Fix missing memcpy, memmove and memset tail calls

Summary:
If a wrapper around one of the mem* stdlib functions bitcasts the returned
pointer value before returning it (e.g. to a wchar_t*), LLVM does not emit a
tail call.

Add a check for this scenario so that we emit a tail call.

Reviewers: wmi, mkuper, ramred01, dmgreen

Reviewed By: wmi, dmgreen

Subscribers: hiraditya, sanwou01, javed.absar, lebedev.ri, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D59078

diff --git a/llvm/lib/CodeGen/Analysis.cpp b/llvm/lib/CodeGen/Analysis.cpp
index 4f24f07..023c236 100644 (file)
--- a/llvm/lib/CodeGen/Analysis.cpp
+++ b/llvm/lib/CodeGen/Analysis.cpp
@@ -611,6 +611,22 @@ bool llvm::attributesPermitTailCall(const Function *F, const Instruction *I,
   return CallerAttrs == CalleeAttrs;
 }
 
+/// Check whether B is a bitcast of a pointer type to another pointer type,
+/// which is equal to A.
+static bool isPointerBitcastEqualTo(const Value *A, const Value *B) {
+  assert(A && B && "Expected non-null inputs!");
+
+  auto *BitCastIn = dyn_cast<BitCastInst>(B);
+
+  if (!BitCastIn)
+    return false;
+
+  if (!A->getType()->isPointerTy() || !B->getType()->isPointerTy())
+    return false;
+
+  return A == BitCastIn->getOperand(0);
+}
+
 bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
                                            const Instruction *I,
                                            const ReturnInst *Ret,
@@ -643,7 +659,8 @@ bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
           TLI.getLibcallName(RTLIB::MEMMOVE) == StringRef("memmove")) ||
          (IID == Intrinsic::memset &&
           TLI.getLibcallName(RTLIB::MEMSET) == StringRef("memset"))) &&
-        RetVal == Call->getArgOperand(0))
+        (RetVal == Call->getArgOperand(0) ||
+         isPointerBitcastEqualTo(RetVal, Call->getArgOperand(0))))
       return true;
   }
 

diff --git a/llvm/test/CodeGen/AArch64/tailcall-bitcast-memcpy.ll b/llvm/test/CodeGen/AArch64/tailcall-bitcast-memcpy.ll
new file mode 100644 (file)
index 0000000..88a0749
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/tailcall-bitcast-memcpy.ll
@@ -0,0 +1,18 @@
+;RUN: llc %s -o - -verify-machineinstrs | FileCheck %s
+target triple = "aarch64-arm-none-eabi"
+
+;CHECK-LABEL: @wmemcpy
+;CHECK: lsl
+;CHECK-NOT: bl
+;CHECK-NOT: mov
+;CHECK-NOT: ldp
+;CHECK-NEXT: b memcpy
+define dso_local i32* @wmemcpy(i32* returned, i32* nocapture readonly, i64) local_unnamed_addr {
+  %4 = bitcast i32* %0 to i8*
+  %5 = bitcast i32* %1 to i8*
+  %6 = shl i64 %2, 2
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %4, i8* align 4 %5, i64 %6, i1 false)
+  ret i32* %0
+}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)