[PGO] Fix name encoding for ObjC-like functions

Function names in ObjC can have spaces in them. This interacts poorly
with name compression, which uses spaces to separate PGO names. Fix the
issue by using a different separator and update a test.

I chose "\01" as the separator because 1) it's non-printable, 2) we
strip it from PGO names, and 3) it's the next natural choice once "\00"
is discarded (that one's overloaded).

Differential Revision: http://reviews.llvm.org/D18516

llvm-svn: 264587

3 files changed, 7 insertions, 4 deletions

diff --git a/llvm/include/llvm/ProfileData/InstrProf.h b/llvm/include/llvm/ProfileData/InstrProf.h
index 3bf0aa38510..31fcffe2ef7 100644
--- a/llvm/include/llvm/ProfileData/InstrProf.h
+++ b/llvm/include/llvm/ProfileData/InstrProf.h
@@ -151,6 +151,9 @@ inline StringRef getInstrProfFileOverriderFuncName() {
   return "__llvm_profile_override_default_filename";
 }
 
+/// Return the marker used to separate PGO names during serialization.
+inline StringRef getInstrProfNameSeparator() { return "\01"; }
+
 /// Return the modified name for function \c F suitable to be
 /// used the key for profile lookup.
 std::string getPGOFuncName(const Function &F,
diff --git a/llvm/lib/ProfileData/InstrProf.cpp b/llvm/lib/ProfileData/InstrProf.cpp
index 2446521a5bc..0bd8318dd43 100644
--- a/llvm/lib/ProfileData/InstrProf.cpp
+++ b/llvm/lib/ProfileData/InstrProf.cpp
@@ -160,7 +160,7 @@ int collectPGOFuncNameStrings(const std::vector<std::string> &NameStrs,
                               bool doCompression, std::string &Result) {
   uint8_t Header[16], *P = Header;
   std::string UncompressedNameStrings =
-      join(NameStrs.begin(), NameStrs.end(), StringRef(" "));
+      join(NameStrs.begin(), NameStrs.end(), getInstrProfNameSeparator());
 
   unsigned EncLen = encodeULEB128(UncompressedNameStrings.length(), P);
   P += EncLen;
@@ -238,7 +238,7 @@ int readPGOFuncNameStrings(StringRef NameStrings, InstrProfSymtab &Symtab) {
     }
     // Now parse the name strings.
     SmallVector<StringRef, 0> Names;
-    NameStrings.split(Names, ' ');
+    NameStrings.split(Names, getInstrProfNameSeparator());
     for (StringRef &Name : Names)
       Symtab.addFuncName(Name);
 
diff --git a/llvm/unittests/ProfileData/InstrProfTest.cpp b/llvm/unittests/ProfileData/InstrProfTest.cpp
index 13d1e059cd2..7dd072c849b 100644
--- a/llvm/unittests/ProfileData/InstrProfTest.cpp
+++ b/llvm/unittests/ProfileData/InstrProfTest.cpp
@@ -893,7 +893,7 @@ TEST_P(MaybeSparseInstrProfTest, instr_prof_symtab_compression_test) {
     OS << "func_" << I;
     FuncNames1.push_back(OS.str());
     str.clear();
-    OS << "fooooooooooooooo_" << I;
+    OS << "f oooooooooooooo_" << I;
     FuncNames1.push_back(OS.str());
     str.clear();
     OS << "BAR_" << I;
@@ -931,7 +931,7 @@ TEST_P(MaybeSparseInstrProfTest, instr_prof_symtab_compression_test) {
       StringRef R = Symtab.getFuncName(IndexedInstrProf::ComputeHash(FuncNames1[0]));
       ASSERT_EQ(StringRef("func_0"), R);
       R = Symtab.getFuncName(IndexedInstrProf::ComputeHash(FuncNames1[1]));
-      ASSERT_EQ(StringRef("fooooooooooooooo_0"), R);
+      ASSERT_EQ(StringRef("f oooooooooooooo_0"), R);
       for (int I = 0; I < 3; I++) {
         std::string N[4];
         N[0] = FuncNames1[2 * I];