diff --git a/clang/test/CodeGen/pseudo-probe-emit.c b/clang/test/CodeGen/pseudo-probe-emit.c
--- a/clang/test/CodeGen/pseudo-probe-emit.c
+++ b/clang/test/CodeGen/pseudo-probe-emit.c
@@ -1,3 +1,4 @@
+// RUN: %clang_cc1 -O0 -fno-legacy-pass-manager -fpseudo-probe-for-profiling -debug-info-kind=limited -emit-llvm -o - %s | FileCheck %s
 // RUN: %clang_cc1 -O2 -fno-legacy-pass-manager -fpseudo-probe-for-profiling -debug-info-kind=limited -emit-llvm -o - %s | FileCheck %s
 
 // Check the generation of pseudoprobe intrinsic call
diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -1924,6 +1924,13 @@
 
   ModulePassManager MPM;
 
+  // Perform pseudo probe instrumentation in O0 mode. This is for the
+  // consistency between different build modes. For example, a LTO build can be
+  // mixed with an O0 prelink and an O2 postlink. Loading a sample profile in
+  // the postlink will require pseudo probe instrumentation in the prelink.
+  if (PGOOpt && PGOOpt->PseudoProbeForProfiling)
+    MPM.addPass(SampleProfileProbePass(TM));
+
   if (PGOOpt && (PGOOpt->Action == PGOOptions::IRInstr ||
                  PGOOpt->Action == PGOOptions::IRUse))
     addPGOInstrPassesForO0(
diff --git a/llvm/tools/llvm-profgen/PerfReader.cpp b/llvm/tools/llvm-profgen/PerfReader.cpp
--- a/llvm/tools/llvm-profgen/PerfReader.cpp
+++ b/llvm/tools/llvm-profgen/PerfReader.cpp
@@ -7,15 +7,23 @@
 //===----------------------------------------------------------------------===//
 #include "PerfReader.h"
 #include "ProfileGenerator.h"
+#include "llvm/ADT/Statistic.h"
 #include "llvm/Support/FileSystem.h"
 
+#define DEBUG_TYPE "perf-reader"
+
+STATISTIC(NumStackSamplesWithInvalidReturnAddress,
+          "Number of stack samples with an invalid return address");
+
+STATISTIC(NumStackSamples, "Number of stack samples");
+
 static cl::opt<bool> ShowMmapEvents("show-mmap-events", cl::ReallyHidden,
                                     cl::init(false), cl::ZeroOrMore,
                                     cl::desc("Print binary load events."));
 
 cl::opt<bool> SkipSymbolization("skip-symbolization", cl::ReallyHidden,
                                 cl::init(false), cl::ZeroOrMore,
-                                cl::desc("Dump the unsumbolized profile to the "
+                                cl::desc("Dump the unsymbolized profile to the "
                                          "output file. It will show unwinder "
                                          "output for CS profile generation."));
 
@@ -510,15 +518,24 @@
     if (!Binary->addressIsCode(FrameAddr))
       break;
 
-    // We need to translate return address to call address
-    // for non-leaf frames
+    // We need to translate return address to call address for non-leaf frames.
     if (!CallStack.empty()) {
-      FrameAddr = Binary->getCallAddrFromFrameAddr(FrameAddr);
+      auto I = Binary->getIndexForAddr(FrameAddr);
+      FrameAddr = I ? Binary->getAddressforIndex(I - 1) : 0;
+      // Stop at an invalid return address caused by bad unwinding. This could
+      // happen to frame-pointer-based unwinding and the callee functions that
+      // do not have the frame pointer chain set up.
+      if (!FrameAddr || !Binary->addressIsCall(FrameAddr)) {
+        NumStackSamplesWithInvalidReturnAddress++;
+        break;
+      }
     }
 
     CallStack.emplace_back(FrameAddr);
   }
 
+  NumStackSamples++;
+
   // Skip other unrelated line, find the next valid LBR line
   // Note that even for empty call stack, we should skip the address at the
   // bottom, otherwise the following pass may generate a truncated callstack