From ff1e98c72ae5f2aa805112925fd5c06049aa8e79 Mon Sep 17 00:00:00 2001 From: Chris Lattner Date: Tue, 8 Sep 2009 00:27:14 +0000 Subject: [PATCH] Fix PR4882, by making MemCpyOpt not dereference removed stores to get the context for the newly created operations. Patch by Jakub Staszak! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@81175 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Transforms/Scalar/MemCpyOptimizer.cpp | 23 ++++++++-------- test/Transforms/MemCpyOpt/crash.ll | 45 +++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+), 12 deletions(-) create mode 100644 test/Transforms/MemCpyOpt/crash.ll diff --git a/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/lib/Transforms/Scalar/MemCpyOptimizer.cpp index d6b1585d7ad..389b3b740c0 100644 --- a/lib/Transforms/Scalar/MemCpyOptimizer.cpp +++ b/lib/Transforms/Scalar/MemCpyOptimizer.cpp @@ -340,13 +340,15 @@ static RegisterPass X("memcpyopt", bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) { if (SI->isVolatile()) return false; + LLVMContext &Context = SI->getContext(); + // There are two cases that are interesting for this code to handle: memcpy // and memset. Right now we only handle memset. // Ensure that the value being stored is something that can be memset'able a // byte at a time like "0" or "-1" or any width, as well as things like // 0xA0A0A0A0 and 0.0. - Value *ByteVal = isBytewiseValue(SI->getOperand(0), SI->getContext()); + Value *ByteVal = isBytewiseValue(SI->getOperand(0), Context); if (!ByteVal) return false; @@ -387,8 +389,7 @@ bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) { if (NextStore->isVolatile()) break; // Check to see if this stored value is of the same byte-splattable value. - if (ByteVal != isBytewiseValue(NextStore->getOperand(0), - NextStore->getContext())) + if (ByteVal != isBytewiseValue(NextStore->getOperand(0), Context)) break; // Check to see if this store is to a constant offset from the start ptr. @@ -408,7 +409,6 @@ bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) { // store as well. We try to avoid this unless there is at least something // interesting as a small compile-time optimization. Ranges.addStore(0, SI); - Function *MemSetF = 0; @@ -432,16 +432,15 @@ bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) { BasicBlock::iterator InsertPt = BI; if (MemSetF == 0) { - const Type *Ty = Type::getInt64Ty(SI->getContext()); + const Type *Ty = Type::getInt64Ty(Context); MemSetF = Intrinsic::getDeclaration(M, Intrinsic::memset, &Ty, 1); - } + } // Get the starting pointer of the block. StartPtr = Range.StartPtr; // Cast the start ptr to be i8* as memset requires. - const Type *i8Ptr = - PointerType::getUnqual(Type::getInt8Ty(SI->getContext())); + const Type *i8Ptr = PointerType::getUnqual(Type::getInt8Ty(Context)); if (StartPtr->getType() != i8Ptr) StartPtr = new BitCastInst(StartPtr, i8Ptr, StartPtr->getName(), InsertPt); @@ -449,10 +448,9 @@ bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) { Value *Ops[] = { StartPtr, ByteVal, // Start, value // size - ConstantInt::get(Type::getInt64Ty(SI->getContext()), - Range.End-Range.Start), + ConstantInt::get(Type::getInt64Ty(Context), Range.End-Range.Start), // align - ConstantInt::get(Type::getInt32Ty(SI->getContext()), Range.Alignment) + ConstantInt::get(Type::getInt32Ty(Context), Range.Alignment) }; Value *C = CallInst::Create(MemSetF, Ops, Ops+4, "", InsertPt); DEBUG(errs() << "Replace stores:\n"; @@ -464,7 +462,8 @@ bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) { BBI = BI; // Zap all the stores. - for (SmallVector::const_iterator SI = Range.TheStores.begin(), + for (SmallVector::const_iterator + SI = Range.TheStores.begin(), SE = Range.TheStores.end(); SI != SE; ++SI) (*SI)->eraseFromParent(); ++NumMemSetInfer; diff --git a/test/Transforms/MemCpyOpt/crash.ll b/test/Transforms/MemCpyOpt/crash.ll new file mode 100644 index 00000000000..ccdfa53b6d7 --- /dev/null +++ b/test/Transforms/MemCpyOpt/crash.ll @@ -0,0 +1,45 @@ +; RUN: opt %s -memcpyopt -disable-output +; PR4882 + +target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64" +target triple = "armv7-eabi" + +%struct.qw = type { [4 x float] } +%struct.bar = type { %struct.qw, %struct.qw, %struct.qw, %struct.qw, %struct.qw, float, float} + +define arm_aapcs_vfpcc void @test1(%struct.bar* %this) { +entry: + %0 = getelementptr inbounds %struct.bar* %this, i32 0, i32 0, i32 0, i32 0 + store float 0.000000e+00, float* %0, align 4 + %1 = getelementptr inbounds %struct.bar* %this, i32 0, i32 0, i32 0, i32 1 + store float 0.000000e+00, float* %1, align 4 + %2 = getelementptr inbounds %struct.bar* %this, i32 0, i32 0, i32 0, i32 2 + store float 0.000000e+00, float* %2, align 4 + %3 = getelementptr inbounds %struct.bar* %this, i32 0, i32 0, i32 0, i32 3 + store float 0.000000e+00, float* %3, align 4 + %4 = getelementptr inbounds %struct.bar* %this, i32 0, i32 1, i32 0, i32 0 + store float 0.000000e+00, float* %4, align 4 + %5 = getelementptr inbounds %struct.bar* %this, i32 0, i32 1, i32 0, i32 1 + store float 0.000000e+00, float* %5, align 4 + %6 = getelementptr inbounds %struct.bar* %this, i32 0, i32 1, i32 0, i32 2 + store float 0.000000e+00, float* %6, align 4 + %7 = getelementptr inbounds %struct.bar* %this, i32 0, i32 1, i32 0, i32 3 + store float 0.000000e+00, float* %7, align 4 + %8 = getelementptr inbounds %struct.bar* %this, i32 0, i32 3, i32 0, i32 1 + store float 0.000000e+00, float* %8, align 4 + %9 = getelementptr inbounds %struct.bar* %this, i32 0, i32 3, i32 0, i32 2 + store float 0.000000e+00, float* %9, align 4 + %10 = getelementptr inbounds %struct.bar* %this, i32 0, i32 3, i32 0, i32 3 + store float 0.000000e+00, float* %10, align 4 + %11 = getelementptr inbounds %struct.bar* %this, i32 0, i32 4, i32 0, i32 0 + store float 0.000000e+00, float* %11, align 4 + %12 = getelementptr inbounds %struct.bar* %this, i32 0, i32 4, i32 0, i32 1 + store float 0.000000e+00, float* %12, align 4 + %13 = getelementptr inbounds %struct.bar* %this, i32 0, i32 4, i32 0, i32 2 + store float 0.000000e+00, float* %13, align 4 + %14 = getelementptr inbounds %struct.bar* %this, i32 0, i32 4, i32 0, i32 3 + store float 0.000000e+00, float* %14, align 4 + %15 = getelementptr inbounds %struct.bar* %this, i32 0, i32 5 + store float 0.000000e+00, float* %15, align 4 + unreachable +} -- 2.11.0