Merge branch 'main' into implicit-binding-cbuffers

Author: hekota

bolt/test/X86/callcont-fallthru.s

@@ -6,7 +6,7 @@
 # RUN: %clangxx %cxxflags %s %t.so -o %t -Wl,-q -nostdlib
 # RUN: link_fdata %s %t %t.pat PREAGGT1
 # RUN: link_fdata %s %t %t.pat2 PREAGGT2
-# RUN: link_fdata %s %t %t.patplt PREAGGPLT
+# DONTRUN: link_fdata %s %t %t.patplt PREAGGPLT
 
 # RUN: llvm-strip --strip-unneeded %t -o %t.strip
 # RUN: llvm-objcopy --remove-section=.eh_frame %t.strip %t.noeh
@@ -26,8 +26,8 @@
 
 ## Check pre-aggregated traces don't report zero-sized PLT fall-through as
 ## invalid trace
-# RUN: llvm-bolt %t.strip --pa -p %t.patplt -o %t.out | FileCheck %s \
-# RUN:   --check-prefix=CHECK-PLT
+# DONTRUN: llvm-bolt %t.strip --pa -p %t.patplt -o %t.out | FileCheck %s \
+# DONTRUN:   --check-prefix=CHECK-PLT
 # CHECK-PLT: traces mismatching disassembled function contents: 0
 
   .globl foo

clang/include/clang/CIR/Dialect/IR/CIROps.td

@@ -269,7 +269,7 @@ def PtrStrideOp : CIR_Op<"ptr_stride",
   let extraClassDeclaration = [{
     // Get type pointed by the base pointer.
     mlir::Type getElementTy() {
-      return mlir::cast<cir::PointerType>(getBase().getType()).getPointee();
+      return getBase().getType().getPointee();
     }
   }];
 }
@@ -1710,7 +1710,7 @@ def GetMemberOp : CIR_Op<"get_member"> {
 
     /// Return the result type.
     cir::PointerType getResultTy() {
-      return mlir::cast<cir::PointerType>(getResult().getType());
+      return getResult().getType();
     }
   }];
 

clang/include/clang/StaticAnalyzer/Core/PathSensitive/SMTConstraintManager.h

@@ -301,8 +301,10 @@ class SMTConstraintManager : public clang::ento::SimpleConstraintManager {
     llvm_unreachable("Unsupported expression to reason about!");
   }
 
+#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   /// Dumps SMT formula
   LLVM_DUMP_METHOD void dump() const { Solver->dump(); }
+#endif
 
 protected:
   // Check whether a new model is satisfiable, and update the program state.

clang/include/clang/StaticAnalyzer/Core/PathSensitive/SymbolManager.h

@@ -103,10 +103,7 @@ class SymbolConjured : public SymbolData {
   const Stmt *getStmt() const {
     switch (Elem->getKind()) {
     case CFGElement::Initializer:
-      if (const auto *Init = Elem->castAs<CFGInitializer>().getInitializer()) {
-        return Init->getInit();
-      }
-      return nullptr;
+      return Elem->castAs<CFGInitializer>().getInitializer()->getInit();
     case CFGElement::ScopeBegin:
       return Elem->castAs<CFGScopeBegin>().getTriggerStmt();
     case CFGElement::ScopeEnd:

clang/lib/CodeGen/CGBuiltin.cpp

@@ -6115,8 +6115,9 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
   case Builtin::BI__builtin_thread_pointer: {
     if (!getContext().getTargetInfo().isTLSSupported())
       CGM.ErrorUnsupported(E, "__builtin_thread_pointer");
-    // Fall through - it's already mapped to the intrinsic by ClangBuiltin.
-    break;
+
+    return RValue::get(Builder.CreateIntrinsic(llvm::Intrinsic::thread_pointer,
+                                               {GlobalsInt8PtrTy}, {}));
   }
   case Builtin::BI__builtin_os_log_format:
     return emitBuiltinOSLogFormat(*E);

clang/lib/CodeGen/CGCall.cpp

@@ -1366,19 +1366,23 @@ static llvm::Value *CreateCoercedLoad(Address Src, llvm::Type *Ty,
       // If we are casting a fixed i8 vector to a scalable i1 predicate
       // vector, use a vector insert and bitcast the result.
       if (ScalableDstTy->getElementType()->isIntegerTy(1) &&
-          ScalableDstTy->getElementCount().isKnownMultipleOf(8) &&
           FixedSrcTy->getElementType()->isIntegerTy(8)) {
         ScalableDstTy = llvm::ScalableVectorType::get(
             FixedSrcTy->getElementType(),
-            ScalableDstTy->getElementCount().getKnownMinValue() / 8);
+            llvm::divideCeil(
+                ScalableDstTy->getElementCount().getKnownMinValue(), 8));
       }
       if (ScalableDstTy->getElementType() == FixedSrcTy->getElementType()) {
         auto *Load = CGF.Builder.CreateLoad(Src);
         auto *PoisonVec = llvm::PoisonValue::get(ScalableDstTy);
         llvm::Value *Result = CGF.Builder.CreateInsertVector(
             ScalableDstTy, PoisonVec, Load, uint64_t(0), "cast.scalable");
-        if (ScalableDstTy != Ty)
-          Result = CGF.Builder.CreateBitCast(Result, Ty);
+        ScalableDstTy = cast<llvm::ScalableVectorType>(
+            llvm::VectorType::getWithSizeAndScalar(ScalableDstTy, Ty));
+        if (Result->getType() != ScalableDstTy)
+          Result = CGF.Builder.CreateBitCast(Result, ScalableDstTy);
+        if (Result->getType() != Ty)
+          Result = CGF.Builder.CreateExtractVector(Ty, Result, uint64_t(0));
         return Result;
       }
     }
@@ -1476,8 +1480,14 @@ CoerceScalableToFixed(CodeGenFunction &CGF, llvm::FixedVectorType *ToTy,
   // If we are casting a scalable i1 predicate vector to a fixed i8
   // vector, first bitcast the source.
   if (FromTy->getElementType()->isIntegerTy(1) &&
-      FromTy->getElementCount().isKnownMultipleOf(8) &&
       ToTy->getElementType() == CGF.Builder.getInt8Ty()) {
+    if (!FromTy->getElementCount().isKnownMultipleOf(8)) {
+      FromTy = llvm::ScalableVectorType::get(
+          FromTy->getElementType(),
+          llvm::alignTo<8>(FromTy->getElementCount().getKnownMinValue()));
+      llvm::Value *ZeroVec = llvm::Constant::getNullValue(FromTy);
+      V = CGF.Builder.CreateInsertVector(FromTy, ZeroVec, V, uint64_t(0));
+    }
     FromTy = llvm::ScalableVectorType::get(
         ToTy->getElementType(),
         FromTy->getElementCount().getKnownMinValue() / 8);

clang/lib/CodeGen/CGExprScalar.cpp

@@ -2491,18 +2491,22 @@ Value *ScalarExprEmitter::VisitCastExpr(CastExpr *CE) {
         // If we are casting a fixed i8 vector to a scalable i1 predicate
         // vector, use a vector insert and bitcast the result.
         if (ScalableDstTy->getElementType()->isIntegerTy(1) &&
-            ScalableDstTy->getElementCount().isKnownMultipleOf(8) &&
             FixedSrcTy->getElementType()->isIntegerTy(8)) {
           ScalableDstTy = llvm::ScalableVectorType::get(
               FixedSrcTy->getElementType(),
-              ScalableDstTy->getElementCount().getKnownMinValue() / 8);
+              llvm::divideCeil(
+                  ScalableDstTy->getElementCount().getKnownMinValue(), 8));
         }
         if (FixedSrcTy->getElementType() == ScalableDstTy->getElementType()) {
           llvm::Value *PoisonVec = llvm::PoisonValue::get(ScalableDstTy);
           llvm::Value *Result = Builder.CreateInsertVector(
               ScalableDstTy, PoisonVec, Src, uint64_t(0), "cast.scalable");
+          ScalableDstTy = cast<llvm::ScalableVectorType>(
+              llvm::VectorType::getWithSizeAndScalar(ScalableDstTy, DstTy));
+          if (Result->getType() != ScalableDstTy)
+            Result = Builder.CreateBitCast(Result, ScalableDstTy);
           if (Result->getType() != DstTy)
-            Result = Builder.CreateBitCast(Result, DstTy);
+            Result = Builder.CreateExtractVector(DstTy, Result, uint64_t(0));
           return Result;
         }
       }
@@ -2516,8 +2520,17 @@ Value *ScalarExprEmitter::VisitCastExpr(CastExpr *CE) {
         // If we are casting a scalable i1 predicate vector to a fixed i8
         // vector, bitcast the source and use a vector extract.
         if (ScalableSrcTy->getElementType()->isIntegerTy(1) &&
-            ScalableSrcTy->getElementCount().isKnownMultipleOf(8) &&
             FixedDstTy->getElementType()->isIntegerTy(8)) {
+          if (!ScalableSrcTy->getElementCount().isKnownMultipleOf(8)) {
+            ScalableSrcTy = llvm::ScalableVectorType::get(
+                ScalableSrcTy->getElementType(),
+                llvm::alignTo<8>(
+                    ScalableSrcTy->getElementCount().getKnownMinValue()));
+            llvm::Value *ZeroVec = llvm::Constant::getNullValue(ScalableSrcTy);
+            Src = Builder.CreateInsertVector(ScalableSrcTy, ZeroVec, Src,
+                                             uint64_t(0));
+          }
+
           ScalableSrcTy = llvm::ScalableVectorType::get(
               FixedDstTy->getElementType(),
               ScalableSrcTy->getElementCount().getKnownMinValue() / 8);

clang/lib/CodeGen/CodeGenModule.cpp

@@ -1689,7 +1689,7 @@ static bool shouldAssumeDSOLocal(const CodeGenModule &CGM,
 
   const llvm::Triple &TT = CGM.getTriple();
   const auto &CGOpts = CGM.getCodeGenOpts();
-  if (TT.isWindowsGNUEnvironment()) {
+  if (TT.isOSCygMing()) {
     // In MinGW, variables without DLLImport can still be automatically
     // imported from a DLL by the linker; don't mark variables that
     // potentially could come from another DLL as DSO local.

clang/lib/CodeGen/ItaniumCXXABI.cpp

@@ -3754,7 +3754,7 @@ static bool ShouldUseExternalRTTIDescriptor(CodeGenModule &CGM,
     bool IsDLLImport = RD->hasAttr<DLLImportAttr>();
 
     // Don't import the RTTI but emit it locally.
-    if (CGM.getTriple().isWindowsGNUEnvironment())
+    if (CGM.getTriple().isOSCygMing())
       return false;
 
     if (CGM.getVTables().isVTableExternal(RD)) {
@@ -4041,10 +4041,7 @@ static llvm::GlobalVariable::LinkageTypes getTypeInfoLinkage(CodeGenModule &CGM,
           return llvm::GlobalValue::ExternalLinkage;
       // MinGW always uses LinkOnceODRLinkage for type info.
       if (RD->isDynamicClass() &&
-          !CGM.getContext()
-               .getTargetInfo()
-               .getTriple()
-               .isWindowsGNUEnvironment())
+          !CGM.getContext().getTargetInfo().getTriple().isOSCygMing())
         return CGM.getVTableLinkage(RD);
     }
 

clang/lib/Sema/SemaDeclCXX.cpp

@@ -6274,7 +6274,7 @@ static void ReferenceDllExportedMembers(Sema &S, CXXRecordDecl *Class) {
     }
   } MarkingDllexportedContext(S, Class, ClassAttr->getLocation());
 
-  if (S.Context.getTargetInfo().getTriple().isWindowsGNUEnvironment())
+  if (S.Context.getTargetInfo().getTriple().isOSCygMing())
     S.MarkVTableUsed(Class->getLocation(), Class, true);
 
   for (Decl *Member : Class->decls()) {
@@ -6576,7 +6576,7 @@ void Sema::checkClassLevelDLLAttribute(CXXRecordDecl *Class) {
   // declarations, except in MinGW mode.
   if (ClassExported && !ClassAttr->isInherited() &&
       TSK == TSK_ExplicitInstantiationDeclaration &&
-      !Context.getTargetInfo().getTriple().isWindowsGNUEnvironment()) {
+      !Context.getTargetInfo().getTriple().isOSCygMing()) {
     Class->dropAttr<DLLExportAttr>();
     return;
   }