diff --git a/llvm/include/llvm/ProfileData/SampleProf.h b/llvm/include/llvm/ProfileData/SampleProf.h
--- a/llvm/include/llvm/ProfileData/SampleProf.h
+++ b/llvm/include/llvm/ProfileData/SampleProf.h
@@ -15,6 +15,7 @@
 #define LLVM_PROFILEDATA_SAMPLEPROF_H
 
 #include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
@@ -96,6 +97,12 @@
   SPF_Binary = 0xff
 };
 
+enum SampleProfileLayout {
+  SPL_None = 0,
+  SPL_Nest = 0x1,
+  SPL_CS = 0x2,
+};
+
 static inline uint64_t SPMagic(SampleProfileFormat Format = SPF_Binary) {
   return uint64_t('S') << (64 - 8) | uint64_t('P') << (64 - 16) |
          uint64_t('R') << (64 - 24) | uint64_t('O') << (64 - 32) |
@@ -358,6 +365,22 @@
                       : sampleprof_error::success;
   }
 
+  /// Remove called function and return its count if it exists.
+  Optional<uint64_t> removeCalledTarget(StringRef F) {
+    Optional<uint64_t> Count;
+    auto I = CallTargets.find(F);
+    if (I != CallTargets.end()) {
+      Count = I->second;
+      CallTargets.erase(I);
+      if (*Count <= NumSamples)
+        NumSamples -= *Count;
+      else {
+        NumSamples = 0;
+      }
+    }
+    return Count;
+  }
+
   /// Return true if this sample record contains function calls.
   bool hasCalls() const { return !CallTargets.empty(); }
 
@@ -737,6 +760,19 @@
         FName, Num, Weight);
   }
 
+  void removeCalledTargetAndUpdateTotalSamples(uint32_t LineOffset,
+                                               uint32_t Discriminator,
+                                               StringRef FName) {
+    auto I = BodySamples.find(LineLocation(LineOffset, Discriminator));
+    if (I != BodySamples.end()) {
+      if (auto C = I->second.removeCalledTarget(FName)) {
+        TotalSamples -= *C;
+        if (!I->second.getSamples())
+          BodySamples.erase(I);
+      }
+    }
+  }
+
   sampleprof_error addBodySamplesForProbe(uint32_t Index, uint64_t Num,
                                           uint64_t Weight = 1) {
     SampleRecord S;
@@ -878,6 +914,8 @@
     return CallsiteSamples;
   }
 
+  CallsiteSampleMap &getCallsiteSamples() { return CallsiteSamples; }
+
   /// Return the maximum of sample counts in a function body including functions
   /// inlined in it.
   uint64_t getMaxCountInside() const {
@@ -1200,11 +1238,14 @@
 };
 
 // CSProfileConverter converts a full context-sensitive flat sample profile into
-// a nested context-sensitive sample profile.
+// a nested sample profile, or the other way around from a nested profile to a
+// CS flat profile.
 class CSProfileConverter {
 public:
-  CSProfileConverter(SampleProfileMap &Profiles);
-  void convertProfiles();
+  CSProfileConverter(SampleProfileMap &Profiles,
+                     std::list<SampleContextFrameVector> *Contexts = nullptr);
+  void convertToCSNestedProfiles();
+  void convertToCSFlatProfiles();
   struct FrameNode {
     FrameNode(StringRef FName = StringRef(),
               FunctionSamples *FSamples = nullptr,
@@ -1226,10 +1267,18 @@
 
 private:
   // Nest all children profiles into the profile of Node.
-  void convertProfiles(FrameNode &Node);
+  void convertToCSNestedProfiles(FrameNode &Node);
+  // Flatten moving all children profiles of `FProfile` out to `NewProfileMap`
+  void convertToCSFlatProfiles(FunctionSamples &FProfile,
+                               SampleProfileMap &NewProfileMap,
+                               SampleContextFrameVector &Context);
   FrameNode *getOrCreateContextPath(const SampleContext &Context);
 
   SampleProfileMap &ProfileMap;
+
+  // Underlying context table serves for sample profile writer when
+  // converting a nested profile to a CS profile.
+  std::list<SampleContextFrameVector> *Contexts;
   FrameNode RootFrame;
 };
 
diff --git a/llvm/lib/ProfileData/SampleProf.cpp b/llvm/lib/ProfileData/SampleProf.cpp
--- a/llvm/lib/ProfileData/SampleProf.cpp
+++ b/llvm/lib/ProfileData/SampleProf.cpp
@@ -24,6 +24,7 @@
 #include "llvm/Support/raw_ostream.h"
 #include <string>
 #include <system_error>
+#include <utility>
 
 using namespace llvm;
 using namespace sampleprof;
@@ -39,6 +40,12 @@
              "generate extra base profile for function with all its context "
              "profiles merged into it."));
 
+cl::opt<bool> PreserveContextAttributes(
+    "preserve-context-attributes", cl::init(true), cl::ZeroOrMore,
+    cl::desc("When generating nested context-sensitive profiles, always "
+             "preserve the attributes of each context."));
+
+
 namespace llvm {
 namespace sampleprof {
 bool FunctionSamples::ProfileIsProbeBased = false;
@@ -217,7 +224,7 @@
 
 unsigned FunctionSamples::getOffset(const DILocation *DIL) {
   return (DIL->getLine() - DIL->getScope()->getSubprogram()->getLine()) &
-      0xffff;
+         0xffff;
 }
 
 LineLocation FunctionSamples::getCallSiteIdentifier(const DILocation *DIL,
@@ -478,15 +485,9 @@
   return &AllChildFrames[Hash];
 }
 
-CSProfileConverter::CSProfileConverter(SampleProfileMap &Profiles)
-    : ProfileMap(Profiles) {
-  for (auto &FuncSample : Profiles) {
-    FunctionSamples *FSamples = &FuncSample.second;
-    auto *NewNode = getOrCreateContextPath(FSamples->getContext());
-    assert(!NewNode->FuncSamples && "New node cannot have sample profile");
-    NewNode->FuncSamples = FSamples;
-  }
-}
+CSProfileConverter::CSProfileConverter(
+    SampleProfileMap &Profiles, std::list<SampleContextFrameVector> *Contexts)
+    : ProfileMap(Profiles), Contexts(Contexts) {}
 
 CSProfileConverter::FrameNode *
 CSProfileConverter::getOrCreateContextPath(const SampleContext &Context) {
@@ -499,17 +500,22 @@
   return Node;
 }
 
-void CSProfileConverter::convertProfiles(CSProfileConverter::FrameNode &Node) {
+void CSProfileConverter::convertToCSNestedProfiles(
+    CSProfileConverter::FrameNode &Node) {
   // Process each child profile. Add each child profile to callsite profile map
   // of the current node `Node` if `Node` comes with a profile. Otherwise
   // promote the child profile to a standalone profile.
   auto *NodeProfile = Node.FuncSamples;
   for (auto &It : Node.AllChildFrames) {
     auto &ChildNode = It.second;
-    convertProfiles(ChildNode);
+    convertToCSNestedProfiles(ChildNode);
     auto *ChildProfile = ChildNode.FuncSamples;
     if (!ChildProfile)
       continue;
+
+    if (!PreserveContextAttributes)
+      ChildProfile->getContext().setAllAttributes(0);
+
     SampleContext OrigChildContext = ChildProfile->getContext();
     // Reset the child context to be contextless.
     ChildProfile->getContext().setName(OrigChildContext.getName());
@@ -518,6 +524,10 @@
       auto &SamplesMap = NodeProfile->functionSamplesAt(ChildNode.CallSiteLoc);
       SamplesMap.emplace(OrigChildContext.getName().str(), *ChildProfile);
       NodeProfile->addTotalSamples(ChildProfile->getTotalSamples());
+      // Remove the corresponding body sample for the callsite and update the total
+      // weight.
+      NodeProfile->removeCalledTargetAndUpdateTotalSamples(
+          ChildNode.CallSiteLoc.LineOffset, ChildNode.CallSiteLoc.Discriminator, OrigChildContext.getName());
     }
 
     // Separate child profile to be a standalone profile, if the current parent
@@ -545,4 +555,67 @@
   }
 }
 
-void CSProfileConverter::convertProfiles() { convertProfiles(RootFrame); }
+void CSProfileConverter::convertToCSNestedProfiles() {
+  for (auto &FuncSample : ProfileMap) {
+    FunctionSamples *FSamples = &FuncSample.second;
+    auto *NewNode = getOrCreateContextPath(FSamples->getContext());
+    assert(!NewNode->FuncSamples && "New node cannot have sample profile");
+    NewNode->FuncSamples = FSamples;
+  }
+  convertToCSNestedProfiles(RootFrame);
+}
+
+void CSProfileConverter::convertToCSFlatProfiles(
+    FunctionSamples &FProfile, SampleProfileMap &NewProfileMap,
+    SampleContextFrameVector &ParentContext) {
+  // Push current frame.
+  ParentContext.emplace_back(FProfile.getName(), LineLocation(0, 0));
+
+  // Recursively promote callee profiles to a standalone top-level profiles with
+  // a flattened context.
+  while (!FProfile.getCallsiteSamples().empty()) {
+    auto I = FProfile.getCallsiteSamples().begin();
+    ParentContext.back().Location = I->first;
+    for (auto &Callee : I->second) {
+      auto &CalleeProfile = Callee.second;
+      // Add body sample.
+      FProfile.addBodySamples(I->first.LineOffset, I->first.Discriminator,
+                              CalleeProfile.getEntrySamples());
+      // Add callsite sample.
+      FProfile.addCalledTargetSamples(
+          I->first.LineOffset, I->first.Discriminator, CalleeProfile.getName(),
+          CalleeProfile.getEntrySamples());
+      // Update total samples.
+      FProfile.addTotalSamples(CalleeProfile.getEntrySamples());
+      // Withdraw callee samples from total samples.
+      FProfile.setTotalSamples(FProfile.getTotalSamples() - CalleeProfile.getTotalSamples());
+      // Recursively convert callee profile.
+      convertToCSFlatProfiles(CalleeProfile, NewProfileMap, ParentContext);
+    }
+
+    // Remove callee profile
+    FProfile.getCallsiteSamples().erase(I);
+    ParentContext.back().Location = LineLocation(0, 0);
+  }
+
+  // Update head samples for callee profiles.
+  if (ParentContext.size() > 1)
+    FProfile.addHeadSamples(FProfile.getEntrySamples());
+
+  // Update current context.
+  Contexts->push_back(ParentContext);
+  SampleContext NewContext(Contexts->back());
+  FProfile.setContext(NewContext);
+  NewProfileMap.emplace(NewContext, FProfile);
+
+  // Pop current frame.
+  ParentContext.pop_back();
+}
+
+void CSProfileConverter::convertToCSFlatProfiles() {
+  SampleProfileMap NewProfileMap;
+  SampleContextFrameVector Context;
+  for (auto &FuncSample : ProfileMap)
+    convertToCSFlatProfiles(FuncSample.second, NewProfileMap, Context);
+  ProfileMap = std::move(NewProfileMap);
+}
diff --git a/llvm/test/Transforms/SampleProfile/csspgo-inline.ll b/llvm/test/Transforms/SampleProfile/csspgo-inline.ll
--- a/llvm/test/Transforms/SampleProfile/csspgo-inline.ll
+++ b/llvm/test/Transforms/SampleProfile/csspgo-inline.ll
@@ -10,7 +10,7 @@
 ; RUN: llvm-profdata merge --sample --extbinary --use-md5 %S/Inputs/profile-context-tracker.prof -o %t.md5
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.md5 -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-BASE
 
-; RUN: llvm-profdata merge --sample --text --gen-cs-nested-profile %S/Inputs/profile-context-tracker.prof -o %t.prof
+; RUN: llvm-profdata merge --sample --text --sample-profile-layout=nest %S/Inputs/profile-context-tracker.prof -o %t.prof
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-BASE
 
 ; With new FDO early inliner, callee entry count is used to drive inlining instead of callee total samples, so we get less inlining for given profile
diff --git a/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll b/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll
--- a/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll
+++ b/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll
@@ -3,7 +3,7 @@
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/csspgo-use-preinliner.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=0 -S 2>&1 | FileCheck %s --check-prefix=DEFAULT
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/csspgo-use-preinliner.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=1 -S 2>&1 | FileCheck %s --check-prefix=PREINLINE
 
-; RUN: llvm-profdata merge --sample --text --gen-cs-nested-profile -generate-merged-base-profiles=0 %S/Inputs/csspgo-use-preinliner.prof -o %t.prof
+; RUN: llvm-profdata merge --sample --text --sample-profile-layout=nest -generate-merged-base-profiles=0 %S/Inputs/csspgo-use-preinliner.prof -o %t.prof
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=0 -S 2>&1 | FileCheck %s --check-prefix=DEFAULT
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=1 -S 2>&1 | FileCheck %s --check-prefix=PREINLINE
 
diff --git a/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline-probe.proftext b/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline-probe.proftext
--- a/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline-probe.proftext
+++ b/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline-probe.proftext
@@ -2,7 +2,7 @@
  0: 6
  1: 6
  3: 287884
- 4: 287864 _Z3fibi:315608
+ 4: 287864 _Z3fibi:287864
  15: 23
  !CFGChecksum: 281479271677951
  !Attributes: 2
@@ -10,21 +10,21 @@
  0: 15
  1: 15
  3: 74946
- 4: 74941 _Z3fibi:82359
+ 4: 74941 _Z3fibi:74941
  10: 23324
- 11: 23327 _Z3fibi:25228
+ 11: 23327 _Z3fibi:23327
  15: 11
  !CFGChecksum: 281479271677951
   !Attributes: 2
 [external:12 @ main]:154:12
  2: 12
  3: 10 _Z5funcAi:7
- 3.1: 10 _Z5funcBi:11
+ 3.1: 10 _Z5funcBi:10
  !CFGChecksum: 563125815542069
 [main]:154:0
  2: 12
  3: 18 _Z5funcAi:11
- 3.1: 18 _Z5funcBi:19
+ 3.1: 18 _Z5funcBi:18
  !CFGChecksum: 563125815542069
 [external:10 @ _Z5funcBi]:120:10
  0: 10
@@ -36,13 +36,13 @@
  !CFGChecksum: 563022570642068
 [main:3.1 @ _Z5funcBi]:120:19
  0: 19
- 1: 19 _Z8funcLeafi:20
+ 1: 19 _Z8funcLeafi:19
  3: 12
  !CFGChecksum: 563022570642068
  !Attributes: 2
 [main:3 @ _Z5funcAi]:99:11
  0: 10
- 1: 10 _Z8funcLeafi:11
+ 1: 10 _Z8funcLeafi:10
  3: 24
  !CFGChecksum: 844530426352218
  !Attributes: 2
diff --git a/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext b/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext
--- a/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext
+++ b/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext
@@ -2,26 +2,26 @@
  0: 6
  1: 6
  3: 287884
- 4: 287864 _Z3fibi:315608
+ 4: 287864 _Z3fibi:287864
  15: 23
  !Attributes: 2
 [main:3.1 @ _Z5funcBi:1 @ _Z8funcLeafi]:500853:20
  0: 15
  1: 15
  3: 74946
- 4: 74941 _Z3fibi:82359
+ 4: 74941 _Z3fibi:74941
  10: 23324
- 11: 23327 _Z3fibi:25228
+ 11: 23327 _Z3fibi:23327
  15: 11
  !Attributes: 2
 [external:12 @ main]:154:12
  2: 12
  3: 10 _Z5funcAi:7
- 3.1: 10 _Z5funcBi:11
+ 3.1: 10 _Z5funcBi:10
 [main]:154:0
  2: 12
  3: 18 _Z5funcAi:11
- 3.1: 18 _Z5funcBi:19
+ 3.1: 18 _Z5funcBi:18
 [external:10 @ _Z5funcBi]:120:10
  0: 10
  1: 10
@@ -30,11 +30,11 @@
  1: 3
 [main:3.1 @ _Z5funcBi]:120:19
  0: 19
- 1: 19 _Z8funcLeafi:20
+ 1: 19 _Z8funcLeafi:19
  3: 12
  !Attributes: 2
 [main:3 @ _Z5funcAi]:99:11
  0: 10
- 1: 10 _Z8funcLeafi:11
+ 1: 10 _Z8funcLeafi:10
  3: 24
  !Attributes: 2
diff --git a/llvm/test/tools/llvm-profdata/cs-sample-flat-profile.test b/llvm/test/tools/llvm-profdata/cs-sample-flat-profile.test
new file mode 100644
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/cs-sample-flat-profile.test
@@ -0,0 +1,23 @@
+RUN: llvm-profdata merge --sample --text -output=%t.proftext %S/Inputs/sample-profile.proftext --sample-profile-layout=cs
+RUN: FileCheck %s < %t.proftext
+RUN: llvm-profdata merge --sample --text -output=%t2.proftext %t.proftext --sample-profile-layout=nest --preserve-context-attributes=0 -generate-merged-base-profiles=0
+RUN: diff %t2.proftext %S/Inputs/sample-profile.proftext
+
+
+; CHECK:      [main]:184019:0
+; CHECK-NEXT:  4: 534
+; CHECK-NEXT:  4.2: 534
+; CHECK-NEXT:  5: 1075
+; CHECK-NEXT:  5.1: 1075
+; CHECK-NEXT:  6: 2080
+; CHECK-NEXT:  7: 534
+; CHECK-NEXT:  9: 2064 _Z3bari:1471 _Z3fooi:631
+; CHECK-NEXT:  10: 3000 inline2:2000 inline1:1000
+; CHECK-NEXT: [_Z3bari]:20301:1437
+; CHECK-NEXT:  1: 1437
+; CHECK-NEXT: [_Z3fooi]:7711:610
+; CHECK-NEXT:  1: 610
+; CHECK-NEXT: [main:10 @ inline2]:2000:2000
+; CHECK-NEXT:  1: 2000
+; CHECK-NEXT: [main:10 @ inline1]:1000:1000
+; CHECK-NEXT:  1: 1000
diff --git a/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test b/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test
--- a/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test
+++ b/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test
@@ -1,46 +1,44 @@
-RUN: llvm-profdata merge --sample --text -output=%t.proftext %S/Inputs/cs-sample-preinline.proftext --gen-cs-nested-profile=1 -generate-merged-base-profiles=0
+RUN: llvm-profdata merge --sample --text -output=%t.proftext %S/Inputs/cs-sample-preinline.proftext --sample-profile-layout=nest -generate-merged-base-profiles=0
 RUN: FileCheck %s < %t.proftext --match-full-lines --strict-whitespace
-RUN: llvm-profdata merge --sample --text -output=%t.probe.proftext %S/Inputs/cs-sample-preinline-probe.proftext --gen-cs-nested-profile=1 -generate-merged-base-profiles=0
+RUN: llvm-profdata merge --sample --text -output=%t.probe.proftext %S/Inputs/cs-sample-preinline-probe.proftext --sample-profile-layout=nest -generate-merged-base-profiles=0
 RUN: FileCheck %s < %t.probe.proftext --match-full-lines --strict-whitespace -check-prefix=PROBE
-RUN: llvm-profdata merge --sample --extbinary -output=%t.profbin %S/Inputs/cs-sample-preinline.proftext --gen-cs-nested-profile=1 -generate-merged-base-profiles=0
+RUN: llvm-profdata merge --sample --extbinary -output=%t.profbin %S/Inputs/cs-sample-preinline.proftext --sample-profile-layout=nest -generate-merged-base-profiles=0
 RUN: llvm-profdata merge --sample --text -output=%t2.proftext %t.profbin
 RUN: FileCheck %s < %t2.proftext --match-full-lines --strict-whitespace
 RUN: llvm-profdata show --sample -show-sec-info-only %t.profbin | FileCheck %s -check-prefix=PREINLINE
-RUN: llvm-profdata merge --sample --text -output=%t3.proftext %S/Inputs/cs-sample-preinline.proftext --gen-cs-nested-profile=1 -generate-merged-base-profiles=1
+RUN: llvm-profdata merge --sample --text -output=%t3.proftext %S/Inputs/cs-sample-preinline.proftext --sample-profile-layout=nest -generate-merged-base-profiles=1
 RUN: FileCheck %s < %t3.proftext --match-full-lines --strict-whitespace -check-prefix=RECOUNT
-RUN: llvm-profdata merge --sample --extbinary -output=%t2.profbin %S/Inputs/cs-sample-preinline.proftext --gen-cs-nested-profile=1 -generate-merged-base-profiles=1
+RUN: llvm-profdata merge --sample --extbinary -output=%t3.profbin %S/Inputs/cs-sample-preinline.proftext --sample-profile-layout=nest -generate-merged-base-profiles=1
 RUN: llvm-profdata show -sample -detailed-summary %S/Inputs/cs-sample-preinline.proftext | FileCheck %s -check-prefix=SUMMARY
-RUN: llvm-profdata show -sample -detailed-summary %t2.profbin | FileCheck %s -check-prefix=SUMMARY
-RUN: llvm-profdata show -sample -detailed-summary %t3.proftext | FileCheck %s -check-prefix=SUMMARY
+RUN: llvm-profdata show -sample -detailed-summary %t3.profbin | FileCheck %s -check-prefix=SUMMARY-NEST
+RUN: llvm-profdata show -sample -detailed-summary %t3.proftext | FileCheck %s -check-prefix=SUMMARY-NEST
 
 
-; CHECK:main:1968679:12
+; CHECK:main:1968621:12
 ; CHECK-NEXT: 2: 24
-; CHECK-NEXT: 3: 28 _Z5funcAi:18
-; CHECK-NEXT: 3.1: 28 _Z5funcBi:30
-; CHECK-NEXT: 3: _Z5funcAi:1467398
+; CHECK-NEXT: 3: 17 _Z5funcAi:7
+; CHECK-NEXT: 3.1: 10 _Z5funcBi:10
+; CHECK-NEXT: 3: _Z5funcAi:1467388
 ; CHECK-NEXT:  0: 10
-; CHECK-NEXT:  1: 10 _Z8funcLeafi:11
 ; CHECK-NEXT:  3: 24
 ; CHECK-NEXT:  1: _Z8funcLeafi:1467299
 ; CHECK-NEXT:   0: 6
 ; CHECK-NEXT:   1: 6
 ; CHECK-NEXT:   3: 287884
-; CHECK-NEXT:   4: 287864 _Z3fibi:315608
+; CHECK-NEXT:   4: 287864 _Z3fibi:287864
 ; CHECK-NEXT:   15: 23
 ; CHECK-NEXT:   !Attributes: 2
 ; CHECK-NEXT:  !Attributes: 2
-; CHECK-NEXT: 3.1: _Z5funcBi:500973
+; CHECK-NEXT: 3.1: _Z5funcBi:500954
 ; CHECK-NEXT:  0: 19
-; CHECK-NEXT:  1: 19 _Z8funcLeafi:20
 ; CHECK-NEXT:  3: 12
 ; CHECK-NEXT:  1: _Z8funcLeafi:500853
 ; CHECK-NEXT:   0: 15
 ; CHECK-NEXT:   1: 15
 ; CHECK-NEXT:   3: 74946
-; CHECK-NEXT:   4: 74941 _Z3fibi:82359
+; CHECK-NEXT:   4: 74941 _Z3fibi:74941
 ; CHECK-NEXT:   10: 23324
-; CHECK-NEXT:   11: 23327 _Z3fibi:25228
+; CHECK-NEXT:   11: 23327 _Z3fibi:23327
 ; CHECK-NEXT:   15: 11
 ; CHECK-NEXT:   !Attributes: 2
 ; CHECK-NEXT:  !Attributes: 2
@@ -49,34 +47,31 @@
 ; CHECK-NEXT: 1: 13
 
 
-
-; RECOUNT:main:1968679:12
+; RECOUNT:main:1968621:12
 ; RECOUNT-NEXT: 2: 24
-; RECOUNT-NEXT: 3: 28 _Z5funcAi:18
-; RECOUNT-NEXT: 3.1: 28 _Z5funcBi:30
-; RECOUNT-NEXT: 3: _Z5funcAi:1467398
+; RECOUNT-NEXT: 3: 17 _Z5funcAi:7
+; RECOUNT-NEXT: 3.1: 10 _Z5funcBi:10
+; RECOUNT-NEXT: 3: _Z5funcAi:1467388
 ; RECOUNT-NEXT:  0: 10
-; RECOUNT-NEXT:  1: 10 _Z8funcLeafi:11
 ; RECOUNT-NEXT:  3: 24
 ; RECOUNT-NEXT:  1: _Z8funcLeafi:1467299
 ; RECOUNT-NEXT:   0: 6
 ; RECOUNT-NEXT:   1: 6
 ; RECOUNT-NEXT:   3: 287884
-; RECOUNT-NEXT:   4: 287864 _Z3fibi:315608
+; RECOUNT-NEXT:   4: 287864 _Z3fibi:287864
 ; RECOUNT-NEXT:   15: 23
 ; RECOUNT-NEXT:   !Attributes: 6
 ; RECOUNT-NEXT:  !Attributes: 6
-; RECOUNT-NEXT: 3.1: _Z5funcBi:500973
+; RECOUNT-NEXT: 3.1: _Z5funcBi:500954
 ; RECOUNT-NEXT:  0: 19
-; RECOUNT-NEXT:  1: 19 _Z8funcLeafi:20
 ; RECOUNT-NEXT:  3: 12
 ; RECOUNT-NEXT:  1: _Z8funcLeafi:500853
 ; RECOUNT-NEXT:   0: 15
 ; RECOUNT-NEXT:   1: 15
 ; RECOUNT-NEXT:   3: 74946
-; RECOUNT-NEXT:   4: 74941 _Z3fibi:82359
+; RECOUNT-NEXT:   4: 74941 _Z3fibi:74941
 ; RECOUNT-NEXT:   10: 23324
-; RECOUNT-NEXT:   11: 23327 _Z3fibi:25228
+; RECOUNT-NEXT:   11: 23327 _Z3fibi:23327
 ; RECOUNT-NEXT:   15: 11
 ; RECOUNT-NEXT:   !Attributes: 6
 ; RECOUNT-NEXT:  !Attributes: 6
@@ -84,66 +79,63 @@
 ; RECOUNT-NEXT: 0: 21
 ; RECOUNT-NEXT: 1: 21
 ; RECOUNT-NEXT: 3: 362830
-; RECOUNT-NEXT: 4: 362805 _Z3fibi:397967
+; RECOUNT-NEXT: 4: 362805 _Z3fibi:362805
 ; RECOUNT-NEXT: 10: 23324
-; RECOUNT-NEXT: 11: 23327 _Z3fibi:25228
+; RECOUNT-NEXT: 11: 23327 _Z3fibi:23327
 ; RECOUNT-NEXT: 15: 34
 ; RECOUNT-NEXT: !Attributes: 2
-; RECOUNT-NEXT:_Z5funcAi:1467398:11
+; RECOUNT-NEXT:_Z5funcAi:1467388:11
 ; RECOUNT-NEXT: 0: 10
-; RECOUNT-NEXT: 1: 10 _Z8funcLeafi:11
 ; RECOUNT-NEXT: 3: 24
 ; RECOUNT-NEXT: 1: _Z8funcLeafi:1467299
 ; RECOUNT-NEXT:  0: 6
 ; RECOUNT-NEXT:  1: 6
 ; RECOUNT-NEXT:  3: 287884
-; RECOUNT-NEXT:  4: 287864 _Z3fibi:315608
+; RECOUNT-NEXT:  4: 287864 _Z3fibi:287864
 ; RECOUNT-NEXT:  15: 23
 ; RECOUNT-NEXT:  !Attributes: 6
 ; RECOUNT-NEXT: !Attributes: 2
-; RECOUNT-NEXT:_Z5funcBi:501213:32
+; RECOUNT-NEXT:_Z5funcBi:501194:32
 ; RECOUNT-NEXT: 0: 32
-; RECOUNT-NEXT: 1: 32 _Z8funcLeafi:20
+; RECOUNT-NEXT: 1: 13
 ; RECOUNT-NEXT: 3: 12
 ; RECOUNT-NEXT: 1: _Z8funcLeafi:500853
 ; RECOUNT-NEXT:  0: 15
 ; RECOUNT-NEXT:  1: 15
 ; RECOUNT-NEXT:  3: 74946
-; RECOUNT-NEXT:  4: 74941 _Z3fibi:82359
+; RECOUNT-NEXT:  4: 74941 _Z3fibi:74941
 ; RECOUNT-NEXT:  10: 23324
-; RECOUNT-NEXT:  11: 23327 _Z3fibi:25228
+; RECOUNT-NEXT:  11: 23327 _Z3fibi:23327
 ; RECOUNT-NEXT:  15: 11
 ; RECOUNT-NEXT:  !Attributes: 6
 
-; PROBE:main:1968679:12
+; PROBE:main:1968621:12
 ; PROBE-NEXT: 2: 24
-; PROBE-NEXT: 3: 28 _Z5funcAi:18
-; PROBE-NEXT: 3.1: 28 _Z5funcBi:30
-; PROBE-NEXT: 3: _Z5funcAi:1467398
+; PROBE-NEXT: 3: 17 _Z5funcAi:7
+; PROBE-NEXT: 3.1: 10 _Z5funcBi:10
+; PROBE-NEXT: 3: _Z5funcAi:1467388
 ; PROBE-NEXT:  0: 10
-; PROBE-NEXT:  1: 10 _Z8funcLeafi:11
 ; PROBE-NEXT:  3: 24
 ; PROBE-NEXT:  1: _Z8funcLeafi:1467299
 ; PROBE-NEXT:   0: 6
 ; PROBE-NEXT:   1: 6
 ; PROBE-NEXT:   3: 287884
-; PROBE-NEXT:   4: 287864 _Z3fibi:315608
+; PROBE-NEXT:   4: 287864 _Z3fibi:287864
 ; PROBE-NEXT:   15: 23
 ; PROBE-NEXT:   !CFGChecksum: 281479271677951
 ; PROBE-NEXT:   !Attributes: 2
 ; PROBE-NEXT:  !CFGChecksum: 844530426352218
 ; PROBE-NEXT:  !Attributes: 2
-; PROBE-NEXT: 3.1: _Z5funcBi:500973
+; PROBE-NEXT: 3.1: _Z5funcBi:500954
 ; PROBE-NEXT:  0: 19
-; PROBE-NEXT:  1: 19 _Z8funcLeafi:20
 ; PROBE-NEXT:  3: 12
 ; PROBE-NEXT:  1: _Z8funcLeafi:500853
 ; PROBE-NEXT:   0: 15
 ; PROBE-NEXT:   1: 15
 ; PROBE-NEXT:   3: 74946
-; PROBE-NEXT:   4: 74941 _Z3fibi:82359
+; PROBE-NEXT:   4: 74941 _Z3fibi:74941
 ; PROBE-NEXT:   10: 23324
-; PROBE-NEXT:   11: 23327 _Z3fibi:25228
+; PROBE-NEXT:   11: 23327 _Z3fibi:23327
 ; PROBE-NEXT:   15: 11
 ; PROBE-NEXT:   !CFGChecksum: 281479271677951
 ; PROBE-NEXT:   !Attributes: 2
@@ -181,3 +173,27 @@
 ; SUMMARY-NEXT: 11 blocks with count >= 24 account for 99.99 percentage of the total counts.
 ; SUMMARY-NEXT: 16 blocks with count >= 10 account for 99.999 percentage of the total counts.
 ; SUMMARY-NEXT: 16 blocks with count >= 10 account for 99.9999 percentage of the total counts.
+
+
+; SUMMARY-NEST:      Total functions: 4
+; SUMMARY-NEST-NEXT: Maximum function count: 32
+; SUMMARY-NEST-NEXT: Maximum block count: 362830
+; SUMMARY-NEST-NEXT: Total number of blocks: 15
+; SUMMARY-NEST-NEXT: Total count: 772504
+; SUMMARY-NEST-NEXT: Detailed summary:
+; SUMMARY-NEST-NEXT: 1 blocks with count >= 362830 account for 1 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 1 blocks with count >= 362830 account for 10 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 1 blocks with count >= 362830 account for 20 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 1 blocks with count >= 362830 account for 30 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 1 blocks with count >= 362830 account for 40 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 2 blocks with count >= 362805 account for 50 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 2 blocks with count >= 362805 account for 60 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 2 blocks with count >= 362805 account for 70 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 2 blocks with count >= 362805 account for 80 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 2 blocks with count >= 362805 account for 90 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 3 blocks with count >= 23327 account for 95 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 4 blocks with count >= 23324 account for 99 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 4 blocks with count >= 23324 account for 99.9 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 10 blocks with count >= 21 account for 99.99 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 15 blocks with count >= 10 account for 99.999 percentage of the total counts.
+; SUMMARY-NEST-NEXT: 15 blocks with count >= 10 account for 99.9999 percentage of the total counts.
diff --git a/llvm/test/tools/llvm-profgen/cs-preinline.test b/llvm/test/tools/llvm-profgen/cs-preinline.test
--- a/llvm/test/tools/llvm-profgen/cs-preinline.test
+++ b/llvm/test/tools/llvm-profgen/cs-preinline.test
@@ -57,10 +57,9 @@
 ; CHECK-TRIM-NEXT: 1: 14
 ; CHECK-TRIM-NEXT: !Attributes: 3
 
-; CHECK-PREINL-NEST:     foo:393:0
+; CHECK-PREINL-NEST:     foo:379:0
 ; CHECK-PREINL-NEST-NEXT: 2.1: 14
 ; CHECK-PREINL-NEST-NEXT: 3: 15
-; CHECK-PREINL-NEST-NEXT: 3.1: 14 bar:14
 ; CHECK-PREINL-NEST-NEXT: 3.2: 1
 ; CHECK-PREINL-NEST-NEXT: 65526: 14
 ; CHECK-PREINL-NEST-NEXT: 3.1: bar:84
diff --git a/llvm/tools/llvm-profdata/llvm-profdata.cpp b/llvm/tools/llvm-profdata/llvm-profdata.cpp
--- a/llvm/tools/llvm-profdata/llvm-profdata.cpp
+++ b/llvm/tools/llvm-profdata/llvm-profdata.cpp
@@ -22,6 +22,7 @@
 #include "llvm/ProfileData/MemProf.h"
 #include "llvm/ProfileData/ProfileCommon.h"
 #include "llvm/ProfileData/RawMemProfReader.h"
+#include "llvm/ProfileData/SampleProf.h"
 #include "llvm/ProfileData/SampleProfReader.h"
 #include "llvm/ProfileData/SampleProfWriter.h"
 #include "llvm/Support/CommandLine.h"
@@ -732,7 +733,7 @@
 mergeSampleProfile(const WeightedFileVector &Inputs, SymbolRemapper *Remapper,
                    StringRef OutputFilename, ProfileFormat OutputFormat,
                    StringRef ProfileSymbolListFile, bool CompressAllSections,
-                   bool UseMD5, bool GenPartialProfile, bool GenCSNestedProfile,
+                   bool UseMD5, bool GenPartialProfile, SampleProfileLayout ProfileLayout,
                    bool SampleMergeColdContext, bool SampleTrimColdContext,
                    bool SampleColdContextFrameDepth, FailureMode FailMode) {
   using namespace sampleprof;
@@ -809,10 +810,19 @@
             SampleMergeColdContext, SampleColdContextFrameDepth, false);
   }
 
-  if (ProfileIsCSFlat && GenCSNestedProfile) {
+
+  // Underlying context table serves for sample profile writer when
+  // converting a nested profile to a CS profile.
+  std::list<SampleContextFrameVector> Contexts;
+
+  if (ProfileIsCSFlat && ProfileLayout == llvm::sampleprof::SPL_Nest) {
     CSProfileConverter CSConverter(ProfileMap);
-    CSConverter.convertProfiles();
+    CSConverter.convertToCSNestedProfiles();
     ProfileIsCSFlat = FunctionSamples::ProfileIsCSFlat = false;
+  } else if (!ProfileIsCSFlat.getValue() && ProfileLayout == llvm::sampleprof::SPL_CS) {
+    CSProfileConverter CSConverter(ProfileMap, &Contexts);
+    CSConverter.convertToCSFlatProfiles();
+    ProfileIsCSFlat = FunctionSamples::ProfileIsCSFlat = true;
   }
 
   auto WriterOrErr =
@@ -994,15 +1004,17 @@
       "instr-prof-cold-threshold", cl::init(0), cl::Hidden,
       cl::desc("User specified cold threshold for instr profile which will "
                "override the cold threshold got from profile summary. "));
-  cl::opt<bool> GenCSNestedProfile(
-      "gen-cs-nested-profile", cl::Hidden, cl::init(false),
-      cl::desc("Generate nested function profiles for CSSPGO"));
   cl::opt<std::string> DebugInfoFilename(
       "debug-info", cl::init(""),
       cl::desc("Use the provided debug info to correlate the raw profile."));
   cl::opt<std::string> ProfiledBinary(
       "profiled-binary", cl::init(""),
       cl::desc("Path to binary from which the profile was collected."));
+  cl::opt<SampleProfileLayout> ProfileLayout(
+    "sample-profile-layout", cl::desc("Convert the generated profile to"), cl::init(SPL_None),
+    cl::values(
+        clEnumValN(SPL_Nest, "nest", "Nested profile"),
+        clEnumValN(SPL_CS, "cs", "Context-sensitive flat profile")));
 
   cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
 
@@ -1049,7 +1061,7 @@
   else
     mergeSampleProfile(WeightedInputs, Remapper.get(), OutputFilename,
                        OutputFormat, ProfileSymbolListFile, CompressAllSections,
-                       UseMD5, GenPartialProfile, GenCSNestedProfile,
+                       UseMD5, GenPartialProfile, ProfileLayout,
                        SampleMergeColdContext, SampleTrimColdContext,
                        SampleColdContextFrameDepth, FailureMode);
   return 0;
diff --git a/llvm/tools/llvm-profgen/ProfileGenerator.cpp b/llvm/tools/llvm-profgen/ProfileGenerator.cpp
--- a/llvm/tools/llvm-profgen/ProfileGenerator.cpp
+++ b/llvm/tools/llvm-profgen/ProfileGenerator.cpp
@@ -905,7 +905,7 @@
   calculateAndShowDensity(ContextLessProfiles);
   if (GenCSNestedProfile) {
     CSProfileConverter CSConverter(ProfileMap);
-    CSConverter.convertProfiles();
+    CSConverter.convertToCSNestedProfiles();
     FunctionSamples::ProfileIsCSFlat = false;
     FunctionSamples::ProfileIsCSNested = EnableCSPreInliner;
   }