[NewPM][Inliner] Move the 'always inliner' case in the same CGSCC pass as 'regular' inliner

[mtrofin]

Summary

Expanding from D94808 - we ensure the same InlineAdvisor is used by both
InlinerPass instances. The notion of mandatory inlining is moved into
the core InlineAdvisor: advisors anyway have to handle that case, so
this change also factors out that a bit better.

[mtrofin]

patched tests other than Other/<NPM> ones.

We want to rationalize emitting remarks, see also D94334; I'd prefer first landing the always inlining refactoring, because that would impact the remarks refactoring more than vice-versa (I think).

[aeubanks]

overall looks good, just a couple small comments

llvm/lib/Analysis/InlineAdvisor.cpp

463

I see this check a lot, should this be handled in some common place instead? Like getMandatoryKind()?

llvm/lib/Analysis/MLInlineAdvisor.cpp

254

Is there a reason to track mandatory inlines? Seems like extra noise

[mtrofin]

llvm/lib/Analysis/InlineAdvisor.cpp

463

this is the recursion avoidance test. it's separate from mandatory - I suppose we can factor it upfront.

llvm/lib/Analysis/MLInlineAdvisor.cpp

254

yes, they change the stats that this inline advisor is tracking (currently nr edges, nodes, stuff like that)

[aeubanks]

llvm/lib/Analysis/InlineAdvisor.cpp

463

We don't inline self-recursive CallBases right? Seems like we should always get a Never in that case. But not super important to factor that out right now.

[mtrofin]

llvm/lib/Analysis/InlineAdvisor.cpp

463

right - I kept going back and forth between letting advisors handle that - you could, for example, imagine one that handled recursion and tracked caller/callee to allow a max number of recursive inlinings. But also something that can be factored now, and we deal with it when we get there.

[mtrofin]

updated with all tests

clang/test/Frontend/optimization-remark-line-directive.c

 // This file tests -Rpass diagnostics together with #line
 // directives. We cannot map #line directives back to
 // a SourceLocation.
 
 // RUN: %clang_cc1 %s -Rpass=inline -debug-info-kind=line-tables-only -emit-llvm-only -verify -fno-experimental-new-pass-manager
 
 // The new PM inliner is not added to the default pipeline at O0, so we add
 // some optimizations to trigger it.
-// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -debug-info-kind=line-tables-only -emit-llvm-only -verify -mllvm -mandatory-inlining-first=0
+// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -debug-info-kind=line-tables-only -emit-llvm-only -verify
 
 int foo(int x, int y) __attribute__((always_inline));
 int foo(int x, int y) { return x + y; }
 
 // expected-remark@+2 {{foo inlined into bar}} expected-note@+2 {{could not determine the original source location for /bad/path/to/original.c:1230:25}}
 #line 1230 "/bad/path/to/original.c"
 int bar(int j) { return foo(j, j - 2); }

clang/test/Frontend/optimization-remark-new-pm.c

 // Verify that remarks for the inliner appear. The remarks under the new PM will
 // be slightly different than those emitted by the legacy PM. The new PM inliner
 // also doesnot appear to be added at O0, so we test at O1.
-// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O1 -fexperimental-new-pass-manager -emit-llvm-only -verify -mllvm -mandatory-inlining-first=0
-// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O1 -fexperimental-new-pass-manager -emit-llvm-only -debug-info-kind=line-tables-only -verify -mllvm -mandatory-inlining-first=0
+// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O1 -fexperimental-new-pass-manager -emit-llvm-only -verify
+// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O1 -fexperimental-new-pass-manager -emit-llvm-only -debug-info-kind=line-tables-only -verify
 
 int foo(int x, int y) __attribute__((always_inline));
 int foo(int x, int y) { return x + y; }
 
 float foz(int x, int y) __attribute__((noinline));
 float foz(int x, int y) { return x * y; }
 
 // The negative diagnostics are emitted twice because the inliner runs
 // twice.
 //
 int bar(int j) {
   // expected-remark@+2 {{foz not inlined into bar because it should never be inlined (cost=never)}}
   // expected-remark@+1 {{foo inlined into bar}}
   return foo(j, j - 2) * foz(j - 2, j);
 }

clang/test/Frontend/optimization-remark-with-hotness-new-pm.c

 // RUN:     %S/Inputs/optimization-remark-with-hotness-sample.proftext \
 // RUN:     -o %t-sample.profdata
 //
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
 // RUN:     -fprofile-instrument-use-path=%t.profdata -Rpass=inline \
 // RUN:     -fexperimental-new-pass-manager -O1 \
 // RUN:     -Rpass-analysis=inline -Rpass-missed=inline \
-// RUN:     -fdiagnostics-show-hotness -verify -mllvm -mandatory-inlining-first=0
+// RUN:     -fdiagnostics-show-hotness -verify
 // The clang version of the previous test.
 // RUN: %clang -target x86_64-apple-macosx10.9 %s -c -emit-llvm -o /dev/null \
 // RUN:     -fprofile-instr-use=%t.profdata -Rpass=inline \
 // RUN:     -fexperimental-new-pass-manager -O1 \
 // RUN:     -Rpass-analysis=inline -Rpass-missed=inline \
-// RUN:     -fdiagnostics-show-hotness -Xclang -verify -mllvm -mandatory-inlining-first=0
+// RUN:     -fdiagnostics-show-hotness -Xclang -verify
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
 // RUN:     -fprofile-sample-use=%t-sample.profdata -Rpass=inline \
 // RUN:     -fexperimental-new-pass-manager -O1 \
 // RUN:     -Rpass-analysis=inline -Rpass-missed=inline \
 // RUN:     -fdiagnostics-show-hotness -fdiagnostics-hotness-threshold=10 \
-// RUN:     -verify -mllvm -mandatory-inlining-first=0
+// RUN:     -verify
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
 // RUN:     -fprofile-instrument-use-path=%t.profdata -Rpass=inline \
 // RUN:     -fexperimental-new-pass-manager -O1 \
 // RUN:     -Rpass-analysis=inline -Rpass-missed=inline \
-// RUN:     -fdiagnostics-show-hotness -fdiagnostics-hotness-threshold=10 -verify -mllvm -mandatory-inlining-first=0
+// RUN:     -fdiagnostics-show-hotness -fdiagnostics-hotness-threshold=10 -verify
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
 // RUN:     -fprofile-instrument-use-path=%t.profdata -Rpass=inline \
-// RUN:     -fexperimental-new-pass-manager -O1 -mllvm -mandatory-inlining-first=0 \
+// RUN:     -fexperimental-new-pass-manager -O1 \
 // RUN:     -Rpass-analysis=inline 2>&1 | FileCheck -check-prefix=HOTNESS_OFF %s
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
 // RUN:     -fprofile-instrument-use-path=%t.profdata -Rpass=inline \
-// RUN:     -fexperimental-new-pass-manager -O1 -mllvm -mandatory-inlining-first=0 \
+// RUN:     -fexperimental-new-pass-manager -O1 \
 // RUN:     -Rpass-analysis=inline -Rno-pass-with-hotness 2>&1 | FileCheck \
 // RUN:     -check-prefix=HOTNESS_OFF %s
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
 // RUN:     -fprofile-instrument-use-path=%t.profdata -Rpass=inline \
-// RUN:     -Rpass-analysis=inline -fdiagnostics-show-hotness -mllvm -mandatory-inlining-first=0 \
+// RUN:     -Rpass-analysis=inline -fdiagnostics-show-hotness \
 // RUN:     -fdiagnostics-hotness-threshold=100 2>&1 \
 // RUN:     | FileCheck -allow-empty -check-prefix=THRESHOLD %s
 // RUN: %clang_cc1 -triple x86_64-apple-macosx10.9 -main-file-name \
 // RUN:     optimization-remark-with-hotness.c %s -emit-llvm-only \
-// RUN:     -Rpass=inline -Rpass-analysis=inline -mllvm -mandatory-inlining-first=0 \
+// RUN:     -Rpass=inline -Rpass-analysis=inline \
 // RUN:     -fdiagnostics-show-hotness -fdiagnostics-hotness-threshold=10 2>&1 \
 // RUN:     | FileCheck -check-prefix=NO_PGO %s
 
 int foo(int x, int y) __attribute__((always_inline));
 int foo(int x, int y) { return x + y; }
 
 int sum = 0;
 

clang/test/Frontend/optimization-remark.c

 // This file tests the -Rpass family of flags (-Rpass, -Rpass-missed
 // and -Rpass-analysis) with the inliner. The test is designed to
 // always trigger the inliner, so it should be independent of the
 // optimization level (under the legacy PM). The inliner is not added to the new
 // PM pipeline unless optimizations are present.
 
 // The inliner for the new PM does not seem to be enabled at O0, but we still
 // get the same remarks with at least O1. The remarks are also slightly
 // different and located in another test file.
-// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O0 -fno-experimental-new-pass-manager -emit-llvm-only -verify -mllvm -mandatory-inlining-first=0
-// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O0 -fno-experimental-new-pass-manager -emit-llvm-only -debug-info-kind=line-tables-only -verify -mllvm -mandatory-inlining-first=0
-// RUN: %clang_cc1 %s -Rpass=inline -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>/dev/null | FileCheck %s
+// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O0 -fno-experimental-new-pass-manager -emit-llvm-only -verify
+// RUN: %clang_cc1 %s -Rpass=inline -Rpass-analysis=inline -Rpass-missed=inline -O0 -fno-experimental-new-pass-manager -emit-llvm-only -debug-info-kind=line-tables-only -verify
+// RUN: %clang_cc1 %s -Rpass=inline -emit-llvm -o - 2>/dev/null | FileCheck %s
 //
 // Check that we can override -Rpass= with -Rno-pass.
-// RUN: %clang_cc1 %s -Rpass=inline -fno-experimental-new-pass-manager -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
-// RUN: %clang_cc1 %s -Rpass=inline -Rno-pass -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-NO-REMARKS
-// RUN: %clang_cc1 %s -Rpass=inline -Rno-everything -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-NO-REMARKS
-// RUN: %clang_cc1 %s -Rpass=inline -fno-experimental-new-pass-manager -Rno-everything -Reverything -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -fno-experimental-new-pass-manager -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -Rno-pass -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-NO-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -Rno-everything -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-NO-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -fno-experimental-new-pass-manager -Rno-everything -Reverything -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
 //
 // The inliner for the new PM does not seem to be enabled at O0, but we still
 // get the same remarks with at least O1.
-// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
-// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -Rno-everything -Reverything -emit-llvm -o - -mllvm -mandatory-inlining-first=0  2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -Rno-everything -Reverything -emit-llvm -o -  2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
 //
 // Check that -w doesn't disable remarks.
-// RUN: %clang_cc1 %s -Rpass=inline -fno-experimental-new-pass-manager -w -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
-// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -w -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -fno-experimental-new-pass-manager -w -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+// RUN: %clang_cc1 %s -Rpass=inline -fexperimental-new-pass-manager -O1 -w -emit-llvm -o - 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
 //
 // FIXME: -Reverything should imply -Rpass=.*.
-// RUN: %clang_cc1 %s -Reverything -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>/dev/null | FileCheck %s --check-prefix=CHECK-NO-REMARKS
+// RUN: %clang_cc1 %s -Reverything -emit-llvm -o - 2>/dev/null | FileCheck %s --check-prefix=CHECK-NO-REMARKS
 //
 // FIXME: -Rpass should either imply -Rpass=.* or should be rejected.
-// RUN: %clang_cc1 %s -Rpass -emit-llvm -o - -mllvm -mandatory-inlining-first=0 2>/dev/null | FileCheck %s --check-prefix=CHECK-NO-REMARKS
+// RUN: %clang_cc1 %s -Rpass -emit-llvm -o - 2>/dev/null | FileCheck %s --check-prefix=CHECK-NO-REMARKS
 
 // CHECK-REMARKS: remark:
 // CHECK-NO-REMARKS-NOT: remark:
 
 // -Rpass should produce source location annotations, exclusively (just
 // like -gmlt).
 // CHECK: , !dbg !
 // CHECK-NOT: DW_TAG_base_type

llvm/include/llvm/Analysis/InlineAdvisor.h

 
 namespace llvm {
 class BasicBlock;
 class CallBase;
 class Function;
 class Module;
 class OptimizationRemarkEmitter;
 
-/// There are 4 scenarios we can use the InlineAdvisor:
+/// There are 3 scenarios we can use the InlineAdvisor:
 /// - Default - use manual heuristics.
 ///
-/// - MandatoryOnly - only mandatory inlinings (i.e. AlwaysInline).
-///
 /// - Release mode, the expected mode for production, day to day deployments.
 /// In this mode, when building the compiler, we also compile a pre-trained ML
 /// model to native code, and link it as a static library. This mode has low
 /// overhead and no additional dependencies for the compiler runtime.
 ///
 /// - Development mode, for training new models.
 /// In this mode, we trade off runtime performance for flexibility. This mode
 /// requires the full C Tensorflow API library, and evaluates models
 /// dynamically. This mode also permits generating training logs, for offline
 /// training.
 enum class InliningAdvisorMode : int {
   Default,
-  MandatoryOnly,
   Release,
   Development
 };
 
 class InlineAdvisor;
 /// Capture state between an inlining decision having had been made, and
 /// its impact being observable. When collecting model training data, this
 /// allows recording features/decisions/partial reward data sets.

 /// Interface for deciding whether to inline a call site or not.
 class InlineAdvisor {
 public:
   InlineAdvisor(InlineAdvisor &&) = delete;
   virtual ~InlineAdvisor() { freeDeletedFunctions(); }
 
   /// Get an InlineAdvice containing a recommendation on whether to
   /// inline or not. \p CB is assumed to be a direct call. \p FAM is assumed to
-  /// be up-to-date wrt previous inlining decisions.
+  /// be up-to-date wrt previous inlining decisions. \p MandatoryOnly indicates
+  /// only mandatory (always-inline) call sites should be recommended - this
+  /// allows the InlineAdvisor track such inlininings.
   /// Returns an InlineAdvice with the inlining recommendation.
-  virtual std::unique_ptr<InlineAdvice> getAdvice(CallBase &CB) = 0;
+  std::unique_ptr<InlineAdvice> getAdvice(CallBase &CB,
+                                          bool MandatoryOnly = false);
 
   /// This must be called when the Inliner pass is entered, to allow the
   /// InlineAdvisor update internal state, as result of function passes run
   /// between Inliner pass runs (for the same module).
   virtual void onPassEntry() {}
 
   /// This must be called when the Inliner pass is exited, as function passes
   /// may be run subsequently. This allows an implementation of InlineAdvisor
   /// to prepare for a partial update.
   virtual void onPassExit() {}
 
 protected:
   InlineAdvisor(FunctionAnalysisManager &FAM) : FAM(FAM) {}
+  virtual std::unique_ptr<InlineAdvice> getAdviceImpl(CallBase &CB) = 0;
+  virtual std::unique_ptr<InlineAdvice> getMandatoryAdvice(CallBase &CB,
+                                                           bool Advice);
 
   FunctionAnalysisManager &FAM;
 
   /// We may want to defer deleting functions to after the inlining for a whole
   /// module has finished. This allows us to reliably use function pointers as
   /// unique identifiers, as an efficient implementation detail of the
   /// InlineAdvisor. Otherwise, it is possible the memory allocator
   /// re-allocate Function objects at the same address of a deleted Function;
   /// and Functions are potentially created during the function passes called
   /// after each SCC inlining (e.g. argument promotion does that).
   void freeDeletedFunctions();
 
   bool isFunctionDeleted(const Function *F) const {
     return DeletedFunctions.count(F);
   }
 
+  enum class MandatoryInliningKind { NotMandatory, Always, Never };
+
+  static MandatoryInliningKind getMandatoryKind(CallBase &CB,
+                                                FunctionAnalysisManager &FAM,
+                                                OptimizationRemarkEmitter &ORE);
+
+  OptimizationRemarkEmitter &getCallerORE(CallBase &CB);
+
 private:
   friend class InlineAdvice;
   void markFunctionAsDeleted(Function *F);
   std::unordered_set<const Function *> DeletedFunctions;
 };
 
 /// The default (manual heuristics) implementation of the InlineAdvisor. This
 /// implementation does not need to keep state between inliner pass runs, and is
 /// reusable as-is for inliner pass test scenarios, as well as for regular use.
 class DefaultInlineAdvisor : public InlineAdvisor {
 public:
   DefaultInlineAdvisor(FunctionAnalysisManager &FAM, InlineParams Params)
       : InlineAdvisor(FAM), Params(Params) {}
 
 private:
-  std::unique_ptr<InlineAdvice> getAdvice(CallBase &CB) override;
+  std::unique_ptr<InlineAdvice> getAdviceImpl(CallBase &CB) override;
 
   void onPassExit() override { freeDeletedFunctions(); }
 
   InlineParams Params;
 };
 
-/// Advisor recommending only mandatory (AlwaysInline) cases.
-class MandatoryInlineAdvisor final : public InlineAdvisor {
-  std::unique_ptr<InlineAdvice> getAdvice(CallBase &CB) override;
-
-public:
-  MandatoryInlineAdvisor(FunctionAnalysisManager &FAM) : InlineAdvisor(FAM) {}
-
-  enum class MandatoryInliningKind { NotMandatory, Always, Never };
-
-  static MandatoryInliningKind getMandatoryKind(CallBase &CB,
-                                                FunctionAnalysisManager &FAM,
-                                                OptimizationRemarkEmitter &ORE);
-};
-
 /// The InlineAdvisorAnalysis is a module pass because the InlineAdvisor
 /// needs to capture state right before inlining commences over a module.
 class InlineAdvisorAnalysis : public AnalysisInfoMixin<InlineAdvisorAnalysis> {
 public:
   static AnalysisKey Key;
   InlineAdvisorAnalysis() = default;
   struct Result {
     Result(Module &M, ModuleAnalysisManager &MAM) : M(M), MAM(MAM) {}

llvm/include/llvm/Analysis/MLInlineAdvisor.h

public:
   MLInlineAdvisor(Module &M, ModuleAnalysisManager &MAM,
                   std::unique_ptr<MLModelRunner> ModelRunner);
 
   CallGraph *callGraph() const { return CG.get(); }
   virtual ~MLInlineAdvisor() = default;
 
   void onPassEntry() override;
 
-  std::unique_ptr<InlineAdvice> getAdvice(CallBase &CB) override;
-
   int64_t getIRSize(const Function &F) const { return F.getInstructionCount(); }
   void onSuccessfulInlining(const MLInlineAdvice &Advice,
                             bool CalleeWasDeleted);
 
   bool isForcedToStop() const { return ForceStop; }
   int64_t getLocalCalls(Function &F);
   const MLModelRunner &getModelRunner() const { return *ModelRunner.get(); }
 
 protected:
-  virtual std::unique_ptr<MLInlineAdvice>
-  getMandatoryAdvice(CallBase &CB, OptimizationRemarkEmitter &ORE);
+  std::unique_ptr<InlineAdvice> getAdviceImpl(CallBase &CB) override;
+
+  std::unique_ptr<InlineAdvice> getMandatoryAdvice(CallBase &CB,
+                                                   bool Advice) override;
+
+  virtual std::unique_ptr<MLInlineAdvice> getMandatoryAdviceImpl(CallBase &CB);
 
   virtual std::unique_ptr<MLInlineAdvice>
   getAdviceFromModel(CallBase &CB, OptimizationRemarkEmitter &ORE);
 
   Module &M;
   std::unique_ptr<MLModelRunner> ModelRunner;
 
 private:

llvm/include/llvm/Analysis/ReplayInlineAdvisor.h

 class OptimizationRemarkEmitter;
 
 /// Replay inline advisor that uses optimization remarks from inlining of
 /// previous build to guide current inlining. This is useful for inliner tuning.
 class ReplayInlineAdvisor : public InlineAdvisor {
 public:
   ReplayInlineAdvisor(FunctionAnalysisManager &FAM, LLVMContext &Context,
                       StringRef RemarksFile, bool EmitRemarks);
-  std::unique_ptr<InlineAdvice> getAdvice(CallBase &CB) override;
+  std::unique_ptr<InlineAdvice> getAdviceImpl(CallBase &CB) override;
   bool areReplayRemarksLoaded() const { return HasReplayRemarks; }
 
 private:
   StringSet<> InlineSitesFromRemarks;
   bool HasReplayRemarks = false;
   bool EmitRemarks = false;
 };
 } // namespace llvm
 #endif // LLVM_ANALYSIS_REPLAYINLINEADVISOR_H

llvm/include/llvm/Passes/PassBuilder.h

public:
   ///
   /// \p Phase indicates the current ThinLTO phase.
   ModulePassManager buildModuleSimplificationPipeline(OptimizationLevel Level,
                                                       ThinOrFullLTOPhase Phase);
 
   /// Construct the module pipeline that performs inlining as well as
   /// the inlining-driven cleanups.
   ModuleInlinerWrapperPass buildInlinerPipeline(OptimizationLevel Level,
-                                                ThinOrFullLTOPhase Phase,
-                                                bool MandatoryOnly);
+                                                ThinOrFullLTOPhase Phase);
 
   /// Construct the core LLVM module optimization pipeline.
   ///
   /// This pipeline focuses on optimizing the execution speed of the IR. It
   /// uses cost modeling and thresholds to balance code growth against runtime
   /// improvements. It includes vectorization and other information destroying
   /// transformations. It also cannot generally be run repeatedly on a module
   /// without potentially seriously regressing either runtime performance of

llvm/include/llvm/Transforms/IPO/Inliner.h

 /// It should be noted that the legacy inliners do considerably more than this
 /// inliner pass does. They provide logic for manually merging allocas, and
 /// doing considerable DCE including the DCE of dead functions. This pass makes
 /// every attempt to be simpler. DCE of functions requires complex reasoning
 /// about comdat groups, etc. Instead, it is expected that other more focused
 /// passes be composed to achieve the same end result.
 class InlinerPass : public PassInfoMixin<InlinerPass> {
 public:
-  InlinerPass() = default;
+  InlinerPass(bool OnlyMandatory = false) : OnlyMandatory(OnlyMandatory) {}
   ~InlinerPass();
-  InlinerPass(InlinerPass &&Arg)
-      : ImportedFunctionsStats(std::move(Arg.ImportedFunctionsStats)) {}
+  InlinerPass(InlinerPass &&Arg) = default;
 
   PreservedAnalyses run(LazyCallGraph::SCC &C, CGSCCAnalysisManager &AM,
                         LazyCallGraph &CG, CGSCCUpdateResult &UR);
 
 private:
   InlineAdvisor &getAdvisor(const ModuleAnalysisManagerCGSCCProxy::Result &MAM,
                             FunctionAnalysisManager &FAM, Module &M);
   std::unique_ptr<ImportedFunctionsInliningStatistics> ImportedFunctionsStats;
-  Optional<DefaultInlineAdvisor> OwnedDefaultAdvisor;
+  std::unique_ptr<InlineAdvisor> OwnedAdvisor;
+  const bool OnlyMandatory;
 };
 
 /// Module pass, wrapping the inliner pass. This works in conjunction with the
 /// InlineAdvisorAnalysis to facilitate inlining decisions taking into account
 /// module-wide state, that need to keep track of inter-inliner pass runs, for
 /// a given module. An InlineAdvisor is configured and kept alive for the
 /// duration of the ModuleInlinerWrapperPass::run.
 class ModuleInlinerWrapperPass
     : public PassInfoMixin<ModuleInlinerWrapperPass> {
 public:
   ModuleInlinerWrapperPass(
       InlineParams Params = getInlineParams(), bool Debugging = false,
+      bool MandatoryFirst = true,
       InliningAdvisorMode Mode = InliningAdvisorMode::Default,
       unsigned MaxDevirtIterations = 0);
   ModuleInlinerWrapperPass(ModuleInlinerWrapperPass &&Arg) = default;
 
   PreservedAnalyses run(Module &, ModuleAnalysisManager &);
 
   /// Allow adding more CGSCC passes, besides inlining. This should be called
   /// before run is called, as part of pass pipeline building.

llvm/lib/Analysis/DevelopmentModeInlineAdvisor.cpp

public:
   void updateNativeSizeEstimate(int64_t Change) {
     *CurrentNativeSize += Change;
   }
   void resetNativeSize(Function *F) {
     FAM.invalidate<InlineSizeEstimatorAnalysis>(*F);
   }
 
   std::unique_ptr<MLInlineAdvice>
-  getMandatoryAdvice(CallBase &CB, OptimizationRemarkEmitter &ORE) override;
-  std::unique_ptr<MLInlineAdvice>
   getAdviceFromModel(CallBase &CB, OptimizationRemarkEmitter &ORE) override;
 
   Optional<size_t> getNativeSizeEstimate(const Function &F) const;
 
 private:
   bool isLogging() const { return !!Logger; }
+  std::unique_ptr<MLInlineAdvice> getMandatoryAdviceImpl(CallBase &CB) override;
 
   std::function<bool(CallBase &)> GetDefaultAdvice;
   const bool IsDoingInference;
   std::unique_ptr<TrainingLogger> Logger;
 
   const Optional<int32_t> InitialNativeSize;
   Optional<int32_t> CurrentNativeSize;
 };
if (!R) {
     F.getParent()->getContext().emitError(
         "Native size estimator is not present.");
     return 0;
   }
   return *R;
 }
 
 std::unique_ptr<MLInlineAdvice>
-DevelopmentModeMLInlineAdvisor::getMandatoryAdvice(
-    CallBase &CB, OptimizationRemarkEmitter &ORE) {
-  if (!isLogging())
-    return MLInlineAdvisor::getMandatoryAdvice(CB, ORE);
-
+DevelopmentModeMLInlineAdvisor::getMandatoryAdviceImpl(CallBase &CB) {
   return std::make_unique<LoggingMLInlineAdvice>(
       /*Advisor=*/this,
-      /*CB=*/CB, /*ORE=*/ORE, /*Recommendation=*/true, /*Logger=*/*Logger,
+      /*CB=*/CB, /*ORE=*/getCallerORE(CB), /*Recommendation=*/true,
+      /*Logger=*/*Logger,
       /*CallerSizeEstimateBefore=*/getNativeSizeEstimate(*CB.getCaller()),
       /*CalleeSizeEstimateBefore=*/
       getNativeSizeEstimate(*CB.getCalledFunction()),
       /*DefaultDecision=*/true, /*Mandatory*/ true);
 }
 
 std::unique_ptr<MLInlineAdvice>
 DevelopmentModeMLInlineAdvisor::getAdviceFromModel(

llvm/lib/Analysis/InlineAdvisor.cpp

bool RemarksEnabled =
             DEBUG_TYPE);
     return getInlineCost(CB, Params, CalleeTTI, GetAssumptionCache, GetTLI,
                          GetBFI, PSI, RemarksEnabled ? &ORE : nullptr);
   };
   return llvm::shouldInline(CB, GetInlineCost, ORE,
                             Params.EnableDeferral.getValueOr(false));
 }
 
-std::unique_ptr<InlineAdvice> DefaultInlineAdvisor::getAdvice(CallBase &CB) {
+std::unique_ptr<InlineAdvice>
+DefaultInlineAdvisor::getAdviceImpl(CallBase &CB) {
   auto OIC = getDefaultInlineAdvice(CB, FAM, Params);
   return std::make_unique<DefaultInlineAdvice>(
       this, CB, OIC,
       FAM.getResult<OptimizationRemarkEmitterAnalysis>(*CB.getCaller()));
 }
 
 InlineAdvice::InlineAdvice(InlineAdvisor *Advisor, CallBase &CB,
                            OptimizationRemarkEmitter &ORE,

 
 bool InlineAdvisorAnalysis::Result::tryCreate(InlineParams Params,
                                               InliningAdvisorMode Mode) {
   auto &FAM = MAM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
   switch (Mode) {
   case InliningAdvisorMode::Default:
     Advisor.reset(new DefaultInlineAdvisor(FAM, Params));
     break;
-  case InliningAdvisorMode::MandatoryOnly:
-    Advisor.reset(new MandatoryInlineAdvisor(FAM));
-    break;
   case InliningAdvisorMode::Development:
 #ifdef LLVM_HAVE_TF_API
     Advisor =
         llvm::getDevelopmentModeAdvisor(M, MAM, [&FAM, Params](CallBase &CB) {
           auto OIC = getDefaultInlineAdvice(CB, FAM, Params);
           return OIC.hasValue();
         });
 #endif
ORE.emit([&]() {
     if (ForProfileContext)
       Remark << " to match profiling context";
     Remark << " with " << IC;
     addLocationToRemarks(Remark, DLoc);
     return Remark;
   });
 }
 
-std::unique_ptr<InlineAdvice> MandatoryInlineAdvisor::getAdvice(CallBase &CB) {
-  auto &Caller = *CB.getCaller();
-  auto &Callee = *CB.getCalledFunction();
-  auto &ORE = FAM.getResult<OptimizationRemarkEmitterAnalysis>(Caller);
-
-  bool Advice = MandatoryInliningKind::Always ==
-                    MandatoryInlineAdvisor::getMandatoryKind(CB, FAM, ORE) &&
-                &Caller != &Callee;
-  return std::make_unique<InlineAdvice>(this, CB, ORE, Advice);
+std::unique_ptr<InlineAdvice> InlineAdvisor::getMandatoryAdvice(CallBase &CB,
+                                                                bool Advice) {
+  return std::make_unique<InlineAdvice>(this, CB, getCallerORE(CB), Advice);
 }
 
-MandatoryInlineAdvisor::MandatoryInliningKind
-MandatoryInlineAdvisor::getMandatoryKind(CallBase &CB,
-                                         FunctionAnalysisManager &FAM,
-                                         OptimizationRemarkEmitter &ORE) {
+InlineAdvisor::MandatoryInliningKind
+InlineAdvisor::getMandatoryKind(CallBase &CB, FunctionAnalysisManager &FAM,
   auto &Callee = *CB.getCalledFunction();
 
   auto GetTLI = [&](Function &F) -> const TargetLibraryInfo & {
     return FAM.getResult<TargetLibraryAnalysis>(F);
   };
 
   auto &TIR = FAM.getResult<TargetIRAnalysis>(Callee);
 
   auto TrivialDecision =
       llvm::getAttributeBasedInliningDecision(CB, &Callee, TIR, GetTLI);
 
   if (TrivialDecision.hasValue()) {
     if (TrivialDecision->isSuccess())
       return MandatoryInliningKind::Always;
     else
       return MandatoryInliningKind::Never;
   }
   return MandatoryInliningKind::NotMandatory;
 }
+
+std::unique_ptr<InlineAdvice> InlineAdvisor::getAdvice(CallBase &CB,
+                                                       bool MandatoryOnly) {
+  if (!MandatoryOnly)
+    return getAdviceImpl(CB);
+  bool Advice = CB.getCaller() != CB.getCalledFunction() &&
+                MandatoryInliningKind::Always ==
+                    getMandatoryKind(CB, FAM, getCallerORE(CB));
+  return getMandatoryAdvice(CB, Advice);
+}
+
+OptimizationRemarkEmitter &InlineAdvisor::getCallerORE(CallBase &CB) {
+  return FAM.getResult<OptimizationRemarkEmitterAnalysis>(*CB.getCaller());
+}

llvm/lib/Analysis/MLInlineAdvisor.cpp

 int64_t MLInlineAdvisor::getModuleIRSize() const {
   int64_t Ret = 0;
   for (auto &F : CG->getModule())
     if (!F.isDeclaration())
       Ret += getIRSize(F);
   return Ret;
 }
 
-std::unique_ptr<InlineAdvice> MLInlineAdvisor::getAdvice(CallBase &CB) {
+std::unique_ptr<InlineAdvice> MLInlineAdvisor::getAdviceImpl(CallBase &CB) {
   auto &Caller = *CB.getCaller();
   auto &Callee = *CB.getCalledFunction();
 
   auto GetAssumptionCache = [&](Function &F) -> AssumptionCache & {
     return FAM.getResult<AssumptionAnalysis>(F);
   };
   auto &TIR = FAM.getResult<TargetIRAnalysis>(Callee);
   auto &ORE = FAM.getResult<OptimizationRemarkEmitterAnalysis>(Caller);
 
-  auto MandatoryKind = MandatoryInlineAdvisor::getMandatoryKind(CB, FAM, ORE);
+  auto MandatoryKind = InlineAdvisor::getMandatoryKind(CB, FAM, ORE);
   // If this is a "never inline" case, there won't be any changes to internal
   // state we need to track, so we can just return the base InlineAdvice, which
   // will do nothing interesting.
   // Same thing if this is a recursive case.
-  if (MandatoryKind == MandatoryInlineAdvisor::MandatoryInliningKind::Never ||
+  if (MandatoryKind == InlineAdvisor::MandatoryInliningKind::Never ||
       &Caller == &Callee)
-    return std::make_unique<InlineAdvice>(this, CB, ORE, false);
+    return getMandatoryAdvice(CB, false);
 
   bool Mandatory =
-      MandatoryKind == MandatoryInlineAdvisor::MandatoryInliningKind::Always;
+      MandatoryKind == InlineAdvisor::MandatoryInliningKind::Always;
 
   // If we need to stop, we won't want to track anymore any state changes, so
   // we just return the base InlineAdvice, which acts as a noop.
   if (ForceStop) {
     ORE.emit([&] {
       return OptimizationRemarkMissed(DEBUG_TYPE, "ForceStop", &CB)
              << "Won't attempt inlining because module size grew too much.";
     });
if (!IsCallSiteInlinable) {
       // InlineAdvice, as we don't care about tracking any state changes (which
       // won't happen).
       return std::make_unique<InlineAdvice>(this, CB, ORE, false);
     }
     CostEstimate = *IsCallSiteInlinable;
   }
 
   if (Mandatory)
-    return getMandatoryAdvice(CB, ORE);
+    return getMandatoryAdvice(CB, true);
 
   auto NrCtantParams = 0;
   for (auto I = CB.arg_begin(), E = CB.arg_end(); I != E; ++I) {
     NrCtantParams += (isa<Constant>(*I));
   }
 
   auto &CallerBefore = FAM.getResult<FunctionPropertiesAnalysis>(Caller);
   auto &CalleeBefore = FAM.getResult<FunctionPropertiesAnalysis>(Callee);

 }
 
 std::unique_ptr<MLInlineAdvice>
 MLInlineAdvisor::getAdviceFromModel(CallBase &CB,
                                     OptimizationRemarkEmitter &ORE) {
   return std::make_unique<MLInlineAdvice>(this, CB, ORE, ModelRunner->run());
 }
 
+std::unique_ptr<InlineAdvice> MLInlineAdvisor::getMandatoryAdvice(CallBase &CB,
+                                                                  bool Advice) {
+  // Make sure we track inlinings in all cases - mandatory or not.
+  if (Advice && !ForceStop)
+    return getMandatoryAdviceImpl(CB);
+
+  // If this is a "never inline" case, there won't be any changes to internal
+  // state we need to track, so we can just return the base InlineAdvice, which
+  // will do nothing interesting.
+  // Same if we are forced to stop - we don't track anymore.
+  return std::make_unique<InlineAdvice>(this, CB, getCallerORE(CB), Advice);
+}
+
 std::unique_ptr<MLInlineAdvice>
-MLInlineAdvisor::getMandatoryAdvice(CallBase &CB,
-                                    OptimizationRemarkEmitter &ORE) {
-  return std::make_unique<MLInlineAdvice>(this, CB, ORE, true);
+MLInlineAdvisor::getMandatoryAdviceImpl(CallBase &CB) {
+  return std::make_unique<MLInlineAdvice>(this, CB, getCallerORE(CB), true);
 }
 
 void MLInlineAdvice::reportContextForRemark(
     DiagnosticInfoOptimizationBase &OR) {
   using namespace ore;
   OR << NV("Callee", Callee->getName());
   for (size_t I = 0; I < NumberOfFeatures; ++I)
     OR << NV(FeatureNameMap[I], getAdvisor()->getModelRunner().getFeature(I));

llvm/lib/Analysis/ReplayInlineAdvisor.cpp

for (; !LineIt.is_at_eof(); ++LineIt) {
 
     std::string Combined = (Callee + CallSite).str();
     InlineSitesFromRemarks.insert(Combined);
   }
 
   HasReplayRemarks = true;
 }
 
-std::unique_ptr<InlineAdvice> ReplayInlineAdvisor::getAdvice(CallBase &CB) {
+std::unique_ptr<InlineAdvice> ReplayInlineAdvisor::getAdviceImpl(CallBase &CB) {
   assert(HasReplayRemarks);
 
   Function &Caller = *CB.getCaller();
   auto &ORE = FAM.getResult<OptimizationRemarkEmitterAnalysis>(Caller);
 
   if (InlineSitesFromRemarks.empty())
     return std::make_unique<DefaultInlineAdvice>(this, CB, None, ORE,
                                                  EmitRemarks);

llvm/lib/Passes/PassBuilder.cpp

void PassBuilder::addPGOInstrPassesForO0(ModulePassManager &MPM,
   MPM.addPass(InstrProfiling(Options, IsCS));
 }
 
 static InlineParams
 getInlineParamsFromOptLevel(PassBuilder::OptimizationLevel Level) {
   return getInlineParams(Level.getSpeedupLevel(), Level.getSizeLevel());
 }
 
-ModuleInlinerWrapperPass PassBuilder::buildInlinerPipeline(
-    OptimizationLevel Level, ThinOrFullLTOPhase Phase, bool MandatoryOnly) {
+ModuleInlinerWrapperPass
+PassBuilder::buildInlinerPipeline(OptimizationLevel Level,
+                                  ThinOrFullLTOPhase Phase) {
   InlineParams IP = getInlineParamsFromOptLevel(Level);
   if (Phase == ThinOrFullLTOPhase::ThinLTOPreLink && PGOOpt &&
       PGOOpt->Action == PGOOptions::SampleUse)
     IP.HotCallSiteThreshold = 0;
 
   if (PGOOpt)
     IP.EnableDeferral = EnablePGOInlineDeferral;
 
-  ModuleInlinerWrapperPass MIWP(
-      IP, DebugLogging,
-      (MandatoryOnly ? InliningAdvisorMode::MandatoryOnly : UseInlineAdvisor),
-      MaxDevirtIterations);
-
-  if (MandatoryOnly)
-    return MIWP;
+  ModuleInlinerWrapperPass MIWP(IP, DebugLogging,
+                                PerformMandatoryInliningsFirst,
+                                UseInlineAdvisor, MaxDevirtIterations);
 
   // Require the GlobalsAA analysis for the module so we can query it within
   // the CGSCC pipeline.
   MIWP.addRequiredModuleAnalysis<GlobalsAA>();
 
   // Require the ProfileSummaryAnalysis for the module so we can query it within
   // the inliner pass.
   MIWP.addRequiredModuleAnalysis<ProfileSummaryAnalysis>();
PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
   if (PGOOpt && Phase != ThinOrFullLTOPhase::ThinLTOPostLink &&
       PGOOpt->CSAction == PGOOptions::CSIRInstr)
     MPM.addPass(PGOInstrumentationGenCreateVar(PGOOpt->CSProfileGenFile));
 
   // Synthesize function entry counts for non-PGO compilation.
   if (EnableSyntheticCounts && !PGOOpt)
     MPM.addPass(SyntheticCountsPropagation());
 
-  if (PerformMandatoryInliningsFirst)
-    MPM.addPass(buildInlinerPipeline(Level, Phase, /*MandatoryOnly=*/true));
-  MPM.addPass(buildInlinerPipeline(Level, Phase, /*MandatoryOnly=*/false));
+  MPM.addPass(buildInlinerPipeline(Level, Phase));
 
   if (EnableMemProfiler && Phase != ThinOrFullLTOPhase::ThinLTOPreLink) {
     MPM.addPass(createModuleToFunctionPassAdaptor(MemProfilerPass()));
     MPM.addPass(ModuleMemProfilerPass());
   }
 
   return MPM;
 }
PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
   FunctionPassManager PeepholeFPM(DebugLogging);
   if (Level == OptimizationLevel::O3)
     PeepholeFPM.addPass(AggressiveInstCombinePass());
   PeepholeFPM.addPass(InstCombinePass());
   invokePeepholeEPCallbacks(PeepholeFPM, Level);
 
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(PeepholeFPM)));
 
-  MPM.addPass(ModuleInlinerWrapperPass(getInlineParamsFromOptLevel(Level),
-                                       DebugLogging,
-                                       InliningAdvisorMode::MandatoryOnly));
   // Note: historically, the PruneEH pass was run first to deduce nounwind and
   // generally clean up exception handling overhead. It isn't clear this is
   // valuable as the inliner doesn't currently care whether it is inlining an
   // invoke or a call.
   // Run the inliner now.
   MPM.addPass(ModuleInlinerWrapperPass(getInlineParamsFromOptLevel(Level),
                                        DebugLogging));
 

llvm/lib/Passes/PassRegistry.def

 MODULE_PASS("globaldce", GlobalDCEPass())
 MODULE_PASS("globalopt", GlobalOptPass())
 MODULE_PASS("globalsplit", GlobalSplitPass())
 MODULE_PASS("hotcoldsplit", HotColdSplittingPass())
 MODULE_PASS("hwasan", HWAddressSanitizerPass(false, false))
 MODULE_PASS("khwasan", HWAddressSanitizerPass(true, true))
 MODULE_PASS("inferattrs", InferFunctionAttrsPass())
 MODULE_PASS("inliner-wrapper", ModuleInlinerWrapperPass())
-MODULE_PASS("always-inliner-wrapper", ModuleInlinerWrapperPass(
+MODULE_PASS("inliner-wrapper-no-mandatory-first", ModuleInlinerWrapperPass(
   getInlineParams(), 
   DebugLogging, 
-  InliningAdvisorMode::MandatoryOnly))
+  false))
 MODULE_PASS("insert-gcov-profiling", GCOVProfilerPass())
 MODULE_PASS("instrorderfile", InstrOrderFilePass())
 MODULE_PASS("instrprof", InstrProfiling())
 MODULE_PASS("internalize", InternalizePass())
 MODULE_PASS("invalidate<all>", InvalidateAllAnalysesPass())
 MODULE_PASS("ipsccp", IPSCCPPass())
 MODULE_PASS("iroutliner", IROutlinerPass())
 MODULE_PASS("print-ir-similarity", IRSimilarityAnalysisPrinterPass(dbgs()))

 MODULE_PASS("print-must-be-executed-contexts", MustBeExecutedContextPrinterPass(dbgs()))
 MODULE_PASS("print-stack-safety", StackSafetyGlobalPrinterPass(dbgs()))
 MODULE_PASS("print<module-debuginfo>", ModuleDebugInfoPrinterPass(dbgs()))
 MODULE_PASS("rewrite-statepoints-for-gc", RewriteStatepointsForGC())
 MODULE_PASS("rewrite-symbols", RewriteSymbolPass())
 MODULE_PASS("rpo-function-attrs", ReversePostOrderFunctionAttrsPass())
 MODULE_PASS("sample-profile", SampleProfileLoaderPass())
 MODULE_PASS("scc-oz-module-inliner",
-  buildInlinerPipeline(OptimizationLevel::Oz, ThinOrFullLTOPhase::None, 
-  /*MandatoryOnly=*/false))
+  buildInlinerPipeline(OptimizationLevel::Oz, ThinOrFullLTOPhase::None))
 MODULE_PASS("loop-extract-single", LoopExtractorPass(1))
 MODULE_PASS("strip", StripSymbolsPass())
 MODULE_PASS("strip-dead-debug-info", StripDeadDebugInfoPass())
 MODULE_PASS("pseudo-probe", SampleProfileProbePass(TM))
 MODULE_PASS("strip-dead-prototypes", StripDeadPrototypesPass())
 MODULE_PASS("strip-debug-declare", StripDebugDeclarePass())
 MODULE_PASS("strip-nondebug", StripNonDebugSymbolsPass())
 MODULE_PASS("strip-nonlinetable-debuginfo", StripNonLineTableDebugInfoPass())

llvm/lib/Transforms/IPO/Inliner.cpp

if (!IAA) {
     // It should still be possible to run the inliner as a stand-alone SCC pass,
     // for test scenarios. In that case, we default to the
     // DefaultInlineAdvisor, which doesn't need to keep state between SCC pass
     // runs. It also uses just the default InlineParams.
     // In this case, we need to use the provided FAM, which is valid for the
     // duration of the inliner pass, and thus the lifetime of the owned advisor.
     // The one we would get from the MAM can be invalidated as a result of the
     // inliner's activity.
-    OwnedDefaultAdvisor.emplace(FAM, getInlineParams());
-    return *OwnedDefaultAdvisor;
+    OwnedAdvisor =
+        std::make_unique<DefaultInlineAdvisor>(FAM, getInlineParams());
+    return *OwnedAdvisor;
   }
   assert(IAA->getAdvisor() &&
          "Expected a present InlineAdvisorAnalysis also have an "
          "InlineAdvisor initialized");
   return *IAA->getAdvisor();
 }
 
 PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
for (; I < (int)Calls.size() && Calls[I].first->getCaller() == &F; ++I) {
           UR.InlinedInternalEdges.count({&N, C})) {
         LLVM_DEBUG(dbgs() << "Skipping inlining internal SCC edge from a node "
                              "previously split out of this SCC by inlining: "
                           << F.getName() << " -> " << Callee.getName() << "\n");
         setInlineRemark(*CB, "recursive SCC split");
         continue;
       }
 
-      auto Advice = Advisor.getAdvice(*CB);
+      auto Advice = Advisor.getAdvice(*CB, OnlyMandatory);
       // Check whether we want to inline this callsite.
       if (!Advice->isInliningRecommended()) {
         Advice->recordUnattemptedInlining();
         continue;
       }
 
       // Setup the data structure used to plumb customization into the
       // `InlineFunction` routine.
PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
   // can preserve the proxy to the function analysis manager.
   PreservedAnalyses PA;
   PA.preserve<FunctionAnalysisManagerCGSCCProxy>();
   return PA;
 }
 
 ModuleInlinerWrapperPass::ModuleInlinerWrapperPass(InlineParams Params,
                                                    bool Debugging,
+                                                   bool MandatoryFirst,
                                                    InliningAdvisorMode Mode,
                                                    unsigned MaxDevirtIterations)
     : Params(Params), Mode(Mode), MaxDevirtIterations(MaxDevirtIterations),
       PM(Debugging), MPM(Debugging) {
   // Run the inliner first. The theory is that we are walking bottom-up and so
   // the callees have already been fully optimized, and we want to inline them
   // into the callers so that our optimizations can reflect that.
   // For PreLinkThinLTO pass, we disable hot-caller heuristic for sample PGO
   // because it makes profile annotation in the backend inaccurate.
+  if (MandatoryFirst)
+    PM.addPass(InlinerPass(/*OnlyMandatory*/ true));
   PM.addPass(InlinerPass());
 }
 
 PreservedAnalyses ModuleInlinerWrapperPass::run(Module &M,
                                                 ModuleAnalysisManager &MAM) {
   auto &IAA = MAM.getResult<InlineAdvisorAnalysis>(M);
   if (!IAA.tryCreate(Params, Mode)) {
     M.getContext().emitError(

llvm/test/Other/new-pm-module-inliner-wrapper.ll

-; RUN: opt -disable-verify -debug-pass-manager -passes='always-inliner-wrapper' -S %s 2>&1 | FileCheck %s
-
-; CHECK: Running pass: InlinerPass
-
-define void @foo() {
-  ret void
-}

llvm/test/Transforms/Inline/inline_stats.ll

 ; First with legacy PM
 ; RUN: opt -S -inline -inliner-function-import-stats=basic < %s 2>&1 | FileCheck %s --check-prefixes=CHECK-BASIC,CHECK
 ; RUN: opt -S -inline -inliner-function-import-stats=verbose < %s 2>&1 | FileCheck %s --check-prefixes="CHECK-VERBOSE",CHECK
 
 ; Do again with new PM
 ; RUN: opt -S -passes=inline -inliner-function-import-stats=basic < %s 2>&1 | FileCheck %s --check-prefixes=CHECK-BASIC,CHECK
 ; RUN: opt -S -passes=inline -inliner-function-import-stats=verbose < %s 2>&1 | FileCheck %s --check-prefixes="CHECK-VERBOSE",CHECK
 
-; RUN: opt -S -passes=inliner-wrapper -inliner-function-import-stats=basic < %s 2>&1 | FileCheck %s --check-prefixes=CHECK-BASIC,CHECK
-; RUN: opt -S -passes=inliner-wrapper -inliner-function-import-stats=verbose < %s 2>&1 | FileCheck %s --check-prefixes="CHECK-VERBOSE",CHECK
+; RUN: opt -S -passes=inliner-wrapper-no-mandatory-first -inliner-function-import-stats=basic < %s 2>&1 | FileCheck %s --check-prefixes=CHECK-BASIC,CHECK
+; RUN: opt -S -passes=inliner-wrapper-no-mandatory-first -inliner-function-import-stats=verbose < %s 2>&1 | FileCheck %s --check-prefixes="CHECK-VERBOSE",CHECK
 
-; RUN: opt -S -passes=always-inliner-wrapper,inliner-wrapper -inliner-function-import-stats=basic < %s 2>&1 | FileCheck %s -check-prefix=WRAPPER
-; RUN: opt -S -passes=always-inliner-wrapper,inliner-wrapper -inliner-function-import-stats=verbose < %s 2>&1 | FileCheck %s --check-prefixes=WRAPPER-VERBOSE,WRAPPER
+; RUN: opt -S -passes=inliner-wrapper -inliner-function-import-stats=basic < %s 2>&1 | FileCheck %s --check-prefix=MANDATORY-FIRST
+; RUN: opt -S -passes=inliner-wrapper -inliner-function-import-stats=verbose < %s 2>&1 | FileCheck %s --check-prefix=MANDATORY-FIRST
 
 ; CHECK: ------- Dumping inliner stats for [<stdin>] -------
 ; CHECK-BASIC-NOT: -- List of inlined functions:
 ; CHECK-BASIC-NOT: -- Inlined not imported function
 ; CHECK-VERBOSE: -- List of inlined functions:
 ; CHECK-VERBOSE: Inlined not imported function [internal2]: #inlines = 6, #inlines_to_importing_module = 2
 ; CHECK-VERBOSE: Inlined imported function [external2]: #inlines = 4, #inlines_to_importing_module = 1
 ; CHECK-VERBOSE: Inlined imported function [external1]: #inlines = 3, #inlines_to_importing_module = 2
 ; CHECK-VERBOSE: Inlined imported function [external5]: #inlines = 1, #inlines_to_importing_module = 1
 ; CHECK-VERBOSE: Inlined imported function [external3]: #inlines = 1, #inlines_to_importing_module = 0
 
 ; CHECK: -- Summary:
 ; CHECK: All functions: 10, imported functions: 7
 ; CHECK: inlined functions: 5 [50% of all functions]
 ; CHECK: imported functions inlined anywhere: 4 [57.14% of imported functions]
 ; CHECK: imported functions inlined into importing module: 3 [42.86% of imported functions], remaining: 4 [57.14% of imported functions]
 ; CHECK: non-imported functions inlined anywhere: 1 [33.33% of non-imported functions]
 ; CHECK: non-imported functions inlined into importing module: 1 [33.33% of non-imported functions]
 
-; WRAPPER-VERBOSE: -- List of inlined functions:
-; WRAPPER-VERBOSE: Inlined imported function [external5]: #inlines = 1, #inlines_to_importing_module = 1
-; WRAPPER: -- Summary:
-; WRAPPER: All functions: 10, imported functions: 7
-; WRAPPER: inlined functions: 1 [10% of all functions]
-; WRAPPER: imported functions inlined anywhere: 1 [14.29% of imported functions]
-; WRAPPER: imported functions inlined into importing module: 1 [14.29% of imported functions], remaining: 6 [85.71% of imported functions]
-; WRAPPER: non-imported functions inlined anywhere: 0 [0% of non-imported functions]
-; WRAPPER: non-imported functions inlined into importing module: 0 [0% of non-imported functions]
+; MANDATORY-FIRST: - Summary:
+; MANDATORY-FIRST: All functions: 10, imported functions: 7
+; MANDATORY-FIRST: inlined functions: 4 [40% of all functions]
+; MANDATORY-FIRST: imported functions inlined anywhere: 3 [42.86% of imported functions]
+; MANDATORY-FIRST: imported functions inlined into importing module: 2 [28.57% of imported functions], remaining: 5 [71.43% of imported functions]
+; MANDATORY-FIRST: non-imported functions inlined anywhere: 1 [33.33% of non-imported functions]
+; MANDATORY-FIRST: non-imported functions inlined into importing module: 1 [33.33% of non-imported functions]
+; MANDATORY-FIRST: -- Summary:
+; MANDATORY-FIRST: All functions: 10, imported functions: 7
+; MANDATORY-FIRST: inlined functions: 1 [10% of all functions]
+; MANDATORY-FIRST: imported functions inlined anywhere: 1 [14.29% of imported functions]
+; MANDATORY-FIRST: imported functions inlined into importing module: 1 [14.29% of imported functions], remaining: 6 [85.71% of imported functions]
+; MANDATORY-FIRST: non-imported functions inlined anywhere: 0 [0% of non-imported functions]
+; MANDATORY-FIRST: non-imported functions inlined into importing module: 0 [0% of non-imported functions]
 
 define void @internal() {
     call fastcc void @external1()
     call fastcc void @internal2()
     call coldcc void @external_big()
     ret void
 }
 

llvm/test/Transforms/Inline/optimization-remarks-with-hotness.ll

 ; RUN: opt < %s -inline -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:     -pass-remarks-analysis=inline -pass-remarks-with-hotness -S 2>&1 \
 ; RUN:     | FileCheck %s
 ; RUN: opt < %s -passes=inline -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:     -pass-remarks-analysis=inline -pass-remarks-with-hotness -S 2>&1 \
 ; RUN:     | FileCheck %s
-; RUN: opt < %s -passes=inliner-wrapper -pass-remarks=inline -pass-remarks-missed=inline \
+; RUN: opt < %s -passes=inliner-wrapper-no-mandatory-first -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:     -pass-remarks-analysis=inline -pass-remarks-with-hotness -S 2>&1 \
 ; RUN:     | FileCheck %s
 
 ; CHECK: foo inlined into bar with (cost=always): always inline attribute (hotness: 30)
 ; CHECK: foz not inlined into bar because it should never be inlined (cost=never): noinline function attribute (hotness: 30)
 
 ; Function Attrs: alwaysinline nounwind uwtable
 define i32 @foo() #0 !prof !1 {

llvm/test/Transforms/Inline/optimization-remarks.ll

 
 ; RUN: opt < %s -passes=inline -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:       -pass-remarks-analysis=inline -S 2>&1 | \
 ; RUN:       FileCheck -check-prefixes=CHECK,NO_HOTNESS,ALWAYS %s
 ; RUN: opt < %s -passes=inline -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:       -pass-remarks-analysis=inline -pass-remarks-with-hotness -S 2>&1 | \
 ; RUN:       FileCheck -check-prefixes=CHECK,HOTNESS,ALWAYS %s
 
-; RUN: opt < %s -passes=inliner-wrapper -pass-remarks=inline -pass-remarks-missed=inline \
+; RUN: opt < %s -passes=inliner-wrapper-no-mandatory-first -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:       -pass-remarks-analysis=inline -S 2>&1 | \
 ; RUN:       FileCheck -check-prefixes=CHECK,NO_HOTNESS,ALWAYS %s
-; RUN: opt < %s -passes=inliner-wrapper -pass-remarks=inline -pass-remarks-missed=inline \
+; RUN: opt < %s -passes=inliner-wrapper-no-mandatory-first -pass-remarks=inline -pass-remarks-missed=inline \
 ; RUN:       -pass-remarks-analysis=inline -pass-remarks-with-hotness -S 2>&1 | \
 ; RUN:       FileCheck -check-prefixes=CHECK,HOTNESS,ALWAYS %s
 
 ; HOTNESS-DAG: fox will not be inlined into bar because its definition is unavailable
 ; NO_HOTNESS-NOT: fox will not be inlined into bar because its definition is unavailable
 ; ALWAYS-DAG: foo inlined into bar with (cost=always): always inline attribute
 ; CHECK-DAG: foz not inlined into bar because it should never be inlined (cost=never): noinline function attribute
 

llvm/test/Transforms/Inline/pr46945.ll

-; RUN: opt %s -o - -S -passes=always-inliner-wrapper | FileCheck %s
 ; RUN: opt %s -o - -S -passes='default<O2>' | FileCheck %s
-; RUN: opt %s -o - -S -passes=inliner-wrapper | FileCheck %s -check-prefix=BASELINE
+; RUN: opt %s -o - -S -passes=inliner-wrapper | FileCheck %s
 
-; In the baseline case, a will be first inlined into b, which makes c recursive,
-; and, thus, un-inlinable. We need a baseline case to make sure intra-SCC order
-; is as expected: b first, then a.
-
-; BASELINE: call void @b()
 ; CHECK-NOT: call void @b()
 define void @b() alwaysinline {
 entry:
   br label %for.cond
 
 for.cond:
   call void @a()
   br label %for.cond
 }
 
 define void @a() {
 entry:
   call void @b()
   ret void
 }