[CSSPGO] Always use callsite samples as callsite probe counts.

[hoy]

Summary

For CS profile, the callsite count of previously inlined callees is populated with the entry count of the callees. Therefore when trying to get a weight for calliste probe after inlinining, the callsite count should always be used. The same fix has already been made for non-probe case.

[wenlei]

llvm/lib/Transforms/IPO/SampleProfile.cpp

527

nit: format the comment to be consistent with the probe version.

[hoy]

Adderssing Wenlei's comment.

llvm/lib/Transforms/IPO/SampleProfile.cpp

if (!DLoc)
     return std::error_code();
 
   // Ignore all intrinsics, phinodes and branch instructions.
   // Branch and phinodes instruction usually contains debug info from sources
   // outside of the residing basic block, thus we ignore them during annotation.
   if (isa<BranchInst>(Inst) || isa<IntrinsicInst>(Inst) || isa<PHINode>(Inst))
     return std::error_code();
 
-  // If a direct call/invoke instruction is inlined in profile
-  // (findCalleeFunctionSamples returns non-empty result), but not inlined here,
-  // it means that the inlined callsite has no sample, thus the call
-  // instruction should have 0 count.
+  // For non-CS profile, if a direct call/invoke instruction is inlined in
+  // profile (findCalleeFunctionSamples returns non-empty result), but not
+  // inlined here, it means that the inlined callsite has no sample, thus the
+  // call instruction should have 0 count.
+  // For CS profile, the callsite count of previously inlined callees is
+  // populated with the entry count of the callees.
   if (!ProfileIsCS)
     if (const auto *CB = dyn_cast<CallBase>(&Inst))
       if (!CB->isIndirectCall() && findCalleeFunctionSamples(*CB))
         return 0;
 
   return getInstWeightImpl(Inst);
 }
 
 ErrorOr<uint64_t> SampleProfileLoader::getProbeWeight(const Instruction &Inst) {
   assert(FunctionSamples::ProfileIsProbeBased &&
          "Profile is not pseudo probe based");
   Optional<PseudoProbe> Probe = extractProbe(Inst);
   if (!Probe)
     return std::error_code();
 
   // Ignore danling probes since they are logically deleted and should not
   // consume any profile samples.
   if (Probe->isDangling())
     return std::error_code();
 
   const FunctionSamples *FS = findFunctionSamples(Inst);
   if (!FS)
     return std::error_code();
 
-  // If a direct call/invoke instruction is inlined in profile
-  // (findCalleeFunctionSamples returns non-empty result), but not inlined here,
-  // it means that the inlined callsite has no sample, thus the call
-  // instruction should have 0 count.
+  // For non-CS profile, If a direct call/invoke instruction is inlined in
+  // profile (findCalleeFunctionSamples returns non-empty result), but not
+  // inlined here, it means that the inlined callsite has no sample, thus the
+  // call instruction should have 0 count.
+  // For CS profile, the callsite count of previously inlined callees is
+  // populated with the entry count of the callees.
+  if (!ProfileIsCS)
     if (const auto *CB = dyn_cast<CallBase>(&Inst))
       if (!CB->isIndirectCall() && findCalleeFunctionSamples(*CB))
         return 0;
 
   const ErrorOr<uint64_t> &R = FS->findSamplesAt(Probe->Id, 0);
   if (R) {
     uint64_t Samples = R.get() * Probe->Factor;
     bool FirstMark = CoverageTracker.markSamplesUsed(FS, Probe->Id, 0, Samples);
     if (FirstMark) {
       ORE->emit([&]() {
         OptimizationRemarkAnalysis Remark(DEBUG_TYPE, "AppliedSamples", &Inst);