[MemCpyOpt] Fix metadata merging during call slot optimization

Call slot optimization currently merges the metadata between the
call and the load. However, we also need to merge in the metadata
of the store.

Part of the reason why we might have gotten away with this
previously is that usually the load and the store are the same
instruction (a memcpy), this can only happen if call slot
optimization occurs on an actual load/store pair.

This addresses the issue reported in
https://reviews.llvm.org/D115615#3251386.

Differential Revision: https://reviews.llvm.org/D117679

llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp

@@ -1022,6 +1022,8 @@ bool MemCpyOptPass::performCallSlotOptzn(Instruction *cpyLoad,
                          LLVMContext::MD_invariant_group,
                          LLVMContext::MD_access_group};
   combineMetadata(C, cpyLoad, KnownIDs, true);
+  if (cpyLoad != cpyStore)
+    combineMetadata(C, cpyStore, KnownIDs, true);
 
   ++NumCallSlot;
   return true;

llvm/test/Transforms/MemCpyOpt/callslot_noalias.ll

@@ -3,11 +3,12 @@
 
 declare void @func(i8* %dst)
 
-; TODO: The noalias metadata on the call is currently incorrect.
+; The noalias metadata from the call, the load and the store should be merged,
+; so that no metadata is left on the call.
 define i8 @test(i8* dereferenceable(1) noalias %dst) {
 ; CHECK-LABEL: @test(
 ; CHECK-NEXT:    [[TMP:%.*]] = alloca i8, align 1
-; CHECK-NEXT:    call void @func(i8* nocapture [[DST:%.*]]) #[[ATTR0:[0-9]+]], !noalias !0
+; CHECK-NEXT:    call void @func(i8* nocapture [[DST:%.*]]) #[[ATTR0:[0-9]+]]{{$}}
 ; CHECK-NEXT:    [[V2:%.*]] = load i8, i8* [[DST]], align 1, !alias.scope !0
 ; CHECK-NEXT:    ret i8 [[V2]]
 ;