[llvm-profgen] Read build ID from binary for perfscript address filtering

llvm/tools/llvm-profgen/ProfiledBinary.cpp

@@ -11,6 +11,8 @@
 #include "MissingFrameInferrer.h"
 #include "Options.h"
 #include "ProfileGenerator.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/BinaryFormat/Magic.h"
 #include "llvm/DebugInfo/PDB/IPDBSession.h"
 #include "llvm/DebugInfo/PDB/PDB.h"
 #include "llvm/DebugInfo/PDB/PDBSymbolFunc.h"
@@ -246,6 +248,19 @@ void ProfiledBinary::load() {
   // Find the preferred load address for text sections.
   setPreferredTextSegmentAddresses(Obj);
 
+  // For shared libraries, read build ID to filter perfscript addresses
+  // in [buildid:]addr format. Main executables (including PIE) use empty
+  // FilterBuildID since their addresses have no buildid prefix.
+  // Both PIE executables and shared libraries are ET_DYN, but only PIE
+  // executables have a PT_INTERP program header.
+  file_magic Magic;
+  if (auto EC = identify_magic(Path, Magic);
+      !EC && Magic == file_magic::elf_shared_object && !HasInterp) {
+    auto BID = object::getBuildID(Obj);
+    if (!BID.empty())
+      FilterBuildID = llvm::toHex(BID, /*LowerCase=*/true);
+  }
+
   // Load debug info of subprograms from DWARF section.
   // If path of debug info binary is specified, use the debug info from it,
   // otherwise use the debug info from the executable binary.
@@ -351,6 +366,8 @@ void ProfiledBinary::setPreferredTextSegmentAddresses(const ELFFile<ELFT> &Obj,
   // because we may build the tools on non-linux.
   uint64_t PageSize = 0x1000;
   for (const typename ELFT::Phdr &Phdr : PhdrRange) {
+    if (Phdr.p_type == ELF::PT_INTERP)
+      HasInterp = true;
     if (Phdr.p_type == ELF::PT_LOAD) {
       if (!FirstLoadableAddress)
         FirstLoadableAddress = Phdr.p_vaddr & ~(PageSize - 1U);

llvm/tools/llvm-profgen/ProfiledBinary.h

@@ -28,6 +28,7 @@
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/MCTargetOptions.h"
+#include "llvm/Object/BuildID.h"
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/ProfileData/SampleProf.h"
 #include "llvm/Support/CommandLine.h"
@@ -337,6 +338,16 @@ class ProfiledBinary {
 
   bool IsCOFF = false;
 
+  // Whether the binary has a PT_INTERP program header (PIE executables do,
+  // true shared libraries don't). Used to distinguish PIE from .so since
+  // both are ET_DYN.
+  bool HasInterp = false;
+
+  // Build ID used to filter perfscript addresses in [buildid:]addr format.
+  // For shared libraries, set to the binary's build ID.
+  // For main executables, kept empty (addresses have no buildid prefix).
+  std::string FilterBuildID;
+
   void setPreferredTextSegmentAddresses(const object::ObjectFile *O);
 
   // LLVMSymbolizer's symbolize{Code, Data} interfaces requires a section index
@@ -425,6 +436,9 @@ class ProfiledBinary {
 
   bool isCOFF() const { return IsCOFF; }
 
+  // Return the build ID used for filtering perfscript addresses.
+  StringRef getFilterBuildID() const { return FilterBuildID; }
+
   // Canonicalize to use preferred load address as base address.
   uint64_t canonicalizeVirtualAddress(uint64_t Address) {
     return Address - BaseAddress + getPreferredBaseAddress();