diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
@@ -116,14 +116,21 @@
   // OpenCL doesn't allow declaring LDS in non-kernels, so in practice this
   // should only appear when IPO passes manages to move LDs defined in a kernel
   // into a single user function.
-
-  for (GlobalVariable &GV : M.globals()) {
-    // TODO: Region address
-    unsigned AS = GV.getAddressSpace();
-    if (AS != AMDGPUAS::LOCAL_ADDRESS && AS != AMDGPUAS::REGION_ADDRESS)
-      continue;
-
-    recursivelyVisitUsers(GV, FuncsToAlwaysInline);
+  //
+  // Now, since LDS uses within non-kernel functions are being handled in the
+  // pass - `LowerModuleLDS`, we *NO* need to *forcefully* inline non-kernel
+  // functions just because they use LDS. Do forceful inlining only when the
+  // pass - `LowerModuleLDS` is not enabled. It is enabled by default.
+
+  if (!AMDGPUTargetMachine::EnableLowerModuleLDS) {
+    for (GlobalVariable &GV : M.globals()) {
+      // TODO: Region address
+      unsigned AS = GV.getAddressSpace();
+      if (AS != AMDGPUAS::LOCAL_ADDRESS && AS != AMDGPUAS::REGION_ADDRESS)
+        continue;
+
+      recursivelyVisitUsers(GV, FuncsToAlwaysInline);
+    }
   }
 
   if (!AMDGPUTargetMachine::EnableFunctionCalls || StressCalls) {
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
@@ -35,6 +35,7 @@
   static bool EnableLateStructurizeCFG;
   static bool EnableFunctionCalls;
   static bool EnableFixedFunctionABI;
+  static bool EnableLowerModuleLDS;
 
   AMDGPUTargetMachine(const Target &T, const Triple &TT, StringRef CPU,
                       StringRef FS, TargetOptions Options,
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -193,10 +193,10 @@
     cl::desc("Enable workarounds for the StructurizeCFG pass"), cl::init(true),
     cl::Hidden);
 
-static cl::opt<bool>
-    EnableLowerModuleLDS("amdgpu-enable-lower-module-lds", cl::Hidden,
-                         cl::desc("Enable lower module lds pass"),
-                         cl::init(true));
+static cl::opt<bool, true> EnableLowerModuleLDS(
+    "amdgpu-enable-lower-module-lds", cl::desc("Enable lower module lds pass"),
+    cl::location(AMDGPUTargetMachine::EnableLowerModuleLDS), cl::init(true),
+    cl::Hidden);
 
 extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   // Register the target
@@ -393,6 +393,7 @@
 bool AMDGPUTargetMachine::EnableLateStructurizeCFG = false;
 bool AMDGPUTargetMachine::EnableFunctionCalls = false;
 bool AMDGPUTargetMachine::EnableFixedFunctionABI = false;
+bool AMDGPUTargetMachine::EnableLowerModuleLDS = false;
 
 AMDGPUTargetMachine::~AMDGPUTargetMachine() = default;
 
diff --git a/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address-codegen.ll b/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address-codegen.ll
--- a/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address-codegen.ll
+++ b/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address-codegen.ll
@@ -1,6 +1,6 @@
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-function-calls -amdgpu-stress-function-calls < %s | FileCheck -check-prefix=GCN %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls < %s | FileCheck -check-prefix=GCN %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-function-calls -amdgpu-stress-function-calls -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=GCN %s
 
 @lds0 = addrspace(3) global i32 undef, align 4
 
diff --git a/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address.ll b/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address.ll
--- a/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address.ll
+++ b/llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address.ll
@@ -1,7 +1,7 @@
-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s
-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s
-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s
-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -passes=amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -passes=amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
 
 target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"