diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -611,7 +611,7 @@
 
   static GlobalVariable *
   chooseBestVariableForModuleStrategy(const DataLayout &DL,
-                                      VariableFunctionMap &LDSVars) {
+                                      const VariableFunctionMap &LDSVars) {
     // Find the global variable with the most indirect uses from kernels
 
     struct CandidateTy {
@@ -755,7 +755,7 @@
 
   static void partitionVariablesIntoIndirectStrategies(
       Module &M, LDSUsesInfoTy const &LDSUsesInfo,
-      VariableFunctionMap &LDSToKernelsThatNeedToAccessItIndirectly,
+      const VariableFunctionMap &LDSToKernelsThatNeedToAccessItIndirectly,
       DenseSet<GlobalVariable *> &ModuleScopeVariables,
       DenseSet<GlobalVariable *> &TableLookupVariables,
       DenseSet<GlobalVariable *> &KernelAccessVariables,
@@ -770,7 +770,7 @@
     DenseSet<Function *> const EmptySet;
     DenseSet<Function *> const &HybridModuleRootKernels =
         HybridModuleRoot
-            ? LDSToKernelsThatNeedToAccessItIndirectly[HybridModuleRoot]
+            ? LDSToKernelsThatNeedToAccessItIndirectly.at(HybridModuleRoot)
             : EmptySet;
 
     for (auto &K : LDSToKernelsThatNeedToAccessItIndirectly) {
@@ -910,6 +910,8 @@
 
     // Create a struct for each kernel for the non-module-scope variables.
 
+    IRBuilder<> Builder(M.getContext());
+
     DenseMap<Function *, LDSVariableReplacement> KernelToReplacement;
     for (Function &Func : M.functions()) {
       if (Func.isDeclaration() || !isKernelLDS(&Func))
@@ -962,6 +964,9 @@
       auto Replacement =
           createLDSVariableReplacement(M, VarName, KernelUsedVariables);
 
+      // In case all uses are from called functions
+      markUsedByKernel(Builder, &Func, Replacement.SGV);
+
       // remove preserves existing codegen
       removeLocalVarsFromUsedLists(M, KernelUsedVariables);
       KernelToReplacement[&Func] = Replacement;
@@ -1155,8 +1160,6 @@
       DenseSet<GlobalVariable *> Vec;
       Vec.insert(GV);
 
-      // TODO: Looks like a latent bug, Replacement may not be marked
-      // UsedByKernel here
       replaceLDSVariablesWithStruct(M, Vec, Replacement, [](Use &U) {
         return isa<Instruction>(U.getUser());
       });
@@ -1171,11 +1174,6 @@
       LLVMContext &Ctx = M.getContext();
       IRBuilder<> Builder(Ctx);
 
-      for (size_t i = 0; i < OrderedKernels.size(); i++) {
-        markUsedByKernel(Builder, OrderedKernels[i],
-                         KernelToReplacement[OrderedKernels[i]].SGV);
-      }
-
       // The order must be consistent between lookup table and accesses to
       // lookup table
       std::vector<GlobalVariable *> TableLookupVariablesOrdered(
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
@@ -0,0 +1,80 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds --amdgpu-lower-module-lds-strategy=hybrid < %s | FileCheck %s
+
+@A = external addrspace(3) global [8 x ptr]
+@B = external addrspace(3) global [0 x i32]
+
+define amdgpu_kernel void @kernel_0() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_0() !llvm.amdgcn.lds.kernel.id !1 {
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.kernel_0.lds) ]
+; CHECK-NEXT:    call void @call_store_A()
+; CHECK-NEXT:    ret void
+;
+  call void @call_store_A()
+  ret void
+}
+
+define amdgpu_kernel void @kernel_1() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_1() !llvm.amdgcn.lds.kernel.id !2 {
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel_1.dynlds) ]
+; CHECK-NEXT:    [[PTR:%.*]] = call ptr @get_B_ptr()
+; CHECK-NEXT:    ret void
+;
+  %ptr = call ptr @get_B_ptr()
+  ret void
+}
+
+define amdgpu_kernel void @kernel_2() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_2() !llvm.amdgcn.lds.kernel.id !3 {
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.kernel_2.lds) ]
+; CHECK-NEXT:    call void @store_A()
+; CHECK-NEXT:    ret void
+;
+  call void @store_A()
+  ret void
+}
+
+define amdgpu_kernel void @kernel_3() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_3() !llvm.amdgcn.lds.kernel.id !4 {
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel_3.dynlds) ]
+; CHECK-NEXT:    [[PTR:%.*]] = call ptr @get_B_ptr()
+; CHECK-NEXT:    ret void
+;
+  %ptr = call ptr @get_B_ptr()
+  ret void
+}
+
+define private void @call_store_A() {
+; CHECK-LABEL: define private void @call_store_A() {
+; CHECK-NEXT:    call void @store_A()
+; CHECK-NEXT:    ret void
+;
+  call void @store_A()
+  ret void
+}
+
+define private void @store_A() {
+; CHECK-LABEL: define private void @store_A() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[A:%.*]] = getelementptr inbounds [4 x [1 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(4) [[A]], align 4
+; CHECK-NEXT:    [[A1:%.*]] = inttoptr i32 [[TMP2]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP3:%.*]] = addrspacecast ptr addrspace(3) [[A1]] to ptr
+; CHECK-NEXT:    store ptr [[TMP3]], ptr null, align 8
+; CHECK-NEXT:    ret void
+;
+  store ptr addrspacecast (ptr addrspace(3) @A to ptr), ptr null
+  ret void
+}
+
+define private ptr @get_B_ptr() {
+; CHECK-LABEL: define private ptr @get_B_ptr() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds [4 x i32], ptr addrspace(4) @llvm.amdgcn.dynlds.offset.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(4) [[B]], align 4
+; CHECK-NEXT:    [[B1:%.*]] = inttoptr i32 [[TMP2]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP3:%.*]] = addrspacecast ptr addrspace(3) [[B1]] to ptr
+; CHECK-NEXT:    ret ptr [[TMP3]]
+;
+  ret ptr addrspacecast (ptr addrspace(3) @B to ptr)
+}