llvm · ZequanWu · Dec 14, 2023 · Oct 17, 2023 · Oct 18, 2023 · Oct 18, 2023
diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
@@ -42,6 +42,7 @@
 #include "llvm/Passes/PassBuilder.h"
 #include "llvm/Passes/PassPlugin.h"
 #include "llvm/Passes/StandardInstrumentations.h"
+#include "llvm/ProfileData/InstrProfCorrelator.h"
 #include "llvm/Support/BuryPointer.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/MemoryBuffer.h"
@@ -55,6 +56,7 @@
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/TargetParser/SubtargetFeature.h"
 #include "llvm/TargetParser/Triple.h"
+#include "llvm/Transforms/HipStdPar/HipStdPar.h"
 #include "llvm/Transforms/IPO/EmbedBitcodePass.h"
 #include "llvm/Transforms/IPO/LowerTypeTests.h"
 #include "llvm/Transforms/IPO/ThinLTOBitcodeWriter.h"
@@ -78,7 +80,6 @@
 #include "llvm/Transforms/Scalar/EarlyCSE.h"
 #include "llvm/Transforms/Scalar/GVN.h"
 #include "llvm/Transforms/Scalar/JumpThreading.h"
-#include "llvm/Transforms/HipStdPar/HipStdPar.h"
 #include "llvm/Transforms/Utils/Debugify.h"
 #include "llvm/Transforms/Utils/EntryExitInstrumenter.h"
 #include "llvm/Transforms/Utils/ModuleUtils.h"
@@ -98,13 +99,17 @@ extern cl::opt<bool> PrintPipelinePasses;
 static cl::opt<bool> ClSanitizeOnOptimizerEarlyEP(
     "sanitizer-early-opt-ep", cl::Optional,
     cl::desc("Insert sanitizers on OptimizerEarlyEP."), cl::init(false));
-}
+
+extern cl::opt<InstrProfCorrelator::ProfCorrelatorKind> ProfileCorrelate;
+} // namespace llvm
 
 namespace {
 
 // Default filename used for profile generation.
 std::string getDefaultProfileGenName() {
-  return DebugInfoCorrelate ? "default_%m.proflite" : "default_%m.profraw";
+  return DebugInfoCorrelate || ProfileCorrelate != InstrProfCorrelator::NONE
+             ? "default_%m.proflite"
+             : "default_%m.profraw";
 }
 
 class EmitAssemblyHelper {
@@ -197,7 +202,7 @@ class EmitAssemblyHelper {
   void EmitAssembly(BackendAction Action,
                     std::unique_ptr<raw_pwrite_stream> OS);
 };
-}
+} // namespace
 
 static SanitizerCoverageOptions
 getSancovOptsFromCGOpts(const CodeGenOptions &CGOpts) {

diff --git a/clang/lib/CodeGen/CoverageMappingGen.cpp b/clang/lib/CodeGen/CoverageMappingGen.cpp
@@ -31,6 +31,10 @@
 // is textually included.
 #define COVMAP_V3
 
+namespace llvm {
+extern cl::opt<InstrProfCorrelator::ProfCorrelatorKind> ProfileCorrelate;
+} // namespace llvm
+
 static llvm::cl::opt<bool> EmptyLineCommentCoverage(
     "emptyline-comment-coverage",
     llvm::cl::desc("Emit emptylines and comment lines as skipped regions (only "
@@ -1829,6 +1833,22 @@ void CoverageMappingModuleGen::emit() {
                              llvm::GlobalValue::InternalLinkage, NamesArrVal,
                              llvm::getCoverageUnusedNamesVarName());
   }
+  const StringRef VarName(INSTR_PROF_QUOTE(INSTR_PROF_RAW_VERSION_VAR));
+  llvm::Type *IntTy64 = llvm::Type::getInt64Ty(Ctx);
+  uint64_t ProfileVersion = INSTR_PROF_RAW_VERSION;
+  if (llvm::ProfileCorrelate == llvm::InstrProfCorrelator::BINARY)
+    ProfileVersion |= VARIANT_MASK_BIN_CORRELATE;
+  auto *VersionVariable = new llvm::GlobalVariable(
+      CGM.getModule(), llvm::Type::getInt64Ty(Ctx), true,
+      llvm::GlobalValue::WeakAnyLinkage,
+      llvm::Constant::getIntegerValue(IntTy64, llvm::APInt(64, ProfileVersion)),
+      VarName);
+  VersionVariable->setVisibility(llvm::GlobalValue::HiddenVisibility);
+  llvm::Triple TT(CGM.getModule().getTargetTriple());
+  if (TT.supportsCOMDAT()) {
+    VersionVariable->setLinkage(llvm::GlobalValue::ExternalLinkage);
+    VersionVariable->setComdat(CGM.getModule().getOrInsertComdat(VarName));
+  }
 }
 
 unsigned CoverageMappingModuleGen::getFileID(FileEntryRef File) {

diff --git a/clang/test/CodeGen/coverage-profile-raw-version.c b/clang/test/CodeGen/coverage-profile-raw-version.c
@@ -0,0 +1,9 @@
+// RUN: %clang_cc1  -fprofile-instrument=clang -fcoverage-mapping -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -mllvm -profile-correlate=binary -fprofile-instrument=clang -fcoverage-mapping -emit-llvm -o - %s | FileCheck %s --check-prefix=BIN-CORRELATE
+
+// CHECK: @__llvm_profile_raw_version = {{.*}} i64 9
+// BIN-CORRELATE: @__llvm_profile_raw_version = {{.*}} i64 4294967305
+
+int main() {
+    return 0;
+}
diff --git a/compiler-rt/include/profile/InstrProfData.inc b/compiler-rt/include/profile/InstrProfData.inc
@@ -665,6 +665,7 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
  * version for other variants of profile. We set the 8th most significant bit 
  * (i.e. bit 56) to 1 to indicate if this is an IR-level instrumentation
  * generated profile, and 0 if this is a Clang FE generated profile.
+ * 1 in bit 32 indicates there is no profile name and data sections.
  * 1 in bit 57 indicates there are context-sensitive records in the profile.
  * The 59th bit indicates whether to use debug info to correlate profiles.
  * The 60th bit indicates single byte coverage instrumentation.
@@ -674,6 +675,7 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
  */
 #define VARIANT_MASKS_ALL 0xffffffff00000000ULL
 #define GET_VERSION(V) ((V) & ~VARIANT_MASKS_ALL)
+#define VARIANT_MASK_BIN_CORRELATE (0x1ULL << 32)
 #define VARIANT_MASK_IR_PROF (0x1ULL << 56)
 #define VARIANT_MASK_CSIR_PROF (0x1ULL << 57)
 #define VARIANT_MASK_INSTR_ENTRY (0x1ULL << 58)

diff --git a/compiler-rt/lib/profile/InstrProfiling.c b/compiler-rt/lib/profile/InstrProfiling.c
@@ -91,5 +91,6 @@ COMPILER_RT_VISIBILITY void __llvm_profile_reset_counters(void) {
 }
 
 COMPILER_RT_VISIBILITY int __llvm_profile_has_correlation() {
-  return (__llvm_profile_get_version() & VARIANT_MASK_DBG_CORRELATE) != 0ULL;
+  return (__llvm_profile_get_version() & VARIANT_MASK_DBG_CORRELATE) != 0ULL ||
+         (__llvm_profile_get_version() & VARIANT_MASK_BIN_CORRELATE) != 0ULL;
 }
diff --git a/compiler-rt/lib/profile/InstrProfiling.h b/compiler-rt/lib/profile/InstrProfiling.h
@@ -272,6 +272,9 @@ uint64_t __llvm_profile_get_num_data(const __llvm_profile_data *Begin,
 uint64_t __llvm_profile_get_data_size(const __llvm_profile_data *Begin,
                                       const __llvm_profile_data *End);
 
+/*! \brief Get the size of the profile name section in bytes. */
+uint64_t __llvm_profile_get_name_size(const char *Begin, const char *End);
+
 /*! \brief Get the size in bytes of a single counter entry. */
 size_t __llvm_profile_counter_entry_size(void);
 

diff --git a/compiler-rt/lib/profile/InstrProfilingPlatformWindows.c b/compiler-rt/lib/profile/InstrProfilingPlatformWindows.c
@@ -13,13 +13,13 @@
 
 #if defined(_MSC_VER)
 /* Merge read-write sections into .data. */
-#pragma comment(linker, "/MERGE:.lprfc=.data")
 #pragma comment(linker, "/MERGE:.lprfb=.data")
-#pragma comment(linker, "/MERGE:.lprfd=.data")
 #pragma comment(linker, "/MERGE:.lprfv=.data")
 #pragma comment(linker, "/MERGE:.lprfnd=.data")
 /* Do *NOT* merge .lprfn and .lcovmap into .rdata. llvm-cov must be able to find
  * after the fact.
+ * Do *NOT* merge .lprfc and lprfd into .rdata. When binary profile correlation
+ * is enabled, llvm-profdata must be able to find after the fact.
  */
 
 /* Allocate read-only section bounds. */

diff --git a/compiler-rt/test/CMakeLists.txt b/compiler-rt/test/CMakeLists.txt
@@ -37,8 +37,9 @@ if(NOT ANDROID)
   if(NOT COMPILER_RT_STANDALONE_BUILD AND NOT LLVM_RUNTIMES_BUILD)
     # Use LLVM utils and Clang from the same build tree.
     list(APPEND SANITIZER_COMMON_LIT_TEST_DEPS
-      clang clang-resource-headers FileCheck count not llvm-config llvm-nm llvm-objdump
-      llvm-readelf llvm-readobj llvm-size llvm-symbolizer compiler-rt-headers sancov split-file)
+      clang clang-resource-headers FileCheck count not llvm-config llvm-nm 
+      llvm-objdump llvm-readelf llvm-readobj llvm-size llvm-symbolizer 
+      compiler-rt-headers sancov split-file llvm-strip)
     if (WIN32)
       list(APPEND SANITIZER_COMMON_LIT_TEST_DEPS KillTheDoctor)
     endif()

diff --git a/compiler-rt/test/profile/Darwin/instrprof-debug-info-correlate.c b/compiler-rt/test/profile/Darwin/instrprof-debug-info-correlate.c
@@ -1,5 +1,5 @@
 // Value profiling is currently not supported in lightweight mode.
-// RUN: %clang_pgogen -o %t -g -mllvm --debug-info-correlate -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: %clang_pgogen -o %t -g -mllvm --profile-correlate=debug-info -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
 // RUN: env LLVM_PROFILE_FILE=%t.proflite %run %t
 // RUN: llvm-profdata merge -o %t.profdata --debug-info=%t.dSYM %t.proflite
 
@@ -9,7 +9,7 @@
 
 // RUN: diff <(llvm-profdata show --all-functions --counts %t.normal.profdata) <(llvm-profdata show --all-functions --counts %t.profdata)
 
-// RUN: %clang_pgogen -o %t.cov -g -mllvm --debug-info-correlate -mllvm -pgo-function-entry-coverage -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: %clang_pgogen -o %t.cov -g -mllvm --profile-correlate=debug-info -mllvm -pgo-function-entry-coverage -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
 // RUN: env LLVM_PROFILE_FILE=%t.cov.proflite %run %t.cov
 // RUN: llvm-profdata merge -o %t.cov.profdata --debug-info=%t.cov.dSYM %t.cov.proflite
 

diff --git a/compiler-rt/test/profile/Linux/instrprof-debug-info-correlate-warnings.c b/compiler-rt/test/profile/Linux/instrprof-debug-info-correlate-warnings.c
@@ -1,6 +1,6 @@
 // Disable full debug info and verify that we get warnings during merging
 
-// RUN: %clang_pgogen -o %t -gline-tables-only -mllvm --debug-info-correlate -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: %clang_pgogen -o %t -gline-tables-only -mllvm --profile-correlate=debug-info -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
 // RUN: env LLVM_PROFILE_FILE=%t.proflite %run %t
 // RUN: llvm-profdata merge -o %t.profdata --debug-info=%t %t.proflite --max-debug-info-correlation-warnings=2 2>&1 >/dev/null | FileCheck %s --check-prefixes=CHECK,LIMIT --implicit-check-not=warning
 // RUN: llvm-profdata merge -o %t.profdata --debug-info=%t %t.proflite --max-debug-info-correlation-warnings=0 2>&1 >/dev/null | FileCheck %s --check-prefixes=CHECK,NOLIMIT --implicit-check-not=warning

diff --git a/compiler-rt/test/profile/Linux/instrprof-debug-info-correlate.c b/compiler-rt/test/profile/Linux/instrprof-debug-info-correlate.c
@@ -3,19 +3,19 @@
 // RUN: env LLVM_PROFILE_FILE=%t.profraw %run %t.normal
 // RUN: llvm-profdata merge -o %t.normal.profdata %t.profraw
 
-// RUN: %clang_pgogen -o %t.d4 -g -gdwarf-4 -mllvm --debug-info-correlate -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: %clang_pgogen -o %t.d4 -g -gdwarf-4 -mllvm --profile-correlate=debug-info -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
 // RUN: env LLVM_PROFILE_FILE=%t.d4.proflite %run %t.d4
 // RUN: llvm-profdata merge -o %t.d4.profdata --debug-info=%t.d4 %t.d4.proflite
 
 // RUN: diff <(llvm-profdata show --all-functions --counts %t.normal.profdata) <(llvm-profdata show --all-functions --counts %t.d4.profdata)
 
-// RUN: %clang_pgogen -o %t -g -mllvm --debug-info-correlate -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: %clang_pgogen -o %t -g -mllvm --profile-correlate=debug-info -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
 // RUN: env LLVM_PROFILE_FILE=%t.proflite %run %t
 // RUN: llvm-profdata merge -o %t.profdata --debug-info=%t %t.proflite
 
 // RUN: diff <(llvm-profdata show --all-functions --counts %t.normal.profdata) <(llvm-profdata show --all-functions --counts %t.profdata)
 
-// RUN: %clang_pgogen -o %t.cov -g -mllvm --debug-info-correlate -mllvm -pgo-function-entry-coverage -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: %clang_pgogen -o %t.cov -g -mllvm --profile-correlate=debug-info -mllvm -pgo-function-entry-coverage -mllvm --disable-vp=true %S/../Inputs/instrprof-debug-info-correlate-main.cpp %S/../Inputs/instrprof-debug-info-correlate-foo.cpp
 // RUN: env LLVM_PROFILE_FILE=%t.cov.proflite %run %t.cov
 // RUN: llvm-profdata merge -o %t.cov.profdata --debug-info=%t.cov %t.cov.proflite
 

diff --git a/compiler-rt/test/profile/Linux/instrprof-show-debug-info-correlation.c b/compiler-rt/test/profile/Linux/instrprof-show-debug-info-correlation.c
@@ -1,8 +1,8 @@
-// RUN: %clang_pgogen -o %t -g -mllvm --debug-info-correlate -mllvm --disable-vp=true %s
+// RUN: %clang_pgogen -o %t -g -mllvm --profile-correlate=debug-info -mllvm --disable-vp=true %s
 // RUN: llvm-profdata show --debug-info=%t --detailed-summary --show-prof-sym-list | FileCheck %s
 // RUN: llvm-profdata show --debug-info=%t --show-format=yaml | FileCheck %s --match-full-lines --check-prefix YAML
 
-// RUN: %clang_pgogen -o %t.no.dbg -mllvm --debug-info-correlate -mllvm --disable-vp=true %s
+// RUN: %clang_pgogen -o %t.no.dbg -mllvm --profile-correlate=debug-info -mllvm --disable-vp=true %s
 // RUN: not llvm-profdata show --debug-info=%t.no.dbg 2>&1 | FileCheck %s --check-prefix NO-DBG
 // NO-DBG: unable to correlate profile: could not find any profile data metadata in correlated file
 

diff --git a/compiler-rt/test/profile/instrprof-binary-correlate.c b/compiler-rt/test/profile/instrprof-binary-correlate.c
@@ -0,0 +1,46 @@
+// REQUIRES: linux || windows
+// Default
+// RUN: %clang -o %t.normal -fprofile-instr-generate -fcoverage-mapping -fuse-ld=lld %S/Inputs/instrprof-debug-info-correlate-main.cpp %S/Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: env LLVM_PROFILE_FILE=%t.profraw %run %t.normal
+// RUN: llvm-profdata merge -o %t.normal.profdata %t.profraw
+// RUN: llvm-cov report --instr-profile=%t.normal.profdata %t.normal > %t.normal.report
+// RUN: llvm-cov show --instr-profile=%t.normal.profdata %t.normal > %t.normal.show
+
+// With -profile-correlate=binary flag
+// RUN: %clang -o %t-1.exe -fprofile-instr-generate -fcoverage-mapping -mllvm -profile-correlate=binary -fuse-ld=lld %S/Inputs/instrprof-debug-info-correlate-main.cpp %S/Inputs/instrprof-debug-info-correlate-foo.cpp
+// RUN: env LLVM_PROFILE_FILE=%t-1.profraw %run %t-1.exe
+// RUN: llvm-profdata merge -o %t-1.profdata --binary-file=%t-1.exe %t-1.profraw
+// RUN: llvm-cov report --instr-profile=%t-1.profdata %t-1.exe > %t-1.report
+// RUN: llvm-cov show --instr-profile=%t-1.profdata %t-1.exe > %t-1.show
+// RUN: diff %t.normal.profdata %t-1.profdata
+// RUN: diff %t.normal.report %t-1.report
+// RUN: diff %t.normal.show %t-1.show
+
+// Strip above binary and run
+// RUN: llvm-strip %t-1.exe -o %t-2.exe
+// RUN: env LLVM_PROFILE_FILE=%t-2.profraw %run %t-2.exe
+// RUN: llvm-profdata merge -o %t-2.profdata --binary-file=%t-1.exe %t-2.profraw
+// RUN: llvm-cov report --instr-profile=%t-2.profdata %t-1.exe > %t-2.report
+// RUN: llvm-cov show --instr-profile=%t-2.profdata %t-1.exe > %t-2.show
+// RUN: diff %t.normal.profdata %t-2.profdata
+// RUN: diff %t.normal.report %t-2.report
+// RUN: diff %t.normal.show %t-2.show
+
+// Online merging.
+// RUN: env LLVM_PROFILE_FILE=%t-3.profraw %run %t.normal
+// RUN: env LLVM_PROFILE_FILE=%t-4.profraw %run %t.normal
+// RUN: llvm-profdata merge -o %t.normal.merged.profdata %t-3.profraw %t-4.profraw
+// RUN: llvm-cov report --instr-profile=%t.normal.merged.profdata %t.normal > %t.normal.merged.report
+// RUN: llvm-cov show --instr-profile=%t.normal.merged.profdata %t.normal > %t.normal.merged.show
+
+// RUN: rm -rf %t.profdir && mkdir %t.profdir
+// RUN: env LLVM_PROFILE_FILE=%t.profdir/%m-4.profraw %run %t-2.exe
+// RUN: env LLVM_PROFILE_FILE=%t.profdir/%m-4.profraw %run %t-2.exe
+// RUN: llvm-profdata merge -o %t-4.profdata --binary-file=%t-1.exe  %t.profdir
+// RUN: llvm-cov report --instr-profile=%t-4.profdata %t-1.exe > %t-4.report
+// RUN: llvm-cov show --instr-profile=%t-4.profdata %t-1.exe > %t-4.show
+// RUN: diff %t.normal.merged.profdata %t-4.profdata
+// RUN: diff %t.normal.merged.report %t-4.report
+// RUN: diff %t.normal.merged.show %t-4.show
+
+// TODO: After adding support for binary ID, test binaries with different binary IDs.
diff --git a/llvm/docs/CommandGuide/llvm-profdata.rst b/llvm/docs/CommandGuide/llvm-profdata.rst
@@ -195,8 +195,14 @@ OPTIONS
 .. option:: --debug-info=<path>
 
  Specify the executable or ``.dSYM`` that contains debug info for the raw profile.
- When ``-debug-info-correlate`` was used for instrumentation, use this option
- to correlate the raw profile.
+ When ``-profile-correlate=debug-info`` was used for instrumentation, use this
+ option to correlate the raw profile.
+
+.. option:: --binary-file=<path>
+
+ Specify the executable that contains profile data and profile name sections for
+ the raw profile. When ``-profile-correlate=binary`` was used for
+ instrumentation, use this option to correlate the raw profile.
 
 .. option:: --temporal-profile-trace-reservoir-size
 
@@ -346,8 +352,8 @@ OPTIONS
 .. option:: --debug-info=<path>
 
  Specify the executable or ``.dSYM`` that contains debug info for the raw profile.
- When ``-debug-info-correlate`` was used for instrumentation, use this option
- to show the correlated functions from the raw profile.
+ When ``-profile-correlate=debug-info`` was used for instrumentation, use this 
+ option to show the correlated functions from the raw profile.
 
 .. option:: --covered
 

diff --git a/llvm/include/llvm/ProfileData/InstrProf.h b/llvm/include/llvm/ProfileData/InstrProf.h
@@ -334,8 +334,8 @@ enum class instrprof_error {
   too_large,
   truncated,
   malformed,
-  missing_debug_info_for_correlation,
-  unexpected_debug_info_for_correlation,
+  missing_correlation_info,
+  unexpected_correlation_info,
   unable_to_correlate_profile,
   unknown_function,
   invalid_prof,
@@ -468,7 +468,7 @@ class InstrProfSymtab {
   /// only initialize the symtab with reference to the data and
   /// the section base address. The decompression will be delayed
   /// until before it is used. See also \c create(StringRef) method.
-  Error create(object::SectionRef &Section);
+  Error create(object::SectionRef &Section, bool MightHasNullByte = false);
 
   /// This interface is used by reader of CoverageMapping test
   /// format.