Index: include/llvm/CodeGen/TargetPassConfig.h
===================================================================
--- include/llvm/CodeGen/TargetPassConfig.h
+++ include/llvm/CodeGen/TargetPassConfig.h
@@ -16,8 +16,11 @@
 
 #include "llvm/Pass.h"
 #include "llvm/Support/CodeGen.h"
+#include "llvm/Support/CommandLine.h"
 #include <string>
 
+extern llvm::cl::opt<bool> UseIPRA;
+
 namespace llvm {
 
 class PassConfigImpl;
Index: include/llvm/Target/TargetFrameLowering.h
===================================================================
--- include/llvm/Target/TargetFrameLowering.h
+++ include/llvm/Target/TargetFrameLowering.h
@@ -331,6 +331,20 @@
   virtual bool canUseAsEpilogue(const MachineBasicBlock &MBB) const {
     return true;
   }
+
+  /// Check if given function is safe for not having callee saved registers.
+  /// This is used when interprocedural register allocation is enabled.
+  static bool isSafeForNoCSROpt(const Function *F) {
+    if (!F->hasLocalLinkage() || F->hasAddressTaken() ||
+        !F->hasFnAttribute(Attribute::NoRecurse))
+      return false;
+    // Function should not be optimized as tail call.
+    for (const User *U : F->users())
+      if (auto CS = ImmutableCallSite(U))
+        if (CS.isTailCall())
+          return false;
+    return true;
+  }
 };
 
 } // End llvm namespace
Index: lib/CodeGen/RegUsageInfoCollector.cpp
===================================================================
--- lib/CodeGen/RegUsageInfoCollector.cpp
+++ lib/CodeGen/RegUsageInfoCollector.cpp
@@ -17,6 +17,7 @@
 ///
 //===----------------------------------------------------------------------===//
 
+#include "llvm/ADT/Statistic.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
@@ -26,11 +27,15 @@
 #include "llvm/CodeGen/RegisterUsageInfo.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/Target/TargetFrameLowering.h"
 
 using namespace llvm;
 
 #define DEBUG_TYPE "ip-regalloc"
 
+STATISTIC(NumCSROpt,
+          "Number of functions optimized for callee saved registers");
+
 namespace llvm {
 void initializeRegUsageInfoCollectorPass(PassRegistry &);
 }
@@ -101,6 +106,8 @@
   unsigned RegMaskSize = (TRI->getNumRegs() + 31) / 32;
   RegMask.resize(RegMaskSize, 0xFFFFFFFF);
 
+  const Function *F = MF.getFunction();
+
   PhysicalRegisterUsageInfo *PRUI = &getAnalysis<PhysicalRegisterUsageInfo>();
 
   PRUI->setTargetMachine(&TM);
@@ -111,11 +118,17 @@
     if (MRI->isPhysRegModified(PReg, true))
       markRegClobbered(TRI, &RegMask[0], PReg);
 
-  const uint32_t *CallPreservedMask =
-      TRI->getCallPreservedMask(MF, MF.getFunction()->getCallingConv());
-  // Set callee saved register as preserved.
-  for (unsigned i = 0; i < RegMaskSize; ++i)
-    RegMask[i] = RegMask[i] | CallPreservedMask[i];
+  if (!TargetFrameLowering::isSafeForNoCSROpt(F)) {
+    const uint32_t *CallPreservedMask =
+        TRI->getCallPreservedMask(MF, F->getCallingConv());
+    // Set callee saved register as preserved.
+    for (unsigned i = 0; i < RegMaskSize; ++i)
+      RegMask[i] = RegMask[i] | CallPreservedMask[i];
+  } else {
+    ++NumCSROpt;
+    DEBUG(dbgs() << MF.getName()
+                 << " function optimized for not having CSR.\n");
+  }
 
   for (unsigned PReg = 1, PRegE = TRI->getNumRegs(); PReg < PRegE; ++PReg)
     if (MachineOperand::clobbersPhysReg(&(RegMask[0]), PReg))
@@ -123,7 +136,7 @@
 
   DEBUG(dbgs() << " \n----------------------------------------\n");
 
-  PRUI->storeUpdateRegUsageInfo(MF.getFunction(), std::move(RegMask));
+  PRUI->storeUpdateRegUsageInfo(F, std::move(RegMask));
 
   return false;
 }
Index: lib/CodeGen/TargetFrameLoweringImpl.cpp
===================================================================
--- lib/CodeGen/TargetFrameLoweringImpl.cpp
+++ lib/CodeGen/TargetFrameLoweringImpl.cpp
@@ -12,13 +12,14 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/BitVector.h"
-#include "llvm/Target/TargetFrameLowering.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/IR/CallingConv.h"
 #include "llvm/IR/Function.h"
+#include "llvm/Target/TargetFrameLowering.h"
 #include "llvm/Target/TargetRegisterInfo.h"
 #include "llvm/Target/TargetSubtargetInfo.h"
 #include <cstdlib>
@@ -59,15 +60,21 @@
 void TargetFrameLowering::determineCalleeSaves(MachineFunction &MF,
                                                BitVector &SavedRegs,
                                                RegScavenger *RS) const {
-  // Get the callee saved register list...
   const TargetRegisterInfo &TRI = *MF.getSubtarget().getRegisterInfo();
-  const MCPhysReg *CSRegs = TRI.getCalleeSavedRegs(&MF);
 
   // Resize before the early returns. Some backends expect that
   // SavedRegs.size() == TRI.getNumRegs() after this call even if there are no
   // saved registers.
   SavedRegs.resize(TRI.getNumRegs());
 
+  // When interprocedural register allocation is enabled caller saved registers
+  // are preferred over callee saved registers.
+  if (UseIPRA && isSafeForNoCSROpt(MF.getFunction()))
+    return;
+
+  // Get the callee saved register list...
+  const MCPhysReg *CSRegs = TRI.getCalleeSavedRegs(&MF);
+
   // Early exit if there are no callee saved registers.
   if (!CSRegs || CSRegs[0] == 0)
     return;
Index: lib/CodeGen/TargetPassConfig.cpp
===================================================================
--- lib/CodeGen/TargetPassConfig.cpp
+++ lib/CodeGen/TargetPassConfig.cpp
@@ -28,7 +28,6 @@
 #include "llvm/IR/LegacyPassManager.h"
 #include "llvm/IR/Verifier.h"
 #include "llvm/MC/MCAsmInfo.h"
-#include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/raw_ostream.h"
Index: test/CodeGen/X86/ipra-local-linkage.ll
===================================================================
--- /dev/null
+++ test/CodeGen/X86/ipra-local-linkage.ll
@@ -0,0 +1,30 @@
+; RUN: llc < %s | FileCheck %s -check-prefix=NOIPRA
+; RUN: llc -enable-ipra < %s | FileCheck %s
+
+target triple = "x86_64--"
+
+define internal void @foo() norecurse {
+; When IPRA is not enabled R15 will be saved by foo as it is callee saved reg.
+; NOIPRA-LABEL: foo:
+; NOIPRA: pushq	%r15
+; When IPRA is enabled none register should be saved as foo() is local function
+; so we optimize it to save no registers.
+; CHECK-LABEL: foo:
+; CHECK-NOT: pushq %r15
+  call void asm sideeffect "movl	%r14d, %r15d", "~{r15}"()
+  ret void
+}
+
+define void @bar(i32 %X) {
+  call void asm sideeffect "movl  %r12d, $0", "{r15}~{r12}"(i32 %X)
+  ; As R15 is clobbered by foo() when IPRA is enabled value of R15 should be
+  ; saved if register containing orignal value is also getting clobbered
+  ; and reloaded after foo(), here original value is loaded back into R15D after
+  ; call to foo.
+  call void @foo()
+  ; CHECK-LABEL: bar:
+  ; CHECK: callq foo
+  ; CHECK-NEXT: movl  %eax, %r15d
+  call void asm sideeffect "movl  $0, %r12d", "{r15}~{r12}"(i32 %X)
+  ret void
+}