.align1, align 16
+    %load16 = load i8, i8 addrspace(1)* %dparam.align16, align 16
+
+    ; Loads from aligned allocas
+; CHECK: %alloca.align1{{.*}}(unaligned)
+; CHECK: %alloca.align16{{.*}}(aligned)
+    %alloca.align1 = alloca i1, align 1
+    %alloca.align16 = alloca i1, align 16
+    %load17 = load i1, i1* %alloca.align1, align 16
+    %load18 = load i1, i1* %alloca.align16, align 16
+
+    ; Loads from GEPs
+; CHECK: %gep.align1.offset1{{.*}}(unaligned)
+; CHECK: %gep.align16.offset1{{.*}}(unaligned)
+; CHECK: %gep.align1.offset16{{.*}}(unaligned)
+; CHECK: %gep.align16.offset16{{.*}}(aligned)
+    %gep.align1.offset1 = getelementptr inbounds i8, i8 addrspace(1)* %dparam.align1, i32 1
+    %gep.align16.offset1 = getelementptr inbounds i8, i8 addrspace(1)* %dparam.align16, i32 1
+    %gep.align1.offset16 = getelementptr inbounds i8, i8 addrspace(1)* %dparam.align1, i32 16
+    %gep.align16.offset16 = getelementptr inbounds i8, i8 addrspace(1)* %dparam.align16, i32 16
+    %load19 = load i8, i8 addrspace(1)* %gep.align1.offset1, align 16
+    %load20 = load i8, i8 addrspace(1)* %gep.align16.offset1, align 16
+    %load21 = load i8, i8 addrspace(1)* %gep.align1.offset16, align 16
+    %load22 = load i8, i8 addrspace(1)* %gep.align16.offset16, align 16
+
     ret void
 }