diff --git a/llvm/include/llvm/Analysis/AliasAnalysis.h b/llvm/include/llvm/Analysis/AliasAnalysis.h
--- a/llvm/include/llvm/Analysis/AliasAnalysis.h
+++ b/llvm/include/llvm/Analysis/AliasAnalysis.h
@@ -38,7 +38,6 @@
 #define LLVM_ANALYSIS_ALIASANALYSIS_H
 
 #include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/None.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/MemoryLocation.h"
diff --git a/llvm/include/llvm/Analysis/AliasAnalysisEvaluator.h b/llvm/include/llvm/Analysis/AliasAnalysisEvaluator.h
--- a/llvm/include/llvm/Analysis/AliasAnalysisEvaluator.h
+++ b/llvm/include/llvm/Analysis/AliasAnalysisEvaluator.h
@@ -24,12 +24,12 @@
 #ifndef LLVM_ANALYSIS_ALIASANALYSISEVALUATOR_H
 #define LLVM_ANALYSIS_ALIASANALYSISEVALUATOR_H
 
-#include "llvm/IR/Function.h"
 #include "llvm/IR/PassManager.h"
-#include "llvm/Pass.h"
 
 namespace llvm {
 class AAResults;
+class Function;
+class FunctionPass;
 
 class AAEvaluator : public PassInfoMixin<AAEvaluator> {
   int64_t FunctionCount = 0;
diff --git a/llvm/include/llvm/Analysis/AliasSetTracker.h b/llvm/include/llvm/Analysis/AliasSetTracker.h
--- a/llvm/include/llvm/Analysis/AliasSetTracker.h
+++ b/llvm/include/llvm/Analysis/AliasSetTracker.h
@@ -22,10 +22,8 @@
 #include "llvm/ADT/ilist_node.h"
 #include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/IR/Instruction.h"
-#include "llvm/IR/Metadata.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/ValueHandle.h"
-#include "llvm/Support/Casting.h"
 #include <cassert>
 #include <cstddef>
 #include <cstdint>
diff --git a/llvm/include/llvm/Analysis/AssumeBundleQueries.h b/llvm/include/llvm/Analysis/AssumeBundleQueries.h
--- a/llvm/include/llvm/Analysis/AssumeBundleQueries.h
+++ b/llvm/include/llvm/Analysis/AssumeBundleQueries.h
@@ -14,10 +14,9 @@
 #ifndef LLVM_ANALYSIS_ASSUMEBUNDLEQUERIES_H
 #define LLVM_ANALYSIS_ASSUMEBUNDLEQUERIES_H
 
-#include "llvm/IR/Attributes.h"
+#include "llvm/ADT/DenseMap.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
-#include "llvm/ADT/DenseMap.h"
 
 namespace llvm {
 class AssumptionCache;
diff --git a/llvm/include/llvm/Analysis/BlockFrequencyInfoImpl.h b/llvm/include/llvm/Analysis/BlockFrequencyInfoImpl.h
--- a/llvm/include/llvm/Analysis/BlockFrequencyInfoImpl.h
+++ b/llvm/include/llvm/Analysis/BlockFrequencyInfoImpl.h
@@ -31,7 +31,6 @@
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/DOTGraphTraits.h"
 #include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/ScaledNumber.h"
 #include "llvm/Support/raw_ostream.h"
diff --git a/llvm/include/llvm/Analysis/BranchProbabilityInfo.h b/llvm/include/llvm/Analysis/BranchProbabilityInfo.h
--- a/llvm/include/llvm/Analysis/BranchProbabilityInfo.h
+++ b/llvm/include/llvm/Analysis/BranchProbabilityInfo.h
@@ -16,14 +16,12 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DenseMapInfo.h"
 #include "llvm/ADT/DenseSet.h"
-#include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/BranchProbability.h"
-#include "llvm/Support/Casting.h"
 #include <algorithm>
 #include <cassert>
 #include <cstdint>
diff --git a/llvm/include/llvm/Analysis/CFLAliasAnalysisUtils.h b/llvm/include/llvm/Analysis/CFLAliasAnalysisUtils.h
--- a/llvm/include/llvm/Analysis/CFLAliasAnalysisUtils.h
+++ b/llvm/include/llvm/Analysis/CFLAliasAnalysisUtils.h
@@ -14,10 +14,11 @@
 #ifndef LLVM_ANALYSIS_CFLALIASANALYSISUTILS_H
 #define LLVM_ANALYSIS_CFLALIASANALYSISUTILS_H
 
-#include "llvm/IR/Function.h"
 #include "llvm/IR/ValueHandle.h"
 
 namespace llvm {
+class Function;
+
 namespace cflaa {
 
 template <typename AAResult> struct FunctionHandle final : public CallbackVH {
diff --git a/llvm/include/llvm/Analysis/CFLSteensAliasAnalysis.h b/llvm/include/llvm/Analysis/CFLSteensAliasAnalysis.h
--- a/llvm/include/llvm/Analysis/CFLSteensAliasAnalysis.h
+++ b/llvm/include/llvm/Analysis/CFLSteensAliasAnalysis.h
@@ -21,7 +21,6 @@
 #include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
 #include <forward_list>
 #include <memory>
 
diff --git a/llvm/include/llvm/Analysis/CGSCCPassManager.h b/llvm/include/llvm/Analysis/CGSCCPassManager.h
--- a/llvm/include/llvm/Analysis/CGSCCPassManager.h
+++ b/llvm/include/llvm/Analysis/CGSCCPassManager.h
@@ -88,19 +88,13 @@
 #ifndef LLVM_ANALYSIS_CGSCCPASSMANAGER_H
 #define LLVM_ANALYSIS_CGSCCPASSMANAGER_H
 
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/PriorityWorklist.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/InstIterator.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/ValueHandle.h"
-#include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <cassert>
diff --git a/llvm/include/llvm/Analysis/CallGraph.h b/llvm/include/llvm/Analysis/CallGraph.h
--- a/llvm/include/llvm/Analysis/CallGraph.h
+++ b/llvm/include/llvm/Analysis/CallGraph.h
@@ -46,8 +46,6 @@
 #define LLVM_ANALYSIS_CALLGRAPH_H
 
 #include "llvm/ADT/GraphTraits.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/PassManager.h"
@@ -62,6 +60,7 @@
 namespace llvm {
 
 class CallGraphNode;
+class Function;
 class Module;
 class raw_ostream;
 
diff --git a/llvm/include/llvm/Analysis/CmpInstAnalysis.h b/llvm/include/llvm/Analysis/CmpInstAnalysis.h
--- a/llvm/include/llvm/Analysis/CmpInstAnalysis.h
+++ b/llvm/include/llvm/Analysis/CmpInstAnalysis.h
@@ -18,6 +18,7 @@
 
 namespace llvm {
   class ICmpInst;
+  class Type;
   class Value;
 
   /// Encode a icmp predicate into a three bit mask. These bits are carefully
diff --git a/llvm/include/llvm/Analysis/ConstraintSystem.h b/llvm/include/llvm/Analysis/ConstraintSystem.h
--- a/llvm/include/llvm/Analysis/ConstraintSystem.h
+++ b/llvm/include/llvm/Analysis/ConstraintSystem.h
@@ -11,7 +11,6 @@
 
 #include "llvm/ADT/APInt.h"
 #include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
 
 #include <string>
diff --git a/llvm/include/llvm/Analysis/DivergenceAnalysis.h b/llvm/include/llvm/Analysis/DivergenceAnalysis.h
--- a/llvm/include/llvm/Analysis/DivergenceAnalysis.h
+++ b/llvm/include/llvm/Analysis/DivergenceAnalysis.h
@@ -18,15 +18,17 @@
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/Analysis/SyncDependenceAnalysis.h"
 #include "llvm/IR/Function.h"
+#include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
 #include <vector>
 
 namespace llvm {
-class Value;
+class Function;
 class Instruction;
 class Loop;
 class raw_ostream;
 class TargetTransformInfo;
+class Value;
 
 /// \brief Generic divergence analysis for reducible CFGs.
 ///
diff --git a/llvm/include/llvm/Analysis/DominanceFrontierImpl.h b/llvm/include/llvm/Analysis/DominanceFrontierImpl.h
--- a/llvm/include/llvm/Analysis/DominanceFrontierImpl.h
+++ b/llvm/include/llvm/Analysis/DominanceFrontierImpl.h
@@ -17,7 +17,6 @@
 #ifndef LLVM_ANALYSIS_DOMINANCEFRONTIERIMPL_H
 #define LLVM_ANALYSIS_DOMINANCEFRONTIERIMPL_H
 
-#include "llvm/ADT/GraphTraits.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/Analysis/DominanceFrontier.h"
 #include "llvm/Config/llvm-config.h"
diff --git a/llvm/include/llvm/Analysis/EHPersonalities.h b/llvm/include/llvm/Analysis/EHPersonalities.h
--- a/llvm/include/llvm/Analysis/EHPersonalities.h
+++ b/llvm/include/llvm/Analysis/EHPersonalities.h
@@ -11,7 +11,6 @@
 
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/TinyPtrVector.h"
-#include "llvm/Support/ErrorHandling.h"
 
 namespace llvm {
 class BasicBlock;
diff --git a/llvm/include/llvm/Analysis/GlobalsModRef.h b/llvm/include/llvm/Analysis/GlobalsModRef.h
--- a/llvm/include/llvm/Analysis/GlobalsModRef.h
+++ b/llvm/include/llvm/Analysis/GlobalsModRef.h
@@ -15,14 +15,13 @@
 
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/IR/Constants.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Module.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/Pass.h"
 #include <list>
 
 namespace llvm {
 class CallGraph;
+class Function;
 
 /// An alias analysis result set for globals.
 ///
diff --git a/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h b/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
--- a/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
+++ b/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
@@ -51,12 +51,13 @@
 
 #include "llvm/IR/InstVisitor.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/Allocator.h"
 
 namespace llvm {
+class Module;
+
 namespace IRSimilarity {
 
 struct IRInstructionDataList;
diff --git a/llvm/include/llvm/Analysis/IVDescriptors.h b/llvm/include/llvm/Analysis/IVDescriptors.h
--- a/llvm/include/llvm/Analysis/IVDescriptors.h
+++ b/llvm/include/llvm/Analysis/IVDescriptors.h
@@ -13,27 +13,23 @@
 #ifndef LLVM_ANALYSIS_IVDESCRIPTORS_H
 #define LLVM_ANALYSIS_IVDESCRIPTORS_H
 
-#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/IR/InstrTypes.h"
-#include "llvm/IR/Instruction.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/ValueHandle.h"
-#include "llvm/Support/Casting.h"
 
 namespace llvm {
 
-class DemandedBits;
 class AssumptionCache;
+class DemandedBits;
+class DominatorTree;
+class Instruction;
 class Loop;
 class PredicatedScalarEvolution;
 class ScalarEvolution;
 class SCEV;
-class DominatorTree;
 
 /// These are the kinds of recurrences that we support.
 enum class RecurKind {
diff --git a/llvm/include/llvm/Analysis/InlineCost.h b/llvm/include/llvm/Analysis/InlineCost.h
--- a/llvm/include/llvm/Analysis/InlineCost.h
+++ b/llvm/include/llvm/Analysis/InlineCost.h
@@ -14,7 +14,6 @@
 #define LLVM_ANALYSIS_INLINECOST_H
 
 #include "llvm/Analysis/AssumptionCache.h"
-#include "llvm/Analysis/CallGraphSCCPass.h"
 #include "llvm/Analysis/InlineModelFeatureMaps.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include <cassert>
diff --git a/llvm/include/llvm/Analysis/InlineOrder.h b/llvm/include/llvm/Analysis/InlineOrder.h
--- a/llvm/include/llvm/Analysis/InlineOrder.h
+++ b/llvm/include/llvm/Analysis/InlineOrder.h
@@ -11,9 +11,6 @@
 
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
 #include <algorithm>
 #include <utility>
 
diff --git a/llvm/include/llvm/Analysis/InstSimplifyFolder.h b/llvm/include/llvm/Analysis/InstSimplifyFolder.h
--- a/llvm/include/llvm/Analysis/InstSimplifyFolder.h
+++ b/llvm/include/llvm/Analysis/InstSimplifyFolder.h
@@ -22,12 +22,11 @@
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/TargetFolder.h"
-#include "llvm/IR/Constants.h"
 #include "llvm/IR/IRBuilderFolder.h"
-#include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instruction.h"
 
 namespace llvm {
+class Constant;
 
 /// InstSimplifyFolder - Use InstructionSimplify to fold operations to existing
 /// values. Also applies target-specific constant folding when not using
diff --git a/llvm/include/llvm/Analysis/InstructionSimplify.h b/llvm/include/llvm/Analysis/InstructionSimplify.h
--- a/llvm/include/llvm/Analysis/InstructionSimplify.h
+++ b/llvm/include/llvm/Analysis/InstructionSimplify.h
@@ -35,8 +35,6 @@
 #ifndef LLVM_ANALYSIS_INSTRUCTIONSIMPLIFY_H
 #define LLVM_ANALYSIS_INSTRUCTIONSIMPLIFY_H
 
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Operator.h"
 #include "llvm/IR/PatternMatch.h"
 
 namespace llvm {
@@ -49,6 +47,7 @@
 class DataLayout;
 class DominatorTree;
 class Function;
+class Instruction;
 struct LoopStandardAnalysisResults;
 class MDNode;
 class OptimizationRemarkEmitter;
diff --git a/llvm/include/llvm/Analysis/IntervalIterator.h b/llvm/include/llvm/Analysis/IntervalIterator.h
--- a/llvm/include/llvm/Analysis/IntervalIterator.h
+++ b/llvm/include/llvm/Analysis/IntervalIterator.h
@@ -36,8 +36,6 @@
 #include "llvm/Analysis/Interval.h"
 #include "llvm/Analysis/IntervalPartition.h"
 #include "llvm/IR/CFG.h"
-#include "llvm/IR/Function.h"
-#include "llvm/Support/ErrorHandling.h"
 #include <algorithm>
 #include <cassert>
 #include <iterator>
@@ -48,6 +46,7 @@
 namespace llvm {
 
 class BasicBlock;
+class Function;
 
 // getNodeHeader - Given a source graph node and the source graph, return the
 // BasicBlock that is the header node.  This is the opposite of
diff --git a/llvm/include/llvm/Analysis/LazyCallGraph.h b/llvm/include/llvm/Analysis/LazyCallGraph.h
--- a/llvm/include/llvm/Analysis/LazyCallGraph.h
+++ b/llvm/include/llvm/Analysis/LazyCallGraph.h
@@ -38,20 +38,14 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/PointerIntPair.h"
-#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
-#include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/iterator.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
-#include "llvm/IR/Constant.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/Allocator.h"
-#include "llvm/Support/Casting.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cassert>
 #include <iterator>
@@ -60,8 +54,11 @@
 
 namespace llvm {
 
+class Constant;
+class Function;
 template <class GraphType> struct GraphTraits;
 class Module;
+class TargetLibraryInfo;
 class Value;
 
 /// A lazily constructed view of the call graph of a module.
diff --git a/llvm/include/llvm/Analysis/LoopAnalysisManager.h b/llvm/include/llvm/Analysis/LoopAnalysisManager.h
--- a/llvm/include/llvm/Analysis/LoopAnalysisManager.h
+++ b/llvm/include/llvm/Analysis/LoopAnalysisManager.h
@@ -29,7 +29,6 @@
 #ifndef LLVM_ANALYSIS_LOOPANALYSISMANAGER_H
 #define LLVM_ANALYSIS_LOOPANALYSISMANAGER_H
 
-#include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/IR/PassManager.h"
 
 namespace llvm {
diff --git a/llvm/include/llvm/Analysis/LoopCacheAnalysis.h b/llvm/include/llvm/Analysis/LoopCacheAnalysis.h
--- a/llvm/include/llvm/Analysis/LoopCacheAnalysis.h
+++ b/llvm/include/llvm/Analysis/LoopCacheAnalysis.h
@@ -15,7 +15,6 @@
 #define LLVM_ANALYSIS_LOOPCACHEANALYSIS_H
 
 #include "llvm/Analysis/LoopAnalysisManager.h"
-#include "llvm/IR/Instructions.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/raw_ostream.h"
 
@@ -23,6 +22,7 @@
 
 class AAResults;
 class DependenceInfo;
+class Instruction;
 class LPMUpdater;
 class ScalarEvolution;
 class SCEV;
diff --git a/llvm/include/llvm/Analysis/LoopInfo.h b/llvm/include/llvm/Analysis/LoopInfo.h
--- a/llvm/include/llvm/Analysis/LoopInfo.h
+++ b/llvm/include/llvm/Analysis/LoopInfo.h
@@ -44,7 +44,6 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/IR/CFG.h"
-#include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
@@ -55,9 +54,10 @@
 namespace llvm {
 
 class DominatorTree;
+class InductionDescriptor;
+class Instruction;
 class LoopInfo;
 class Loop;
-class InductionDescriptor;
 class MDNode;
 class MemorySSAUpdater;
 class ScalarEvolution;
diff --git a/llvm/include/llvm/Analysis/LoopInfoImpl.h b/llvm/include/llvm/Analysis/LoopInfoImpl.h
--- a/llvm/include/llvm/Analysis/LoopInfoImpl.h
+++ b/llvm/include/llvm/Analysis/LoopInfoImpl.h
@@ -14,7 +14,6 @@
 #ifndef LLVM_ANALYSIS_LOOPINFOIMPL_H
 #define LLVM_ANALYSIS_LOOPINFOIMPL_H
 
-#include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetOperations.h"
diff --git a/llvm/include/llvm/Analysis/LoopUnrollAnalyzer.h b/llvm/include/llvm/Analysis/LoopUnrollAnalyzer.h
--- a/llvm/include/llvm/Analysis/LoopUnrollAnalyzer.h
+++ b/llvm/include/llvm/Analysis/LoopUnrollAnalyzer.h
@@ -36,6 +36,8 @@
 // And finally:
 //   v = b[1]
 namespace llvm {
+class Instruction;
+
 class UnrolledInstAnalyzer : private InstVisitor<UnrolledInstAnalyzer, bool> {
   typedef InstVisitor<UnrolledInstAnalyzer, bool> Base;
   friend class InstVisitor<UnrolledInstAnalyzer, bool>;
diff --git a/llvm/include/llvm/Analysis/MLModelRunner.h b/llvm/include/llvm/Analysis/MLModelRunner.h
--- a/llvm/include/llvm/Analysis/MLModelRunner.h
+++ b/llvm/include/llvm/Analysis/MLModelRunner.h
@@ -10,10 +10,10 @@
 #ifndef LLVM_ANALYSIS_MLMODELRUNNER_H
 #define LLVM_ANALYSIS_MLMODELRUNNER_H
 
-#include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/PassManager.h"
 
 namespace llvm {
+class LLVMContext;
 
 /// MLModelRunner interface: abstraction of a mechanism for evaluating a
 /// tensorflow "saved model".
diff --git a/llvm/include/llvm/Analysis/MemoryLocation.h b/llvm/include/llvm/Analysis/MemoryLocation.h
--- a/llvm/include/llvm/Analysis/MemoryLocation.h
+++ b/llvm/include/llvm/Analysis/MemoryLocation.h
@@ -36,6 +36,7 @@
 class AnyMemIntrinsic;
 class TargetLibraryInfo;
 class VAArgInst;
+class Value;
 
 // Represents the size of a MemoryLocation. Logically, it's an
 // Optional<uint63_t> that also carries a bit to represent whether the integer
diff --git a/llvm/include/llvm/Analysis/MemorySSA.h b/llvm/include/llvm/Analysis/MemorySSA.h
--- a/llvm/include/llvm/Analysis/MemorySSA.h
+++ b/llvm/include/llvm/Analysis/MemorySSA.h
@@ -76,27 +76,16 @@
 #include "llvm/ADT/GraphTraits.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/ilist.h"
 #include "llvm/ADT/ilist_node.h"
-#include "llvm/ADT/iterator.h"
 #include "llvm/ADT/iterator_range.h"
-#include "llvm/ADT/simple_ilist.h"
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/Analysis/PHITransAddr.h"
-#include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/DerivedUser.h"
 #include "llvm/IR/Dominators.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/Operator.h"
 #include "llvm/IR/Type.h"
-#include "llvm/IR/Use.h"
 #include "llvm/IR/User.h"
-#include "llvm/IR/Value.h"
-#include "llvm/IR/ValueHandle.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/CommandLine.h"
 #include <algorithm>
 #include <cassert>
 #include <cstddef>
@@ -106,11 +95,15 @@
 
 namespace llvm {
 
+class BasicBlock;
 class Function;
 class Instruction;
+class LLVMContext;
 class MemoryAccess;
 class MemorySSAWalker;
-class LLVMContext;
+class Module;
+class Use;
+class Value;
 class raw_ostream;
 
 namespace MSSAHelpers {
diff --git a/llvm/include/llvm/Analysis/ModuleDebugInfoPrinter.h b/llvm/include/llvm/Analysis/ModuleDebugInfoPrinter.h
--- a/llvm/include/llvm/Analysis/ModuleDebugInfoPrinter.h
+++ b/llvm/include/llvm/Analysis/ModuleDebugInfoPrinter.h
@@ -11,9 +11,9 @@
 
 #include "llvm/IR/DebugInfo.h"
 #include "llvm/IR/PassManager.h"
-#include "llvm/Support/raw_ostream.h"
 
 namespace llvm {
+class raw_ostream;
 
 class ModuleDebugInfoPrinterPass
     : public PassInfoMixin<ModuleDebugInfoPrinterPass> {
diff --git a/llvm/include/llvm/Analysis/MustExecute.h b/llvm/include/llvm/Analysis/MustExecute.h
--- a/llvm/include/llvm/Analysis/MustExecute.h
+++ b/llvm/include/llvm/Analysis/MustExecute.h
@@ -28,7 +28,6 @@
 #include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/Analysis/InstructionPrecedenceTracking.h"
 #include "llvm/IR/PassManager.h"
-#include "llvm/Support/raw_ostream.h"
 
 namespace llvm {
 
@@ -42,6 +41,7 @@
 class Loop;
 class LoopInfo;
 class PostDominatorTree;
+class raw_ostream;
 
 /// Captures loop safety information.
 /// It keep information for loop blocks may throw exception or otherwise
diff --git a/llvm/include/llvm/Analysis/OverflowInstAnalysis.h b/llvm/include/llvm/Analysis/OverflowInstAnalysis.h
--- a/llvm/include/llvm/Analysis/OverflowInstAnalysis.h
+++ b/llvm/include/llvm/Analysis/OverflowInstAnalysis.h
@@ -14,11 +14,9 @@
 #ifndef LLVM_ANALYSIS_OVERFLOWINSTANALYSIS_H
 #define LLVM_ANALYSIS_OVERFLOWINSTANALYSIS_H
 
-#include "llvm/IR/InstrTypes.h"
-
 namespace llvm {
-class Value;
 class Use;
+class Value;
 
 /// Match one of the patterns up to the select/logic op:
 ///   %Op0 = icmp ne i4 %X, 0
diff --git a/llvm/include/llvm/Analysis/PtrUseVisitor.h b/llvm/include/llvm/Analysis/PtrUseVisitor.h
--- a/llvm/include/llvm/Analysis/PtrUseVisitor.h
+++ b/llvm/include/llvm/Analysis/PtrUseVisitor.h
@@ -26,22 +26,16 @@
 #include "llvm/ADT/PointerIntPair.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/InstVisitor.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
-#include "llvm/IR/Intrinsics.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Use.h"
-#include "llvm/IR/User.h"
-#include "llvm/Support/Casting.h"
 #include <algorithm>
 #include <cassert>
 #include <type_traits>
 
 namespace llvm {
+class DataLayout;
+class Use;
 
 namespace detail {
 
diff --git a/llvm/include/llvm/Analysis/RegionInfo.h b/llvm/include/llvm/Analysis/RegionInfo.h
--- a/llvm/include/llvm/Analysis/RegionInfo.h
+++ b/llvm/include/llvm/Analysis/RegionInfo.h
@@ -42,11 +42,9 @@
 #include "llvm/ADT/PointerIntPair.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/Config/llvm-config.h"
-#include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <cassert>
 #include <map>
@@ -58,6 +56,7 @@
 
 namespace llvm {
 
+class BasicBlock;
 class DominanceFrontier;
 class Loop;
 class LoopInfo;
@@ -67,6 +66,7 @@
 class RegionInfo;
 template <class RegionTr> class RegionInfoBase;
 class RegionNode;
+class raw_ostream;
 
 // Class to be specialized for different users of RegionInfo
 // (i.e. BasicBlocks or MachineBasicBlocks). This is only to avoid needing to
diff --git a/llvm/include/llvm/Analysis/RegionInfoImpl.h b/llvm/include/llvm/Analysis/RegionInfoImpl.h
--- a/llvm/include/llvm/Analysis/RegionInfoImpl.h
+++ b/llvm/include/llvm/Analysis/RegionInfoImpl.h
@@ -15,8 +15,6 @@
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/iterator_range.h"
-#include "llvm/Analysis/DominanceFrontier.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/PostDominators.h"
 #include "llvm/Analysis/RegionInfo.h"
@@ -24,7 +22,6 @@
 #include "llvm/Config/llvm-config.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <cassert>
 #include <iterator>
@@ -37,6 +34,7 @@
 #define DEBUG_TYPE "region"
 
 namespace llvm {
+class raw_ostream;
 
 //===----------------------------------------------------------------------===//
 /// RegionBase Implementation
diff --git a/llvm/include/llvm/Analysis/RegionIterator.h b/llvm/include/llvm/Analysis/RegionIterator.h
--- a/llvm/include/llvm/Analysis/RegionIterator.h
+++ b/llvm/include/llvm/Analysis/RegionIterator.h
@@ -14,8 +14,6 @@
 #include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/GraphTraits.h"
 #include "llvm/ADT/PointerIntPair.h"
-#include "llvm/Analysis/RegionInfo.h"
-#include "llvm/IR/CFG.h"
 #include <cassert>
 #include <iterator>
 #include <type_traits>
@@ -23,6 +21,7 @@
 namespace llvm {
 
 class BasicBlock;
+class RegionInfo;
 
 //===----------------------------------------------------------------------===//
 /// Hierarchical RegionNode successor iterator.
diff --git a/llvm/include/llvm/Analysis/RegionPass.h b/llvm/include/llvm/Analysis/RegionPass.h
--- a/llvm/include/llvm/Analysis/RegionPass.h
+++ b/llvm/include/llvm/Analysis/RegionPass.h
@@ -15,7 +15,6 @@
 #ifndef LLVM_ANALYSIS_REGIONPASS_H
 #define LLVM_ANALYSIS_REGIONPASS_H
 
-#include "llvm/Analysis/RegionInfo.h"
 #include "llvm/IR/LegacyPassManagers.h"
 #include "llvm/Pass.h"
 #include <deque>
@@ -23,6 +22,8 @@
 namespace llvm {
 class Function;
 class RGPassManager;
+class Region;
+class RegionInfo;
 
 //===----------------------------------------------------------------------===//
 /// A pass that runs on each Region in a function.
diff --git a/llvm/include/llvm/Analysis/ScalarEvolution.h b/llvm/include/llvm/Analysis/ScalarEvolution.h
--- a/llvm/include/llvm/Analysis/ScalarEvolution.h
+++ b/llvm/include/llvm/Analysis/ScalarEvolution.h
@@ -31,7 +31,6 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/IR/ConstantRange.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Operator.h"
@@ -39,9 +38,6 @@
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/IR/ValueMap.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Allocator.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/Compiler.h"
 #include <algorithm>
 #include <cassert>
 #include <cstdint>
@@ -56,6 +52,7 @@
 class ConstantInt;
 class DataLayout;
 class DominatorTree;
+class Function;
 class GEPOperator;
 class Instruction;
 class LLVMContext;
diff --git a/llvm/include/llvm/Analysis/ScalarEvolutionAliasAnalysis.h b/llvm/include/llvm/Analysis/ScalarEvolutionAliasAnalysis.h
--- a/llvm/include/llvm/Analysis/ScalarEvolutionAliasAnalysis.h
+++ b/llvm/include/llvm/Analysis/ScalarEvolutionAliasAnalysis.h
@@ -15,12 +15,12 @@
 
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/ScalarEvolutionExpressions.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Module.h"
 #include "llvm/Pass.h"
 
 namespace llvm {
 
+class Function;
+
 /// A simple alias analysis implementation that uses ScalarEvolution to answer
 /// queries.
 class SCEVAAResult : public AAResultBase<SCEVAAResult> {
diff --git a/llvm/include/llvm/Analysis/ScalarEvolutionExpressions.h b/llvm/include/llvm/Analysis/ScalarEvolutionExpressions.h
--- a/llvm/include/llvm/Analysis/ScalarEvolutionExpressions.h
+++ b/llvm/include/llvm/Analysis/ScalarEvolutionExpressions.h
@@ -14,13 +14,10 @@
 #define LLVM_ANALYSIS_SCALAREVOLUTIONEXPRESSIONS_H
 
 #include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/FoldingSet.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/Analysis/ScalarEvolution.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/Value.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -31,9 +28,11 @@
 
 class APInt;
 class Constant;
+class ConstantInt;
 class ConstantRange;
 class Loop;
 class Type;
+class Value;
 
 enum SCEVTypes : unsigned short {
   // These should be ordered in terms of increasing complexity to make the
diff --git a/llvm/include/llvm/Analysis/StackLifetime.h b/llvm/include/llvm/Analysis/StackLifetime.h
--- a/llvm/include/llvm/Analysis/StackLifetime.h
+++ b/llvm/include/llvm/Analysis/StackLifetime.h
@@ -14,7 +14,6 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringExtras.h"
-#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cassert>
@@ -26,6 +25,7 @@
 class BasicBlock;
 class Function;
 class Instruction;
+class IntrinsicInst;
 
 /// Compute live ranges of allocas.
 /// Live ranges are represented as sets of "interesting" instructions, which are
diff --git a/llvm/include/llvm/Analysis/SyncDependenceAnalysis.h b/llvm/include/llvm/Analysis/SyncDependenceAnalysis.h
--- a/llvm/include/llvm/Analysis/SyncDependenceAnalysis.h
+++ b/llvm/include/llvm/Analysis/SyncDependenceAnalysis.h
@@ -16,10 +16,8 @@
 #ifndef LLVM_ANALYSIS_SYNCDEPENDENCEANALYSIS_H
 #define LLVM_ANALYSIS_SYNCDEPENDENCEANALYSIS_H
 
-#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/Analysis/LoopInfo.h"
 #include <map>
 #include <memory>
 #include <unordered_map>
@@ -28,6 +26,8 @@
 
 class BasicBlock;
 class DominatorTree;
+class Instruction;
+class LoopInfo;
 class PostDominatorTree;
 
 using ConstBlockSet = SmallPtrSet<const BasicBlock *, 4>;
diff --git a/llvm/include/llvm/Analysis/TargetFolder.h b/llvm/include/llvm/Analysis/TargetFolder.h
--- a/llvm/include/llvm/Analysis/TargetFolder.h
+++ b/llvm/include/llvm/Analysis/TargetFolder.h
@@ -20,13 +20,13 @@
 
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/Analysis/ConstantFolding.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/IRBuilderFolder.h"
 
 namespace llvm {
 
+class Constant;
 class DataLayout;
+class Type;
 
 /// TargetFolder - Create constants with target dependent folding.
 class TargetFolder final : public IRBuilderFolder {
diff --git a/llvm/include/llvm/Analysis/TargetLibraryInfo.h b/llvm/include/llvm/Analysis/TargetLibraryInfo.h
--- a/llvm/include/llvm/Analysis/TargetLibraryInfo.h
+++ b/llvm/include/llvm/Analysis/TargetLibraryInfo.h
@@ -12,14 +12,15 @@
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/Optional.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/InstrTypes.h"
-#include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
 
 namespace llvm {
+
 template <typename T> class ArrayRef;
+class Function;
+class Module;
 class Triple;
 
 /// Describes a possible vectorization of a function.
@@ -49,7 +50,7 @@
   friend class TargetLibraryInfo;
 
   unsigned char AvailableArray[(NumLibFuncs+3)/4];
-  llvm::DenseMap<unsigned, std::string> CustomNames;
+  DenseMap<unsigned, std::string> CustomNames;
   static StringLiteral const StandardNames[NumLibFuncs];
   bool ShouldExtI32Param, ShouldExtI32Return, ShouldSignExtI32Param;
   unsigned SizeOfInt;
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -27,7 +27,6 @@
 #include "llvm/Pass.h"
 #include "llvm/Support/AtomicOrdering.h"
 #include "llvm/Support/BranchProbability.h"
-#include "llvm/Support/DataTypes.h"
 #include "llvm/Support/InstructionCost.h"
 #include <functional>
 #include <utility>
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -18,18 +18,18 @@
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/VectorUtils.h"
 #include "llvm/IR/DataLayout.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/PatternMatch.h"
-#include "llvm/IR/Type.h"
 #include <utility>
 
 using namespace llvm::PatternMatch;
 
 namespace llvm {
 
+class Function;
+
 /// Base class for use as a mix-in that aids implementing
 /// a TargetTransformInfo-compatible class.
 class TargetTransformInfoImplBase {
diff --git a/llvm/include/llvm/Analysis/ValueLattice.h b/llvm/include/llvm/Analysis/ValueLattice.h
--- a/llvm/include/llvm/Analysis/ValueLattice.h
+++ b/llvm/include/llvm/Analysis/ValueLattice.h
@@ -10,7 +10,6 @@
 #define LLVM_ANALYSIS_VALUELATTICE_H
 
 #include "llvm/IR/ConstantRange.h"
-#include "llvm/IR/Constants.h"
 #include "llvm/IR/Instructions.h"
 //
 //===----------------------------------------------------------------------===//
@@ -19,6 +18,8 @@
 
 namespace llvm {
 
+class Constant;
+
 /// This class represents lattice values for constants.
 ///
 /// FIXME: This is basically just for bringup, this can be made a lot more rich
diff --git a/llvm/lib/Analysis/DependenceGraphBuilder.cpp b/llvm/lib/Analysis/DependenceGraphBuilder.cpp
--- a/llvm/lib/Analysis/DependenceGraphBuilder.cpp
+++ b/llvm/lib/Analysis/DependenceGraphBuilder.cpp
@@ -12,6 +12,7 @@
 #include "llvm/Analysis/DependenceGraphBuilder.h"
 #include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/EnumeratedArray.h"
+#include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/SCCIterator.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/DDG.h"
diff --git a/llvm/lib/Analysis/LegacyDivergenceAnalysis.cpp b/llvm/lib/Analysis/LegacyDivergenceAnalysis.cpp
--- a/llvm/lib/Analysis/LegacyDivergenceAnalysis.cpp
+++ b/llvm/lib/Analysis/LegacyDivergenceAnalysis.cpp
@@ -68,6 +68,7 @@
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/Analysis/CFG.h"
 #include "llvm/Analysis/DivergenceAnalysis.h"
+#include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/Passes.h"
 #include "llvm/Analysis/PostDominators.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
diff --git a/llvm/lib/Analysis/MemorySSA.cpp b/llvm/lib/Analysis/MemorySSA.cpp
--- a/llvm/lib/Analysis/MemorySSA.cpp
+++ b/llvm/lib/Analysis/MemorySSA.cpp
@@ -38,6 +38,7 @@
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/Operator.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/Use.h"
 #include "llvm/InitializePasses.h"
diff --git a/llvm/lib/Analysis/RegionInfo.cpp b/llvm/lib/Analysis/RegionInfo.cpp
--- a/llvm/lib/Analysis/RegionInfo.cpp
+++ b/llvm/lib/Analysis/RegionInfo.cpp
@@ -10,6 +10,7 @@
 
 #include "llvm/Analysis/RegionInfo.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/DominanceFrontier.h"
 #include "llvm/InitializePasses.h"
 #ifndef NDEBUG
 #include "llvm/Analysis/RegionPrinter.h"
diff --git a/llvm/lib/Analysis/RegionPass.cpp b/llvm/lib/Analysis/RegionPass.cpp
--- a/llvm/lib/Analysis/RegionPass.cpp
+++ b/llvm/lib/Analysis/RegionPass.cpp
@@ -12,7 +12,9 @@
 // Most of this code has been COPIED from LoopPass.cpp
 //
 //===----------------------------------------------------------------------===//
+
 #include "llvm/Analysis/RegionPass.h"
+#include "llvm/Analysis/RegionInfo.h"
 #include "llvm/IR/OptBisect.h"
 #include "llvm/IR/PassTimingInfo.h"
 #include "llvm/IR/PrintPasses.h"
diff --git a/llvm/lib/Analysis/SyncDependenceAnalysis.cpp b/llvm/lib/Analysis/SyncDependenceAnalysis.cpp
--- a/llvm/lib/Analysis/SyncDependenceAnalysis.cpp
+++ b/llvm/lib/Analysis/SyncDependenceAnalysis.cpp
@@ -116,9 +116,11 @@
 //   around from the latch.
 //
 //===----------------------------------------------------------------------===//
+
 #include "llvm/Analysis/SyncDependenceAnalysis.h"
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/PostDominators.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CFG.h"
diff --git a/llvm/lib/Transforms/Utils/LCSSA.cpp b/llvm/lib/Transforms/Utils/LCSSA.cpp
--- a/llvm/lib/Transforms/Utils/LCSSA.cpp
+++ b/llvm/lib/Transforms/Utils/LCSSA.cpp
@@ -33,6 +33,7 @@
 #include "llvm/Analysis/BasicAliasAnalysis.h"
 #include "llvm/Analysis/BranchProbabilityInfo.h"
 #include "llvm/Analysis/GlobalsModRef.h"
+#include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/LoopPass.h"
 #include "llvm/Analysis/MemorySSA.h"
 #include "llvm/Analysis/ScalarEvolution.h"