merge main into amd-staging (#685)

Author: z1-cciauto

bolt/include/bolt/Core/MCPlusBuilder.h

@@ -1869,6 +1869,20 @@ class MCPlusBuilder {
     llvm_unreachable("not implemented");
   }
 
+  /// Check if an Instruction is a BTI landing pad with the required properties.
+  /// Takes both explicit and implicit BTIs into account.
+  virtual bool isBTILandingPad(MCInst &Inst, bool CallTarget,
+                               bool JumpTarget) const {
+    llvm_unreachable("not implemented");
+    return false;
+  }
+
+  /// Check if an Instruction is an implicit BTI c landing pad.
+  virtual bool isImplicitBTIC(MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return false;
+  }
+
   /// Create a BTI landing pad instruction.
   virtual void createBTI(MCInst &Inst, bool CallTarget, bool JumpTarget) const {
     llvm_unreachable("not implemented");

bolt/lib/Target/AArch64/AArch64MCPlusBuilder.cpp

@@ -2782,6 +2782,24 @@ class AArch64MCPlusBuilder : public MCPlusBuilder {
     Inst.addOperand(MCOperand::createImm(HintNum));
   }
 
+  bool isBTILandingPad(MCInst &Inst, bool CallTarget,
+                       bool JumpTarget) const override {
+    unsigned HintNum = getBTIHintNum(CallTarget, JumpTarget);
+    bool IsExplicitBTI =
+        Inst.getOpcode() == AArch64::HINT && Inst.getNumOperands() == 1 &&
+        Inst.getOperand(0).isImm() && Inst.getOperand(0).getImm() == HintNum;
+
+    bool IsImplicitBTI = HintNum == 34 && isImplicitBTIC(Inst);
+    return IsExplicitBTI || IsImplicitBTI;
+  }
+
+  bool isImplicitBTIC(MCInst &Inst) const override {
+    // PACI[AB]SP are always implicitly BTI C, independently of
+    // SCTLR_EL1.BT[01].
+    return Inst.getOpcode() == AArch64::PACIASP ||
+           Inst.getOpcode() == AArch64::PACIBSP;
+  }
+
   InstructionListType materializeAddress(const MCSymbol *Target, MCContext *Ctx,
                                          MCPhysReg RegName,
                                          int64_t Addend = 0) const override {

bolt/test/X86/lit.local.cfg

@@ -1,7 +1,7 @@
 if not "X86" in config.root.targets:
     config.unsupported = True
 
-flags = "--target=x86_64-unknown-linux-gnu -nostdlib"
+flags = "--target=x86_64-unknown-linux-gnu -nostdlib -mllvm -x86-asm-syntax=att"
 
 config.substitutions.insert(0, ("%cflags", f"%cflags {flags}"))
 config.substitutions.insert(0, ("%cxxflags", f"%cxxflags {flags}"))

bolt/test/lit.local.cfg

@@ -5,7 +5,7 @@ if not "linux" in host_triple:
   host_triple = host_triple.split("-")[0] + "-unknown-linux-gnu"
 
 common_linker_flags = "-fuse-ld=lld -Wl,--unresolved-symbols=ignore-all -Wl,--build-id=none -pie"
-flags = f"--target={host_triple} -fPIE {common_linker_flags} -mllvm -x86-asm-syntax=att"
+flags = f"--target={host_triple} -fPIE {common_linker_flags}"
 
 config.substitutions.insert(0, ("%cflags", f"%cflags {flags}"))
 config.substitutions.insert(0, ("%cxxflags", f"%cxxflags {flags}"))

bolt/unittests/Core/MCPlusBuilder.cpp

@@ -155,22 +155,39 @@ TEST_P(MCPlusBuilderTester, AArch64_BTI) {
   auto II = BB->begin();
   ASSERT_EQ(II->getOpcode(), AArch64::HINT);
   ASSERT_EQ(II->getOperand(0).getImm(), 38);
+  ASSERT_TRUE(BC->MIB->isBTILandingPad(*II, true, true));
 
   MCInst BTIj;
   BC->MIB->createBTI(BTIj, false, true);
   II = BB->addInstruction(BTIj);
   ASSERT_EQ(II->getOpcode(), AArch64::HINT);
   ASSERT_EQ(II->getOperand(0).getImm(), 36);
+  ASSERT_TRUE(BC->MIB->isBTILandingPad(*II, false, true));
 
   MCInst BTIc;
   BC->MIB->createBTI(BTIc, true, false);
   II = BB->addInstruction(BTIc);
   ASSERT_EQ(II->getOpcode(), AArch64::HINT);
   ASSERT_EQ(II->getOperand(0).getImm(), 34);
+  ASSERT_TRUE(BC->MIB->isBTILandingPad(*II, true, false));
 
   MCInst BTIinvalid;
   ASSERT_DEATH(BC->MIB->createBTI(BTIinvalid, false, false),
                "No target kinds!");
+
+  MCInst Paciasp = MCInstBuilder(AArch64::PACIASP);
+  II = BB->addInstruction(Paciasp);
+  ASSERT_TRUE(BC->MIB->isBTILandingPad(*II, true, false));
+  ASSERT_FALSE(BC->MIB->isBTILandingPad(*II, true, true));
+  ASSERT_FALSE(BC->MIB->isBTILandingPad(*II, false, true));
+  ASSERT_TRUE(BC->MIB->isImplicitBTIC(*II));
+
+  MCInst Pacibsp = MCInstBuilder(AArch64::PACIBSP);
+  II = BB->addInstruction(Pacibsp);
+  ASSERT_TRUE(BC->MIB->isBTILandingPad(*II, true, false));
+  ASSERT_FALSE(BC->MIB->isBTILandingPad(*II, true, true));
+  ASSERT_FALSE(BC->MIB->isBTILandingPad(*II, false, true));
+  ASSERT_TRUE(BC->MIB->isImplicitBTIC(*II));
 }
 
 TEST_P(MCPlusBuilderTester, AArch64_CmpJNE) {

clang/include/clang/Analysis/FlowSensitive/ASTOps.h

@@ -19,7 +19,6 @@
 #include "clang/AST/ExprCXX.h"
 #include "clang/AST/Type.h"
 #include "clang/Analysis/FlowSensitive/StorageLocation.h"
-#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/SetVector.h"
 
 namespace clang {
@@ -145,17 +144,17 @@ struct ReferencedDecls {
   FieldSet Fields;
   /// All variables with static storage duration, notably including static
   /// member variables and static variables declared within a function.
-  llvm::DenseSet<const VarDecl *> Globals;
+  llvm::SetVector<const VarDecl *> Globals;
   /// Local variables, not including parameters or static variables declared
   /// within a function.
-  llvm::DenseSet<const VarDecl *> Locals;
+  llvm::SetVector<const VarDecl *> Locals;
   /// Free functions and member functions which are referenced (but not
   /// necessarily called).
-  llvm::DenseSet<const FunctionDecl *> Functions;
+  llvm::SetVector<const FunctionDecl *> Functions;
   /// When analyzing a lambda's call operator, the set of all parameters (from
   /// the surrounding function) that the lambda captures. Captured local
   /// variables are already included in `Locals` above.
-  llvm::DenseSet<const ParmVarDecl *> LambdaCapturedParams;
+  llvm::SetVector<const ParmVarDecl *> LambdaCapturedParams;
 };
 
 /// Returns declarations that are declared in or referenced from `FD`.

clang/include/clang/Basic/DiagnosticParseKinds.td

@@ -1724,6 +1724,10 @@ def warn_omp_invalid_attribute_for_ompx_attributes : Warning<"'ompx_attribute' c
   "%0 is ignored">, InGroup<OpenMPExtensions>;
 def err_omp_duplicate_modifier : Error<"duplicate modifier '%0' in '%1' clause">;
 def err_omp_expected_modifier : Error<"expected modifier in '%0' clause">;
+def err_omp_unknown_need_device_ptr_kind
+    : Error<
+        "invalid argument for 'need_device_ptr' kind in 'adjust_args' clause; "
+        "expected 'fp_nullify' or 'fb_preserve'">;
 
 // Pragma loop support.
 def err_pragma_loop_missing_argument : Error<

clang/include/clang/Basic/OpenMPKinds.def

@@ -107,6 +107,9 @@
 #ifndef OPENMP_THREADSET_KIND
 #define OPENMP_THREADSET_KIND(Name)
 #endif
+#ifndef OPENMP_NEED_DEVICE_PTR_KIND
+#define OPENMP_NEED_DEVICE_PTR_KIND(Name)
+#endif
 
 // Static attributes for 'schedule' clause.
 OPENMP_SCHEDULE_KIND(static)
@@ -274,6 +277,10 @@ OPENMP_DOACROSS_MODIFIER(source_omp_cur_iteration)
 OPENMP_THREADSET_KIND(omp_pool)
 OPENMP_THREADSET_KIND(omp_team)
 
+// OpenMP 6.1 modifiers for 'adjust_args' clause.
+OPENMP_NEED_DEVICE_PTR_KIND(fb_nullify)
+OPENMP_NEED_DEVICE_PTR_KIND(fb_preserve)
+
 #undef OPENMP_NUMTASKS_MODIFIER
 #undef OPENMP_NUMTHREADS_MODIFIER
 #undef OPENMP_DYN_GROUPPRIVATE_MODIFIER
@@ -306,3 +313,4 @@ OPENMP_THREADSET_KIND(omp_team)
 #undef OPENMP_DOACROSS_MODIFIER
 #undef OPENMP_ALLOCATE_MODIFIER
 #undef OPENMP_THREADSET_KIND
+#undef OPENMP_NEED_DEVICE_PTR_KIND

clang/include/clang/Basic/OpenMPKinds.h

@@ -211,6 +211,13 @@ enum OpenMPAdjustArgsOpKind {
   OMPC_ADJUST_ARGS_unknown,
 };
 
+/// OpenMP 6.1 need_device modifier
+enum OpenMPNeedDevicePtrModifier {
+#define OPENMP_NEED_DEVICE_PTR_KIND(Name) OMPC_NEED_DEVICE_PTR_##Name,
+#include "clang/Basic/OpenMPKinds.def"
+  OMPC_NEED_DEVICE_PTR_unknown,
+};
+
 /// OpenMP bindings for the 'bind' clause.
 enum OpenMPBindClauseKind {
 #define OPENMP_BIND_KIND(Name) OMPC_BIND_##Name,

clang/include/clang/Sema/SemaOpenMP.h

@@ -1174,6 +1174,8 @@ class SemaOpenMP : public SemaBase {
     int ExtraModifier = -1; ///< Additional modifier for linear, map, depend or
                             ///< lastprivate clause.
     int OriginalSharingModifier = 0; // Default is shared
+    int NeedDevicePtrModifier = 0;
+    SourceLocation NeedDevicePtrModifierLoc;
     SmallVector<OpenMPMapModifierKind, NumberOfOMPMapClauseModifiers>
         MapTypeModifiers;
     SmallVector<SourceLocation, NumberOfOMPMapClauseModifiers>