[SampleFDO] Extend SampleProfReader to handle demangled names

[wmi]

Summary

SampleProfReader assumes function names in the profile are all mangled names. However, there are cases that few demangled names are somehow contained in the profile (usually because of debug info problems), which may trigger parsing error in SampleProfReader and cause the whole profile to be unusable. The patch extends SampleProfReader to handle profiles with demangled names, so that those profiles can still be useful.

[danielcdh]

Just to confirm, this only applies to text format. Binary format should not have this problem, right?

[wmi]

Right, binary format does not have this problem.

llvm/trunk/lib/ProfileData/SampleProfReader.cpp

if (Rest[0] >= '0' && Rest[0] <= '9') {
     size_t n3 = Rest.find(' ');
     if (n3 == StringRef::npos) {
       if (Rest.getAsInteger(10, NumSamples))
         return false;
     } else {
       if (Rest.substr(0, n3).getAsInteger(10, NumSamples))
         return false;
     }
+    // Find call targets and their sample counts.
+    // Note: In some cases, there are symbols in the profile which are not
+    // mangled. To accommodate such cases, use colon + integer pairs as the
+    // anchor points.
+    // An example:
+    // _M_construct<char *>:1000 string_view<std::allocator<char> >:437
+    // ":1000" and ":437" are used as anchor points so the string above will
+    // be interpreted as
+    // target: _M_construct<char *>
+    // count: 1000
+    // target: string_view<std::allocator<char> >
+    // count: 437
     while (n3 != StringRef::npos) {
       n3 += Rest.substr(n3).find_first_not_of(' ');
       Rest = Rest.substr(n3);
-      n3 = Rest.find(' ');
-      StringRef pair = Rest;
-      if (n3 != StringRef::npos) {
-        pair = Rest.substr(0, n3);
-      }
-      size_t n4 = pair.find(':');
-      uint64_t count;
-      if (pair.substr(n4 + 1).getAsInteger(10, count))
+      n3 = Rest.find_first_of(':');
+      if (n3 == StringRef::npos || n3 == 0)
         return false;
-      TargetCountMap[pair.substr(0, n4)] = count;
+
+      StringRef Target;
+      uint64_t count, n4;
+      while (true) {
+        // Get the segment after the current colon.
+        StringRef AfterColon = Rest.substr(n3 + 1);
+        // Get the target symbol before the current colon.
+        Target = Rest.substr(0, n3);
+        // Check if the word after the current colon is an integer.
+        n4 = AfterColon.find_first_of(' ');
+        n4 = (n4 != StringRef::npos) ? n3 + n4 + 1 : Rest.size();
+        StringRef WordAfterColon = Rest.substr(n3 + 1, n4 - n3 - 1);
+        if (!WordAfterColon.getAsInteger(10, count))
+          break;
+
+        // Try to find the next colon.
+        uint64_t n5 = AfterColon.find_first_of(':');
+        if (n5 == StringRef::npos)
+          return false;
+        n3 += n5 + 1;
+      }
+
+      // An anchor point is found. Save the {target, count} pair
+      TargetCountMap[Target] = count;
+      if (n4 == Rest.size())
+        break;
+      // Change n3 to the next blank space after colon + integer pair.
+      n3 = n4;
     }
   } else {
     IsCallsite = true;
     size_t n3 = Rest.find_last_of(':');
     CalleeName = Rest.substr(0, n3);
     if (Rest.substr(n3 + 1).getAsInteger(10, NumSamples))
       return false;
   }

llvm/trunk/unittests/ProfileData/SampleProfTest.cpp

void testRoundTrip(SampleProfileFormat Format) {
     FooSamples.addBodySamples(10, 0, 605);
 
     StringRef BarName("_Z3bari");
     FunctionSamples BarSamples;
     BarSamples.setName(BarName);
     BarSamples.addTotalSamples(20301);
     BarSamples.addHeadSamples(1437);
     BarSamples.addBodySamples(1, 0, 1437);
+    BarSamples.addCalledTargetSamples(1, 0, "_M_construct<char *>", 1000);
+    BarSamples.addCalledTargetSamples(
+        1, 0, "string_view<std::allocator<char> >", 437);
 
     StringMap<FunctionSamples> Profiles;
     Profiles[FooName] = std::move(FooSamples);
     Profiles[BarName] = std::move(BarSamples);
 
     std::error_code EC;
     EC = Writer->write(Profiles);
     ASSERT_TRUE(NoError(EC));
void testRoundTrip(SampleProfileFormat Format) {
 
     FunctionSamples &ReadFooSamples = ReadProfiles[FooName];
     ASSERT_EQ(7711u, ReadFooSamples.getTotalSamples());
     ASSERT_EQ(610u, ReadFooSamples.getHeadSamples());
 
     FunctionSamples &ReadBarSamples = ReadProfiles[BarName];
     ASSERT_EQ(20301u, ReadBarSamples.getTotalSamples());
     ASSERT_EQ(1437u, ReadBarSamples.getHeadSamples());
+    ErrorOr<SampleRecord::CallTargetMap> CTMap =
+        ReadBarSamples.findCallTargetMapAt(1, 0);
+    ASSERT_FALSE(CTMap.getError());
+    ASSERT_EQ(1000u, CTMap.get()["_M_construct<char *>"]);
+    ASSERT_EQ(437u, CTMap.get()["string_view<std::allocator<char> >"]);
 
     auto VerifySummary = [](ProfileSummary &Summary) mutable {
       ASSERT_EQ(ProfileSummary::PSK_Sample, Summary.getKind());
       ASSERT_EQ(123603u, Summary.getTotalCount());
       ASSERT_EQ(6u, Summary.getNumCounts());
       ASSERT_EQ(2u, Summary.getNumFunctions());
       ASSERT_EQ(1437u, Summary.getMaxFunctionCount());
       ASSERT_EQ(60351u, Summary.getMaxCount());