[𝘀𝗽𝗿] changes to main this commit is based onusers/Prabhuk/sprmain.asmprintercallgraphsection-emit-call-graph-section-5

Created using spr 1.3.6-beta.1

[skip ci]

40 files changed, 1135 insertions, 19 deletions

diff --git a/clang/docs/CallGraphSection.rst b/clang/docs/CallGraphSection.rst
new file mode 100644
index 0000000..d5db507
--- /dev/null
+++ b/clang/docs/CallGraphSection.rst
@@ -0,0 +1,251 @@
+==================
+Call Graph Section
+==================
+
+Introduction
+============
+
+With ``-fcall-graph-section``, the compiler will create a call graph section 
+in the object file. It will include type identifiers for indirect calls and 
+targets. This information can be used to map indirect calls to their receivers 
+with matching types. A complete and high-precision call graph can be 
+reconstructed by complementing this information with disassembly 
+(see ``llvm-objdump --call-graph-info``).
+
+Semantics
+=========
+
+A coarse-grained, type-agnostic call graph may allow indirect calls to target
+any function in the program. This approach ensures completeness since no
+indirect call edge is missing. However, it is generally poor in precision
+due to having unneeded edges.
+
+A call graph section provides type identifiers for indirect calls and targets.
+This information can be used to restrict the receivers of an indirect target to
+indirect calls with matching type. Consequently, the precision for indirect
+call edges are improved while maintaining the completeness.
+
+The ``llvm-objdump`` utility provides a ``--call-graph-info`` option to extract
+full call graph information by parsing the content of the call graph section
+and disassembling the program for complementary information, e.g., direct
+calls.
+
+Section layout
+==============
+
+A call graph section consists of zero or more call graph entries.
+Each entry contains information on a function and its indirect calls.
+
+An entry of a call graph section has the following layout in the binary:
+
++---------------------+-----------------------------------------------------------------------+
+| Element             | Content                                                               |
++=====================+=======================================================================+
+| FormatVersionNumber | Format version number.                                                |
++---------------------+-----------------------------------------------------------------------+
+| FunctionEntryPc     | Function entry address.                                               |
++---------------------+-----------------------------------+-----------------------------------+
+|                     | A flag whether the function is an | - 0: not an indirect target       |
+| FunctionKind        | indirect target, and if so,       | - 1: indirect target, unknown id  |
+|                     | whether its type id is known.     | - 2: indirect target, known id    |
++---------------------+-----------------------------------+-----------------------------------+
+| FunctionTypeId      | Type id for the indirect target. Present only when FunctionKind is 2. |
++---------------------+-----------------------------------------------------------------------+
+| CallSiteCount       | Number of type id to indirect call site mappings that follow.         |
++---------------------+-----------------------------------------------------------------------+
+| CallSiteList        | List of type id and indirect call site pc pairs.                      |
++---------------------+-----------------------------------------------------------------------+
+
+Each element in an entry (including each element of the contained lists and
+pairs) occupies 64-bit space.
+
+The format version number is repeated per entry to support concatenation of
+call graph sections with different format versions by the linker.
+
+As of now, the only supported format version is described above and has version
+number 0.
+
+Type identifiers
+================
+
+The type for an indirect call or target is the function signature.
+The mapping from a type to an identifier is an ABI detail.
+In the current experimental implementation, an identifier of type T is
+computed as follows:
+
+  -  Obtain the generalized mangled name for “typeinfo name for T”.
+  -  Compute MD5 hash of the name as a string.
+  -  Reinterpret the first 8 bytes of the hash as a little-endian 64-bit integer.
+
+To avoid mismatched pointer types, generalizations are applied.
+Pointers in return and argument types are treated as equivalent as long as the
+qualifiers for the type they point to match.
+For example, ``char*``, ``char**``, and ``int*`` are considered equivalent
+types. However, ``char*`` and ``const char*`` are considered separate types.
+
+Missing type identifiers
+========================
+
+For functions, two cases need to be considered. First, if the compiler cannot
+deduce a type id for an indirect target, it will be listed as an indirect target
+without a type id. Second, if an object without a call graph section gets
+linked, the final call graph section will lack information on functions from
+the object. For completeness, these functions need to be taken as receiver to
+any indirect call regardless of their type id.
+``llvm-objdump --call-graph-info`` lists these functions as indirect targets
+with `UNKNOWN` type id.
+
+For indirect calls, current implementation guarantees a type id for each
+compiled call. However, if an object without a call graph section gets linked,
+no type id will be present for its indirect calls. For completeness, these calls
+need to be taken to target any indirect target regardless of their type id. For
+indirect calls, ``llvm-objdump --call-graph-info`` prints 1) a complete list of
+indirect calls, 2) type id to indirect call mappings. The difference of these
+lists allow to deduce the indirect calls with missing type ids.
+
+TODO: measure and report the ratio of missed type ids
+
+Performance
+===========
+
+A call graph section does not affect the executable code and does not occupy
+memory during process execution. Therefore, there is no performance overhead.
+
+The scheme has not yet been optimized for binary size.
+
+TODO: measure and report the increase in the binary size
+
+Example
+=======
+
+For example, consider the following C++ code:
+
+.. code-block:: cpp
+
+    namespace {
+      // Not an indirect target
+      void foo() {}
+    }
+
+    // Indirect target 1
+    void bar() {}
+
+    // Indirect target 2
+    int baz(char a, float *b) {
+      return 0;
+    }
+
+    // Indirect target 3
+    int main() {
+      char a;
+      float b;
+      void (*fp_bar)() = bar;
+      int (*fp_baz1)(char, float*) = baz;
+      int (*fp_baz2)(char, float*) = baz;
+
+      // Indirect call site 1
+      fp_bar();
+
+      // Indirect call site 2
+      fp_baz1(a, &b);
+
+      // Indirect call site 3: shares the type id with indirect call site 2
+      fp_baz2(a, &b);
+
+      // Direct call sites
+      foo();
+      bar();
+      baz(a, &b);
+
+      return 0;
+    }
+
+Following will compile it with a call graph section created in the binary:
+
+.. code-block:: bash
+
+  $ clang -fcall-graph-section example.cpp
+
+During the construction of the call graph section, the type identifiers are 
+computed as follows:
+
++---------------+-----------------------+----------------------------+----------------------------+
+| Function name | Generalized signature | Mangled name (itanium ABI) | Numeric type id (md5 hash) |
++===============+=======================+============================+============================+
+|  bar          | void ()               | _ZTSFvvE.generalized       | f85c699bb8ef20a2           |
++---------------+-----------------------+----------------------------+----------------------------+
+|  baz          | int (char, void*)     | _ZTSFicPvE.generalized     | e3804d2a7f2b03fe           |
++---------------+-----------------------+----------------------------+----------------------------+
+|  main         | int ()                | _ZTSFivE.generalized       | a9494def81a01dc            |
++---------------+-----------------------+----------------------------+----------------------------+
+
+The call graph section will have the following content:
+
++---------------+-----------------+--------------+----------------+---------------+--------------------------------------+
+| FormatVersion | FunctionEntryPc | FunctionKind | FunctionTypeId | CallSiteCount | CallSiteList                         |
++===============+=================+==============+================+===============+======================================+
+| 0             | EntryPc(foo)    | 0            | (empty)        | 0             | (empty)                              |
++---------------+-----------------+--------------+----------------+---------------+--------------------------------------+
+| 0             | EntryPc(bar)    | 2            | TypeId(bar)    | 0             | (empty)                              |
++---------------+-----------------+--------------+----------------+---------------+--------------------------------------+
+| 0             | EntryPc(baz)    | 2            | TypeId(baz)    | 0             | (empty)                              |
++---------------+-----------------+--------------+----------------+---------------+--------------------------------------+
+| 0             | EntryPc(main)   | 2            | TypeId(main)   | 3             | * TypeId(bar), CallSitePc(fp_bar())  |
+|               |                 |              |                |               | * TypeId(baz), CallSitePc(fp_baz1()) |
+|               |                 |              |                |               | * TypeId(baz), CallSitePc(fp_baz2()) |
++---------------+-----------------+--------------+----------------+---------------+--------------------------------------+
+
+
+The ``llvm-objdump`` utility can parse the call graph section and disassemble
+the program to provide complete call graph information. This includes any
+additional call sites from the binary:
+
+.. code-block:: bash
+
+    $ llvm-objdump --call-graph-info a.out
+
+    # Comments are not a part of the llvm-objdump's output but inserted for clarifications.
+
+    a.out:  file format elf64-x86-64
+    # These warnings are due to the functions and the indirect calls coming from linked objects.
+    llvm-objdump: warning: 'a.out': callgraph section does not have type ids for 3 indirect calls
+    llvm-objdump: warning: 'a.out': callgraph section does not have information for 10 functions
+
+    # Unknown targets are the 10 functions the warnings mention.
+    INDIRECT TARGET TYPES (TYPEID [FUNC_ADDR,])
+    UNKNOWN 401000 401100 401234 401050 401090 4010d0 4011d0 401020 401060 401230
+    a9494def81a01dc 401150            # main()
+    f85c699bb8ef20a2 401120           # bar()
+    e3804d2a7f2b03fe 401130           # baz()
+
+    # Notice that the call sites share the same type id as target functions
+    INDIRECT CALL TYPES (TYPEID [CALL_SITE_ADDR,])
+    f85c699bb8ef20a2 401181           # Indirect call site 1 (fp_bar())
+    e3804d2a7f2b03fe 401191 4011a1    # Indirect call site 2 and 3 (fp_baz1() and fp_baz2())
+
+    INDIRECT CALL SITES (CALLER_ADDR [CALL_SITE_ADDR,])
+    401000 401012                     # _init
+    401150 401181 401191 4011a1       # main calls fp_bar(), fp_baz1(), fp_baz2()
+    4011d0 401215                     # __libc_csu_init
+    401020 40104a                     # _start
+
+    DIRECT CALL SITES (CALLER_ADDR [(CALL_SITE_ADDR, TARGET_ADDR),])
+    4010d0 4010e2 401060              # __do_global_dtors_aux
+    401150 4011a6 401110 4011ab 401120 4011ba 401130   # main calls foo(), bar(), baz()
+    4011d0 4011fd 401000              # __libc_csu_init
+
+    FUNCTIONS (FUNC_ENTRY_ADDR, SYM_NAME)
+    401000 _init
+    401100 frame_dummy
+    401234 _fini
+    401050 _dl_relocate_static_pie
+    401090 register_tm_clones
+    4010d0 __do_global_dtors_aux
+    401110 _ZN12_GLOBAL__N_13fooEv    # (anonymous namespace)::foo()
+    401150 main                       # main
+    4011d0 __libc_csu_init
+    401020 _start
+    401060 deregister_tm_clones
+    401120 _Z3barv                    # bar()
+    401130 _Z3bazcPf                  # baz(char, float*)
+    401230 __libc_csu_fini
diff --git a/clang/include/clang/Basic/CodeGenOptions.def b/clang/include/clang/Basic/CodeGenOptions.def
index 340b08dd..9a8d629 100644
--- a/clang/include/clang/Basic/CodeGenOptions.def
+++ b/clang/include/clang/Basic/CodeGenOptions.def
@@ -76,6 +76,8 @@ CODEGENOPT(EnableNoundefAttrs, 1, 0) ///< Enable emitting `noundef` attributes o
 CODEGENOPT(DebugPassManager, 1, 0) ///< Prints debug information for the new
                                    ///< pass manager.
 CODEGENOPT(DisableRedZone    , 1, 0) ///< Set when -mno-red-zone is enabled.
+CODEGENOPT(CallGraphSection, 1, 0) ///< Emit a call graph section into the
+                                   ///< object file.
 CODEGENOPT(EmitCallSiteInfo, 1, 0) ///< Emit call site info only in the case of
                                    ///< '-g' + 'O>0' level.
 CODEGENOPT(IndirectTlsSegRefs, 1, 0) ///< Set when -mno-tls-direct-seg-refs
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index d83031b0..bd3383a 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -4099,6 +4099,10 @@ defm data_sections : BoolFOption<"data-sections",
   PosFlag<SetTrue, [], [ClangOption, CC1Option],
           "Place each data in its own section">,
   NegFlag<SetFalse>>;
+defm call_graph_section : BoolFOption<"call-graph-section",
+  CodeGenOpts<"CallGraphSection">, DefaultFalse,
+  PosFlag<SetTrue, [], [CC1Option], "Emit a call graph section">,
+  NegFlag<SetFalse>>;
 defm stack_size_section : BoolFOption<"stack-size-section",
   CodeGenOpts<"StackSizeSection">, DefaultFalse,
   PosFlag<SetTrue, [], [ClangOption, CC1Option],
diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
index 6cc00b8..0508077 100644
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -416,6 +416,7 @@ static bool initTargetOptions(DiagnosticsEngine &Diags,
   Options.StackUsageOutput = CodeGenOpts.StackUsageOutput;
   Options.EmitAddrsig = CodeGenOpts.Addrsig;
   Options.ForceDwarfFrameSection = CodeGenOpts.ForceDwarfFrameSection;
+  Options.EmitCallGraphSection = CodeGenOpts.CallGraphSection;
   Options.EmitCallSiteInfo = CodeGenOpts.EmitCallSiteInfo;
   Options.EnableAIXExtendedAltivecABI = LangOpts.EnableAIXExtendedAltivecABI;
   Options.XRayFunctionIndex = CodeGenOpts.XRayFunctionIndex;
diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
index 6c33cc1..473cd30 100644
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -5687,6 +5687,28 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
   AllocAlignAttrEmitter AllocAlignAttrEmitter(*this, TargetDecl, CallArgs);
   Attrs = AllocAlignAttrEmitter.TryEmitAsCallSiteAttribute(Attrs);
 
+  if (CGM.getCodeGenOpts().CallGraphSection) {
+    // FIXME: create operand bundle only for indirect calls, not for all
+
+    assert((TargetDecl && TargetDecl->getFunctionType() ||
+            Callee.getAbstractInfo().getCalleeFunctionProtoType()) &&
+           "cannot find callsite type");
+
+    QualType CST;
+    if (TargetDecl && TargetDecl->getFunctionType())
+      CST = QualType(TargetDecl->getFunctionType(), 0);
+    else if (const auto *FPT =
+                 Callee.getAbstractInfo().getCalleeFunctionProtoType())
+      CST = QualType(FPT, 0);
+
+    if (!CST.isNull()) {
+      auto *TypeIdMD = CGM.CreateMetadataIdentifierGeneralized(CST);
+      auto *TypeIdMDVal =
+          llvm::MetadataAsValue::get(getLLVMContext(), TypeIdMD);
+      BundleList.emplace_back("type", TypeIdMDVal);
+    }
+  }
+
   // Emit the actual call/invoke instruction.
   llvm::CallBase *CI;
   if (!InvokeDest) {
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index 0c447b2..3526699 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -2685,7 +2685,17 @@ static void setLinkageForGV(llvm::GlobalValue *GV, const NamedDecl *ND) {
 
 void CodeGenModule::CreateFunctionTypeMetadataForIcall(const FunctionDecl *FD,
                                                        llvm::Function *F) {
-  // Only if we are checking indirect calls.
+  bool EmittedMDIdGeneralized = false;
+  if (CodeGenOpts.CallGraphSection &&
+      (!F->hasLocalLinkage() ||
+       F->getFunction().hasAddressTaken(nullptr, /* IgnoreCallbackUses */ true,
+                                        /* IgnoreAssumeLikeCalls */ true,
+                                        /* IgnoreLLVMUsed */ false))) {
+    F->addTypeMetadata(0, CreateMetadataIdentifierGeneralized(FD->getType()));
+    EmittedMDIdGeneralized = true;
+  }
+
+  // Add additional metadata only if we are checking indirect calls with CFI.
   if (!LangOpts.Sanitize.has(SanitizerKind::CFIICall))
     return;
 
@@ -2696,7 +2706,9 @@ void CodeGenModule::CreateFunctionTypeMetadataForIcall(const FunctionDecl *FD,
 
   llvm::Metadata *MD = CreateMetadataIdentifierForType(FD->getType());
   F->addTypeMetadata(0, MD);
-  F->addTypeMetadata(0, CreateMetadataIdentifierGeneralized(FD->getType()));
+  // Add the generalized identifier if not added already.
+  if (!EmittedMDIdGeneralized)
+    F->addTypeMetadata(0, CreateMetadataIdentifierGeneralized(FD->getType()));
 
   // Emit a hash-based bit set entry for cross-DSO calls.
   if (CodeGenOpts.SanitizeCfiCrossDso)
@@ -2831,7 +2843,8 @@ void CodeGenModule::SetFunctionAttributes(GlobalDecl GD, llvm::Function *F,
   // are non-canonical then we need type metadata in order to produce the local
   // jump table.
   if (!CodeGenOpts.SanitizeCfiCrossDso ||
-      !CodeGenOpts.SanitizeCfiCanonicalJumpTables)
+      !CodeGenOpts.SanitizeCfiCanonicalJumpTables ||
+      CodeGenOpts.CallGraphSection)
     CreateFunctionTypeMetadataForIcall(FD, F);
 
   if (LangOpts.Sanitize.has(SanitizerKind::KCFI))
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 456ea74..fa39df0 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6444,6 +6444,10 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back(A->getValue());
   }
 
+  if (Args.hasFlag(options::OPT_fcall_graph_section,
+                   options::OPT_fno_call_graph_section, false))
+    CmdArgs.push_back("-fcall-graph-section");
+
   Args.addOptInFlag(CmdArgs, options::OPT_fstack_size_section,
                     options::OPT_fno_stack_size_section);
 
diff --git a/clang/test/CodeGen/call-graph-section-1.cpp b/clang/test/CodeGen/call-graph-section-1.cpp
new file mode 100644
index 0000000..a7ef25d
--- /dev/null
+++ b/clang/test/CodeGen/call-graph-section-1.cpp
@@ -0,0 +1,110 @@
+// Tests that we assign appropriate identifiers to indirect calls and targets
+// specifically for C++ class and instance methods.
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux -fcall-graph-section -S \
+// RUN: -emit-llvm -o %t %s
+// RUN: FileCheck --check-prefix=FT %s < %t
+// RUN: FileCheck --check-prefix=CST %s < %t
+
+////////////////////////////////////////////////////////////////////////////////
+// Class definitions (check for indirect target metadata)
+
+class Cls1 {
+public:
+  // FT-DAG: define {{.*}} i32* @_ZN4Cls18receiverEPcPf({{.*}} !type [[F_TCLS1RECEIVER:![0-9]+]]
+  static int *receiver(char *a, float *b) { return 0; }
+};
+
+class Cls2 {
+public:
+  int *(*fp)(char *, float *);
+
+  // FT-DAG: define {{.*}} i32 @_ZN4Cls22f1Ecfd({{.*}} !type [[F_TCLS2F1:![0-9]+]]
+  int f1(char a, float b, double c) { return 0; }
+
+  // FT-DAG: define {{.*}} i32* @_ZN4Cls22f2EPcPfPd({{.*}} !type [[F_TCLS2F2:![0-9]+]]
+  int *f2(char *a, float *b, double *c) { return 0; }
+
+  // FT-DAG: define {{.*}} void @_ZN4Cls22f3E4Cls1({{.*}} !type [[F_TCLS2F3F4:![0-9]+]]
+  void f3(Cls1 a) {}
+
+  // FT-DAG: define {{.*}} void @_ZN4Cls22f4E4Cls1({{.*}} !type [[F_TCLS2F3F4]]
+  void f4(const Cls1 a) {}
+
+  // FT-DAG: define {{.*}} void @_ZN4Cls22f5EP4Cls1({{.*}} !type [[F_TCLS2F5:![0-9]+]]
+  void f5(Cls1 *a) {}
+
+  // FT-DAG: define {{.*}} void @_ZN4Cls22f6EPK4Cls1({{.*}} !type [[F_TCLS2F6:![0-9]+]]
+  void f6(const Cls1 *a) {}
+
+  // FT-DAG: define {{.*}} void @_ZN4Cls22f7ER4Cls1({{.*}} !type [[F_TCLS2F7:![0-9]+]]
+  void f7(Cls1 &a) {}
+
+  // FT-DAG: define {{.*}} void @_ZN4Cls22f8ERK4Cls1({{.*}} !type [[F_TCLS2F8:![0-9]+]]
+  void f8(const Cls1 &a) {}
+
+  // FT-DAG: define {{.*}} void @_ZNK4Cls22f9Ev({{.*}} !type [[F_TCLS2F9:![0-9]+]]
+  void f9() const {}
+};
+
+// FT-DAG: [[F_TCLS1RECEIVER]] = !{i64 0, !"_ZTSFPvS_S_E.generalized"}
+// FT-DAG: [[F_TCLS2F2]]   = !{i64 0, !"_ZTSFPvS_S_S_E.generalized"}
+// FT-DAG: [[F_TCLS2F1]]   = !{i64 0, !"_ZTSFicfdE.generalized"}
+// FT-DAG: [[F_TCLS2F3F4]] = !{i64 0, !"_ZTSFv4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F5]]   = !{i64 0, !"_ZTSFvPvE.generalized"}
+// FT-DAG: [[F_TCLS2F6]]   = !{i64 0, !"_ZTSFvPKvE.generalized"}
+// FT-DAG: [[F_TCLS2F7]]   = !{i64 0, !"_ZTSFvR4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F8]]   = !{i64 0, !"_ZTSFvRK4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F9]]   = !{i64 0, !"_ZTSKFvvE.generalized"}
+
+////////////////////////////////////////////////////////////////////////////////
+// Callsites (check for indirect callsite operand bundles)
+
+// CST-LABEL: define {{.*}} @_Z3foov
+void foo() {
+  Cls2 ObjCls2;
+  ObjCls2.fp = &Cls1::receiver;
+
+  // CST: call i32* {{.*}} [ "type"(metadata !"_ZTSFPvS_S_E.generalized") ]
+  ObjCls2.fp(0, 0);
+
+  auto fp_f1 = &Cls2::f1;
+  auto fp_f2 = &Cls2::f2;
+  auto fp_f3 = &Cls2::f3;
+  auto fp_f4 = &Cls2::f4;
+  auto fp_f5 = &Cls2::f5;
+  auto fp_f6 = &Cls2::f6;
+  auto fp_f7 = &Cls2::f7;
+  auto fp_f8 = &Cls2::f8;
+  auto fp_f9 = &Cls2::f9;
+
+  Cls2 *ObjCls2Ptr = &ObjCls2;
+  Cls1 Cls1Param;
+
+  // CST: call i32 %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFicfdE.generalized") ]
+  (ObjCls2Ptr->*fp_f1)(0, 0, 0);
+
+  // CST: call i32* %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFPvS_S_S_E.generalized") ]
+  (ObjCls2Ptr->*fp_f2)(0, 0, 0);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFv4Cls1E.generalized") ]
+  (ObjCls2Ptr->*fp_f3)(Cls1Param);
+
+  // CST: call void  %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFv4Cls1E.generalized") ]
+  (ObjCls2Ptr->*fp_f4)(Cls1Param);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvPvE.generalized") ]
+  (ObjCls2Ptr->*fp_f5)(&Cls1Param);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvPKvE.generalized") ]
+  (ObjCls2Ptr->*fp_f6)(&Cls1Param);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvR4Cls1E.generalized") ]
+  (ObjCls2Ptr->*fp_f7)(Cls1Param);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvRK4Cls1E.generalized") ]
+  (ObjCls2Ptr->*fp_f8)(Cls1Param);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSKFvvE.generalized") ]
+  (ObjCls2Ptr->*fp_f9)();
+}
diff --git a/clang/test/CodeGen/call-graph-section-2.cpp b/clang/test/CodeGen/call-graph-section-2.cpp
new file mode 100644
index 0000000..c98448b
--- /dev/null
+++ b/clang/test/CodeGen/call-graph-section-2.cpp
@@ -0,0 +1,95 @@
+// Tests that we assign appropriate identifiers to indirect calls and targets
+// specifically for C++ templates.
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux -fcall-graph-section -S \
+// RUN: -emit-llvm -o %t %s
+// RUN: FileCheck --check-prefix=FT    %s < %t
+// RUN: FileCheck --check-prefix=CST   %s < %t
+// RUN: FileCheck --check-prefix=CHECK %s < %t
+
+////////////////////////////////////////////////////////////////////////////////
+// Class definitions and template classes (check for indirect target metadata)
+
+class Cls1 {};
+
+// Cls2 is instantiated with T=Cls1 in foo(). Following checks are for this
+// instantiation.
+template <class T>
+class Cls2 {
+public:
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f1Ev({{.*}} !type [[F_TCLS2F1:![0-9]+]]
+  void f1() {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f2ES0_({{.*}} !type [[F_TCLS2F2:![0-9]+]]
+  void f2(T a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f3EPS0_({{.*}} !type [[F_TCLS2F3:![0-9]+]]
+  void f3(T *a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f4EPKS0_({{.*}} !type [[F_TCLS2F4:![0-9]+]]
+  void f4(const T *a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f5ERS0_({{.*}} !type [[F_TCLS2F5:![0-9]+]]
+  void f5(T &a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f6ERKS0_({{.*}} !type [[F_TCLS2F6:![0-9]+]]
+  void f6(const T &a) {}
+
+  // Mixed type function pointer member
+  T *(*fp)(T a, T *b, const T *c, T &d, const T &e);
+};
+
+// FT-DAG: [[F_TCLS2F1]] = !{i64 0, !"_ZTSFvvE.generalized"}
+// FT-DAG: [[F_TCLS2F2]] = !{i64 0, !"_ZTSFv4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F3]] = !{i64 0, !"_ZTSFvPvE.generalized"}
+// FT-DAG: [[F_TCLS2F4]] = !{i64 0, !"_ZTSFvPKvE.generalized"}
+// FT-DAG: [[F_TCLS2F5]] = !{i64 0, !"_ZTSFvR4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F6]] = !{i64 0, !"_ZTSFvRK4Cls1E.generalized"}
+
+////////////////////////////////////////////////////////////////////////////////
+// Callsites (check for indirect callsite operand bundles)
+
+template <class T>
+T *T_func(T a, T *b, const T *c, T &d, const T &e) { return b; }
+
+// CST-LABEL: define {{.*}} @_Z3foov
+void foo() {
+  // Methods for Cls2<Cls1> is checked above within the template description.
+  Cls2<Cls1> Obj;
+
+  // CHECK-DAG: define {{.*}} @_Z6T_funcI4Cls1EPT_S1_S2_PKS1_RS1_RS3_({{.*}} !type [[F_TFUNC_CLS1:![0-9]+]]
+  // CHECK-DAG: [[F_TFUNC_CLS1]] = !{i64 0, !"_ZTSFPv4Cls1S_PKvRS0_RKS0_E.generalized"}
+  Obj.fp = T_func<Cls1>;
+  Cls1 Cls1Obj;
+
+  // CST: call %class.Cls1* {{.*}} [ "type"(metadata !"_ZTSFPv4Cls1S_PKvRS0_RKS0_E.generalized") ]
+  Obj.fp(Cls1Obj, &Cls1Obj, &Cls1Obj, Cls1Obj, Cls1Obj);
+
+  // Make indirect calls to Cls2's member methods
+  auto fp_f1 = &Cls2<Cls1>::f1;
+  auto fp_f2 = &Cls2<Cls1>::f2;
+  auto fp_f3 = &Cls2<Cls1>::f3;
+  auto fp_f4 = &Cls2<Cls1>::f4;
+  auto fp_f5 = &Cls2<Cls1>::f5;
+  auto fp_f6 = &Cls2<Cls1>::f6;
+
+  auto *Obj2Ptr = &Obj;
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvvE.generalized") ]
+  (Obj2Ptr->*fp_f1)();
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFv4Cls1E.generalized") ]
+  (Obj2Ptr->*fp_f2)(Cls1Obj);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvPvE.generalized") ]
+  (Obj2Ptr->*fp_f3)(&Cls1Obj);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvPKvE.generalized") ]
+  (Obj2Ptr->*fp_f4)(&Cls1Obj);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvR4Cls1E.generalized") ]
+  (Obj2Ptr->*fp_f5)(Cls1Obj);
+
+  // CST: call void %{{.*}}(%class.Cls2*{{.*}} [ "type"(metadata !"_ZTSFvRK4Cls1E.generalized") ]
+  (Obj2Ptr->*fp_f6)(Cls1Obj);
+}
diff --git a/clang/test/CodeGen/call-graph-section-3.cpp b/clang/test/CodeGen/call-graph-section-3.cpp
new file mode 100644
index 0000000..d4a0d66
--- /dev/null
+++ b/clang/test/CodeGen/call-graph-section-3.cpp
@@ -0,0 +1,52 @@
+// Tests that we assign appropriate identifiers to indirect calls and targets
+// specifically for virtual methods.
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux -fcall-graph-section -S \
+// RUN: -emit-llvm -o %t %s
+// RUN: FileCheck --check-prefix=FT %s < %t
+// RUN: FileCheck --check-prefix=CST %s < %t
+
+////////////////////////////////////////////////////////////////////////////////
+// Class definitions (check for indirect target metadata)
+
+class Base {
+public:
+  // FT-DAG: define {{.*}} @_ZN4Base2vfEPc({{.*}} !type [[F_TVF:![0-9]+]]
+  virtual int vf(char *a) { return 0; };
+};
+
+class Derived : public Base {
+public:
+  // FT-DAG: define {{.*}} @_ZN7Derived2vfEPc({{.*}} !type [[F_TVF]]
+  int vf(char *a) override { return 1; };
+};
+
+// FT-DAG: [[F_TVF]] = !{i64 0, !"_ZTSFiPvE.generalized"}
+
+////////////////////////////////////////////////////////////////////////////////
+// Callsites (check for indirect callsite operand bundles)
+
+// CST-LABEL: define {{.*}} @_Z3foov
+void foo() {
+  auto B = Base();
+  auto D = Derived();
+
+  Base *Bptr = &B;
+  Base *BptrToD = &D;
+  Derived *Dptr = &D;
+
+  auto FpBaseVf = &Base::vf;
+  auto FpDerivedVf = &Derived::vf;
+
+  // CST: call i32 %{{.*}}(%class.Base* {{.*}} [ "type"(metadata !"_ZTSFiPvE.generalized") ]
+  (Bptr->*FpBaseVf)(0);
+
+  // CST: call i32 %{{.*}}(%class.Base* {{.*}} [ "type"(metadata !"_ZTSFiPvE.generalized") ]
+  (BptrToD->*FpBaseVf)(0);
+
+  // CST: call i32 %{{.*}}(%class.Base* {{.*}} [ "type"(metadata !"_ZTSFiPvE.generalized") ]
+  (Dptr->*FpBaseVf)(0);
+
+  // CST: call i32 %{{.*}}(%class.Derived* {{.*}} [ "type"(metadata !"_ZTSFiPvE.generalized") ]
+  (Dptr->*FpDerivedVf)(0);
+}
diff --git a/clang/test/CodeGen/call-graph-section.c b/clang/test/CodeGen/call-graph-section.c
new file mode 100644
index 0000000..9b2ef81
--- /dev/null
+++ b/clang/test/CodeGen/call-graph-section.c
@@ -0,0 +1,85 @@
+// Tests that we assign appropriate identifiers to indirect calls and targets.
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux -fcall-graph-section -S \
+// RUN: -emit-llvm -o - %s | FileCheck --check-prefixes=CHECK,ITANIUM %s
+
+// RUN: %clang_cc1 -triple x86_64-pc-windows-msvc -fcall-graph-section -S \
+// RUN: -emit-llvm -o - %s | FileCheck --check-prefixes=CHECK,MS %s
+
+// CHECK-DAG: define {{(dso_local)?}} void @foo({{.*}} !type [[F_TVOID:![0-9]+]]
+void foo() {
+}
+
+// CHECK-DAG: define {{(dso_local)?}} void @bar({{.*}} !type [[F_TVOID]]
+void bar() {
+  void (*fp)() = foo;
+  // ITANIUM: call {{.*}} [ "type"(metadata !"_ZTSFvE.generalized") ]
+  // MS:      call {{.*}} [ "type"(metadata !"?6AX@Z.generalized") ]
+  fp();
+}
+
+// CHECK-DAG: define {{(dso_local)?}} i32 @baz({{.*}} !type [[F_TPRIMITIVE:![0-9]+]]
+int baz(char a, float b, double c) {
+  return 1;
+}
+
+// CHECK-DAG: define {{(dso_local)?}} i32* @qux({{.*}} !type [[F_TPTR:![0-9]+]]
+int *qux(char *a, float *b, double *c) {
+  return 0;
+}
+
+// CHECK-DAG: define {{(dso_local)?}} void @corge({{.*}} !type [[F_TVOID]]
+void corge() {
+  int (*fp_baz)(char, float, double) = baz;
+  // ITANIUM: call i32 {{.*}} [ "type"(metadata !"_ZTSFicfdE.generalized") ]
+  // MS:      call i32 {{.*}} [ "type"(metadata !"?6AHDMN@Z.generalized") ]
+  fp_baz('a', .0f, .0);
+
+  int *(*fp_qux)(char *, float *, double *) = qux;
+  // ITANIUM: call i32* {{.*}} [ "type"(metadata !"_ZTSFPvS_S_S_E.generalized") ]
+  // MS:      call i32* {{.*}} [ "type"(metadata !"?6APEAXPEAX00@Z.generalized") ]
+  fp_qux(0, 0, 0);
+}
+
+struct st1 {
+  int *(*fp)(char *, float *, double *);
+};
+
+struct st2 {
+  struct st1 m;
+};
+
+// CHECK-DAG: define {{(dso_local)?}} void @stparam({{.*}} !type [[F_TSTRUCT:![0-9]+]]
+void stparam(struct st2 a, struct st2 *b) {}
+
+// CHECK-DAG: define {{(dso_local)?}} void @stf({{.*}} !type [[F_TVOID]]
+void stf() {
+  struct st1 St1;
+  St1.fp = qux;
+  // ITANIUM: call i32* {{.*}} [ "type"(metadata !"_ZTSFPvS_S_S_E.generalized") ]
+  // MS:      call i32* {{.*}} [ "type"(metadata !"?6APEAXPEAX00@Z.generalized") ]
+  St1.fp(0, 0, 0);
+
+  struct st2 St2;
+  St2.m.fp = qux;
+  // ITANIUM: call i32* {{.*}} [ "type"(metadata !"_ZTSFPvS_S_S_E.generalized") ]
+  // MS:      call i32* {{.*}} [ "type"(metadata !"?6APEAXPEAX00@Z.generalized") ]
+  St2.m.fp(0, 0, 0);
+
+  // ITANIUM: call void {{.*}} [ "type"(metadata !"_ZTSFv3st2PvE.generalized") ]
+  // MS:      call void {{.*}} [ "type"(metadata !"?6AXUst2@@PEAX@Z.generalized") ]
+  void (*fp_stparam)(struct st2, struct st2 *) = stparam;
+  fp_stparam(St2, &St2);
+}
+
+// ITANIUM-DAG: [[F_TVOID]] = !{i64 0, !"_ZTSFvE.generalized"}
+// MS-DAG:      [[F_TVOID]] = !{i64 0, !"?6AX@Z.generalized"}
+
+// ITANIUM-DAG: [[F_TPRIMITIVE]] = !{i64 0, !"_ZTSFicfdE.generalized"}
+// MS-DAG:      [[F_TPRIMITIVE]] = !{i64 0, !"?6AHDMN@Z.generalized"}
+
+// ITANIUM-DAG: [[F_TPTR]] = !{i64 0, !"_ZTSFPvS_S_S_E.generalized"}
+// MS-DAG:      [[F_TPTR]] = !{i64 0, !"?6APEAXPEAX00@Z.generalized"}
+
+// ITANIUM-DAG: [[F_TSTRUCT]] = !{i64 0, !"_ZTSFv3st2PvE.generalized"}
+// MS-DAG:      [[F_TSTRUCT]] = !{i64 0, !"?6AXUst2@@PEAX@Z.generalized"}
diff --git a/clang/test/Driver/call-graph-section.c b/clang/test/Driver/call-graph-section.c
new file mode 100644
index 0000000..5832aa6
--- /dev/null
+++ b/clang/test/Driver/call-graph-section.c
@@ -0,0 +1,5 @@
+// RUN: %clang -### -S -fcall-graph-section %s 2>&1 | FileCheck --check-prefix=CALL-GRAPH-SECTION %s
+// RUN: %clang -### -S -fcall-graph-section -fno-call-graph-section %s 2>&1 | FileCheck --check-prefix=NO-CALL-GRAPH-SECTION %s
+
+// CALL-GRAPH-SECTION: "-fcall-graph-section"
+// NO-CALL-GRAPH-SECTION-NOT: "-fcall-graph-section"
diff --git a/llvm/include/llvm/CodeGen/CommandFlags.h b/llvm/include/llvm/CodeGen/CommandFlags.h
index 244dabd..1f216b2 100644
--- a/llvm/include/llvm/CodeGen/CommandFlags.h
+++ b/llvm/include/llvm/CodeGen/CommandFlags.h
@@ -130,6 +130,8 @@ bool getEnableStackSizeSection();
 
 bool getEnableAddrsig();
 
+bool getEnableCallGraphSection();
+
 bool getEmitCallSiteInfo();
 
 bool getEnableMachineFunctionSplitter();
diff --git a/llvm/include/llvm/CodeGen/MIRYamlMapping.h b/llvm/include/llvm/CodeGen/MIRYamlMapping.h
index bb8dbb0..d71cdc6 100644
--- a/llvm/include/llvm/CodeGen/MIRYamlMapping.h
+++ b/llvm/include/llvm/CodeGen/MIRYamlMapping.h
@@ -480,6 +480,10 @@ struct CallSiteInfo {
   MachineInstrLoc CallLocation;
   std::vector<ArgRegPair> ArgForwardingRegs;
 
+  /// Numeric callee type identifier used for call graph section.
+  using TypeIdTy = std::optional<uint64_t>;
+  TypeIdTy TypeId;
+
   bool operator==(const CallSiteInfo &Other) const {
     return CallLocation.BlockNum == Other.CallLocation.BlockNum &&
            CallLocation.Offset == Other.CallLocation.Offset;
@@ -508,6 +512,7 @@ template <> struct MappingTraits<CallSiteInfo> {
     YamlIO.mapRequired("offset", CSInfo.CallLocation.Offset);
     YamlIO.mapOptional("fwdArgRegs", CSInfo.ArgForwardingRegs,
                        std::vector<CallSiteInfo::ArgRegPair>());
+    YamlIO.mapOptional("typeId", CSInfo.TypeId);
   }
 
   static const bool flow = true;
diff --git a/llvm/include/llvm/CodeGen/MachineFunction.h b/llvm/include/llvm/CodeGen/MachineFunction.h
index 470997b..d53c959 100644
--- a/llvm/include/llvm/CodeGen/MachineFunction.h
+++ b/llvm/include/llvm/CodeGen/MachineFunction.h
@@ -27,7 +27,9 @@
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineMemOperand.h"
+#include "llvm/IR/Constants.h"
 #include "llvm/IR/EHPersonalities.h"
+#include "llvm/IR/Instructions.h"
 #include "llvm/Support/Allocator.h"
 #include "llvm/Support/ArrayRecycler.h"
 #include "llvm/Support/AtomicOrdering.h"
@@ -485,6 +487,41 @@ public:
   struct CallSiteInfo {
     /// Vector of call argument and its forwarding register.
     SmallVector<ArgRegPair, 1> ArgRegPairs;
+
+    /// Callee type id.
+    ConstantInt *TypeId = nullptr;
+
+    CallSiteInfo() {}
+
+    /// Extracts the numeric type id from the CallBase's type operand bundle,
+    /// and sets TypeId. This is used as type id for the indirect call in the
+    /// call graph section.
+    CallSiteInfo(const CallBase &CB) {
+      // Call graph section needs numeric type id only for indirect calls.
+      if (!CB.isIndirectCall())
+        return;
+
+      auto Opt = CB.getOperandBundle(LLVMContext::OB_type);
+      if (!Opt.has_value()) {
+        errs() << "warning: cannot find indirect call type operand bundle for  "
+                  "call graph section\n";
+        return;
+      }
+
+      // Get generalized type id string
+      auto OB = Opt.value();
+      assert(OB.Inputs.size() == 1 && "invalid input size");
+      auto *OBVal = OB.Inputs.front().get();
+      auto *TypeIdMD = cast<MetadataAsValue>(OBVal)->getMetadata();
+      auto *TypeIdStr = cast<MDString>(TypeIdMD);
+      assert(TypeIdStr->getString().endswith(".generalized") &&
+             "invalid type identifier");
+
+      // Compute numeric type id from generalized type id string
+      uint64_t TypeIdVal = llvm::MD5Hash(TypeIdStr->getString());
+      IntegerType *Int64Ty = Type::getInt64Ty(CB.getContext());
+      TypeId = llvm::ConstantInt::get(Int64Ty, TypeIdVal, /*IsSigned=*/false);
+    }
   };
 
 private:
@@ -492,7 +529,7 @@ private:
   GISelChangeObserver *Observer = nullptr;
 
   using CallSiteInfoMap = DenseMap<const MachineInstr *, CallSiteInfo>;
-  /// Map a call instruction to call site arguments forwarding info.
+  /// Map a call instruction to call site arguments forwarding and type id.
   CallSiteInfoMap CallSitesInfo;
 
   /// A helper function that returns call site info for a give call
@@ -1346,7 +1383,7 @@ public:
     });
   }
 
-  /// Start tracking the arguments passed to the call \p CallI.
+  /// Start tracking the arguments passed to the call \p CallI and call type.
   void addCallSiteInfo(const MachineInstr *CallI, CallSiteInfo &&CallInfo) {
     assert(CallI->isCandidateForCallSiteEntry());
     bool Inserted =
diff --git a/llvm/include/llvm/IR/LLVMContext.h b/llvm/include/llvm/IR/LLVMContext.h
index e5786af..20a0bf7 100644
--- a/llvm/include/llvm/IR/LLVMContext.h
+++ b/llvm/include/llvm/IR/LLVMContext.h
@@ -96,6 +96,7 @@ public:
     OB_ptrauth = 7,                // "ptrauth"
     OB_kcfi = 8,                   // "kcfi"
     OB_convergencectrl = 9,        // "convergencectrl"
+    OB_type = 10,                  // "type"
   };
 
   /// getMDKindID - Return a unique non-zero ID for the specified metadata kind.
diff --git a/llvm/include/llvm/Target/TargetOptions.h b/llvm/include/llvm/Target/TargetOptions.h
index d37e9d9..09bb008 100644
--- a/llvm/include/llvm/Target/TargetOptions.h
+++ b/llvm/include/llvm/Target/TargetOptions.h
@@ -149,7 +149,7 @@ namespace llvm {
           EnableTLSDESC(false), EnableIPRA(false), EmitStackSizeSection(false),
           EnableMachineOutliner(false), EnableMachineFunctionSplitter(false),
           SupportsDefaultOutlining(false), EmitAddrsig(false), BBAddrMap(false),
-          EmitCallSiteInfo(false), SupportsDebugEntryValues(false),
+          EmitCallGraphSection(false), EmitCallSiteInfo(false), SupportsDebugEntryValues(false),
           EnableDebugEntryValues(false), ValueTrackingVariableLocations(false),
           ForceDwarfFrameSection(false), XRayFunctionIndex(true),
           DebugStrictDwarf(false), Hotpatch(false),
@@ -323,6 +323,9 @@ namespace llvm {
     /// to selectively generate basic block sections.
     std::shared_ptr<MemoryBuffer> BBSectionsFuncListBuf;
 
+    /// Emit section containing call graph metadata.
+    unsigned EmitCallGraphSection : 1;
+
     /// The flag enables call site info production. It is used only for debug
     /// info, and it is restricted only to optimized code. This can be used for
     /// something else, so that should be controlled in the frontend.
diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index 2902bd9..8cb55bc 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/llvm/lib/AsmParser/LLParser.cpp
@@ -3135,9 +3135,21 @@ bool LLParser::parseOptionalOperandBundles(
         return true;
 
       Type *Ty = nullptr;
-      Value *Input = nullptr;
-      if (parseType(Ty) || parseValue(Ty, Input, PFS))
+      if (parseType(Ty))
         return true;
+
+      Value *Input = nullptr;
+      // FIXME: Metadata operand bundle value is garbage when LLVM IR is
+      // compiled to bitcode, then disassembled back to LLVM IR. See D107039
+      // for the reproducers, and https://bugs.llvm.org/show_bug.cgi?id=51264
+      // for the bug report.
+      if (Ty->isMetadataTy()) {
+        if (parseMetadataAsValue(Input, PFS))
+          return true;
+      } else {
+        if (parseValue(Ty, Input, PFS))
+          return true;
+      }
       Inputs.push_back(Input);
     }
 
diff --git a/llvm/lib/CodeGen/CommandFlags.cpp b/llvm/lib/CodeGen/CommandFlags.cpp
index 14ac4b21..6d31681 100644
--- a/llvm/lib/CodeGen/CommandFlags.cpp
+++ b/llvm/lib/CodeGen/CommandFlags.cpp
@@ -100,6 +100,7 @@ CGOPT(EABI, EABIVersion)
 CGOPT(DebuggerKind, DebuggerTuningOpt)
 CGOPT(bool, EnableStackSizeSection)
 CGOPT(bool, EnableAddrsig)
+CGOPT(bool, EnableCallGraphSection)
 CGOPT(bool, EmitCallSiteInfo)
 CGOPT(bool, EnableMachineFunctionSplitter)
 CGOPT(bool, EnableDebugEntryValues)
@@ -450,6 +451,11 @@ codegen::RegisterCodeGenFlags::RegisterCodeGenFlags() {
       cl::init(false));
   CGBINDOPT(EnableAddrsig);
 
+  static cl::opt<bool> EnableCallGraphSection(
+      "call-graph-section", cl::desc("Emit a call graph section"),
+      cl::init(false));
+  CGBINDOPT(EnableCallGraphSection);
+
   static cl::opt<bool> EmitCallSiteInfo(
       "emit-call-site-info",
       cl::desc(
@@ -578,6 +584,7 @@ codegen::InitTargetOptionsFromCodeGenFlags(const Triple &TheTriple) {
   Options.EmitStackSizeSection = getEnableStackSizeSection();
   Options.EnableMachineFunctionSplitter = getEnableMachineFunctionSplitter();
   Options.EmitAddrsig = getEnableAddrsig();
+  Options.EmitCallGraphSection = getEnableCallGraphSection();
   Options.EmitCallSiteInfo = getEmitCallSiteInfo();
   Options.EnableDebugEntryValues = getEnableDebugEntryValues();
   Options.ForceDwarfFrameSection = getForceDwarfFrameSection();
diff --git a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
index 4d9a8dc..4737ff5 100644
--- a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
@@ -427,12 +427,18 @@ bool MIRParserImpl::initializeCallSiteInfo(
         return error(Error, ArgRegPair.Reg.SourceRange);
       CSInfo.ArgRegPairs.emplace_back(Reg, ArgRegPair.ArgNo);
     }
+    if (YamlCSInfo.TypeId.has_value()) {
+      IntegerType *Int64Ty = Type::getInt64Ty(Context);
+      CSInfo.TypeId = ConstantInt::get(Int64Ty, YamlCSInfo.TypeId.value(),
+                                       /*isSigned=*/false);
+    }
 
-    if (TM.Options.EmitCallSiteInfo)
+    if (TM.Options.EmitCallSiteInfo || TM.Options.EmitCallGraphSection)
       MF.addCallSiteInfo(&*CallI, std::move(CSInfo));
   }
 
-  if (YamlMF.CallSitesInfo.size() && !TM.Options.EmitCallSiteInfo)
+  if (YamlMF.CallSitesInfo.size() &&
+      !(TM.Options.EmitCallSiteInfo || TM.Options.EmitCallGraphSection))
     return error(Twine("Call site info provided but not used"));
   return false;
 }
diff --git a/llvm/lib/CodeGen/MIRPrinter.cpp b/llvm/lib/CodeGen/MIRPrinter.cpp
index bf3aee6..a702e96 100644
--- a/llvm/lib/CodeGen/MIRPrinter.cpp
+++ b/llvm/lib/CodeGen/MIRPrinter.cpp
@@ -548,6 +548,9 @@ void MIRPrinter::convertCallSiteObjects(yaml::MachineFunction &YMF,
       printRegMIR(ArgReg.Reg, YmlArgReg.Reg, TRI);
       YmlCS.ArgForwardingRegs.emplace_back(YmlArgReg);
     }
+    // Get type id.
+    if (CSInfo.second.TypeId)
+      YmlCS.TypeId = CSInfo.second.TypeId->getZExtValue();
     YMF.CallSitesInfo.push_back(YmlCS);
   }
 
diff --git a/llvm/lib/CodeGen/MachineFunction.cpp b/llvm/lib/CodeGen/MachineFunction.cpp
index ad53214..dd0f4e1 100644
--- a/llvm/lib/CodeGen/MachineFunction.cpp
+++ b/llvm/lib/CodeGen/MachineFunction.cpp
@@ -878,7 +878,7 @@ MachineFunction::getCallSiteInfo(const MachineInstr *MI) {
   assert(MI->isCandidateForCallSiteEntry() &&
          "Call site info refers only to call (MI) candidates");
 
-  if (!Target.Options.EmitCallSiteInfo)
+  if (!Target.Options.EmitCallSiteInfo && !Target.Options.EmitCallGraphSection)
     return CallSitesInfo.end();
   return CallSitesInfo.find(MI);
 }
diff --git a/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp b/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp
index 379456e..18ae2fd 100644
--- a/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp
@@ -888,7 +888,8 @@ EmitSchedule(MachineBasicBlock::iterator &InsertPos) {
     }
 
     if (MI->isCandidateForCallSiteEntry() &&
-        DAG->getTarget().Options.EmitCallSiteInfo) {
+        (DAG->getTarget().Options.EmitCallSiteInfo ||
+         DAG->getTarget().Options.EmitCallGraphSection)) {      
       MF.addCallSiteInfo(MI, DAG->getCallSiteInfo(Node));
     }
 
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 3f69f7a..afa705f 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -3308,7 +3308,7 @@ void SelectionDAGBuilder::visitInvoke(const InvokeInst &I) {
              {LLVMContext::OB_deopt, LLVMContext::OB_gc_transition,
               LLVMContext::OB_gc_live, LLVMContext::OB_funclet,
               LLVMContext::OB_cfguardtarget,
-              LLVMContext::OB_clang_arc_attachedcall}) &&
+              LLVMContext::OB_clang_arc_attachedcall, LLVMContext::OB_type}) &&
          "Cannot lower invokes with arbitrary operand bundles yet!");
 
   const Value *Callee(I.getCalledOperand());
@@ -3395,8 +3395,9 @@ void SelectionDAGBuilder::visitCallBr(const CallBrInst &I) {
 
   // Deopt bundles are lowered in LowerCallSiteWithDeoptBundle, and we don't
   // have to do anything here to lower funclet bundles.
-  assert(!I.hasOperandBundlesOtherThan(
-             {LLVMContext::OB_deopt, LLVMContext::OB_funclet}) &&
+  assert(!I.hasOperandBundlesOtherThan({LLVMContext::OB_deopt,
+                                        LLVMContext::OB_funclet,
+                                        LLVMContext::OB_type}) &&
          "Cannot lower callbrs with arbitrary operand bundles yet!");
 
   assert(I.isInlineAsm() && "Only know how to handle inlineasm callbr");
@@ -9188,7 +9189,8 @@ void SelectionDAGBuilder::visitCall(const CallInst &I) {
              {LLVMContext::OB_deopt, LLVMContext::OB_funclet,
               LLVMContext::OB_cfguardtarget, LLVMContext::OB_preallocated,
               LLVMContext::OB_clang_arc_attachedcall, LLVMContext::OB_kcfi,
-              LLVMContext::OB_convergencectrl}) &&
+              LLVMContext::OB_convergencectrl,
+              LLVMContext::OB_type}) &&
          "Cannot lower calls with arbitrary operand bundles!");
 
   SDValue Callee = getValue(I.getCalledOperand());
diff --git a/llvm/lib/IR/LLVMContext.cpp b/llvm/lib/IR/LLVMContext.cpp
index 57077e7..d987acf 100644
--- a/llvm/lib/IR/LLVMContext.cpp
+++ b/llvm/lib/IR/LLVMContext.cpp
@@ -97,6 +97,11 @@ LLVMContext::LLVMContext() : pImpl(new LLVMContextImpl(*this)) {
          "convergencectrl operand bundle id drifted!");
   (void)ConvergenceCtrlEntry;
 
+  auto *TypeEntry = pImpl->getOrInsertBundleTag("type");
+  assert(TypeEntry->second == LLVMContext::OB_type &&
+         "type operand bundle id drifted!");
+  (void)TypeEntry;
+
   SyncScope::ID SingleThreadSSID =
       pImpl->getOrInsertSyncScopeID("singlethread");
   assert(SingleThreadSSID == SyncScope::SingleThread &&
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index 0d6db3d..b49c156 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -3629,13 +3629,13 @@ void Verifier::visitCallBase(CallBase &Call) {
       visitIntrinsicCall(ID, Call);
 
   // Verify that a callsite has at most one "deopt", at most one "funclet", at
-  // most one "gc-transition", at most one "cfguardtarget", at most one
+  // most one "gc-transition", at most one "cfguardtarget", at most one "type", at most one
   // "preallocated" operand bundle, and at most one "ptrauth" operand bundle.
   bool FoundDeoptBundle = false, FoundFuncletBundle = false,
        FoundGCTransitionBundle = false, FoundCFGuardTargetBundle = false,
        FoundPreallocatedBundle = false, FoundGCLiveBundle = false,
        FoundPtrauthBundle = false, FoundKCFIBundle = false,
-       FoundAttachedCallBundle = false;
+       FoundAttachedCallBundle = false, FoundTypeBundle = false;
   for (unsigned i = 0, e = Call.getNumOperandBundles(); i < e; ++i) {
     OperandBundleUse BU = Call.getOperandBundleAt(i);
     uint32_t Tag = BU.getTagID();
@@ -3698,6 +3698,9 @@ void Verifier::visitCallBase(CallBase &Call) {
             "Multiple \"clang.arc.attachedcall\" operand bundles", Call);
       FoundAttachedCallBundle = true;
       verifyAttachedCallBundle(Call, BU);
+    } else if (Tag == LLVMContext::OB_type) {
+      Check(!FoundTypeBundle, "Multiple \"type\" operand bundles", Call);
+      FoundTypeBundle = true;
     }
   }
 
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 3d1453e..64e172b 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -7811,6 +7811,7 @@ AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
   bool &IsTailCall = CLI.IsTailCall;
   CallingConv::ID &CallConv = CLI.CallConv;
   bool IsVarArg = CLI.IsVarArg;
+  const auto *CB = CLI.CB;
 
   MachineFunction &MF = DAG.getMachineFunction();
   MachineFunction::CallSiteInfo CSInfo;
@@ -7850,6 +7851,10 @@ AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
                     *DAG.getContext());
   RetCCInfo.AnalyzeCallResult(Ins, RetCC);
 
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
+
   // Check callee args/returns for SVE registers and set calling convention
   // accordingly.
   if (CallConv == CallingConv::C || CallConv == CallingConv::Fast) {
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 3907131..cb9392c 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -2359,6 +2359,7 @@ ARMTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   CallingConv::ID CallConv              = CLI.CallConv;
   bool doesNotRet                       = CLI.DoesNotReturn;
   bool isVarArg                         = CLI.IsVarArg;
+  const auto *CB = CLI.CB;
 
   MachineFunction &MF = DAG.getMachineFunction();
   ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
@@ -2375,6 +2376,10 @@ ARMTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
       !Subtarget->noBTIAtReturnTwice())
     GuardWithBTI = AFI->branchTargetEnforcement();
 
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
+
   // Determine whether this is a non-secure function call.
   if (CLI.CB && CLI.CB->getAttributes().hasFnAttr("cmse_nonsecure_call"))
     isCmseNSCall = true;
diff --git a/llvm/lib/Target/Mips/MipsISelLowering.cpp b/llvm/lib/Target/Mips/MipsISelLowering.cpp
index 7bc66b2..c64ac44 100644
--- a/llvm/lib/Target/Mips/MipsISelLowering.cpp
+++ b/llvm/lib/Target/Mips/MipsISelLowering.cpp
@@ -3185,6 +3185,7 @@ MipsTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   bool &IsTailCall                      = CLI.IsTailCall;
   CallingConv::ID CallConv              = CLI.CallConv;
   bool IsVarArg                         = CLI.IsVarArg;
+  const auto *CB = CLI.CB;
 
   MachineFunction &MF = DAG.getMachineFunction();
   MachineFrameInfo &MFI = MF.getFrameInfo();
@@ -3242,8 +3243,11 @@ MipsTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   // Get a count of how many bytes are to be pushed on the stack.
   unsigned StackSize = CCInfo.getStackSize();
 
-  // Call site info for function parameters tracking.
+  // Call site info for function parameters tracking and call base type info.
   MachineFunction::CallSiteInfo CSInfo;
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
 
   // Check if it's really possible to do a tail call. Restrict it to functions
   // that are part of this compilation unit.
diff --git a/llvm/lib/Target/X86/X86FastISel.cpp b/llvm/lib/Target/X86/X86FastISel.cpp
index 2eae155..391dc3f 100644
--- a/llvm/lib/Target/X86/X86FastISel.cpp
+++ b/llvm/lib/Target/X86/X86FastISel.cpp
@@ -3630,6 +3630,12 @@ bool X86FastISel::fastLowerCall(CallLoweringInfo &CLI) {
   CLI.NumResultRegs = RVLocs.size();
   CLI.Call = MIB;
 
+  // Add call site info for call graph section.
+  if (TM.Options.EmitCallGraphSection && CB && CB->isIndirectCall()) {
+    MachineFunction::CallSiteInfo CSInfo(*CB);
+    MF->addCallSiteInfo(CLI.Call, std::move(CSInfo));
+  }
+
   return true;
 }
 
@@ -4025,6 +4031,8 @@ bool X86FastISel::tryToFoldLoadIntoMI(MachineInstr *MI, unsigned OpNo,
     MO.setReg(IndexReg);
   }
 
+  if (MI->isCall())
+    FuncInfo.MF->moveCallSiteInfo(MI, Result);
   Result->addMemOperand(*FuncInfo.MF, createMachineMemOperandFor(LI));
   Result->cloneInstrSymbols(*FuncInfo.MF, *MI);
   MachineBasicBlock::iterator I(MI);
diff --git a/llvm/lib/Target/X86/X86ISelLoweringCall.cpp b/llvm/lib/Target/X86/X86ISelLoweringCall.cpp
index 1f76f74..a8c4747 100644
--- a/llvm/lib/Target/X86/X86ISelLoweringCall.cpp
+++ b/llvm/lib/Target/X86/X86ISelLoweringCall.cpp
@@ -2021,6 +2021,10 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   if (CallConv == CallingConv::X86_INTR)
     report_fatal_error("X86 interrupts may not be called directly");
 
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
+
   bool IsMustTail = CLI.CB && CLI.CB->isMustTailCall();
   if (Subtarget.isPICStyleGOT() && !IsGuaranteeTCO && !IsMustTail) {
     // If we are using a GOT, disable tail calls to external symbols with
diff --git a/llvm/test/Bitcode/2021-07-22-Parse-Metadata-Operand-Bundles.ll b/llvm/test/Bitcode/2021-07-22-Parse-Metadata-Operand-Bundles.ll
new file mode 100644
index 0000000..35c6131b
--- /dev/null
+++ b/llvm/test/Bitcode/2021-07-22-Parse-Metadata-Operand-Bundles.ll
@@ -0,0 +1,9 @@
+; This test ensures that we parse metadata operand bundle values.
+; RUN: llvm-as < %s
+
+declare void @callee()
+
+define void @call_with_operand_bundle() {
+  call void @callee() [ "op_type"(metadata !"metadata_string") ]
+  ret void
+}
diff --git a/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll b/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll
index d860104..5628e17 100644
--- a/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll
+++ b/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll
@@ -13,6 +13,7 @@
 ; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
 ; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
 ; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
+; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
 ; CHECK-NEXT:  </OPERAND_BUNDLE_TAGS_BLOCK
 
 ; CHECK:   <FUNCTION_BLOCK
diff --git a/llvm/test/CodeGen/AArch64/call-site-info-typeid.ll b/llvm/test/CodeGen/AArch64/call-site-info-typeid.ll
new file mode 100644
index 0000000..f0a6b44
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/call-site-info-typeid.ll
@@ -0,0 +1,39 @@
+; Tests that call site type ids can be extracted and set from type operand
+; bundles.
+
+; Verify the exact typeId value to ensure it is not garbage but the value
+; computed as the type id from the type operand bundle.
+; RUN: llc --call-graph-section -mtriple aarch64-linux-gnu %s -stop-before=finalize-isel -o - | FileCheck %s
+
+; ModuleID = 'test.c'
+source_filename = "test.c"
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-linux-gnu"
+
+define dso_local void @foo(i8 signext %a) !type !3 {
+entry:
+  ret void
+}
+
+; CHECK: name: main
+define dso_local i32 @main() !type !4 {
+entry:
+  %retval = alloca i32, align 4
+  %fp = alloca void (i8)*, align 8
+  store i32 0, i32* %retval, align 4
+  store void (i8)* @foo, void (i8)** %fp, align 8
+  %0 = load void (i8)*, void (i8)** %fp, align 8
+  ; CHECK: callSites:
+  ; CHECK-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+  ; CHECK-NEXT: 7854600665770582568 }
+  call void %0(i8 signext 97) [ "type"(metadata !"_ZTSFvcE.generalized") ]
+  ret i32 0
+}
+
+!llvm.module.flags = !{!0, !1, !2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 7, !"uwtable", i32 1}
+!2 = !{i32 7, !"frame-pointer", i32 2}
+!3 = !{i64 0, !"_ZTSFvcE.generalized"}
+!4 = !{i64 0, !"_ZTSFiE.generalized"}
diff --git a/llvm/test/CodeGen/ARM/call-site-info-typeid.ll b/llvm/test/CodeGen/ARM/call-site-info-typeid.ll
new file mode 100644
index 0000000..ec7f8a4
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/call-site-info-typeid.ll
@@ -0,0 +1,39 @@
+; Tests that call site type ids can be extracted and set from type operand
+; bundles.
+
+; Verify the exact typeId value to ensure it is not garbage but the value
+; computed as the type id from the type operand bundle.
+; RUN: llc --call-graph-section -mtriple arm-linux-gnu %s -stop-before=finalize-isel -o - | FileCheck %s
+
+; ModuleID = 'test.c'
+source_filename = "test.c"
+target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
+target triple = "armv4t-unknown-linux-gnu"
+
+define dso_local void @foo(i8 signext %a) !type !3 {
+entry:
+  ret void
+}
+
+; CHECK: name: main
+define dso_local i32 @main() !type !4 {
+entry:
+  %retval = alloca i32, align 4
+  %fp = alloca void (i8)*, align 8
+  store i32 0, i32* %retval, align 4
+  store void (i8)* @foo, void (i8)** %fp, align 8
+  %0 = load void (i8)*, void (i8)** %fp, align 8
+  ; CHECK: callSites:
+  ; CHECK-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+  ; CHECK-NEXT: 7854600665770582568 }
+  call void %0(i8 signext 97) [ "type"(metadata !"_ZTSFvcE.generalized") ]
+  ret i32 0
+}
+
+!llvm.module.flags = !{!0, !1, !2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 7, !"uwtable", i32 1}
+!2 = !{i32 7, !"frame-pointer", i32 2}
+!3 = !{i64 0, !"_ZTSFvcE.generalized"}
+!4 = !{i64 0, !"_ZTSFiE.generalized"}
diff --git a/llvm/test/CodeGen/MIR/X86/call-site-info-typeid.ll b/llvm/test/CodeGen/MIR/X86/call-site-info-typeid.ll
new file mode 100644
index 0000000..b769a72
--- /dev/null
+++ b/llvm/test/CodeGen/MIR/X86/call-site-info-typeid.ll
@@ -0,0 +1,112 @@
+; Test MIR printer and parser for type id field in call site info. Test that
+; it works well with/without --emit-call-site-info.
+
+; Multiplex --call-graph-section and -emit-call-site-info as both utilize
+; CallSiteInfo and callSites.
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Test printer and parser with --call-graph-section only.
+
+; Test printer.
+; Verify that fwdArgRegs is not set, typeId is set.
+; Verify the exact typeId value to ensure it is not garbage but the value
+; computed as the type id from the type operand bundle.
+; RUN: llc --call-graph-section %s -stop-before=finalize-isel -o %t1.mir
+; RUN: cat %t1.mir | FileCheck %s --check-prefix=PRINTER_CGS
+; PRINTER_CGS: name: main
+; PRINTER_CGS: callSites:
+; PRINTER_CGS-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+; PRINTER_CGS-NEXT: 7854600665770582568 }
+
+
+; Test parser.
+; Verify that we get the same result.
+; RUN: llc --call-graph-section %t1.mir -run-pass=finalize-isel -o - \
+; RUN: | FileCheck %s --check-prefix=PARSER_CGS
+; PARSER_CGS: name: main
+; PARSER_CGS: callSites:
+; PARSER_CGS-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+; PARSER_CGS-NEXT: 7854600665770582568 }
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Test printer and parser with -emit-call-site-info only.
+
+; Test printer.
+; Verify that fwdArgRegs is set, typeId is not set.
+; RUN: llc -emit-call-site-info %s -stop-before=finalize-isel -o %t2.mir
+; RUN: cat %t2.mir | FileCheck %s --check-prefix=PRINTER_CSI
+; PRINTER_CSI: name: main
+; PRINTER_CSI: callSites:
+; PRINTER_CSI-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs:
+; PRINTER_CSI-NEXT: { arg: 0, reg: '$edi' }
+; PRINTER_CSI-NOT: typeId:
+
+
+; Test parser.
+; Verify that we get the same result.
+; RUN: llc -emit-call-site-info %t2.mir -run-pass=finalize-isel -o - \
+; RUN: | FileCheck %s --check-prefix=PARSER_CSI
+; PARSER_CSI: name: main
+; PARSER_CSI: callSites:
+; PARSER_CSI-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs:
+; PARSER_CSI-NEXT: { arg: 0, reg: '$edi' }
+; PARSER_CSI-NOT: typeId:
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Test printer and parser with both -emit-call-site-info and --call-graph-section.
+
+; Test printer.
+; Verify both fwdArgRegs and typeId are set.
+; Verify the exact typeId value to ensure it is not garbage but the value
+; computed as the type id from the type operand bundle.
+; RUN: llc --call-graph-section -emit-call-site-info %s -stop-before=finalize-isel -o %t2.mir
+; RUN: cat %t2.mir | FileCheck %s --check-prefix=PRINTER_CGS_CSI
+; PRINTER_CGS_CSI: name: main
+; PRINTER_CGS_CSI: callSites:
+; PRINTER_CGS_CSI-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs:
+; PRINTER_CGS_CSI-NEXT: { arg: 0, reg: '$edi' }, typeId:
+; PRINTER_CGS_CSI-NEXT:   7854600665770582568 }
+
+
+; Test parser.
+; Verify that we get the same result.
+; RUN: llc --call-graph-section -emit-call-site-info %t2.mir -run-pass=finalize-isel -o - \
+; RUN: | FileCheck %s --check-prefix=PARSER_CGS_CSI
+; PARSER_CGS_CSI: name: main
+; PARSER_CGS_CSI: callSites:
+; PARSER_CGS_CSI-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs:
+; PARSER_CGS_CSI-NEXT: { arg: 0, reg: '$edi' }, typeId:
+; PARSER_CGS_CSI-NEXT:   7854600665770582568 }
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+; ModuleID = 'test.c'
+source_filename = "test.c"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: noinline nounwind optnone uwtable
+define dso_local void @foo(i8 signext %a) !type !3 {
+entry:
+  ret void
+}
+
+; Function Attrs: noinline nounwind optnone uwtable
+define dso_local i32 @main() !type !4 {
+entry:
+  %retval = alloca i32, align 4
+  %fp = alloca void (i8)*, align 8
+  store i32 0, i32* %retval, align 4
+  store void (i8)* @foo, void (i8)** %fp, align 8
+  %0 = load void (i8)*, void (i8)** %fp, align 8
+  call void %0(i8 signext 97) [ "type"(metadata !"_ZTSFvcE.generalized") ]
+  ret i32 0
+}
+
+!llvm.module.flags = !{!0, !1, !2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 7, !"uwtable", i32 1}
+!2 = !{i32 7, !"frame-pointer", i32 2}
+!3 = !{i64 0, !"_ZTSFvcE.generalized"}
+!4 = !{i64 0, !"_ZTSFiE.generalized"}
diff --git a/llvm/test/CodeGen/MIR/X86/call-site-info-typeid.mir b/llvm/test/CodeGen/MIR/X86/call-site-info-typeid.mir
new file mode 100644
index 0000000..5ab797b
--- /dev/null
+++ b/llvm/test/CodeGen/MIR/X86/call-site-info-typeid.mir
@@ -0,0 +1,68 @@
+# Test MIR printer and parser for type id field in callSites. It is used
+# for propogating call site type identifiers to emit in the call graph section.
+
+# RUN: llc --call-graph-section %s -run-pass=none -o - | FileCheck %s
+# CHECK: name: main
+# CHECK: callSites:
+# CHECK-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+# CHECK-NEXT: 123456789 }
+
+--- |
+  ; ModuleID = 'test.ll'
+  source_filename = "test.ll"
+  target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+  target triple = "x86_64-unknown-linux-gnu"
+  
+  define dso_local void @foo(i8 signext %a) {
+  entry:
+    ret void
+  }
+  
+  define dso_local i32 @main() {
+  entry:
+    %retval = alloca i32, align 4
+    %fp = alloca void (i8)*, align 8
+    store i32 0, i32* %retval, align 4
+    store void (i8)* @foo, void (i8)** %fp, align 8
+    %0 = load void (i8)*, void (i8)** %fp, align 8
+    call void %0(i8 signext 97)
+    ret i32 0
+  }
+
+...
+---
+name:            foo
+tracksRegLiveness: true
+body:             |
+  bb.0.entry:
+    RET 0
+
+...
+---
+name:            main
+tracksRegLiveness: true
+stack:
+  - { id: 0, name: retval, type: default, offset: 0, size: 4, alignment: 4, 
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true, 
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: fp, type: default, offset: 0, size: 8, alignment: 8, 
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true, 
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:
+  - { bb: 0, offset: 6, fwdArgRegs: [], typeId: 
+    123456789 }
+body:             |
+  bb.0.entry:
+    MOV32mi %stack.0.retval, 1, $noreg, 0, $noreg, 0 :: (store (s32) into %ir.retval)
+    MOV64mi32 %stack.1.fp, 1, $noreg, 0, $noreg, @foo :: (store (s64) into %ir.fp)
+    %0:gr64 = MOV32ri64 @foo
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+    %1:gr32 = MOV32ri 97
+    $edi = COPY %1
+    CALL64r killed %0, csr_64, implicit $rsp, implicit $ssp, implicit $edi, implicit-def $rsp, implicit-def $ssp
+    ADJCALLSTACKUP64 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+    %2:gr32 = MOV32r0 implicit-def dead $eflags
+    $eax = COPY %2
+    RET 0, $eax
+
+...
diff --git a/llvm/test/CodeGen/Mips/call-site-info-typeid.ll b/llvm/test/CodeGen/Mips/call-site-info-typeid.ll
new file mode 100644
index 0000000..8596ebb
--- /dev/null
+++ b/llvm/test/CodeGen/Mips/call-site-info-typeid.ll
@@ -0,0 +1,39 @@
+; Tests that call site type ids can be extracted and set from type operand
+; bundles.
+
+; Verify the exact typeId value to ensure it is not garbage but the value
+; computed as the type id from the type operand bundle.
+; RUN: llc --call-graph-section -mtriple=mips-linux-gnu %s -stop-before=finalize-isel -o - | FileCheck %s
+
+; ModuleID = 'test.c'
+source_filename = "test.c"
+target datalayout = "E-m:m-p:32:32-i8:8:32-i16:16:32-i64:64-n32-S64"
+target triple = "mips-unknown-linux-gnu"
+
+define dso_local void @foo(i8 signext %a) !type !3 {
+entry:
+  ret void
+}
+
+; CHECK: name: main
+define dso_local i32 @main() !type !4 {
+entry:
+  %retval = alloca i32, align 4
+  %fp = alloca void (i8)*, align 8
+  store i32 0, i32* %retval, align 4
+  store void (i8)* @foo, void (i8)** %fp, align 8
+  %0 = load void (i8)*, void (i8)** %fp, align 8
+  ; CHECK: callSites:
+  ; CHECK-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+  ; CHECK-NEXT: 7854600665770582568 }
+  call void %0(i8 signext 97) [ "type"(metadata !"_ZTSFvcE.generalized") ]
+  ret i32 0
+}
+
+!llvm.module.flags = !{!0, !1, !2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 7, !"uwtable", i32 1}
+!2 = !{i32 7, !"frame-pointer", i32 2}
+!3 = !{i64 0, !"_ZTSFvcE.generalized"}
+!4 = !{i64 0, !"_ZTSFiE.generalized"}
diff --git a/llvm/test/CodeGen/X86/call-site-info-typeid.ll b/llvm/test/CodeGen/X86/call-site-info-typeid.ll
new file mode 100644
index 0000000..61777b7
--- /dev/null
+++ b/llvm/test/CodeGen/X86/call-site-info-typeid.ll
@@ -0,0 +1,39 @@
+; Tests that call site type ids can be extracted and set from type operand
+; bundles.
+
+; Verify the exact typeId value to ensure it is not garbage but the value
+; computed as the type id from the type operand bundle.
+; RUN: llc --call-graph-section -mtriple=x86_64-unknown-linux %s -stop-before=finalize-isel -o - | FileCheck %s
+
+; ModuleID = 'test.c'
+source_filename = "test.c"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define dso_local void @foo(i8 signext %a) !type !3 {
+entry:
+  ret void
+}
+
+; CHECK: name: main
+define dso_local i32 @main() !type !4 {
+entry:
+  %retval = alloca i32, align 4
+  %fp = alloca void (i8)*, align 8
+  store i32 0, i32* %retval, align 4
+  store void (i8)* @foo, void (i8)** %fp, align 8
+  %0 = load void (i8)*, void (i8)** %fp, align 8
+  ; CHECK: callSites:
+  ; CHECK-NEXT: - { bb: {{.*}}, offset: {{.*}}, fwdArgRegs: [], typeId:
+  ; CHECK-NEXT: 7854600665770582568 }
+  call void %0(i8 signext 97) [ "type"(metadata !"_ZTSFvcE.generalized") ]
+  ret i32 0
+}
+
+!llvm.module.flags = !{!0, !1, !2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 7, !"uwtable", i32 1}
+!2 = !{i32 7, !"frame-pointer", i32 2}
+!3 = !{i64 0, !"_ZTSFvcE.generalized"}
+!4 = !{i64 0, !"_ZTSFiE.generalized"}
diff --git a/llvm/test/Verifier/operand-bundles.ll b/llvm/test/Verifier/operand-bundles.ll
index db85b6a..7880064 100644
--- a/llvm/test/Verifier/operand-bundles.ll
+++ b/llvm/test/Verifier/operand-bundles.ll
@@ -105,4 +105,17 @@ declare ptr @objc_retainAutoreleasedReturnValue(ptr)
 declare ptr @objc_unsafeClaimAutoreleasedReturnValue(ptr)
 declare void @llvm.assume(i1)
 
+define void @f_type(i32* %ptr) {
+; CHECK: Multiple "type" operand bundles
+; CHECK-NEXT: call void @g() [ "type"(metadata !"_ZTSFvE.generalized"), "type"(metadata !"_ZTSFvE.generalized") ]
+; CHECK-NOT: call void @g() [ "type"(metadata !"_ZTSFvE.generalized") ]
+
+ entry:
+  %l = load i32, i32* %ptr
+  call void @g() [ "type"(metadata !"_ZTSFvE.generalized"), "type"(metadata !"_ZTSFvE.generalized") ]
+  call void @g() [ "type"(metadata !"_ZTSFvE.generalized") ]
+  %x = add i32 42, 1
+  ret void
+}
+
 attributes #0 = { noreturn }