[llvm-profgen][NFC] Fix the incorrect computation of callsite sample count

[wlei]

Summary

For branch sample, we don't need add total sample count since it's included in the range sample.

For the inferred sample count, we should accumulate its caller's body sample count.

[hoy]

llvm/tools/llvm-profgen/ProfileGenerator.cpp

278

What is this check?

[wlei]

llvm/tools/llvm-profgen/ProfileGenerator.cpp

278

Good catch! This is to filter the invalid negative LineOffset same as updateBodySamplesforFunctionProfile. but I think here it's only for the inferred context, shouldn't have the negative line. I will remove this.

[wlei]

remove updateBodySamplesforFunctionProfile and redundant check

[wenlei]

lgtm, thanks!

llvm/test/tools/llvm-profgen/inline-cs-noprobe.test

 ; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --show-unwinder-output | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
-; CHECK:[main:1 @ foo]:44:0
+; CHECK:[main:1 @ foo]:58:0
 ; CHECK: 2.2: 14
 ; CHECK: 3: 15
-; CHECK: 3.2: 14 bar:14
+; CHECK: 3.2: 28 bar:14
 ; CHECK: 3.4: 1
 ; CHECK:[main:1 @ foo:3.2 @ bar]:14:0
 ; CHECK: 1: 14
 
 ; CHECK-UNWINDER: Binary(inline-cs-noprobe.perfbin)'s Range Counter:
 ; CHECK-UNWINDER: main:1 @ foo
 ; CHECK-UNWINDER:   (670, 6ad): 1
 ; CHECK-UNWINDER:   (67e, 69b): 1

llvm/test/tools/llvm-profgen/noinline-cs-noprobe.test

 ; RUN: llvm-profgen --perfscript=%S/Inputs/noinline-cs-noprobe.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t --show-unwinder-output | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK:[main:1 @ foo:3 @ bar]:12:3
 ; CHECK: 0: 3
 ; CHECK: 1: 3
 ; CHECK: 2: 2
 ; CHECK: 4: 1
 ; CHECK: 5: 3
-; CHECK:[main:1 @ foo]:9:0
+; CHECK:[main:1 @ foo]:6:0
 ; CHECK: 2: 3
 ; CHECK: 3: 3 bar:3
 
 ; CHECK-UNWINDER: Binary(noinline-cs-noprobe.perfbin)'s Range Counter:
 ; CHECK-UNWINDER: main:1 @ foo
 ; CHECK-UNWINDER:   (5ff, 62f): 3
 ; CHECK-UNWINDER:   (634, 637): 3
 ; CHECK-UNWINDER:   (645, 645): 3

llvm/tools/llvm-profgen/ProfileGenerator.cpp

for (auto Entry : BranchCounters) {
     // Get the callee name by branch target if it's a call branch
     StringRef CalleeName = FunctionSamples::getCanonicalFnName(
         Binary->getFuncFromStartOffset(TargetOffset));
     if (CalleeName.size() == 0)
       continue;
 
     // Record called target sample and its count
     const FrameLocation &LeafLoc = Binary->getInlineLeafFrameLoc(SourceOffset);
-
     FunctionProfile.addCalledTargetSamples(LeafLoc.second.LineOffset,
                                            LeafLoc.second.Discriminator,
                                            CalleeName, Count);
-    FunctionProfile.addTotalSamples(Count);
 
     // Record head sample for called target(callee)
     // TODO: Cleanup ' @ '
     std::string CalleeContextId =
         getCallSite(LeafLoc) + " @ " + CalleeName.str();
     if (ContextId.find(" @ ") != StringRef::npos) {
       CalleeContextId =
           ContextId.rsplit(" @ ").first.str() + " @ " + CalleeContextId;
static FrameLocation getCallerContext(StringRef CalleeContext,
   FrameLocation LeafFrameLoc = {"", {0, 0}};
   StringRef Funcname;
   SampleContext::decodeContextString(ContextSplit.second, Funcname,
                                      LeafFrameLoc.second);
   LeafFrameLoc.first = Funcname.str();
   return LeafFrameLoc;
 }
 
+static void accumulateBodySamples(FunctionSamples &FunctionProfile,
+                                  const FrameLocation &LeafLoc,
+                                  uint64_t Count) {
+  if (LeafLoc.second.LineOffset & 0x80000000)
+    return;
+  FunctionProfile.addBodySamples(LeafLoc.second.LineOffset,
+                                 LeafLoc.second.Discriminator, Count);
+  FunctionProfile.addTotalSamples(Count);
+}
+
 void CSProfileGenerator::populateInferredFunctionSamples() {
   for (const auto &Item : ProfileMap) {
     const StringRef CalleeContext = Item.first();
     const FunctionSamples &CalleeProfile = Item.second;
 
     // If we already have head sample counts, we must have value profile
     // for call sites added already. Skip to avoid double counting.
     if (CalleeProfile.getHeadSamples())
for (const auto &Item : ProfileMap) {
     if (!EstimatedCallCount && !CalleeProfile.getBodySamples().size())
       EstimatedCallCount = 1;
     CallerProfile.addCalledTargetSamples(
         CallerLeafFrameLoc.second.LineOffset,
         CallerLeafFrameLoc.second.Discriminator, CalleeProfile.getName(),
         EstimatedCallCount);
     updateBodySamplesforFunctionProfile(CallerProfile, CallerLeafFrameLoc,
                                         EstimatedCallCount);
+    accumulateBodySamples(CallerProfile, CallerLeafFrameLoc,
+                          EstimatedCallCount);
   }
 }
 
 } // end namespace sampleprof
 } // end namespace llvm