[llvm][NFC] Cleanup uses of std::function in Inlining-related APIs

[mtrofin]

Summary

Replacing uses of std::function pointers or refs, or Optional, to
function_ref, since the usage pattern allows that. If the function is
optional, using a default parameter value (nullptr). This led to a few
parameter reshufles, to push all optionals to the end of the parameter
list.

[dblaikie]

Looks good at a glance to me - welcome to make changes like that without review in the future.

llvm/lib/Transforms/Utils/InlineFunction.cpp

1907–1910

Aside: This set of {} seems sort of arbitrary - given the larger for loop outside this doesn't use {} and the ifs inside don't... why this particular level of nesting with {}? Could remove those in a separate patch if you like

2498

This still seems to have unnecessary parentheses, instead: &IFI.GetAssumptionCache(*Caller) should be fine. (few other cases of similarly unnecessary () in other similar places in this file you could remove, since you're moving them around anyway)

[mtrofin]

Reverted reason: http://lab.llvm.org:8011/builders/sanitizer-x86_64-linux-bootstrap-msan/builds/19317

llvm/include/llvm/Analysis/InlineCost.h

 /// Note that a default threshold is passed into this function. This threshold
 /// could be modified based on callsite's properties and only costs below this
 /// new threshold are computed with any accuracy. The new threshold can be
 /// used to bound the computation necessary to determine whether the cost is
 /// sufficiently low to warrant inlining.
 ///
 /// Also note that calling this function *dynamically* computes the cost of
 /// inlining the callsite. It is an expensive, heavyweight call.
-InlineCost getInlineCost(
-    CallBase &Call, const InlineParams &Params, TargetTransformInfo &CalleeTTI,
-    std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-    Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI,
+InlineCost
+getInlineCost(CallBase &Call, const InlineParams &Params,
+              TargetTransformInfo &CalleeTTI,
+              function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
               function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
-    ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE = nullptr);
+              function_ref<BlockFrequencyInfo &(Function &)> GetBFI = nullptr,
+              ProfileSummaryInfo *PSI = nullptr,
+              OptimizationRemarkEmitter *ORE = nullptr);
 
 /// Get an InlineCost with the callee explicitly specified.
 /// This allows you to calculate the cost of inlining a function via a
 /// pointer. This behaves exactly as the version with no explicit callee
 /// parameter in all other respects.
 //
 InlineCost
 getInlineCost(CallBase &Call, Function *Callee, const InlineParams &Params,
               TargetTransformInfo &CalleeTTI,
-              std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-              Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI,
+              function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
               function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
-              ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE);
+              function_ref<BlockFrequencyInfo &(Function &)> GetBFI = nullptr,
+              ProfileSummaryInfo *PSI = nullptr,
+              OptimizationRemarkEmitter *ORE = nullptr);
 
 /// Returns InlineResult::success() if the call site should be always inlined
 /// because of user directives, and the inlining is viable. Returns
 /// InlineResult::failure() if the inlining may never happen because of user
 /// directives or incompatibilities detectable without needing callee traversal.
 /// Otherwise returns None, meaning that inlining should be decided based on
 /// other criteria (e.g. cost modeling).
 Optional<InlineResult> getAttributeBasedInliningDecision(
     CallBase &Call, Function *Callee, TargetTransformInfo &CalleeTTI,
     function_ref<const TargetLibraryInfo &(Function &)> GetTLI);
 
 /// Get the cost estimate ignoring thresholds. This is similar to getInlineCost
 /// when passed InlineParams::ComputeFullInlineCost, or a non-null ORE. It
 /// uses default InlineParams otherwise.
 /// Contrary to getInlineCost, which makes a threshold-based final evaluation of
 /// should/shouldn't inline, captured in InlineResult, getInliningCostEstimate
 /// returns:
 /// - None, if the inlining cannot happen (is illegal)
 /// - an integer, representing the cost.
 Optional<int> getInliningCostEstimate(
     CallBase &Call, TargetTransformInfo &CalleeTTI,
-    std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-    Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI,
-    ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE);
+    function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
+    function_ref<BlockFrequencyInfo &(Function &)> GetBFI = nullptr,
+    ProfileSummaryInfo *PSI = nullptr,
+    OptimizationRemarkEmitter *ORE = nullptr);
 
 /// Minimal filter to detect invalid constructs for inlining.
 InlineResult isInlineViable(Function &Callee);
 } // namespace llvm
 
 #endif

llvm/include/llvm/Transforms/Utils/Cloning.h

void CloneAndPruneFunctionInto(Function *NewFunc, const Function *OldFunc,
                                const char *NameSuffix = "",
                                ClonedCodeInfo *CodeInfo = nullptr,
                                Instruction *TheCall = nullptr);
 
 /// This class captures the data input to the InlineFunction call, and records
 /// the auxiliary results produced by it.
 class InlineFunctionInfo {
 public:
-  explicit InlineFunctionInfo(CallGraph *cg = nullptr,
-                              std::function<AssumptionCache &(Function &)>
-                                  *GetAssumptionCache = nullptr,
-                              ProfileSummaryInfo *PSI = nullptr,
-                              BlockFrequencyInfo *CallerBFI = nullptr,
-                              BlockFrequencyInfo *CalleeBFI = nullptr)
+  explicit InlineFunctionInfo(
+      CallGraph *cg = nullptr,
+      function_ref<AssumptionCache &(Function &)> GetAssumptionCache = nullptr,
       : CG(cg), GetAssumptionCache(GetAssumptionCache), PSI(PSI),
         CallerBFI(CallerBFI), CalleeBFI(CalleeBFI) {}
 
   /// If non-null, InlineFunction will update the callgraph to reflect the
   /// changes it makes.
   CallGraph *CG;
-  std::function<AssumptionCache &(Function &)> *GetAssumptionCache;
+  function_ref<AssumptionCache &(Function &)> GetAssumptionCache;
   ProfileSummaryInfo *PSI;
   BlockFrequencyInfo *CallerBFI, *CalleeBFI;
 
   /// InlineFunction fills this in with all static allocas that get copied into
   /// the caller.
   SmallVector<AllocaInst *, 4> StaticAllocas;
 
   /// InlineFunction fills this in with callsites that were inlined from the

llvm/lib/Analysis/InlineAdvisor.cpp

 DefaultInlineAdvisor::getAdvice(CallBase &CB, FunctionAnalysisManager &FAM) {
   Function &Caller = *CB.getCaller();
   ProfileSummaryInfo *PSI =
       FAM.getResult<ModuleAnalysisManagerFunctionProxy>(Caller)
           .getCachedResult<ProfileSummaryAnalysis>(
               *CB.getParent()->getParent()->getParent());
 
   auto &ORE = FAM.getResult<OptimizationRemarkEmitterAnalysis>(Caller);
-  // FIXME: make GetAssumptionCache's decl similar to the other 2 below. May
-  // need changing the type of getInlineCost parameters? Also see similar case
-  // in Inliner.cpp
-  std::function<AssumptionCache &(Function &)> GetAssumptionCache =
-      [&](Function &F) -> AssumptionCache & {
+  auto GetAssumptionCache = [&](Function &F) -> AssumptionCache & {
     return FAM.getResult<AssumptionAnalysis>(F);
   };
   auto GetBFI = [&](Function &F) -> BlockFrequencyInfo & {
     return FAM.getResult<BlockFrequencyAnalysis>(F);
   };
   auto GetTLI = [&](Function &F) -> const TargetLibraryInfo & {
     return FAM.getResult<TargetLibraryAnalysis>(F);
   };
 
   auto GetInlineCost = [&](CallBase &CB) {
     Function &Callee = *CB.getCalledFunction();
     auto &CalleeTTI = FAM.getResult<TargetIRAnalysis>(Callee);
     bool RemarksEnabled =
         Callee.getContext().getDiagHandlerPtr()->isMissedOptRemarkEnabled(
             DEBUG_TYPE);
-    return getInlineCost(CB, Params, CalleeTTI, GetAssumptionCache, {GetBFI},
-                         GetTLI, PSI, RemarksEnabled ? &ORE : nullptr);
+    return getInlineCost(CB, Params, CalleeTTI, GetAssumptionCache, GetTLI,
+                         GetBFI, PSI, RemarksEnabled ? &ORE : nullptr);
   };
   auto OIC = llvm::shouldInline(CB, GetInlineCost, ORE);
   return std::make_unique<DefaultInlineAdvice>(this, CB, OIC, ORE);
 }
 
 InlineAdvice::InlineAdvice(InlineAdvisor *Advisor, CallBase &CB,
                            bool IsInliningRecommended)
     : Advisor(Advisor), Caller(CB.getCaller()), Callee(CB.getCalledFunction()),

llvm/lib/Analysis/InlineCost.cpp

class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   friend class InstVisitor<CallAnalyzer, bool>;
 
 protected:
   virtual ~CallAnalyzer() {}
   /// The TargetTransformInfo available for this compilation.
   const TargetTransformInfo &TTI;
 
   /// Getter for the cache of @llvm.assume intrinsics.
-  std::function<AssumptionCache &(Function &)> &GetAssumptionCache;
+  function_ref<AssumptionCache &(Function &)> GetAssumptionCache;
 
   /// Getter for BlockFrequencyInfo
-  Optional<function_ref<BlockFrequencyInfo &(Function &)>> &GetBFI;
+  function_ref<BlockFrequencyInfo &(Function &)> GetBFI;
 
   /// Profile summary information.
   ProfileSummaryInfo *PSI;
 
   /// The called function.
   Function &F;
 
   // Cache the DataLayout since we use it a lot.
protected:
   bool visitSwitchInst(SwitchInst &SI);
   bool visitIndirectBrInst(IndirectBrInst &IBI);
   bool visitResumeInst(ResumeInst &RI);
   bool visitCleanupReturnInst(CleanupReturnInst &RI);
   bool visitCatchReturnInst(CatchReturnInst &RI);
   bool visitUnreachableInst(UnreachableInst &I);
 
 public:
-  CallAnalyzer(const TargetTransformInfo &TTI,
-               std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-               Optional<function_ref<BlockFrequencyInfo &(Function &)>> &GetBFI,
-               ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE,
-               Function &Callee, CallBase &Call)
+  CallAnalyzer(
+      Function &Callee, CallBase &Call, const TargetTransformInfo &TTI,
+      const std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
+      function_ref<BlockFrequencyInfo &(Function &)> GetBFI = nullptr,
+      ProfileSummaryInfo *PSI = nullptr,
+      OptimizationRemarkEmitter *ORE = nullptr)
       : TTI(TTI), GetAssumptionCache(GetAssumptionCache), GetBFI(GetBFI),
         PSI(PSI), F(Callee), DL(F.getParent()->getDataLayout()), ORE(ORE),
         CandidateCall(Call), EnableLoadElimination(true) {}
 
   InlineResult analyze();
 
   // Keep a bunch of stats about the cost savings found so we can print them
   // out when debugging.
void onLoweredCall(Function *F, CallBase &Call,
     // inlining, but cap that bonus in the event that inlining wouldn't pan out.
     // Pretend to inline the function, with a custom threshold.
     if (IsIndirectCall && BoostIndirectCalls) {
       auto IndirectCallParams = Params;
       IndirectCallParams.DefaultThreshold =
           InlineConstants::IndirectCallThreshold;
       /// FIXME: if InlineCostCallAnalyzer is derived from, this may need
       /// to instantiate the derived class.
-      InlineCostCallAnalyzer CA(TTI, GetAssumptionCache, GetBFI, PSI, ORE, *F,
-                                Call, IndirectCallParams, false);
+      InlineCostCallAnalyzer CA(*F, Call, IndirectCallParams, TTI,
+                                GetAssumptionCache, GetBFI, PSI, ORE, false);
       if (CA.analyze().isSuccess()) {
         // We were able to inline the indirect call! Subtract the cost from the
         // threshold to get the bonus we want to apply, but don't go below zero.
         Cost -= std::max(0, CA.getThreshold() - CA.getCost());
       }
     } else
       // Otherwise simply add the cost for merely making the call.
       addCost(InlineConstants::CallPenalty);
InlineResult onAnalysisStart() override {
     if (Cost >= Threshold && !ComputeFullInlineCost)
       return InlineResult::failure("high cost");
 
     return InlineResult::success();
   }
 
 public:
   InlineCostCallAnalyzer(
+      Function &Callee, CallBase &Call, const InlineParams &Params,
       const TargetTransformInfo &TTI,
-      std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-      Optional<function_ref<BlockFrequencyInfo &(Function &)>> &GetBFI,
-      ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE, Function &Callee,
-      CallBase &Call, const InlineParams &Params, bool BoostIndirect = true,
+      function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
+      function_ref<BlockFrequencyInfo &(Function &)> GetBFI = nullptr,
+      ProfileSummaryInfo *PSI = nullptr,
+      OptimizationRemarkEmitter *ORE = nullptr, bool BoostIndirect = true,
       bool IgnoreThreshold = false)
-      : CallAnalyzer(TTI, GetAssumptionCache, GetBFI, PSI, ORE, Callee, Call),
+      : CallAnalyzer(Callee, Call, TTI, GetAssumptionCache, GetBFI, PSI, ORE),
         ComputeFullInlineCost(OptComputeFullInlineCost ||
                               Params.ComputeFullInlineCost || ORE),
         Params(Params), Threshold(Params.DefaultThreshold),
         BoostIndirectCalls(BoostIndirect), IgnoreThreshold(IgnoreThreshold) {}
 
   /// Annotation Writer for cost annotation
   CostAnnotationWriter Writer;
 
if (!Caller->hasMinSize()) {
 
     // FIXME: After switching to the new passmanager, simplify the logic below
     // by checking only the callsite hotness/coldness as we will reliably
     // have local profile information.
     //
     // Callsite hotness and coldness can be determined if sample profile is
     // used (which adds hotness metadata to calls) or if caller's
     // BlockFrequencyInfo is available.
-    BlockFrequencyInfo *CallerBFI = GetBFI ? &((*GetBFI)(*Caller)) : nullptr;
+    BlockFrequencyInfo *CallerBFI = GetBFI ? &(GetBFI(*Caller)) : nullptr;
     auto HotCallSiteThreshold = getHotCallSiteThreshold(Call, CallerBFI);
     if (!Caller->hasOptSize() && HotCallSiteThreshold) {
       LLVM_DEBUG(dbgs() << "Hot callsite.\n");
       // FIXME: This should update the threshold only if it exceeds the
       // current threshold, but AutoFDO + ThinLTO currently relies on this
       // behavior to prevent inlining of hot callsites during ThinLTO
       // compile phase.
       Threshold = HotCallSiteThreshold.getValue();
bool CallAnalyzer::visitSwitchInst(SwitchInst &SI) {
   // proportional to the size of the tree or the size of jump table range.
   //
   // NB: We convert large switches which are just used to initialize large phi
   // nodes to lookup tables instead in simplify-cfg, so this shouldn't prevent
   // inlining those. It will prevent inlining in cases where the optimization
   // does not (yet) fire.
 
   unsigned JumpTableSize = 0;
-  BlockFrequencyInfo *BFI = GetBFI ? &((*GetBFI)(F)) : nullptr;
+  BlockFrequencyInfo *BFI = GetBFI ? &(GetBFI(F)) : nullptr;
   unsigned NumCaseCluster =
       TTI.getEstimatedNumberOfCaseClusters(SI, JumpTableSize, PSI, BFI);
 
   onFinalizeSwitch(JumpTableSize, NumCaseCluster);
   return false;
 }
 
 bool CallAnalyzer::visitIndirectBrInst(IndirectBrInst &IBI) {
int llvm::getCallsiteCost(CallBase &Call, const DataLayout &DL) {
   }
   // The call instruction also disappears after inlining.
   Cost += InlineConstants::InstrCost + InlineConstants::CallPenalty;
   return Cost;
 }
 
 InlineCost llvm::getInlineCost(
     CallBase &Call, const InlineParams &Params, TargetTransformInfo &CalleeTTI,
-    std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-    Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI,
+    function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
     function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
+    function_ref<BlockFrequencyInfo &(Function &)> GetBFI,
     ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE) {
   return getInlineCost(Call, Call.getCalledFunction(), Params, CalleeTTI,
-                       GetAssumptionCache, GetBFI, GetTLI, PSI, ORE);
+                       GetAssumptionCache, GetTLI, GetBFI, PSI, ORE);
 }
 
 Optional<int> llvm::getInliningCostEstimate(
     CallBase &Call, TargetTransformInfo &CalleeTTI,
-    std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-    Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI,
+    function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
+    function_ref<BlockFrequencyInfo &(Function &)> GetBFI,
     ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE) {
   const InlineParams Params = {/* DefaultThreshold*/ 0,
                                /*HintThreshold*/ {},
                                /*ColdThreshold*/ {},
                                /*OptSizeThreshold*/ {},
                                /*OptMinSizeThreshold*/ {},
                                /*HotCallSiteThreshold*/ {},
                                /*LocallyHotCallSiteThreshold*/ {},
                                /*ColdCallSiteThreshold*/ {},
                                /* ComputeFullInlineCost*/ true};
 
-  InlineCostCallAnalyzer CA(CalleeTTI, GetAssumptionCache, GetBFI, PSI, ORE,
-                            *Call.getCalledFunction(), Call, Params, true,
+  InlineCostCallAnalyzer CA(*Call.getCalledFunction(), Call, Params, CalleeTTI,
+                            GetAssumptionCache, GetBFI, PSI, ORE, true,
                             /*IgnoreThreshold*/ true);
   auto R = CA.analyze();
   if (!R.isSuccess())
     return None;
   return CA.getCost();
 }
 
 Optional<InlineResult> llvm::getAttributeBasedInliningDecision(
if (Call.isNoInline())
     return InlineResult::failure("noinline call site attribute");
 
   return None;
 }
 
 InlineCost llvm::getInlineCost(
     CallBase &Call, Function *Callee, const InlineParams &Params,
     TargetTransformInfo &CalleeTTI,
-    std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
-    Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI,
+    function_ref<AssumptionCache &(Function &)> GetAssumptionCache,
     function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
+    function_ref<BlockFrequencyInfo &(Function &)> GetBFI,
     ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE) {
 
   auto UserDecision =
       llvm::getAttributeBasedInliningDecision(Call, Callee, CalleeTTI, GetTLI);
 
   if (UserDecision.hasValue()) {
     if (UserDecision->isSuccess())
       return llvm::InlineCost::getAlways("always inline attribute");
     return llvm::InlineCost::getNever(UserDecision->getFailureReason());
   }
 
   LLVM_DEBUG(llvm::dbgs() << "      Analyzing call of " << Callee->getName()
                           << "... (caller:" << Call.getCaller()->getName()
                           << ")\n");
 
-  InlineCostCallAnalyzer CA(CalleeTTI, GetAssumptionCache, GetBFI, PSI, ORE,
-                            *Callee, Call, Params);
+  InlineCostCallAnalyzer CA(*Callee, Call, Params, CalleeTTI,
+                            GetAssumptionCache, GetBFI, PSI, ORE);
   InlineResult ShouldInline = CA.analyze();
 
   LLVM_DEBUG(CA.dump());
 
   // Check if there was a reason to force inlining or no inlining.
   if (!ShouldInline.isSuccess() && CA.getCost() < CA.getThreshold())
     return InlineCost::getNever(ShouldInline.getFailureReason());
   if (ShouldInline.isSuccess() && CA.getCost() >= CA.getThreshold())

llvm/lib/Target/AMDGPU/AMDGPUInline.cpp

InlineCost AMDGPUInliner::getInlineCost(CallBase &CB) {
   const auto &BBs = Caller->getBasicBlockList();
   if (!BBs.empty()) {
     auto DI = OptimizationRemark(DEBUG_TYPE, "", DebugLoc(), &BBs.front());
     if (DI.isEnabled())
       RemarksEnabled = true;
   }
 
   OptimizationRemarkEmitter ORE(Caller);
-  std::function<AssumptionCache &(Function &)> GetAssumptionCache =
-      [this](Function &F) -> AssumptionCache & {
+  auto GetAssumptionCache = [this](Function &F) -> AssumptionCache & {
     return ACT->getAssumptionCache(F);
   };
 
-  auto IC =
-      llvm::getInlineCost(CB, Callee, LocalParams, TTI, GetAssumptionCache,
-                          None, GetTLI, PSI, RemarksEnabled ? &ORE : nullptr);
+  auto IC = llvm::getInlineCost(CB, Callee, LocalParams, TTI,
+                                GetAssumptionCache, GetTLI, nullptr, PSI,
+                                RemarksEnabled ? &ORE : nullptr);
 
   if (IC && !IC.isAlways() && !Callee->hasFnAttribute(Attribute::InlineHint)) {
     // Single BB does not increase total BB amount, thus subtract 1
     size_t Size = Caller->size() + Callee->size() - 1;
     if (MaxBB && Size > MaxBB)
       return llvm::InlineCost::getNever("max number of bb exceeded");
   }
   return IC;
 }

llvm/lib/Transforms/IPO/AlwaysInliner.cpp

 
 #define DEBUG_TYPE "inline"
 
 PreservedAnalyses AlwaysInlinerPass::run(Module &M,
                                          ModuleAnalysisManager &MAM) {
   // Add inline assumptions during code generation.
   FunctionAnalysisManager &FAM =
       MAM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
-  std::function<AssumptionCache &(Function &)> GetAssumptionCache =
-      [&](Function &F) -> AssumptionCache & {
+  auto GetAssumptionCache = [&](Function &F) -> AssumptionCache & {
     return FAM.getResult<AssumptionAnalysis>(F);
   };
-  InlineFunctionInfo IFI(/*cg=*/nullptr, &GetAssumptionCache);
+  InlineFunctionInfo IFI(/*cg=*/nullptr, GetAssumptionCache);
 
   SmallSetVector<CallBase *, 16> Calls;
   bool Changed = false;
   SmallVector<Function *, 16> InlinedFunctions;
   for (Function &F : M)
     if (!F.isDeclaration() && F.hasFnAttribute(Attribute::AlwaysInline) &&
         isInlineViable(F).isSuccess()) {
       Calls.clear();

llvm/lib/Transforms/IPO/InlineSimple.cpp

if (!BBs.empty()) {
         RemarksEnabled = true;
     }
     OptimizationRemarkEmitter ORE(CB.getCaller());
 
     std::function<AssumptionCache &(Function &)> GetAssumptionCache =
         [&](Function &F) -> AssumptionCache & {
       return ACT->getAssumptionCache(F);
     };
-    return llvm::getInlineCost(CB, Params, TTI, GetAssumptionCache,
-                               /*GetBFI=*/None, GetTLI, PSI,
+    return llvm::getInlineCost(CB, Params, TTI, GetAssumptionCache, GetTLI,
+                               /*GetBFI=*/nullptr, PSI,
                                RemarksEnabled ? &ORE : nullptr);
   }
 
   bool runOnSCC(CallGraphSCC &SCC) override;
   void getAnalysisUsage(AnalysisUsage &AU) const override;
 
 private:
   TargetTransformInfoWrapperPass *TTIWP;

llvm/lib/Transforms/IPO/Inliner.cpp

inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
   // current SCC to the end of the list.
   unsigned FirstCallInSCC = CallSites.size();
   for (unsigned I = 0; I < FirstCallInSCC; ++I)
     if (Function *F = CallSites[I].first->getCalledFunction())
       if (SCCFunctions.count(F))
         std::swap(CallSites[I--], CallSites[--FirstCallInSCC]);
 
   InlinedArrayAllocasTy InlinedArrayAllocas;
-  InlineFunctionInfo InlineInfo(&CG, &GetAssumptionCache, PSI);
+  InlineFunctionInfo InlineInfo(&CG, GetAssumptionCache, PSI);
 
   // Now that we have all of the call sites, loop over them and inline them if
   // it looks profitable to do so.
   bool Changed = false;
   bool LocalChange;
   do {
     LocalChange = false;
     // Iterate over the outer loop because inlining functions can cause indirect
if (CG.lookupSCC(N) != C)
       continue;
     if (F.hasOptNone()) {
       setInlineRemark(*Calls[I].first, "optnone attribute");
       continue;
     }
 
     LLVM_DEBUG(dbgs() << "Inlining calls in: " << F.getName() << "\n");
 
-    std::function<AssumptionCache &(Function &)> GetAssumptionCache =
-        [&](Function &F) -> AssumptionCache & {
+    auto GetAssumptionCache = [&](Function &F) -> AssumptionCache & {
       return FAM.getResult<AssumptionAnalysis>(F);
     };
 
     // Now process as many calls as we have within this caller in the sequnece.
     // We bail out as soon as the caller has to change so we can update the
     // call graph and prepare the context of that new caller.
     bool DidInline = false;
     for (; I < (int)Calls.size() && Calls[I].first->getCaller() == &F; ++I) {
for (; I < (int)Calls.size() && Calls[I].first->getCaller() == &F; ++I) {
       if (!Advice->isInliningRecommended()) {
         Advice->recordUnattemptedInlining();
         continue;
       }
 
       // Setup the data structure used to plumb customization into the
       // `InlineFunction` routine.
       InlineFunctionInfo IFI(
-          /*cg=*/nullptr, &GetAssumptionCache, PSI,
+          /*cg=*/nullptr, GetAssumptionCache, PSI,
           &FAM.getResult<BlockFrequencyAnalysis>(*(CB->getCaller())),
           &FAM.getResult<BlockFrequencyAnalysis>(Callee));
 
       InlineResult IR = InlineFunction(*CB, IFI);
       if (!IR.isSuccess()) {
         Advice->recordUnsuccessfulInlining(IR);
         continue;
       }

llvm/lib/Transforms/IPO/PartialInlining.cpp

struct FunctionOutliningMultiRegionInfo {
   };
 
   SmallVector<OutlineRegionInfo, 4> ORI;
 };
 
 struct PartialInlinerImpl {
 
   PartialInlinerImpl(
-      std::function<AssumptionCache &(Function &)> *GetAC,
+      function_ref<AssumptionCache &(Function &)> GetAC,
       function_ref<AssumptionCache *(Function &)> LookupAC,
-      std::function<TargetTransformInfo &(Function &)> *GTTI,
-      Optional<function_ref<BlockFrequencyInfo &(Function &)>> GBFI,
-      std::function<const TargetLibraryInfo &(Function &)> *GTLI,
-      ProfileSummaryInfo *ProfSI)
+      function_ref<TargetTransformInfo &(Function &)> GTTI,
+      function_ref<const TargetLibraryInfo &(Function &)> GTLI,
+      ProfileSummaryInfo &ProfSI,
+      function_ref<BlockFrequencyInfo &(Function &)> GBFI = nullptr)
       : GetAssumptionCache(GetAC), LookupAssumptionCache(LookupAC),
         GetTTI(GTTI), GetBFI(GBFI), GetTLI(GTLI), PSI(ProfSI) {}
 
   bool run(Module &M);
   // Main part of the transformation that calls helper functions to find
   // outlining candidates, clone & outline the function, and attempt to
   // partially inline the resulting function. Returns true if
   // inlining was successful, false otherwise.  Also returns the outline
struct FunctionCloner {
     std::unique_ptr<FunctionOutliningMultiRegionInfo> ClonedOMRI = nullptr;
     std::unique_ptr<BlockFrequencyInfo> ClonedFuncBFI = nullptr;
     OptimizationRemarkEmitter &ORE;
     function_ref<AssumptionCache *(Function &)> LookupAC;
   };
 
 private:
   int NumPartialInlining = 0;
-  std::function<AssumptionCache &(Function &)> *GetAssumptionCache;
+  function_ref<AssumptionCache &(Function &)> GetAssumptionCache;
   function_ref<AssumptionCache *(Function &)> LookupAssumptionCache;
-  std::function<TargetTransformInfo &(Function &)> *GetTTI;
-  Optional<function_ref<BlockFrequencyInfo &(Function &)>> GetBFI;
-  std::function<const TargetLibraryInfo &(Function &)> *GetTLI;
-  ProfileSummaryInfo *PSI;
+  function_ref<TargetTransformInfo &(Function &)> GetTTI;
+  function_ref<BlockFrequencyInfo &(Function &)> GetBFI;
+  function_ref<const TargetLibraryInfo &(Function &)> GetTLI;
+  ProfileSummaryInfo &PSI;
 
   // Return the frequency of the OutlininingBB relative to F's entry point.
   // The result is no larger than 1 and is represented using BP.
   // (Note that the outlined region's 'head' block can only have incoming
   // edges from the guarding entry blocks).
   BranchProbability getOutliningCallBBRelativeFreq(FunctionCloner &Cloner);
 
   // Return true if the callee of CB should be partially inlined with
struct PartialInlinerLegacyPass : public ModulePass {
 
   bool runOnModule(Module &M) override {
     if (skipModule(M))
       return false;
 
     AssumptionCacheTracker *ACT = &getAnalysis<AssumptionCacheTracker>();
     TargetTransformInfoWrapperPass *TTIWP =
         &getAnalysis<TargetTransformInfoWrapperPass>();
-    ProfileSummaryInfo *PSI =
-        &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+    ProfileSummaryInfo &PSI =
+        getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
 
-    std::function<AssumptionCache &(Function &)> GetAssumptionCache =
-        [&ACT](Function &F) -> AssumptionCache & {
+    auto GetAssumptionCache = [&ACT](Function &F) -> AssumptionCache & {
       return ACT->getAssumptionCache(F);
     };
 
     auto LookupAssumptionCache = [ACT](Function &F) -> AssumptionCache * {
       return ACT->lookupAssumptionCache(F);
     };
 
-    std::function<TargetTransformInfo &(Function &)> GetTTI =
-        [&TTIWP](Function &F) -> TargetTransformInfo & {
+    auto GetTTI = [&TTIWP](Function &F) -> TargetTransformInfo & {
       return TTIWP->getTTI(F);
     };
 
-    std::function<const TargetLibraryInfo &(Function &)> GetTLI =
-        [this](Function &F) -> TargetLibraryInfo & {
+    auto GetTLI = [this](Function &F) -> TargetLibraryInfo & {
       return this->getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
     };
 
-    return PartialInlinerImpl(&GetAssumptionCache, LookupAssumptionCache,
-                              &GetTTI, NoneType::None, &GetTLI, PSI)
+    return PartialInlinerImpl(GetAssumptionCache, LookupAssumptionCache, GetTTI,
+                              GetTLI, PSI)
         .run(M);
   }
 };
 
 } // end anonymous namespace
 
 std::unique_ptr<FunctionOutliningMultiRegionInfo>
 PartialInlinerImpl::computeOutliningColdRegionsInfo(Function *F,
                                                     OptimizationRemarkEmitter &ORE) {
   BasicBlock *EntryBlock = &F->front();
 
   DominatorTree DT(*F);
   LoopInfo LI(DT);
   BranchProbabilityInfo BPI(*F, LI);
   std::unique_ptr<BlockFrequencyInfo> ScopedBFI;
   BlockFrequencyInfo *BFI;
   if (!GetBFI) {
     ScopedBFI.reset(new BlockFrequencyInfo(*F, BPI, LI));
     BFI = ScopedBFI.get();
   } else
-    BFI = &(*GetBFI)(*F);
+    BFI = &(GetBFI(*F));
 
   // Return if we don't have profiling information.
-  if (!PSI->hasInstrumentationProfile())
+  if (!PSI.hasInstrumentationProfile())
     return std::unique_ptr<FunctionOutliningMultiRegionInfo>();
 
   std::unique_ptr<FunctionOutliningMultiRegionInfo> OutliningInfo =
       std::make_unique<FunctionOutliningMultiRegionInfo>();
 
   auto IsSingleEntry = [](SmallVectorImpl<BasicBlock *> &BlockList) {
     BasicBlock *Dom = BlockList.front();
     return BlockList.size() > 1 && Dom->hasNPredecessors(1);
#endif
   // if it reduced the inline cost of the function by 'MinOutlineRegionCost' or
   // more.
   while (!DFS.empty()) {
     auto *thisBB = DFS.back();
     DFS.pop_back();
     // Only consider regions with predecessor blocks that are considered
     // not-cold (default: part of the top 99.99% of all block counters)
     // AND greater than our minimum block execution count (default: 100).
-    if (PSI->isColdBlock(thisBB, BFI) ||
+    if (PSI.isColdBlock(thisBB, BFI) ||
         BBProfileCount(thisBB) < MinBlockCounterExecution)
       continue;
     for (auto SI = succ_begin(thisBB); SI != succ_end(thisBB); ++SI) {
       if (VisitedMap[*SI])
         continue;
       VisitedMap[*SI] = true;
       DFS.push_back(*SI);
       // If branch isn't cold, we skip to the next one.
bool PartialInlinerImpl::shouldPartialInline(
 
   Function *Callee = CB.getCalledFunction();
   assert(Callee == Cloner.ClonedFunc);
 
   if (SkipCostAnalysis)
     return isInlineViable(*Callee).isSuccess();
 
   Function *Caller = CB.getCaller();
-  auto &CalleeTTI = (*GetTTI)(*Callee);
+  auto &CalleeTTI = GetTTI(*Callee);
   bool RemarksEnabled =
       Callee->getContext().getDiagHandlerPtr()->isMissedOptRemarkEnabled(
           DEBUG_TYPE);
   InlineCost IC =
-      getInlineCost(CB, getInlineParams(), CalleeTTI, *GetAssumptionCache,
-                    GetBFI, *GetTLI, PSI, RemarksEnabled ? &ORE : nullptr);
+      getInlineCost(CB, getInlineParams(), CalleeTTI, GetAssumptionCache,
+                    GetTLI, GetBFI, &PSI, RemarksEnabled ? &ORE : nullptr);
 
   if (IC.isAlways()) {
     ORE.emit([&]() {
       return OptimizationRemarkAnalysis(DEBUG_TYPE, "AlwaysInline", &CB)
              << NV("Callee", Cloner.OrigFunc)
              << " should always be fully inlined, not partially";
     });
     return false;
auto ComputeCurrBFI = [&,this](Function *Caller) {
       if (!GetBFI) {
         DominatorTree DT(*Caller);
         LoopInfo LI(DT);
         BranchProbabilityInfo BPI(*Caller, LI);
         TempBFI.reset(new BlockFrequencyInfo(*Caller, BPI, LI));
         CurrentCallerBFI = TempBFI.get();
       } else {
         // New pass manager:
-        CurrentCallerBFI = &(*GetBFI)(*Caller);
+        CurrentCallerBFI = &(GetBFI(*Caller));
       }
   };
 
   for (User *User : Users) {
     CallBase *CB = getSupportedCallBase(User);
     Function *Caller = CB->getCaller();
     if (CurrentCaller != Caller) {
       CurrentCaller = Caller;
std::pair<bool, Function *> PartialInlinerImpl::unswitchFunction(Function *F) {
 
   // Let inliner handle it
   if (F->hasFnAttribute(Attribute::AlwaysInline))
     return {false, nullptr};
 
   if (F->hasFnAttribute(Attribute::NoInline))
     return {false, nullptr};
 
-  if (PSI->isFunctionEntryCold(F))
+  if (PSI.isFunctionEntryCold(F))
     return {false, nullptr};
 
   if (F->users().empty())
     return {false, nullptr};
 
   OptimizationRemarkEmitter ORE(F);
 
   // Only try to outline cold regions if we have a profile summary, which
   // implies we have profiling information.
-  if (PSI->hasProfileSummary() && F->hasProfileData() &&
+  if (PSI.hasProfileSummary() && F->hasProfileData() &&
       !DisableMultiRegionPartialInline) {
     std::unique_ptr<FunctionOutliningMultiRegionInfo> OMRI =
         computeOutliningColdRegionsInfo(F, ORE);
     if (OMRI) {
       FunctionCloner Cloner(F, OMRI.get(), ORE, LookupAssumptionCache);
 
 #ifndef NDEBUG
       if (TracePartialInlining) {
-        dbgs() << "HotCountThreshold = " << PSI->getHotCountThreshold() << "\n";
-        dbgs() << "ColdCountThreshold = " << PSI->getColdCountThreshold()
+        dbgs() << "HotCountThreshold = " << PSI.getHotCountThreshold() << "\n";
+        dbgs() << "ColdCountThreshold = " << PSI.getColdCountThreshold()
                << "\n";
       }
 #endif
       bool DidOutline = Cloner.doMultiRegionFunctionOutlining();
 
       if (DidOutline) {
 #ifndef NDEBUG
         if (TracePartialInlining) {
if (!shouldPartialInline(*CB, Cloner, WeightedRcost, CallerORE))
       continue;
 
     // Construct remark before doing the inlining, as after successful inlining
     // the callsite is removed.
     OptimizationRemark OR(DEBUG_TYPE, "PartiallyInlined", CB);
     OR << ore::NV("Callee", Cloner.OrigFunc) << " partially inlined into "
        << ore::NV("Caller", CB->getCaller());
 
-    InlineFunctionInfo IFI(nullptr, GetAssumptionCache, PSI);
+    InlineFunctionInfo IFI(nullptr, GetAssumptionCache, &PSI);
     // We can only forward varargs when we outlined a single region, else we
     // bail on vararg functions.
     if (!InlineFunction(*CB, IFI, nullptr, true,
                         (Cloner.ClonedOI ? Cloner.OutlinedFunctions.back().first
                                          : nullptr))
              .isSuccess())
       continue;
 

 ModulePass *llvm::createPartialInliningPass() {
   return new PartialInlinerLegacyPass();
 }
 
 PreservedAnalyses PartialInlinerPass::run(Module &M,
                                           ModuleAnalysisManager &AM) {
   auto &FAM = AM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
 
-  std::function<AssumptionCache &(Function &)> GetAssumptionCache =
-      [&FAM](Function &F) -> AssumptionCache & {
+  auto GetAssumptionCache = [&FAM](Function &F) -> AssumptionCache & {
     return FAM.getResult<AssumptionAnalysis>(F);
   };
 
   auto LookupAssumptionCache = [&FAM](Function &F) -> AssumptionCache * {
     return FAM.getCachedResult<AssumptionAnalysis>(F);
   };
 
-  std::function<BlockFrequencyInfo &(Function &)> GetBFI =
-      [&FAM](Function &F) -> BlockFrequencyInfo & {
+  auto GetBFI = [&FAM](Function &F) -> BlockFrequencyInfo & {
     return FAM.getResult<BlockFrequencyAnalysis>(F);
   };
 
-  std::function<TargetTransformInfo &(Function &)> GetTTI =
-      [&FAM](Function &F) -> TargetTransformInfo & {
+  auto GetTTI = [&FAM](Function &F) -> TargetTransformInfo & {
     return FAM.getResult<TargetIRAnalysis>(F);
   };
 
-  std::function<const TargetLibraryInfo &(Function &)> GetTLI =
-      [&FAM](Function &F) -> TargetLibraryInfo & {
+  auto GetTLI = [&FAM](Function &F) -> TargetLibraryInfo & {
     return FAM.getResult<TargetLibraryAnalysis>(F);
   };
 
-  ProfileSummaryInfo *PSI = &AM.getResult<ProfileSummaryAnalysis>(M);
+  ProfileSummaryInfo &PSI = AM.getResult<ProfileSummaryAnalysis>(M);
 
-  if (PartialInlinerImpl(&GetAssumptionCache, LookupAssumptionCache, &GetTTI,
-                         {GetBFI}, &GetTLI, PSI)
+  if (PartialInlinerImpl(GetAssumptionCache, LookupAssumptionCache, GetTTI,
+                         GetTLI, PSI, GetBFI)
           .run(M))
     return PreservedAnalyses::none();
   return PreservedAnalyses::all();
 }

llvm/lib/Transforms/IPO/SampleProfile.cpp

bool SampleProfileLoader::inlineCallInstruction(CallBase &CB) {
   InlineParams Params = getInlineParams();
   Params.ComputeFullInlineCost = true;
   // Checks if there is anything in the reachable portion of the callee at
   // this callsite that makes this inlining potentially illegal. Need to
   // set ComputeFullInlineCost, otherwise getInlineCost may return early
   // when cost exceeds threshold without checking all IRs in the callee.
   // The acutal cost does not matter because we only checks isNever() to
   // see if it is legal to inline the callsite.
-  InlineCost Cost = getInlineCost(CB, Params, GetTTI(*CalledFunction), GetAC,
-                                  None, GetTLI, nullptr, nullptr);
+  InlineCost Cost =
+      getInlineCost(CB, Params, GetTTI(*CalledFunction), GetAC, GetTLI);
   if (Cost.isNever()) {
     ORE->emit(OptimizationRemarkAnalysis(CSINLINE_DEBUG, "InlineFail", DLoc, BB)
               << "incompatible inlining");
     return false;
   }
-  InlineFunctionInfo IFI(nullptr, &GetAC);
+  InlineFunctionInfo IFI(nullptr, GetAC);
   if (InlineFunction(CB, IFI).isSuccess()) {
     // The call to InlineFunction erases I, so we can't pass it here.
     ORE->emit(OptimizationRemark(CSINLINE_DEBUG, "InlineSuccess", DLoc, BB)
               << "inlined callee '" << ore::NV("Callee", CalledFunction)
               << "' into '" << ore::NV("Caller", BB->getParent()) << "'");
     return true;
   }
   return false;
 }
 
 bool SampleProfileLoader::shouldInlineColdCallee(CallBase &CallInst) {
   if (!ProfileSizeInline)
     return false;
 
   Function *Callee = CallInst.getCalledFunction();
   if (Callee == nullptr)
     return false;
 
   InlineCost Cost = getInlineCost(CallInst, getInlineParams(), GetTTI(*Callee),
-                                  GetAC, None, GetTLI, nullptr, nullptr);
+                                  GetAC, GetTLI);
 
   return Cost.getCost() <= SampleColdCallSiteThreshold;
 }
 
 void SampleProfileLoader::emitOptimizationRemarksForInlineCandidates(
     const SmallVectorImpl<CallBase *> &Candidates, const Function &F,
     bool Hot) {
   for (auto I : Candidates) {

llvm/lib/Transforms/Utils/InlineFunction.cpp

 }
 
 /// If the inlined function has non-byval align arguments, then
 /// add @llvm.assume-based alignment assumptions to preserve this information.
 static void AddAlignmentAssumptions(CallBase &CB, InlineFunctionInfo &IFI) {
   if (!PreserveAlignmentAssumptions || !IFI.GetAssumptionCache)
     return;
 
-  AssumptionCache *AC = &(*IFI.GetAssumptionCache)(*CB.getCaller());
+  AssumptionCache *AC = &IFI.GetAssumptionCache(*CB.getCaller());
   auto &DL = CB.getCaller()->getParent()->getDataLayout();
 
   // To avoid inserting redundant assumptions, we should check for assumptions
   // already in the caller. To do this, we might need a DT of the caller.
   DominatorTree DT;
   bool DTCalculated = false;
 
   Function *CalledFunc = CB.getCalledFunction();
static Value *HandleByValArgument(Value *Arg, Instruction *TheCall,
   if (CalledFunc->onlyReadsMemory()) {
     // If the byval argument has a specified alignment that is greater than the
     // passed in pointer, then we either have to round up the input pointer or
     // give up on this transformation.
     if (ByValAlignment <= 1)  // 0 = unspecified, 1 = no particular alignment.
       return Arg;
 
     AssumptionCache *AC =
-        IFI.GetAssumptionCache ? &(*IFI.GetAssumptionCache)(*Caller) : nullptr;
+        IFI.GetAssumptionCache ? &IFI.GetAssumptionCache(*Caller) : nullptr;
 
     // If the pointer is already known to be sufficiently aligned, or if we can
     // round it up to a larger alignment, then we don't need a temporary.
     if (getOrEnforceKnownAlignment(Arg, Align(ByValAlignment), DL, TheCall,
                                    AC) >= ByValAlignment)
       return Arg;
 
     // Otherwise, we have to make a memcpy to get a safe alignment.  This is bad
Function::iterator FirstNewBlock;
 
     // TODO: Remove this when users have been updated to the assume bundles.
     // Add alignment assumptions if necessary. We do this before the inlined
     // instructions are actually cloned into the caller so that we can easily
     // check what will be known at the start of the inlined code.
     AddAlignmentAssumptions(CB, IFI);
 
     AssumptionCache *AC =
-        IFI.GetAssumptionCache ? &(*IFI.GetAssumptionCache)(*Caller) : nullptr;
+        IFI.GetAssumptionCache ? &IFI.GetAssumptionCache(*Caller) : nullptr;
 
     /// Preserve all attributes on of the call and its parameters.
     salvageKnowledge(&CB, AC);
 
     // We want the inliner to prune the code as it copies.  We would LOVE to
     // have no dead or constant instructions leftover after inlining occurs
     // (which can happen, e.g., because an argument was constant), but we'll be
     // happy with whatever the cloner can do.
Function::iterator FirstNewBlock;
 
     // Propagate llvm.mem.parallel_loop_access if necessary.
     PropagateParallelLoopAccessMetadata(CB, VMap);
 
     // Register any cloned assumptions.
     if (IFI.GetAssumptionCache)
       for (BasicBlock &NewBlock :
            make_range(FirstNewBlock->getIterator(), Caller->end()))
-        for (Instruction &I : NewBlock) {
+        for (Instruction &I : NewBlock)
           if (auto *II = dyn_cast<IntrinsicInst>(&I))
             if (II->getIntrinsicID() == Intrinsic::assume)
-              (*IFI.GetAssumptionCache)(*Caller).registerAssumption(II);
-        }
+              IFI.GetAssumptionCache(*Caller).registerAssumption(II);
   }
 
   // If there are any alloca instructions in the block that used to be the entry
   // block for the callee, move them to the entry block of the caller.  First
   // calculate which instruction they should be inserted before.  We insert the
   // instructions at the end of the current alloca list.
   {
     BasicBlock::iterator InsertPoint = Caller->begin()->begin();
llvm::InlineResult llvm::InlineFunction(CallBase &CB, InlineFunctionInfo &IFI,
   // Now we can remove the CalleeEntry block, which is now empty.
   Caller->getBasicBlockList().erase(CalleeEntry);
 
   // If we inserted a phi node, check to see if it has a single value (e.g. all
   // the entries are the same or undef).  If so, remove the PHI so it doesn't
   // block other optimizations.
   if (PHI) {
     AssumptionCache *AC =
-        IFI.GetAssumptionCache ? &(*IFI.GetAssumptionCache)(*Caller) : nullptr;
+        IFI.GetAssumptionCache ? &IFI.GetAssumptionCache(*Caller) : nullptr;
     auto &DL = Caller->getParent()->getDataLayout();
     if (Value *V = SimplifyInstruction(PHI, {DL, nullptr, nullptr, AC})) {
       PHI->replaceAllUsesWith(V);
       PHI->eraseFromParent();
     }
   }
 
   return InlineResult::success();
 }