1 files changed, 93 insertions, 9 deletions

diff --git a/contrib/llvm-project/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp b/contrib/llvm-project/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
index 3dfa2d821e83..2076ed48ea34 100644
--- a/contrib/llvm-project/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
+++ b/contrib/llvm-project/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
@@ -80,6 +80,8 @@ static cl::opt<std::string> ModuleSummaryDotFile(
     "module-summary-dot-file", cl::Hidden, cl::value_desc("filename"),
     cl::desc("File to emit dot graph of new summary into"));
 
+extern cl::opt<bool> ScalePartialSampleProfileWorkingSetSize;
+
 // Walk through the operands of a given User via worklist iteration and populate
 // the set of GlobalValue references encountered. Invoked either on an
 // Instruction or a GlobalVariable (which walks its initializer).
@@ -196,6 +198,7 @@ static void addIntrinsicToSummary(
     break;
   }
 
+  case Intrinsic::type_checked_load_relative:
   case Intrinsic::type_checked_load: {
     auto *TypeMDVal = cast<MetadataAsValue>(CI->getArgOperand(2));
     auto *TypeId = dyn_cast<MDString>(TypeMDVal->getMetadata());
@@ -263,7 +266,9 @@ static void computeFunctionSummary(
   unsigned NumInsts = 0;
   // Map from callee ValueId to profile count. Used to accumulate profile
   // counts for all static calls to a given callee.
-  MapVector<ValueInfo, CalleeInfo> CallGraphEdges;
+  MapVector<ValueInfo, CalleeInfo, DenseMap<ValueInfo, unsigned>,
+            std::vector<std::pair<ValueInfo, CalleeInfo>>>
+      CallGraphEdges;
   SetVector<ValueInfo> RefEdges, LoadRefEdges, StoreRefEdges;
   SetVector<GlobalValue::GUID> TypeTests;
   SetVector<FunctionSummary::VFuncId> TypeTestAssumeVCalls,
@@ -282,6 +287,10 @@ static void computeFunctionSummary(
   std::vector<CallsiteInfo> Callsites;
   std::vector<AllocInfo> Allocs;
 
+#ifndef NDEBUG
+  DenseSet<const CallBase *> CallsThatMayHaveMemprofSummary;
+#endif
+
   bool HasInlineAsmMaybeReferencingInternal = false;
   bool HasIndirBranchToBlockAddress = false;
   bool HasUnknownCall = false;
@@ -425,6 +434,10 @@ static void computeFunctionSummary(
               .updateHotness(getHotness(Candidate.Count, PSI));
       }
 
+      // Summarize memprof related metadata. This is only needed for ThinLTO.
+      if (!IsThinLTO)
+        continue;
+
       // TODO: Skip indirect calls for now. Need to handle these better, likely
       // by creating multiple Callsites, one per target, then speculatively
       // devirtualize while applying clone info in the ThinLTO backends. This
@@ -435,6 +448,14 @@ static void computeFunctionSummary(
       if (!CalledFunction)
         continue;
 
+      // Ensure we keep this analysis in sync with the handling in the ThinLTO
+      // backend (see MemProfContextDisambiguation::applyImport). Save this call
+      // so that we can skip it in checking the reverse case later.
+      assert(mayHaveMemprofSummary(CB));
+#ifndef NDEBUG
+      CallsThatMayHaveMemprofSummary.insert(CB);
+#endif
+
       // Compute the list of stack ids first (so we can trim them from the stack
       // ids on any MIBs).
       CallStack<MDNode, MDNode::op_iterator> InstCallsite(
@@ -477,7 +498,9 @@ static void computeFunctionSummary(
       }
     }
   }
-  Index.addBlockCount(F.size());
+
+  if (PSI->hasPartialSampleProfile() && ScalePartialSampleProfileWorkingSetSize)
+    Index.addBlockCount(F.size());
 
   std::vector<ValueInfo> Refs;
   if (IsThinLTO) {
@@ -542,6 +565,25 @@ static void computeFunctionSummary(
             ? CalleeInfo::HotnessType::Cold
             : CalleeInfo::HotnessType::Critical);
 
+#ifndef NDEBUG
+  // Make sure that all calls we decided could not have memprof summaries get a
+  // false value for mayHaveMemprofSummary, to ensure that this handling remains
+  // in sync with the ThinLTO backend handling.
+  if (IsThinLTO) {
+    for (const BasicBlock &BB : F) {
+      for (const Instruction &I : BB) {
+        const auto *CB = dyn_cast<CallBase>(&I);
+        if (!CB)
+          continue;
+        // We already checked these above.
+        if (CallsThatMayHaveMemprofSummary.count(CB))
+          continue;
+        assert(!mayHaveMemprofSummary(CB));
+      }
+    }
+  }
+#endif
+
   bool NonRenamableLocal = isNonRenamableLocal(F);
   bool NotEligibleForImport = NonRenamableLocal ||
                               HasInlineAsmMaybeReferencingInternal ||
@@ -583,12 +625,17 @@ static void findFuncPointers(const Constant *I, uint64_t StartingOffset,
                              VTableFuncList &VTableFuncs) {
   // First check if this is a function pointer.
   if (I->getType()->isPointerTy()) {
-    auto Fn = dyn_cast<Function>(I->stripPointerCasts());
-    // We can disregard __cxa_pure_virtual as a possible call target, as
-    // calls to pure virtuals are UB.
-    if (Fn && Fn->getName() != "__cxa_pure_virtual")
-      VTableFuncs.push_back({Index.getOrInsertValueInfo(Fn), StartingOffset});
-    return;
+    auto C = I->stripPointerCasts();
+    auto A = dyn_cast<GlobalAlias>(C);
+    if (isa<Function>(C) || (A && isa<Function>(A->getAliasee()))) {
+      auto GV = dyn_cast<GlobalValue>(C);
+      assert(GV);
+      // We can disregard __cxa_pure_virtual as a possible call target, as
+      // calls to pure virtuals are UB.
+      if (GV && GV->getName() != "__cxa_pure_virtual")
+        VTableFuncs.push_back({Index.getOrInsertValueInfo(GV), StartingOffset});
+      return;
+    }
   }
 
   // Walk through the elements in the constant struct or array and recursively
@@ -741,10 +788,14 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
     std::function<const StackSafetyInfo *(const Function &F)> GetSSICallback) {
   assert(PSI);
   bool EnableSplitLTOUnit = false;
+  bool UnifiedLTO = false;
   if (auto *MD = mdconst::extract_or_null<ConstantInt>(
           M.getModuleFlag("EnableSplitLTOUnit")))
     EnableSplitLTOUnit = MD->getZExtValue();
-  ModuleSummaryIndex Index(/*HaveGVs=*/true, EnableSplitLTOUnit);
+  if (auto *MD =
+          mdconst::extract_or_null<ConstantInt>(M.getModuleFlag("UnifiedLTO")))
+    UnifiedLTO = MD->getZExtValue();
+  ModuleSummaryIndex Index(/*HaveGVs=*/true, EnableSplitLTOUnit, UnifiedLTO);
 
   // Identify the local values in the llvm.used and llvm.compiler.used sets,
   // which should not be exported as they would then require renaming and
@@ -1033,3 +1084,36 @@ ImmutablePass *llvm::createImmutableModuleSummaryIndexWrapperPass(
 
 INITIALIZE_PASS(ImmutableModuleSummaryIndexWrapperPass, "module-summary-info",
                 "Module summary info", false, true)
+
+bool llvm::mayHaveMemprofSummary(const CallBase *CB) {
+  if (!CB)
+    return false;
+  if (CB->isDebugOrPseudoInst())
+    return false;
+  auto *CI = dyn_cast<CallInst>(CB);
+  auto *CalledValue = CB->getCalledOperand();
+  auto *CalledFunction = CB->getCalledFunction();
+  if (CalledValue && !CalledFunction) {
+    CalledValue = CalledValue->stripPointerCasts();
+    // Stripping pointer casts can reveal a called function.
+    CalledFunction = dyn_cast<Function>(CalledValue);
+  }
+  // Check if this is an alias to a function. If so, get the
+  // called aliasee for the checks below.
+  if (auto *GA = dyn_cast<GlobalAlias>(CalledValue)) {
+    assert(!CalledFunction &&
+           "Expected null called function in callsite for alias");
+    CalledFunction = dyn_cast<Function>(GA->getAliaseeObject());
+  }
+  // Check if this is a direct call to a known function or a known
+  // intrinsic, or an indirect call with profile data.
+  if (CalledFunction) {
+    if (CI && CalledFunction->isIntrinsic())
+      return false;
+  } else {
+    // TODO: For now skip indirect calls. See comments in
+    // computeFunctionSummary for what is needed to handle this.
+    return false;
+  }
+  return true;
+}