Index: llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -478,7 +478,7 @@
       Args.insert(Ptr);
 
   // Instruction to lift before P.
-  SmallVector<Instruction*, 8> ToLift;
+  SmallVector<Instruction *, 8> ToLift{SI};
 
   // Memory locations of lifted instructions.
   SmallVector<MemoryLocation, 8> MemLocs{StoreLoc};
@@ -544,10 +544,20 @@
       }
   }
 
-  // We made it, we need to lift
+  // We made it, we need to lift.
+  MemoryUseOrDef *MemInsertPoint =
+      MSSAU ? MSSAU->getMemorySSA()->getMemoryAccess(P) : nullptr;
   for (auto *I : llvm::reverse(ToLift)) {
     LLVM_DEBUG(dbgs() << "Lifting " << *I << " before " << *P << "\n");
     I->moveBefore(P);
+    if (MSSAU) {
+      if (MemoryUseOrDef *MA = MSSAU->getMemorySSA()->getMemoryAccess(I)) {
+        if (MemInsertPoint)
+          MSSAU->moveBefore(MA, MemInsertPoint);
+        else
+          MemInsertPoint = MA;
+      }
+    }
   }
 
   return true;
@@ -631,9 +641,8 @@
                             << *M << "\n");
 
           if (MSSAU) {
-            assert(isa<MemoryDef>(MSSAU->getMemorySSA()->getMemoryAccess(P)));
             auto *LastDef =
-                cast<MemoryDef>(MSSAU->getMemorySSA()->getMemoryAccess(P));
+                cast<MemoryDef>(MSSAU->getMemorySSA()->getMemoryAccess(SI));
             auto *NewAccess =
                 MSSAU->createMemoryAccessAfter(M, LastDef, LastDef);
             MSSAU->insertDef(cast<MemoryDef>(NewAccess), /*RenameUses=*/true);
Index: llvm/test/Transforms/MemCpyOpt/preserve-memssa.ll
===================================================================
--- llvm/test/Transforms/MemCpyOpt/preserve-memssa.ll
+++ llvm/test/Transforms/MemCpyOpt/preserve-memssa.ll
@@ -148,6 +148,21 @@
   ret void
 }
 
+define void @test8(%t* noalias %src, %t* %dst) {
+; CHECK-LABEL: @test8(
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast %t* [[SRC:%.*]] to i8*
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast %t* [[DST:%.*]] to i8*
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast %t* [[SRC]] to i8*
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 [[TMP2]], i8* align 1 [[TMP3]], i64 8224, i1 false)
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 1 [[TMP1]], i8 0, i64 8224, i1 false)
+; CHECK-NEXT:    ret void
+;
+  %1 = load %t, %t* %src
+  store %t zeroinitializer, %t* %src
+  store %t %1, %t* %dst
+  ret void
+}
+
 declare void @clobber()
 
 ; Function Attrs: argmemonly nounwind willreturn