[InstCombine] Make strlen optimization more resilient to different gep types. (#153623)

This makes the optimization in optimizeStringLength for strlen(gep
@glob, %x) -> sub endof@glob, %x a little more resilient, and maybe a
bit more correct for geps with non-array types.

1 files changed, 11 insertions, 6 deletions

diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
index cc4eb2d..2d6a748 100644
--- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -20,6 +20,7 @@
 #include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/Utils/Local.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/AttributeMask.h"
 #include "llvm/IR/DataLayout.h"
@@ -977,8 +978,14 @@ Value *LibCallSimplifier::optimizeStringLength(CallInst *CI, IRBuilderBase &B,
   // it's not very useful because calling strlen for a pointer of other types is
   // very uncommon.
   if (GEPOperator *GEP = dyn_cast<GEPOperator>(Src)) {
-    // TODO: Handle subobjects.
-    if (!isGEPBasedOnPointerToString(GEP, CharSize))
+    unsigned BW = DL.getIndexTypeSizeInBits(GEP->getType());
+    SmallMapVector<Value *, APInt, 4> VarOffsets;
+    APInt ConstOffset(BW, 0);
+    assert(CharSize % 8 == 0 && "Expected a multiple of 8 sized CharSize");
+    // Check the gep is a single variable offset.
+    if (!GEP->collectOffset(DL, BW, VarOffsets, ConstOffset) ||
+        VarOffsets.size() != 1 || ConstOffset != 0 ||
+        VarOffsets.begin()->second != CharSize / 8)
       return nullptr;
 
     ConstantDataArraySlice Slice;
@@ -1000,10 +1007,8 @@ Value *LibCallSimplifier::optimizeStringLength(CallInst *CI, IRBuilderBase &B,
           return nullptr;
       }
 
-      Value *Offset = GEP->getOperand(2);
+      Value *Offset = VarOffsets.begin()->first;
       KnownBits Known = computeKnownBits(Offset, DL, nullptr, CI, nullptr);
-      uint64_t ArrSize =
-             cast<ArrayType>(GEP->getSourceElementType())->getNumElements();
 
       // If Offset is not provably in the range [0, NullTermIdx], we can still
       // optimize if we can prove that the program has undefined behavior when
@@ -1011,7 +1016,7 @@ Value *LibCallSimplifier::optimizeStringLength(CallInst *CI, IRBuilderBase &B,
       // is a pointer to an object whose memory extent is NullTermIdx+1.
       if ((Known.isNonNegative() && Known.getMaxValue().ule(NullTermIdx)) ||
           (isa<GlobalVariable>(GEP->getOperand(0)) &&
-           NullTermIdx == ArrSize - 1)) {
+           NullTermIdx == Slice.Length - 1)) {
         Offset = B.CreateSExtOrTrunc(Offset, CI->getType());
         return B.CreateSub(ConstantInt::get(CI->getType(), NullTermIdx),
                            Offset);