[InstrProfiling] Generate runtime hook for ELF platforms

When using -fprofile-list to selectively apply instrumentation only
to certain files or functions, we may end up with a binary that doesn't
have any counters in the case where no files were selected. However,
because on Linux and Fuchsia, we pass -u__llvm_profile_runtime, the
runtime would still be pulled in and incur some non-trivial overhead,
especially in the case when the continuous or runtime counter relocation
mode is being used. A better way would be to pull in the profile runtime
only when needed by declaring the __llvm_profile_runtime symbol in the
translation unit only when needed.

This approach was already used prior to 9a041a7, but we changed it
to always generate the __llvm_profile_runtime due to a TAPI limitation.
Since TAPI is only used on Mach-O platforms, we could use the early
emission of __llvm_profile_runtime there, and on other platforms we
could change back to the earlier approach where the symbol is generated
later only when needed. We can stop passing -u__llvm_profile_runtime to
the linker on Linux and Fuchsia since the generated undefined symbol in
each translation unit that needed it serves the same purpose.

Differential Revision: https://reviews.llvm.org/D98061

Author: petrhosek

clang/docs/UsersManual.rst

@@ -2301,6 +2301,14 @@ In these cases, you can use the flag ``-fno-profile-instr-generate`` (or
 Note that these flags should appear after the corresponding profile
 flags to have an effect.
 
+.. note::
+
+  When none of the translation units inside a binary is instrumented, in the
+  case of ELF and COFF binary format the profile runtime will not be linked
+  into the binary and no profile will be produced, while in the case of Mach-O
+  the profile runtime will be linked and profile will be produced but there
+  will not be any counters.
+
 Instrumenting only selected files or functions
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

clang/lib/Driver/ToolChains/Fuchsia.cpp

@@ -394,13 +394,3 @@ SanitizerMask Fuchsia::getDefaultSanitizers() const {
   }
   return Res;
 }
-
-void Fuchsia::addProfileRTLibs(const llvm::opt::ArgList &Args,
-                               llvm::opt::ArgStringList &CmdArgs) const {
-  // Add linker option -u__llvm_profile_runtime to cause runtime
-  // initialization module to be linked in.
-  if (needsProfileRT(Args))
-    CmdArgs.push_back(Args.MakeArgString(
-        Twine("-u", llvm::getInstrProfRuntimeHookVarName())));
-  ToolChain::addProfileRTLibs(Args, CmdArgs);
-}

clang/lib/Driver/ToolChains/Fuchsia.h

@@ -71,9 +71,6 @@ class LLVM_LIBRARY_VISIBILITY Fuchsia : public ToolChain {
   SanitizerMask getSupportedSanitizers() const override;
   SanitizerMask getDefaultSanitizers() const override;
 
-  void addProfileRTLibs(const llvm::opt::ArgList &Args,
-                        llvm::opt::ArgStringList &CmdArgs) const override;
-
   RuntimeLibType
   GetRuntimeLibType(const llvm::opt::ArgList &Args) const override;
   CXXStdlibType

clang/lib/Driver/ToolChains/Linux.cpp

@@ -925,16 +925,6 @@ SanitizerMask Linux::getSupportedSanitizers() const {
   return Res;
 }
 
-void Linux::addProfileRTLibs(const llvm::opt::ArgList &Args,
-                             llvm::opt::ArgStringList &CmdArgs) const {
-  // Add linker option -u__llvm_profile_runtime to cause runtime
-  // initialization module to be linked in.
-  if (needsProfileRT(Args))
-    CmdArgs.push_back(Args.MakeArgString(
-        Twine("-u", llvm::getInstrProfRuntimeHookVarName())));
-  ToolChain::addProfileRTLibs(Args, CmdArgs);
-}
-
 llvm::DenormalMode
 Linux::getDefaultDenormalModeForType(const llvm::opt::ArgList &DriverArgs,
                                      const JobAction &JA,

clang/lib/Driver/ToolChains/Linux.h

@@ -43,8 +43,6 @@ class LLVM_LIBRARY_VISIBILITY Linux : public Generic_ELF {
   bool isNoExecStackDefault() const override;
   bool IsMathErrnoDefault() const override;
   SanitizerMask getSupportedSanitizers() const override;
-  void addProfileRTLibs(const llvm::opt::ArgList &Args,
-                        llvm::opt::ArgStringList &CmdArgs) const override;
   std::string computeSysRoot() const override;
 
   std::string getDynamicLinker(const llvm::opt::ArgList &Args) const override;

clang/test/Driver/coverage-ld.c

@@ -12,9 +12,7 @@
 // RUN:     --sysroot=%S/Inputs/basic_linux_tree \
 // RUN:   | FileCheck --check-prefix=CHECK-LINUX-I386 %s
 //
-// CHECK-LINUX-I386-NOT: "-u__llvm_profile_runtime"
 // CHECK-LINUX-I386: /Inputs/resource_dir{{/|\\\\}}lib{{/|\\\\}}linux{{/|\\\\}}libclang_rt.profile-i386.a"
-// CHECK-LINUX-I386-NOT: "-u__llvm_profile_runtime"
 // CHECK-LINUX-I386: "-lc"
 //
 // RUN: %clang -no-canonical-prefixes %s -### -o %t.o 2>&1 \

clang/test/Driver/fuchsia.c

@@ -249,7 +249,6 @@
 // RUN:     -fuse-ld=lld 2>&1 \
 // RUN:     | FileCheck %s -check-prefix=CHECK-PROFRT-AARCH64
 // CHECK-PROFRT-AARCH64: "-resource-dir" "[[RESOURCE_DIR:[^"]+]]"
-// CHECK-PROFRT-AARCH64: "-u__llvm_profile_runtime"
 // CHECK-PROFRT-AARCH64: "[[RESOURCE_DIR]]{{/|\\\\}}lib{{/|\\\\}}aarch64-fuchsia{{/|\\\\}}libclang_rt.profile.a"
 
 // RUN: %clang %s -### --target=x86_64-fuchsia \
@@ -258,5 +257,4 @@
 // RUN:     -fuse-ld=lld 2>&1 \
 // RUN:     | FileCheck %s -check-prefix=CHECK-PROFRT-X86_64
 // CHECK-PROFRT-X86_64: "-resource-dir" "[[RESOURCE_DIR:[^"]+]]"
-// CHECK-PROFRT-X86_64: "-u__llvm_profile_runtime"
 // CHECK-PROFRT-X86_64: "[[RESOURCE_DIR]]{{/|\\\\}}lib{{/|\\\\}}x86_64-fuchsia{{/|\\\\}}libclang_rt.profile.a"

llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp

@@ -543,8 +543,10 @@ bool InstrProfiling::run(
   UsedVars.clear();
   TT = Triple(M.getTargetTriple());
 
-  // Emit the runtime hook even if no counters are present.
-  bool MadeChange = emitRuntimeHook();
+  bool MadeChange = false;
+  // Emit the runtime hook even if no counters are present in Mach-O.
+  if (TT.isOSBinFormatMachO())
+    MadeChange = emitRuntimeHook();
 
   // Improve compile time by avoiding linear scans when there is no work.
   GlobalVariable *CoverageNamesVar =
@@ -584,6 +586,8 @@ bool InstrProfiling::run(
   emitVNodes();
   emitNameData();
   emitRegistration();
+  if (!TT.isOSBinFormatMachO())
+    emitRuntimeHook();
   emitUses();
   emitInitialization();
   return true;
@@ -1058,11 +1062,6 @@ void InstrProfiling::emitRegistration() {
 }
 
 bool InstrProfiling::emitRuntimeHook() {
-  // We expect the linker to be invoked with -u<hook_var> flag for Linux or
-  // Fuchsia, in which case there is no need to emit the user function.
-  if (TT.isOSLinux() || TT.isOSFuchsia())
-    return false;
-
   // If the module's provided its own runtime, we don't need to do anything.
   if (M->getGlobalVariable(getInstrProfRuntimeHookVarName()))
     return false;

llvm/test/Instrumentation/InstrProfiling/linkage.ll

@@ -10,7 +10,6 @@
 ; RUN: opt < %s  -mtriple=x86_64-pc-win32-coff -passes=instrprof -S | FileCheck %s --check-prefixes=COFF
 
 ; MACHO: @__llvm_profile_runtime = external global i32
-; ELF-NOT: @__llvm_profile_runtime = external global i32
 
 ; ELF: $__profd_foo = comdat noduplicates
 ; ELF: $__profd_foo_weak = comdat noduplicates

llvm/test/Instrumentation/InstrProfiling/profiling.ll

@@ -1,14 +1,11 @@
 ; RUN: opt < %s -mtriple=x86_64 -passes=instrprof -S | FileCheck %s --check-prefixes=CHECK,ELF,ELF_GENERIC
 ; RUN: opt < %s -mtriple=x86_64-linux -passes=instrprof -S | FileCheck %s --check-prefixes=CHECK,ELF_LINUX
 ; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -passes=instrprof -S | FileCheck %s --check-prefixes=CHECK,MACHO
-; RUN: opt < %s -mtriple=x86_64-windows -passes=instrprof -S | FileCheck %s --check-prefixes=CHECK,WIN
+; RUN: opt < %s -mtriple=x86_64-windows -passes=instrprof -S | FileCheck %s --check-prefixes=CHECK,COFF
 
 ; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -instrprof -S | FileCheck %s
 
-; ELF_GENERIC: @__llvm_profile_runtime = external global i32
-; ELF_LINUX-NOT: @__llvm_profile_runtime
 ; MACHO: @__llvm_profile_runtime = external global i32
-; WIN: @__llvm_profile_runtime = external global i32
 
 @__profn_foo = hidden constant [3 x i8] c"foo"
 ; CHECK-NOT: __profn_foo
@@ -21,8 +18,8 @@
 ; ELF:   @__profd_foo = hidden {{.*}}, section "__llvm_prf_data", comdat, align 8
 ; MACHO: @__profc_foo = hidden global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
 ; MACHO: @__profd_foo = hidden {{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
-; WIN:   @__profc_foo = internal global [1 x i64] zeroinitializer, section ".lprfc$M", align 8
-; WIN:   @__profd_foo = internal {{.*}}, section ".lprfd$M", align 8
+; COFF:   @__profc_foo = internal global [1 x i64] zeroinitializer, section ".lprfc$M", align 8
+; COFF:   @__profd_foo = internal {{.*}}, section ".lprfd$M", align 8
 define void @foo() {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_foo, i32 0, i32 0), i64 0, i32 1, i32 0)
   ret void
@@ -32,8 +29,8 @@ define void @foo() {
 ; ELF:   @__profd_bar = hidden {{.*}}, section "__llvm_prf_data", comdat, align 8
 ; MACHO: @__profc_bar = hidden global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
 ; MACHO: @__profd_bar = hidden {{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
-; WIN:   @__profc_bar = internal global [1 x i64] zeroinitializer, section ".lprfc$M", align 8
-; WIN:   @__profd_bar = internal {{.*}}, section ".lprfd$M", align 8
+; COFF:   @__profc_bar = internal global [1 x i64] zeroinitializer, section ".lprfc$M", align 8
+; COFF:   @__profd_bar = internal {{.*}}, section ".lprfd$M", align 8
 define void @bar() {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @__profn_bar, i32 0, i32 0), i64 0, i32 1, i32 0)
   ret void
@@ -43,8 +40,8 @@ define void @bar() {
 ; ELF:   @__profd_baz = hidden {{.*}}, section "__llvm_prf_data", comdat, align 8
 ; MACHO: @__profc_baz = hidden global [3 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
 ; MACHO: @__profd_baz = hidden {{.*}}, section "__DATA,__llvm_prf_data,regular,live_support", align 8
-; WIN:   @__profc_baz = internal global [3 x i64] zeroinitializer, section ".lprfc$M", align 8
-; WIN:   @__profd_baz = internal {{.*}}, section ".lprfd$M", align 8
+; COFF:   @__profc_baz = internal global [3 x i64] zeroinitializer, section ".lprfc$M", align 8
+; COFF:   @__profd_baz = internal {{.*}}, section ".lprfd$M", align 8
 define void @baz() {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_baz, i32 0, i32 0), i64 0, i32 3, i32 0)
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_baz, i32 0, i32 0), i64 0, i32 3, i32 1)
@@ -54,12 +51,14 @@ define void @baz() {
 
 declare void @llvm.instrprof.increment(i8*, i64, i32, i32)
 
-; ELF:   @llvm.compiler.used = appending global {{.*}} @__llvm_profile_runtime {{.*}} @__profd_foo {{.*}} @__profd_bar {{.*}} @__profd_baz
+; ELF:   @__llvm_profile_runtime = external global i32
+; COFF:  @__llvm_profile_runtime = external global i32
+
+; ELF:   @llvm.compiler.used = appending global {{.*}} @__profd_foo {{.*}} @__profd_bar {{.*}} @__profd_baz {{.*}} @__llvm_profile_runtime
 ; MACHO: @llvm.used = appending global {{.*}} @__llvm_profile_runtime {{.*}} @__profd_foo {{.*}} @__profd_bar {{.*}} @__profd_baz
-; WIN:   @llvm.used = appending global {{.*}} @__llvm_profile_runtime {{.*}} @__profd_foo {{.*}} @__profd_bar {{.*}} @__profd_baz
+; COFF:   @llvm.used = appending global {{.*}} @__profd_foo {{.*}} @__profd_bar {{.*}} @__profd_baz {{.*}} @__llvm_profile_runtime
 
 ; ELF_GENERIC:      define internal void @__llvm_profile_register_functions() unnamed_addr {
-; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast (i32* @__llvm_profile_runtime to i8*))
 ; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*))
 ; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_bar to i8*))
 ; ELF_GENERIC-NEXT:   call void @__llvm_profile_register_function(i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_baz to i8*))