diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -576,7 +576,6 @@
   Options.ForceDwarfFrameSection = CodeGenOpts.ForceDwarfFrameSection;
   Options.EmitCallSiteInfo = CodeGenOpts.EmitCallSiteInfo;
   Options.EnableAIXExtendedAltivecABI = CodeGenOpts.EnableAIXExtendedAltivecABI;
-  Options.PseudoProbeForProfiling = CodeGenOpts.PseudoProbeForProfiling;
   Options.ValueTrackingVariableLocations =
       CodeGenOpts.ValueTrackingVariableLocations;
   Options.XRayOmitFunctionIndex = CodeGenOpts.XRayOmitFunctionIndex;
diff --git a/lld/ELF/Config.h b/lld/ELF/Config.h
--- a/lld/ELF/Config.h
+++ b/lld/ELF/Config.h
@@ -183,7 +183,6 @@
   bool ltoDebugPassManager;
   bool ltoEmitAsm;
   bool ltoNewPassManager;
-  bool ltoPseudoProbeForProfiling;
   bool ltoUniqueBasicBlockSectionNames;
   bool ltoWholeProgramVisibility;
   bool mergeArmExidx;
diff --git a/lld/ELF/Driver.cpp b/lld/ELF/Driver.cpp
--- a/lld/ELF/Driver.cpp
+++ b/lld/ELF/Driver.cpp
@@ -1084,8 +1084,6 @@
   config->ltoo = args::getInteger(args, OPT_lto_O, 2);
   config->ltoObjPath = args.getLastArgValue(OPT_lto_obj_path_eq);
   config->ltoPartitions = args::getInteger(args, OPT_lto_partitions, 1);
-  config->ltoPseudoProbeForProfiling =
-      args.hasArg(OPT_lto_pseudo_probe_for_profiling);
   config->ltoSampleProfile = args.getLastArgValue(OPT_lto_sample_profile);
   config->ltoBasicBlockSections =
       args.getLastArgValue(OPT_lto_basic_block_sections);
diff --git a/lld/ELF/LTO.cpp b/lld/ELF/LTO.cpp
--- a/lld/ELF/LTO.cpp
+++ b/lld/ELF/LTO.cpp
@@ -112,7 +112,6 @@
     }
   }
 
-  c.Options.PseudoProbeForProfiling = config->ltoPseudoProbeForProfiling;
   c.Options.UniqueBasicBlockSectionNames =
       config->ltoUniqueBasicBlockSectionNames;
 
diff --git a/lld/ELF/Options.td b/lld/ELF/Options.td
--- a/lld/ELF/Options.td
+++ b/lld/ELF/Options.td
@@ -574,8 +574,6 @@
 defm lto_whole_program_visibility: BB<"lto-whole-program-visibility",
   "Asserts that the LTO link has whole program visibility",
   "Asserts that the LTO link does not have whole program visibility">;
-def lto_pseudo_probe_for_profiling: F<"lto-pseudo-probe-for-profiling">,
-  HelpText<"Emit pseudo probes for sample profiling">;
 def disable_verify: F<"disable-verify">;
 defm mllvm: Eq<"mllvm", "Additional arguments to forward to LLVM's option processing">;
 def opt_remarks_filename: Separate<["--"], "opt-remarks-filename">,
@@ -651,8 +649,6 @@
 def: J<"plugin-opt=opt-remarks-hotness-threshold=">,
   Alias<opt_remarks_hotness_threshold>,
   HelpText<"Alias for --opt-remarks-hotness-threshold">;
-def: J<"plugin-opt=pseudo-probe-for-profiling">,
-  Alias<lto_pseudo_probe_for_profiling>, HelpText<"Alias for --lto-pseudo-probe-for-profiling">;
 def: J<"plugin-opt=sample-profile=">,
   Alias<lto_sample_profile>, HelpText<"Alias for --lto-sample-profile">;
 def: F<"plugin-opt=save-temps">, Alias<save_temps>, HelpText<"Alias for --save-temps">;
diff --git a/lld/test/ELF/lto/pseudo-probe-lto.ll b/lld/test/ELF/lto/pseudo-probe-lto.ll
--- a/lld/test/ELF/lto/pseudo-probe-lto.ll
+++ b/lld/test/ELF/lto/pseudo-probe-lto.ll
@@ -1,7 +1,6 @@
 ; REQUIRES: x86
 ; RUN: opt < %s -passes=pseudo-probe -function-sections -o %t.o
-; RUN: ld.lld %t.o -shared --lto-pseudo-probe-for-profiling --lto-emit-asm -o - | FileCheck %s
-; RUN: ld.lld %t.o -shared -plugin-opt=pseudo-probe-for-profiling --lto-emit-asm -o - | FileCheck %s
+; RUN: ld.lld %t.o -shared --lto-emit-asm -o - | FileCheck %s
 
 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-scei-ps4"
diff --git a/llvm/include/llvm/CodeGen/CommandFlags.h b/llvm/include/llvm/CodeGen/CommandFlags.h
--- a/llvm/include/llvm/CodeGen/CommandFlags.h
+++ b/llvm/include/llvm/CodeGen/CommandFlags.h
@@ -129,8 +129,6 @@
 
 bool getEnableDebugEntryValues();
 
-bool getPseudoProbeForProfiling();
-
 bool getValueTrackingVariableLocations();
 
 bool getForceDwarfFrameSection();
diff --git a/llvm/include/llvm/Target/TargetOptions.h b/llvm/include/llvm/Target/TargetOptions.h
--- a/llvm/include/llvm/Target/TargetOptions.h
+++ b/llvm/include/llvm/Target/TargetOptions.h
@@ -140,7 +140,7 @@
           EnableMachineFunctionSplitter(false), SupportsDefaultOutlining(false),
           EmitAddrsig(false), EmitCallSiteInfo(false),
           SupportsDebugEntryValues(false), EnableDebugEntryValues(false),
-          PseudoProbeForProfiling(false), ValueTrackingVariableLocations(false),
+          ValueTrackingVariableLocations(false),
           ForceDwarfFrameSection(false), XRayOmitFunctionIndex(false),
           DebugStrictDwarf(false),
           FPDenormalMode(DenormalMode::IEEE, DenormalMode::IEEE) {}
@@ -321,9 +321,6 @@
     /// production.
     bool ShouldEmitDebugEntryValues() const;
 
-    /// Emit pseudo probes into the binary for sample profiling
-    unsigned PseudoProbeForProfiling : 1;
-
     // When set to true, use experimental new debug variable location tracking,
     // which seeks to follow the values of variables rather than their location,
     // post isel.
diff --git a/llvm/lib/CodeGen/CommandFlags.cpp b/llvm/lib/CodeGen/CommandFlags.cpp
--- a/llvm/lib/CodeGen/CommandFlags.cpp
+++ b/llvm/lib/CodeGen/CommandFlags.cpp
@@ -90,7 +90,6 @@
 CGOPT(bool, EmitCallSiteInfo)
 CGOPT(bool, EnableMachineFunctionSplitter)
 CGOPT(bool, EnableDebugEntryValues)
-CGOPT(bool, PseudoProbeForProfiling)
 CGOPT(bool, ValueTrackingVariableLocations)
 CGOPT(bool, ForceDwarfFrameSection)
 CGOPT(bool, XRayOmitFunctionIndex)
@@ -434,11 +433,6 @@
       cl::init(false));
   CGBINDOPT(EnableDebugEntryValues);
 
-  static cl::opt<bool> PseudoProbeForProfiling(
-      "pseudo-probe-for-profiling", cl::desc("Emit pseudo probes for AutoFDO"),
-      cl::init(false));
-  CGBINDOPT(PseudoProbeForProfiling);
-
   static cl::opt<bool> ValueTrackingVariableLocations(
       "experimental-debug-variable-locations",
       cl::desc("Use experimental new value-tracking variable locations"),
@@ -540,7 +534,6 @@
   Options.EmitAddrsig = getEnableAddrsig();
   Options.EmitCallSiteInfo = getEmitCallSiteInfo();
   Options.EnableDebugEntryValues = getEnableDebugEntryValues();
-  Options.PseudoProbeForProfiling = getPseudoProbeForProfiling();
   Options.ValueTrackingVariableLocations = getValueTrackingVariableLocations();
   Options.ForceDwarfFrameSection = getForceDwarfFrameSection();
   Options.XRayOmitFunctionIndex = getXRayOmitFunctionIndex();
diff --git a/llvm/lib/CodeGen/PseudoProbeInserter.cpp b/llvm/lib/CodeGen/PseudoProbeInserter.cpp
--- a/llvm/lib/CodeGen/PseudoProbeInserter.cpp
+++ b/llvm/lib/CodeGen/PseudoProbeInserter.cpp
@@ -44,7 +44,14 @@
     MachineFunctionPass::getAnalysisUsage(AU);
   }
 
+  bool doInitialization(Module &M) override {
+    ShouldRun = M.getNamedMetadata(PseudoProbeDescMetadataName);
+    return false;
+  }
+
   bool runOnMachineFunction(MachineFunction &MF) override {
+    if (!ShouldRun)
+      return false;
     const TargetInstrInfo *TII = MF.getSubtarget().getInstrInfo();
     bool Changed = false;
     for (MachineBasicBlock &MBB : MF) {
@@ -129,6 +136,8 @@
       Name = SP->getName();
     return Function::getGUID(Name);
   }
+
+  bool ShouldRun = false;
 };
 } // namespace
 
diff --git a/llvm/lib/CodeGen/TargetPassConfig.cpp b/llvm/lib/CodeGen/TargetPassConfig.cpp
--- a/llvm/lib/CodeGen/TargetPassConfig.cpp
+++ b/llvm/lib/CodeGen/TargetPassConfig.cpp
@@ -1276,10 +1276,6 @@
   // Add passes that directly emit MI after all other MI passes.
   addPreEmitPass2();
 
-  // Insert pseudo probe annotation for callsite profiling
-  if (TM->Options.PseudoProbeForProfiling)
-    addPass(createPseudoProbeInserter());
-
   AddingMachinePasses = false;
 }
 
diff --git a/llvm/lib/Target/X86/X86TargetMachine.cpp b/llvm/lib/Target/X86/X86TargetMachine.cpp
--- a/llvm/lib/Target/X86/X86TargetMachine.cpp
+++ b/llvm/lib/Target/X86/X86TargetMachine.cpp
@@ -585,6 +585,9 @@
     addPass(createEHContGuardCatchretPass());
   }
   addPass(createX86LoadValueInjectionRetHardeningPass());
+
+  // Insert pseudo probe annotation for callsite profiling
+  addPass(createPseudoProbeInserter());
 }
 
 bool X86PassConfig::addPostFastRegAllocRewrite() {
diff --git a/llvm/test/CodeGen/X86/O0-pipeline.ll b/llvm/test/CodeGen/X86/O0-pipeline.ll
--- a/llvm/test/CodeGen/X86/O0-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O0-pipeline.ll
@@ -72,7 +72,8 @@
 ; CHECK-NEXT:       X86 Speculative Execution Side Effect Suppression
 ; CHECK-NEXT:       X86 Indirect Thunks
 ; CHECK-NEXT:       Check CFA info and insert CFI instructions if needed
-; CHECK-NEXT:       X86 Load Value Injection (LVI) Ret-Hardening
+; CHECK-NEXT:       X86 Load Value Injection (LVI) Ret-Hardening  
+; CHECK-NEXT:       Pseudo Probe Inserter
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
 ; CHECK-NEXT:       X86 Assembly Printer
diff --git a/llvm/test/CodeGen/X86/opt-pipeline.ll b/llvm/test/CodeGen/X86/opt-pipeline.ll
--- a/llvm/test/CodeGen/X86/opt-pipeline.ll
+++ b/llvm/test/CodeGen/X86/opt-pipeline.ll
@@ -200,6 +200,7 @@
 ; CHECK-NEXT:       X86 Indirect Thunks
 ; CHECK-NEXT:       Check CFA info and insert CFI instructions if needed
 ; CHECK-NEXT:       X86 Load Value Injection (LVI) Ret-Hardening
+; CHECK-NEXT:       Pseudo Probe Inserter
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
 ; CHECK-NEXT:       X86 Assembly Printer
diff --git a/llvm/test/Transforms/SampleProfile/pseudo-probe-dangle.ll b/llvm/test/Transforms/SampleProfile/pseudo-probe-dangle.ll
--- a/llvm/test/Transforms/SampleProfile/pseudo-probe-dangle.ll
+++ b/llvm/test/Transforms/SampleProfile/pseudo-probe-dangle.ll
@@ -1,9 +1,9 @@
 ; REQUIRES: x86_64-linux
 ; RUN: opt < %s -passes='pseudo-probe,jump-threading' -S -o %t
 ; RUN: FileCheck %s < %t --check-prefix=JT
-; RUN: llc -pseudo-probe-for-profiling -function-sections <%t -filetype=asm | FileCheck %s --check-prefix=ASM
+; RUN: llc  -function-sections <%t -filetype=asm | FileCheck %s --check-prefix=ASM
 ; RUN: opt < %s -passes='pseudo-probe' -S -o %t1
-; RUN: llc -pseudo-probe-for-profiling -stop-after=tailduplication <%t1 | FileCheck %s --check-prefix=MIR-tail
+; RUN: llc  -stop-after=tailduplication <%t1 | FileCheck %s --check-prefix=MIR-tail
 ; RUN: opt < %s -passes='pseudo-probe,simplifycfg' -S | FileCheck %s --check-prefix=SC
 
 declare i32 @f1()
diff --git a/llvm/test/Transforms/SampleProfile/pseudo-probe-emit-inline.ll b/llvm/test/Transforms/SampleProfile/pseudo-probe-emit-inline.ll
--- a/llvm/test/Transforms/SampleProfile/pseudo-probe-emit-inline.ll
+++ b/llvm/test/Transforms/SampleProfile/pseudo-probe-emit-inline.ll
@@ -1,9 +1,9 @@
 ; REQUIRES: x86_64-linux
 ; RUN: opt < %s -passes='pseudo-probe,cgscc(inline)' -function-sections -mtriple=x86_64-unknown-linux-gnu -S -o %t
 ; RUN: FileCheck %s < %t --check-prefix=CHECK-IL
-; RUN: llc -pseudo-probe-for-profiling -function-sections <%t -filetype=asm -o %t1
+; RUN: llc -function-sections <%t -filetype=asm -o %t1
 ; RUN: FileCheck %s < %t1 --check-prefix=CHECK-ASM
-; RUN: llc -pseudo-probe-for-profiling -function-sections <%t -filetype=obj -o %t2
+; RUN: llc -function-sections <%t -filetype=obj -o %t2
 ; RUN: llvm-objdump --section-headers  %t2 | FileCheck %s --check-prefix=CHECK-OBJ
 ; RUN: llvm-mc -filetype=asm <%t1 -o %t3
 ; RUN: FileCheck %s < %t3 --check-prefix=CHECK-ASM
diff --git a/llvm/test/Transforms/SampleProfile/pseudo-probe-emit.ll b/llvm/test/Transforms/SampleProfile/pseudo-probe-emit.ll
--- a/llvm/test/Transforms/SampleProfile/pseudo-probe-emit.ll
+++ b/llvm/test/Transforms/SampleProfile/pseudo-probe-emit.ll
@@ -1,10 +1,10 @@
 ; REQUIRES: x86_64-linux
 ; RUN: opt < %s -passes=pseudo-probe -function-sections -S -o %t
 ; RUN: FileCheck %s < %t --check-prefix=CHECK-IL
-; RUN: llc %t -pseudo-probe-for-profiling -stop-after=pseudo-probe-inserter -o - | FileCheck %s --check-prefix=CHECK-MIR
-; RUN: llc %t -pseudo-probe-for-profiling -function-sections -filetype=asm -o %t1
+; RUN: llc %t -stop-after=pseudo-probe-inserter -o - | FileCheck %s --check-prefix=CHECK-MIR
+; RUN: llc %t -function-sections -filetype=asm -o %t1
 ; RUN: FileCheck %s < %t1 --check-prefix=CHECK-ASM
-; RUN: llc %t -pseudo-probe-for-profiling -function-sections -filetype=obj -o %t2
+; RUN: llc %t -function-sections -filetype=obj -o %t2
 ; RUN: llvm-objdump --section-headers  %t2 | FileCheck %s --check-prefix=CHECK-OBJ
 ; RUN: llvm-mc %t1 -filetype=obj -o %t3
 ; RUN: llvm-objdump --section-headers  %t3 | FileCheck %s --check-prefix=CHECK-OBJ
diff --git a/llvm/test/Transforms/SampleProfile/pseudo-probe-instsched.ll b/llvm/test/Transforms/SampleProfile/pseudo-probe-instsched.ll
--- a/llvm/test/Transforms/SampleProfile/pseudo-probe-instsched.ll
+++ b/llvm/test/Transforms/SampleProfile/pseudo-probe-instsched.ll
@@ -1,5 +1,5 @@
 ; REQUIRES: x86_64-linux
-; RUN: llc < %s -mcpu=generic -mtriple=x86_64-- -pseudo-probe-for-profiling -O3 | FileCheck %s
+; RUN: llc < %s -mcpu=generic -mtriple=x86_64-- -O3 | FileCheck %s
 
 define float @foo(float %x) #0 {
   %tmp1 = fmul float %x, 3.000000e+00
diff --git a/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test b/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test
--- a/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test
+++ b/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test
@@ -20,5 +20,5 @@
 ; CHECK-NEXT:  !Attributes: 1
 
 ; truncated-pseudoprobe.perfbin is from the following compile commands:
-; llc -pseudo-probe-for-profiling truncated-pseudoprobe.ll -filetype=obj -o truncated-pseudoprobe.o
+; llc truncated-pseudoprobe.ll -filetype=obj -o truncated-pseudoprobe.o
 ; clang truncated-pseudoprobe.o -o truncated-pseudoprobe.perfbin