Vendor import of llvm-project branch release/19.x llvmorg-19.1.0-rc1-0-ga4902a36d5c2.vendor/llvm-project/llvmorg-19.1.0-rc1-0-ga4902a36d5c2

78 files changed, 768 insertions, 321 deletions

diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index b8d97a6b14fe..eb0506e71fe3 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -942,6 +942,9 @@ def warn_ptrauth_auth_null_pointer :
   InGroup<PtrAuthNullPointers>;
 def err_ptrauth_string_not_literal : Error<
   "argument must be a string literal%select{| of char type}0">;
+def err_ptrauth_type_disc_undiscriminated : Error<
+  "cannot pass undiscriminated type %0 to "
+  "'__builtin_ptrauth_type_discriminator'">;
 
 def note_ptrauth_virtual_function_pointer_incomplete_arg_ret :
   Note<"cannot take an address of a virtual member function if its return or "
diff --git a/clang/include/clang/Basic/TokenKinds.def b/clang/include/clang/Basic/TokenKinds.def
index 7f4912b9bcd9..8c54661e65cf 100644
--- a/clang/include/clang/Basic/TokenKinds.def
+++ b/clang/include/clang/Basic/TokenKinds.def
@@ -596,6 +596,8 @@ ALIAS("__is_same_as", __is_same, KEYCXX)
 KEYWORD(__private_extern__          , KEYALL)
 KEYWORD(__module_private__          , KEYALL)
 
+UNARY_EXPR_OR_TYPE_TRAIT(__builtin_ptrauth_type_discriminator, PtrAuthTypeDiscriminator, KEYALL)
+
 // Extension that will be enabled for Microsoft, Borland and PS4, but can be
 // disabled via '-fno-declspec'.
 KEYWORD(__declspec                  , 0)
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 69269cf7537b..359a698ea87d 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -1165,19 +1165,19 @@ def client__name : JoinedOrSeparate<["-"], "client_name">;
 def combine : Flag<["-", "--"], "combine">, Flags<[NoXarchOption, Unsupported]>;
 def compatibility__version : JoinedOrSeparate<["-"], "compatibility_version">;
 def config : Joined<["--"], "config=">, Flags<[NoXarchOption]>,
-  Visibility<[ClangOption, CLOption, DXCOption]>, MetaVarName<"<file>">,
+  Visibility<[ClangOption, CLOption, DXCOption, FlangOption]>, MetaVarName<"<file>">,
   HelpText<"Specify configuration file">;
-def : Separate<["--"], "config">, Alias<config>;
+def : Separate<["--"], "config">, Visibility<[ClangOption, CLOption, DXCOption, FlangOption]>, Alias<config>;
 def no_default_config : Flag<["--"], "no-default-config">,
-  Flags<[NoXarchOption]>, Visibility<[ClangOption, CLOption, DXCOption]>,
+  Flags<[NoXarchOption]>, Visibility<[ClangOption, CLOption, DXCOption, FlangOption]>,
   HelpText<"Disable loading default configuration files">;
 def config_system_dir_EQ : Joined<["--"], "config-system-dir=">,
   Flags<[NoXarchOption, HelpHidden]>,
-  Visibility<[ClangOption, CLOption, DXCOption]>,
+  Visibility<[ClangOption, CLOption, DXCOption, FlangOption]>,
   HelpText<"System directory for configuration files">;
 def config_user_dir_EQ : Joined<["--"], "config-user-dir=">,
   Flags<[NoXarchOption, HelpHidden]>,
-  Visibility<[ClangOption, CLOption, DXCOption]>,
+  Visibility<[ClangOption, CLOption, DXCOption, FlangOption]>,
   HelpText<"User directory for configuration files">;
 def coverage : Flag<["-", "--"], "coverage">, Group<Link_Group>,
   Visibility<[ClangOption, CLOption]>;
diff --git a/clang/include/clang/Parse/Parser.h b/clang/include/clang/Parse/Parser.h
index 613bab9120df..35bb1a19d40f 100644
--- a/clang/include/clang/Parse/Parser.h
+++ b/clang/include/clang/Parse/Parser.h
@@ -3890,6 +3890,8 @@ private:
   ExprResult ParseArrayTypeTrait();
   ExprResult ParseExpressionTrait();
 
+  ExprResult ParseBuiltinPtrauthTypeDiscriminator();
+
   //===--------------------------------------------------------------------===//
   // Preprocessor code-completion pass-through
   void CodeCompleteDirective(bool InConditional) override;
diff --git a/clang/include/clang/Sema/Overload.h b/clang/include/clang/Sema/Overload.h
index 9d8b797af666..26ffe057c74a 100644
--- a/clang/include/clang/Sema/Overload.h
+++ b/clang/include/clang/Sema/Overload.h
@@ -998,7 +998,9 @@ class Sema;
   private:
     friend class OverloadCandidateSet;
     OverloadCandidate()
-        : IsSurrogate(false), IsADLCandidate(CallExpr::NotADL), RewriteKind(CRK_None) {}
+        : IsSurrogate(false), IgnoreObjectArgument(false),
+          TookAddressOfOverload(false), IsADLCandidate(CallExpr::NotADL),
+          RewriteKind(CRK_None) {}
   };
 
   /// OverloadCandidateSet - A set of overload candidates, used in C++
diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h
index d638d31e050d..7bfdaaae45a9 100644
--- a/clang/include/clang/Sema/Sema.h
+++ b/clang/include/clang/Sema/Sema.h
@@ -3456,6 +3456,8 @@ public:
                                     TemplateIdAnnotation *TemplateId,
                                     bool IsMemberSpecialization);
 
+  bool checkPointerAuthEnabled(SourceLocation Loc, SourceRange Range);
+
   bool checkConstantPointerAuthKey(Expr *keyExpr, unsigned &key);
 
   /// Diagnose function specifiers on a declaration of an identifier that
diff --git a/clang/lib/AST/ExprConstant.cpp b/clang/lib/AST/ExprConstant.cpp
index fcb382474ea6..5e57b5e8bc8f 100644
--- a/clang/lib/AST/ExprConstant.cpp
+++ b/clang/lib/AST/ExprConstant.cpp
@@ -2839,6 +2839,8 @@ static bool handleIntIntBinOp(EvalInfo &Info, const BinaryOperator *E,
       // During constant-folding, a negative shift is an opposite shift. Such
       // a shift is not a constant expression.
       Info.CCEDiag(E, diag::note_constexpr_negative_shift) << RHS;
+      if (!Info.noteUndefinedBehavior())
+        return false;
       RHS = -RHS;
       goto shift_right;
     }
@@ -2849,19 +2851,23 @@ static bool handleIntIntBinOp(EvalInfo &Info, const BinaryOperator *E,
     if (SA != RHS) {
       Info.CCEDiag(E, diag::note_constexpr_large_shift)
         << RHS << E->getType() << LHS.getBitWidth();
+      if (!Info.noteUndefinedBehavior())
+        return false;
     } else if (LHS.isSigned() && !Info.getLangOpts().CPlusPlus20) {
       // C++11 [expr.shift]p2: A signed left shift must have a non-negative
       // operand, and must not overflow the corresponding unsigned type.
       // C++2a [expr.shift]p2: E1 << E2 is the unique value congruent to
       // E1 x 2^E2 module 2^N.
-      if (LHS.isNegative())
+      if (LHS.isNegative()) {
         Info.CCEDiag(E, diag::note_constexpr_lshift_of_negative) << LHS;
-      else if (LHS.countl_zero() < SA)
+        if (!Info.noteUndefinedBehavior())
+          return false;
+      } else if (LHS.countl_zero() < SA) {
         Info.CCEDiag(E, diag::note_constexpr_lshift_discards);
+        if (!Info.noteUndefinedBehavior())
+          return false;
+      }
     }
-    if (Info.EvalStatus.Diag && !Info.EvalStatus.Diag->empty() &&
-        Info.getLangOpts().CPlusPlus11)
-      return false;
     Result = LHS << SA;
     return true;
   }
@@ -2875,6 +2881,8 @@ static bool handleIntIntBinOp(EvalInfo &Info, const BinaryOperator *E,
       // During constant-folding, a negative shift is an opposite shift. Such a
       // shift is not a constant expression.
       Info.CCEDiag(E, diag::note_constexpr_negative_shift) << RHS;
+      if (!Info.noteUndefinedBehavior())
+        return false;
       RHS = -RHS;
       goto shift_left;
     }
@@ -2882,13 +2890,13 @@ static bool handleIntIntBinOp(EvalInfo &Info, const BinaryOperator *E,
     // C++11 [expr.shift]p1: Shift width must be less than the bit width of the
     // shifted type.
     unsigned SA = (unsigned) RHS.getLimitedValue(LHS.getBitWidth()-1);
-    if (SA != RHS)
+    if (SA != RHS) {
       Info.CCEDiag(E, diag::note_constexpr_large_shift)
         << RHS << E->getType() << LHS.getBitWidth();
+      if (!Info.noteUndefinedBehavior())
+        return false;
+    }
 
-    if (Info.EvalStatus.Diag && !Info.EvalStatus.Diag->empty() &&
-        Info.getLangOpts().CPlusPlus11)
-      return false;
     Result = LHS >> SA;
     return true;
   }
@@ -14054,6 +14062,12 @@ bool IntExprEvaluator::VisitUnaryExprOrTypeTraitExpr(
                      E);
   }
 
+  case UETT_PtrAuthTypeDiscriminator: {
+    if (E->getArgumentType()->isDependentType())
+      return false;
+    return Success(
+        Info.Ctx.getPointerAuthTypeDiscriminator(E->getArgumentType()), E);
+  }
   case UETT_VecStep: {
     QualType Ty = E->getTypeOfArgument();
 
diff --git a/clang/lib/AST/Interp/Interp.h b/clang/lib/AST/Interp/Interp.h
index 8e96f78d9056..253a433e7340 100644
--- a/clang/lib/AST/Interp/Interp.h
+++ b/clang/lib/AST/Interp/Interp.h
@@ -153,7 +153,8 @@ bool CheckShift(InterpState &S, CodePtr OpPC, const LT &LHS, const RT &RHS,
   if (RHS.isNegative()) {
     const SourceInfo &Loc = S.Current->getSource(OpPC);
     S.CCEDiag(Loc, diag::note_constexpr_negative_shift) << RHS.toAPSInt();
-    return false;
+    if (!S.noteUndefinedBehavior())
+      return false;
   }
 
   // C++11 [expr.shift]p1: Shift width must be less than the bit width of
@@ -163,17 +164,24 @@ bool CheckShift(InterpState &S, CodePtr OpPC, const LT &LHS, const RT &RHS,
     const APSInt Val = RHS.toAPSInt();
     QualType Ty = E->getType();
     S.CCEDiag(E, diag::note_constexpr_large_shift) << Val << Ty << Bits;
-    return !(S.getEvalStatus().Diag && !S.getEvalStatus().Diag->empty() && S.getLangOpts().CPlusPlus11);
+    if (!S.noteUndefinedBehavior())
+      return false;
   }
 
   if (LHS.isSigned() && !S.getLangOpts().CPlusPlus20) {
     const Expr *E = S.Current->getExpr(OpPC);
     // C++11 [expr.shift]p2: A signed left shift must have a non-negative
     // operand, and must not overflow the corresponding unsigned type.
-    if (LHS.isNegative())
+    if (LHS.isNegative()) {
       S.CCEDiag(E, diag::note_constexpr_lshift_of_negative) << LHS.toAPSInt();
-    else if (LHS.toUnsigned().countLeadingZeros() < static_cast<unsigned>(RHS))
+      if (!S.noteUndefinedBehavior())
+        return false;
+    } else if (LHS.toUnsigned().countLeadingZeros() <
+               static_cast<unsigned>(RHS)) {
       S.CCEDiag(E, diag::note_constexpr_lshift_discards);
+      if (!S.noteUndefinedBehavior())
+        return false;
+    }
   }
 
   // C++2a [expr.shift]p2: [P0907R4]:
@@ -2269,8 +2277,7 @@ inline bool DoShift(InterpState &S, CodePtr OpPC, LT &LHS, RT &RHS) {
     // shift is not a constant expression.
     const SourceInfo &Loc = S.Current->getSource(OpPC);
     S.CCEDiag(Loc, diag::note_constexpr_negative_shift) << RHS.toAPSInt();
-    if (S.getLangOpts().CPlusPlus11 && S.getEvalStatus().Diag &&
-        !S.getEvalStatus().Diag->empty())
+    if (!S.noteUndefinedBehavior())
       return false;
     RHS = -RHS;
     return DoShift < LT, RT,
@@ -2286,8 +2293,7 @@ inline bool DoShift(InterpState &S, CodePtr OpPC, LT &LHS, RT &RHS) {
       // E1 x 2^E2 module 2^N.
       const SourceInfo &Loc = S.Current->getSource(OpPC);
       S.CCEDiag(Loc, diag::note_constexpr_lshift_of_negative) << LHS.toAPSInt();
-      if (S.getLangOpts().CPlusPlus11 && S.getEvalStatus().Diag &&
-          !S.getEvalStatus().Diag->empty())
+      if (!S.noteUndefinedBehavior())
         return false;
     }
   }
diff --git a/clang/lib/AST/ItaniumMangle.cpp b/clang/lib/AST/ItaniumMangle.cpp
index 40ef82785f45..d46d621d4c7d 100644
--- a/clang/lib/AST/ItaniumMangle.cpp
+++ b/clang/lib/AST/ItaniumMangle.cpp
@@ -5179,6 +5179,14 @@ recurse:
       Diags.Report(DiagID);
       return;
     }
+    case UETT_PtrAuthTypeDiscriminator: {
+      DiagnosticsEngine &Diags = Context.getDiags();
+      unsigned DiagID = Diags.getCustomDiagID(
+          DiagnosticsEngine::Error,
+          "cannot yet mangle __builtin_ptrauth_type_discriminator expression");
+      Diags.Report(E->getExprLoc(), DiagID);
+      return;
+    }
     case UETT_VecStep: {
       DiagnosticsEngine &Diags = Context.getDiags();
       unsigned DiagID = Diags.getCustomDiagID(DiagnosticsEngine::Error,
diff --git a/clang/lib/Basic/Targets/PPC.cpp b/clang/lib/Basic/Targets/PPC.cpp
index 4ba4a49311d3..9ff54083c923 100644
--- a/clang/lib/Basic/Targets/PPC.cpp
+++ b/clang/lib/Basic/Targets/PPC.cpp
@@ -385,6 +385,8 @@ void PPCTargetInfo::getTargetDefines(const LangOptions &Opts,
     Builder.defineMacro("_ARCH_PWR9");
   if (ArchDefs & ArchDefinePwr10)
     Builder.defineMacro("_ARCH_PWR10");
+  if (ArchDefs & ArchDefinePwr11)
+    Builder.defineMacro("_ARCH_PWR11");
   if (ArchDefs & ArchDefineA2)
     Builder.defineMacro("_ARCH_A2");
   if (ArchDefs & ArchDefineE500)
@@ -622,10 +624,17 @@ bool PPCTargetInfo::initFeatureMap(
     addP10SpecificFeatures(Features);
   }
 
-  // Future CPU should include all of the features of Power 10 as well as any
+  // Power11 includes all the same features as Power10 plus any features
+  // specific to the Power11 core.
+  if (CPU == "pwr11" || CPU == "power11") {
+    initFeatureMap(Features, Diags, "pwr10", FeaturesVec);
+    addP11SpecificFeatures(Features);
+  }
+
+  // Future CPU should include all of the features of Power 11 as well as any
   // additional features (yet to be determined) specific to it.
   if (CPU == "future") {
-    initFeatureMap(Features, Diags, "pwr10", FeaturesVec);
+    initFeatureMap(Features, Diags, "pwr11", FeaturesVec);
     addFutureSpecificFeatures(Features);
   }
 
@@ -696,6 +705,10 @@ void PPCTargetInfo::addP10SpecificFeatures(
   Features["isa-v31-instructions"] = true;
 }
 
+// Add any Power11 specific features.
+void PPCTargetInfo::addP11SpecificFeatures(
+    llvm::StringMap<bool> &Features) const {}
+
 // Add features specific to the "Future" CPU.
 void PPCTargetInfo::addFutureSpecificFeatures(
     llvm::StringMap<bool> &Features) const {}
@@ -870,17 +883,17 @@ ArrayRef<TargetInfo::AddlRegName> PPCTargetInfo::getGCCAddlRegNames() const {
 }
 
 static constexpr llvm::StringLiteral ValidCPUNames[] = {
-    {"generic"},     {"440"},     {"450"},    {"601"},       {"602"},
-    {"603"},         {"603e"},    {"603ev"},  {"604"},       {"604e"},
-    {"620"},         {"630"},     {"g3"},     {"7400"},      {"g4"},
-    {"7450"},        {"g4+"},     {"750"},    {"8548"},      {"970"},
-    {"g5"},          {"a2"},      {"e500"},   {"e500mc"},    {"e5500"},
-    {"power3"},      {"pwr3"},    {"power4"}, {"pwr4"},      {"power5"},
-    {"pwr5"},        {"power5x"}, {"pwr5x"},  {"power6"},    {"pwr6"},
-    {"power6x"},     {"pwr6x"},   {"power7"}, {"pwr7"},      {"power8"},
-    {"pwr8"},        {"power9"},  {"pwr9"},   {"power10"},   {"pwr10"},
-    {"powerpc"},     {"ppc"},     {"ppc32"},  {"powerpc64"}, {"ppc64"},
-    {"powerpc64le"}, {"ppc64le"}, {"future"}};
+    {"generic"},   {"440"},     {"450"},         {"601"},     {"602"},
+    {"603"},       {"603e"},    {"603ev"},       {"604"},     {"604e"},
+    {"620"},       {"630"},     {"g3"},          {"7400"},    {"g4"},
+    {"7450"},      {"g4+"},     {"750"},         {"8548"},    {"970"},
+    {"g5"},        {"a2"},      {"e500"},        {"e500mc"},  {"e5500"},
+    {"power3"},    {"pwr3"},    {"power4"},      {"pwr4"},    {"power5"},
+    {"pwr5"},      {"power5x"}, {"pwr5x"},       {"power6"},  {"pwr6"},
+    {"power6x"},   {"pwr6x"},   {"power7"},      {"pwr7"},    {"power8"},
+    {"pwr8"},      {"power9"},  {"pwr9"},        {"power10"}, {"pwr10"},
+    {"power11"},   {"pwr11"},   {"powerpc"},     {"ppc"},     {"ppc32"},
+    {"powerpc64"}, {"ppc64"},   {"powerpc64le"}, {"ppc64le"}, {"future"}};
 
 bool PPCTargetInfo::isValidCPUName(StringRef Name) const {
   return llvm::is_contained(ValidCPUNames, Name);
diff --git a/clang/lib/Basic/Targets/PPC.h b/clang/lib/Basic/Targets/PPC.h
index b15ab6fbcf49..6d5d8dd54d01 100644
--- a/clang/lib/Basic/Targets/PPC.h
+++ b/clang/lib/Basic/Targets/PPC.h
@@ -44,8 +44,9 @@ class LLVM_LIBRARY_VISIBILITY PPCTargetInfo : public TargetInfo {
     ArchDefinePwr8 = 1 << 12,
     ArchDefinePwr9 = 1 << 13,
     ArchDefinePwr10 = 1 << 14,
-    ArchDefineFuture = 1 << 15,
-    ArchDefineA2 = 1 << 16,
+    ArchDefinePwr11 = 1 << 15,
+    ArchDefineFuture = 1 << 16,
+    ArchDefineA2 = 1 << 17,
     ArchDefineE500 = 1 << 18
   } ArchDefineTypes;
 
@@ -166,11 +167,16 @@ public:
                          ArchDefinePwr7 | ArchDefinePwr6 | ArchDefinePwr5x |
                          ArchDefinePwr5 | ArchDefinePwr4 | ArchDefinePpcgr |
                          ArchDefinePpcsq)
+              .Cases("power11", "pwr11",
+                     ArchDefinePwr11 | ArchDefinePwr10 | ArchDefinePwr9 |
+                         ArchDefinePwr8 | ArchDefinePwr7 | ArchDefinePwr6 |
+                         ArchDefinePwr5x | ArchDefinePwr5 | ArchDefinePwr4 |
+                         ArchDefinePpcgr | ArchDefinePpcsq)
               .Case("future",
-                    ArchDefineFuture | ArchDefinePwr10 | ArchDefinePwr9 |
-                        ArchDefinePwr8 | ArchDefinePwr7 | ArchDefinePwr6 |
-                        ArchDefinePwr5x | ArchDefinePwr5 | ArchDefinePwr4 |
-                        ArchDefinePpcgr | ArchDefinePpcsq)
+                    ArchDefineFuture | ArchDefinePwr11 | ArchDefinePwr10 |
+                        ArchDefinePwr9 | ArchDefinePwr8 | ArchDefinePwr7 |
+                        ArchDefinePwr6 | ArchDefinePwr5x | ArchDefinePwr5 |
+                        ArchDefinePwr4 | ArchDefinePpcgr | ArchDefinePpcsq)
               .Cases("8548", "e500", ArchDefineE500)
               .Default(ArchDefineNone);
     }
@@ -192,6 +198,7 @@ public:
                  const std::vector<std::string> &FeaturesVec) const override;
 
   void addP10SpecificFeatures(llvm::StringMap<bool> &Features) const;
+  void addP11SpecificFeatures(llvm::StringMap<bool> &Features) const;
   void addFutureSpecificFeatures(llvm::StringMap<bool> &Features) const;
 
   bool handleTargetFeatures(std::vector<std::string> &Features,
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index f5bd4a141cc2..8965a14d88a6 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -1695,7 +1695,8 @@ void CGOpenMPRuntimeGPU::emitReduction(
                          CGF.AllocaInsertPt->getIterator());
   InsertPointTy CodeGenIP(CGF.Builder.GetInsertBlock(),
                           CGF.Builder.GetInsertPoint());
-  llvm::OpenMPIRBuilder::LocationDescription OmpLoc(CodeGenIP);
+  llvm::OpenMPIRBuilder::LocationDescription OmpLoc(
+      CodeGenIP, CGF.SourceLocToDebugLoc(Loc));
   llvm::SmallVector<llvm::OpenMPIRBuilder::ReductionInfo> ReductionInfos;
 
   CodeGenFunction::OMPPrivateScope Scope(CGF);
diff --git a/clang/lib/Driver/ToolChains/Arch/PPC.cpp b/clang/lib/Driver/ToolChains/Arch/PPC.cpp
index 634c09652331..acd5757d6ea9 100644
--- a/clang/lib/Driver/ToolChains/Arch/PPC.cpp
+++ b/clang/lib/Driver/ToolChains/Arch/PPC.cpp
@@ -70,6 +70,7 @@ static std::string normalizeCPUName(StringRef CPUName, const llvm::Triple &T) {
       .Case("power8", "pwr8")
       .Case("power9", "pwr9")
       .Case("power10", "pwr10")
+      .Case("power11", "pwr11")
       .Case("future", "future")
       .Case("powerpc", "ppc")
       .Case("powerpc64", "ppc64")
@@ -103,6 +104,8 @@ const char *ppc::getPPCAsmModeForCPU(StringRef Name) {
       .Case("power9", "-mpower9")
       .Case("pwr10", "-mpower10")
       .Case("power10", "-mpower10")
+      .Case("pwr11", "-mpower11")
+      .Case("power11", "-mpower11")
       .Default("-many");
 }
 
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 78936fd634f3..5de29f1eca61 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -1516,6 +1516,10 @@ static void handlePAuthABI(const ArgList &DriverArgs, ArgStringList &CC1Args) {
           options::OPT_fno_ptrauth_vtable_pointer_type_discrimination))
     CC1Args.push_back("-fptrauth-vtable-pointer-type-discrimination");
 
+  if (!DriverArgs.hasArg(options::OPT_fptrauth_indirect_gotos,
+                         options::OPT_fno_ptrauth_indirect_gotos))
+    CC1Args.push_back("-fptrauth-indirect-gotos");
+
   if (!DriverArgs.hasArg(options::OPT_fptrauth_init_fini,
                          options::OPT_fno_ptrauth_init_fini))
     CC1Args.push_back("-fptrauth-init-fini");
diff --git a/clang/lib/Headers/ptrauth.h b/clang/lib/Headers/ptrauth.h
index e0bc8c4f9acf..4724155b0dc7 100644
--- a/clang/lib/Headers/ptrauth.h
+++ b/clang/lib/Headers/ptrauth.h
@@ -202,6 +202,23 @@ typedef __UINTPTR_TYPE__ ptrauth_generic_signature_t;
 #define ptrauth_string_discriminator(__string)                                 \
   __builtin_ptrauth_string_discriminator(__string)
 
+/* Compute a constant discriminator from the given type.
+
+   The result can be used as the second argument to
+   ptrauth_blend_discriminator or the third argument to the
+   __ptrauth qualifier.  It has type size_t.
+
+   If the type is a C++ member function pointer type, the result is
+   the discriminator used to signed member function pointers of that
+   type.  If the type is a function, function pointer, or function
+   reference type, the result is the discriminator used to sign
+   functions of that type.  It is ill-formed to use this macro with any
+   other type.
+
+   A call to this function is an integer constant expression. */
+#define ptrauth_type_discriminator(__type)                                     \
+  __builtin_ptrauth_type_discriminator(__type)
+
 /* Compute a signature for the given pair of pointer-sized values.
    The order of the arguments is significant.
 
@@ -289,6 +306,8 @@ typedef __UINTPTR_TYPE__ ptrauth_generic_signature_t;
     ((ptrauth_extra_data_t)0);                                                 \
   })
 
+#define ptrauth_type_discriminator(__type) ((ptrauth_extra_data_t)0)
+
 #define ptrauth_sign_generic_data(__value, __data)                             \
   ({                                                                           \
     (void)__value;                                                             \
diff --git a/clang/lib/Headers/stdarg.h b/clang/lib/Headers/stdarg.h
index 8292ab907bec..6203d7a600a2 100644
--- a/clang/lib/Headers/stdarg.h
+++ b/clang/lib/Headers/stdarg.h
@@ -20,19 +20,18 @@
  * modules.
  */
 #if defined(__MVS__) && __has_include_next(<stdarg.h>)
-#include <__stdarg_header_macro.h>
 #undef __need___va_list
 #undef __need_va_list
 #undef __need_va_arg
 #undef __need___va_copy
 #undef __need_va_copy
+#include <__stdarg_header_macro.h>
 #include_next <stdarg.h>
 
 #else
 #if !defined(__need___va_list) && !defined(__need_va_list) &&                  \
     !defined(__need_va_arg) && !defined(__need___va_copy) &&                   \
     !defined(__need_va_copy)
-#include <__stdarg_header_macro.h>
 #define __need___va_list
 #define __need_va_list
 #define __need_va_arg
@@ -45,6 +44,7 @@
     !defined(__STRICT_ANSI__)
 #define __need_va_copy
 #endif
+#include <__stdarg_header_macro.h>
 #endif
 
 #ifdef __need___va_list
diff --git a/clang/lib/Headers/stdatomic.h b/clang/lib/Headers/stdatomic.h
index 2027055f3879..1991351f9e9e 100644
--- a/clang/lib/Headers/stdatomic.h
+++ b/clang/lib/Headers/stdatomic.h
@@ -172,7 +172,11 @@ typedef _Atomic(uintmax_t)          atomic_uintmax_t;
 
 typedef struct atomic_flag { atomic_bool _Value; } atomic_flag;
 
+#ifdef __cplusplus
+#define ATOMIC_FLAG_INIT {false}
+#else
 #define ATOMIC_FLAG_INIT { 0 }
+#endif
 
 /* These should be provided by the libc implementation. */
 #ifdef __cplusplus
diff --git a/clang/lib/Headers/stddef.h b/clang/lib/Headers/stddef.h
index 8985c526e8fc..99b275aebf5a 100644
--- a/clang/lib/Headers/stddef.h
+++ b/clang/lib/Headers/stddef.h
@@ -20,7 +20,6 @@
  * modules.
  */
 #if defined(__MVS__) && __has_include_next(<stddef.h>)
-#include <__stddef_header_macro.h>
 #undef __need_ptrdiff_t
 #undef __need_size_t
 #undef __need_rsize_t
@@ -31,6 +30,7 @@
 #undef __need_max_align_t
 #undef __need_offsetof
 #undef __need_wint_t
+#include <__stddef_header_macro.h>
 #include_next <stddef.h>
 
 #else
@@ -40,7 +40,6 @@
     !defined(__need_NULL) && !defined(__need_nullptr_t) &&                     \
     !defined(__need_unreachable) && !defined(__need_max_align_t) &&            \
     !defined(__need_offsetof) && !defined(__need_wint_t)
-#include <__stddef_header_macro.h>
 #define __need_ptrdiff_t
 #define __need_size_t
 /* ISO9899:2011 7.20 (C11 Annex K): Define rsize_t if __STDC_WANT_LIB_EXT1__ is
@@ -49,7 +48,24 @@
 #define __need_rsize_t
 #endif
 #define __need_wchar_t
+#if !defined(__STDDEF_H) || __has_feature(modules)
+/*
+ * __stddef_null.h is special when building without modules: if __need_NULL is
+ * set, then it will unconditionally redefine NULL. To avoid stepping on client
+ * definitions of NULL, __need_NULL should only be set the first time this
+ * header is included, that is when __STDDEF_H is not defined. However, when
+ * building with modules, this header is a textual header and needs to
+ * unconditionally include __stdef_null.h to support multiple submodules
+ * exporting _Builtin_stddef.null. Take module SM with submodules A and B, whose
+ * headers both include stddef.h When SM.A builds, __STDDEF_H will be defined.
+ * When SM.B builds, the definition from SM.A will leak when building without
+ * local submodule visibility. stddef.h wouldn't include __stddef_null.h, and
+ * SM.B wouldn't import _Builtin_stddef.null, and SM.B's `export *` wouldn't
+ * export NULL as expected. When building with modules, always include
+ * __stddef_null.h so that everything works as expected.
+ */
 #define __need_NULL
+#endif
 #if (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 202311L) ||              \
     defined(__cplusplus)
 #define __need_nullptr_t
@@ -65,6 +81,7 @@
 /* wint_t is provided by <wchar.h> and not <stddef.h>. It's here
  * for compatibility, but must be explicitly requested. Therefore
  * __need_wint_t is intentionally not defined here. */
+#include <__stddef_header_macro.h>
 #endif
 
 #if defined(__need_ptrdiff_t)
diff --git a/clang/lib/Parse/ParseExpr.cpp b/clang/lib/Parse/ParseExpr.cpp
index a12c375c8d48..e82b56527283 100644
--- a/clang/lib/Parse/ParseExpr.cpp
+++ b/clang/lib/Parse/ParseExpr.cpp
@@ -763,6 +763,9 @@ class CastExpressionIdValidator final : public CorrectionCandidateCallback {
 bool Parser::isRevertibleTypeTrait(const IdentifierInfo *II,
                                    tok::TokenKind *Kind) {
   if (RevertibleTypeTraits.empty()) {
+// Revertible type trait is a feature for backwards compatibility with older
+// standard libraries that declare their own structs with the same name as
+// the builtins listed below. New builtins should NOT be added to this list.
 #define RTT_JOIN(X, Y) X##Y
 #define REVERTIBLE_TYPE_TRAIT(Name)                                            \
   RevertibleTypeTraits[PP.getIdentifierInfo(#Name)] = RTT_JOIN(tok::kw_, Name)
@@ -790,7 +793,6 @@ bool Parser::isRevertibleTypeTrait(const IdentifierInfo *II,
     REVERTIBLE_TYPE_TRAIT(__is_fundamental);
     REVERTIBLE_TYPE_TRAIT(__is_integral);
     REVERTIBLE_TYPE_TRAIT(__is_interface_class);
-    REVERTIBLE_TYPE_TRAIT(__is_layout_compatible);
     REVERTIBLE_TYPE_TRAIT(__is_literal);
     REVERTIBLE_TYPE_TRAIT(__is_lvalue_expr);
     REVERTIBLE_TYPE_TRAIT(__is_lvalue_reference);
@@ -841,6 +843,26 @@ bool Parser::isRevertibleTypeTrait(const IdentifierInfo *II,
   return false;
 }
 
+ExprResult Parser::ParseBuiltinPtrauthTypeDiscriminator() {
+  SourceLocation Loc = ConsumeToken();
+
+  BalancedDelimiterTracker T(*this, tok::l_paren);
+  if (T.expectAndConsume())
+    return ExprError();
+
+  TypeResult Ty = ParseTypeName();
+  if (Ty.isInvalid()) {
+    SkipUntil(tok::r_paren, StopAtSemi);
+    return ExprError();
+  }
+
+  SourceLocation EndLoc = Tok.getLocation();
+  T.consumeClose();
+  return Actions.ActOnUnaryExprOrTypeTraitExpr(
+      Loc, UETT_PtrAuthTypeDiscriminator,
+      /*isType=*/true, Ty.get().getAsOpaquePtr(), SourceRange(Loc, EndLoc));
+}
+
 /// Parse a cast-expression, or, if \pisUnaryExpression is true, parse
 /// a unary-expression.
 ///
@@ -1806,6 +1828,9 @@ ExprResult Parser::ParseCastExpression(CastParseKind ParseKind,
     Res = ParseArrayTypeTrait();
     break;
 
+  case tok::kw___builtin_ptrauth_type_discriminator:
+    return ParseBuiltinPtrauthTypeDiscriminator();
+
   case tok::kw___is_lvalue_expr:
   case tok::kw___is_rvalue_expr:
     if (NotPrimaryExpression)
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 45b9bbb23dbf..cf1196ad23c2 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -1489,14 +1489,18 @@ enum PointerAuthOpKind {
 };
 }
 
-static bool checkPointerAuthEnabled(Sema &S, Expr *E) {
-  if (S.getLangOpts().PointerAuthIntrinsics)
+bool Sema::checkPointerAuthEnabled(SourceLocation Loc, SourceRange Range) {
+  if (getLangOpts().PointerAuthIntrinsics)
     return false;
 
-  S.Diag(E->getExprLoc(), diag::err_ptrauth_disabled) << E->getSourceRange();
+  Diag(Loc, diag::err_ptrauth_disabled) << Range;
   return true;
 }
 
+static bool checkPointerAuthEnabled(Sema &S, Expr *E) {
+  return S.checkPointerAuthEnabled(E->getExprLoc(), E->getSourceRange());
+}
+
 static bool checkPointerAuthKey(Sema &S, Expr *&Arg) {
   // Convert it to type 'int'.
   if (convertArgumentToType(S, Arg, S.Context.IntTy))
diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
index 439db55668cc..74c0e0170590 100644
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -4117,6 +4117,21 @@ static bool CheckVectorElementsTraitOperandType(Sema &S, QualType T,
   return false;
 }
 
+static bool checkPtrAuthTypeDiscriminatorOperandType(Sema &S, QualType T,
+                                                     SourceLocation Loc,
+                                                     SourceRange ArgRange) {
+  if (S.checkPointerAuthEnabled(Loc, ArgRange))
+    return true;
+
+  if (!T->isFunctionType() && !T->isFunctionPointerType() &&
+      !T->isFunctionReferenceType() && !T->isMemberFunctionPointerType()) {
+    S.Diag(Loc, diag::err_ptrauth_type_disc_undiscriminated) << T << ArgRange;
+    return true;
+  }
+
+  return false;
+}
+
 static bool CheckExtensionTraitOperandType(Sema &S, QualType T,
                                            SourceLocation Loc,
                                            SourceRange ArgRange,
@@ -4511,6 +4526,10 @@ bool Sema::CheckUnaryExprOrTypeTraitOperand(QualType ExprType,
     return CheckVectorElementsTraitOperandType(*this, ExprType, OpLoc,
                                                ExprRange);
 
+  if (ExprKind == UETT_PtrAuthTypeDiscriminator)
+    return checkPtrAuthTypeDiscriminatorOperandType(*this, ExprType, OpLoc,
+                                                    ExprRange);
+
   // Explicitly list some types as extensions.
   if (!CheckExtensionTraitOperandType(*this, ExprType, OpLoc, ExprRange,
                                       ExprKind))
@@ -5711,7 +5730,6 @@ static bool isParenthetizedAndQualifiedAddressOfExpr(Expr *Fn) {
   if (!UO || UO->getOpcode() != clang::UO_AddrOf)
     return false;
   if (auto *DRE = dyn_cast<DeclRefExpr>(UO->getSubExpr()->IgnoreParens())) {
-    assert(isa<FunctionDecl>(DRE->getDecl()) && "expected a function");
     return DRE->hasQualifier();
   }
   if (auto *OVL = dyn_cast<OverloadExpr>(UO->getSubExpr()->IgnoreParens()))
@@ -17027,7 +17045,8 @@ Sema::VerifyIntegerConstantExpression(Expr *E, llvm::APSInt *Result,
   // not a constant expression as a side-effect.
   bool Folded =
       E->EvaluateAsRValue(EvalResult, Context, /*isConstantContext*/ true) &&
-      EvalResult.Val.isInt() && !EvalResult.HasSideEffects;
+      EvalResult.Val.isInt() && !EvalResult.HasSideEffects &&
+      (!getLangOpts().CPlusPlus || !EvalResult.HasUndefinedBehavior);
 
   if (!isa<ConstantExpr>(E))
     E = ConstantExpr::Create(Context, E, EvalResult.Val);
diff --git a/clang/lib/Sema/SemaOverload.cpp b/clang/lib/Sema/SemaOverload.cpp
index a8d250fbabfe..554a2df14bea 100644
--- a/clang/lib/Sema/SemaOverload.cpp
+++ b/clang/lib/Sema/SemaOverload.cpp
@@ -6857,10 +6857,7 @@ void Sema::AddOverloadCandidate(
   Candidate.Viable = true;
   Candidate.RewriteKind =
       CandidateSet.getRewriteInfo().getRewriteKind(Function, PO);
-  Candidate.IsSurrogate = false;
   Candidate.IsADLCandidate = IsADLCandidate;
-  Candidate.IgnoreObjectArgument = false;
-  Candidate.TookAddressOfOverload = false;
   Candidate.ExplicitCallArguments = Args.size();
 
   // Explicit functions are not actually candidates at all if we're not
@@ -7422,8 +7419,6 @@ Sema::AddMethodCandidate(CXXMethodDecl *Method, DeclAccessPair FoundDecl,
   Candidate.Function = Method;
   Candidate.RewriteKind =
       CandidateSet.getRewriteInfo().getRewriteKind(Method, PO);
-  Candidate.IsSurrogate = false;
-  Candidate.IgnoreObjectArgument = false;
   Candidate.TookAddressOfOverload =
       CandidateSet.getKind() == OverloadCandidateSet::CSK_AddressOfOverloadSet;
   Candidate.ExplicitCallArguments = Args.size();
@@ -7617,7 +7612,6 @@ void Sema::AddMethodTemplateCandidate(
     Candidate.IgnoreObjectArgument =
         cast<CXXMethodDecl>(Candidate.Function)->isStatic() ||
         ObjectType.isNull();
-    Candidate.TookAddressOfOverload = false;
     Candidate.ExplicitCallArguments = Args.size();
     if (Result == TemplateDeductionResult::NonDependentConversionFailure)
       Candidate.FailureKind = ovl_fail_bad_conversion;
@@ -7705,7 +7699,6 @@ void Sema::AddTemplateOverloadCandidate(
     Candidate.IgnoreObjectArgument =
         isa<CXXMethodDecl>(Candidate.Function) &&
         !isa<CXXConstructorDecl>(Candidate.Function);
-    Candidate.TookAddressOfOverload = false;
     Candidate.ExplicitCallArguments = Args.size();
     if (Result == TemplateDeductionResult::NonDependentConversionFailure)
       Candidate.FailureKind = ovl_fail_bad_conversion;
@@ -7886,9 +7879,6 @@ void Sema::AddConversionCandidate(
   OverloadCandidate &Candidate = CandidateSet.addCandidate(1);
   Candidate.FoundDecl = FoundDecl;
   Candidate.Function = Conversion;
-  Candidate.IsSurrogate = false;
-  Candidate.IgnoreObjectArgument = false;
-  Candidate.TookAddressOfOverload = false;
   Candidate.FinalConversion.setAsIdentityConversion();
   Candidate.FinalConversion.setFromType(ConvType);
   Candidate.FinalConversion.setAllToTypes(ToType);
@@ -8084,9 +8074,6 @@ void Sema::AddTemplateConversionCandidate(
     Candidate.Function = FunctionTemplate->getTemplatedDecl();
     Candidate.Viable = false;
     Candidate.FailureKind = ovl_fail_bad_deduction;
-    Candidate.IsSurrogate = false;
-    Candidate.IgnoreObjectArgument = false;
-    Candidate.TookAddressOfOverload = false;
     Candidate.ExplicitCallArguments = 1;
     Candidate.DeductionFailure = MakeDeductionFailureInfo(Context, Result,
                                                           Info);
@@ -8119,10 +8106,8 @@ void Sema::AddSurrogateCandidate(CXXConversionDecl *Conversion,
   Candidate.FoundDecl = FoundDecl;
   Candidate.Function = nullptr;
   Candidate.Surrogate = Conversion;
-  Candidate.Viable = true;
   Candidate.IsSurrogate = true;
-  Candidate.IgnoreObjectArgument = false;
-  Candidate.TookAddressOfOverload = false;
+  Candidate.Viable = true;
   Candidate.ExplicitCallArguments = Args.size();
 
   // Determine the implicit conversion sequence for the implicit
@@ -8328,9 +8313,6 @@ void Sema::AddBuiltinCandidate(QualType *ParamTys, ArrayRef<Expr *> Args,
   OverloadCandidate &Candidate = CandidateSet.addCandidate(Args.size());
   Candidate.FoundDecl = DeclAccessPair::make(nullptr, AS_none);
   Candidate.Function = nullptr;
-  Candidate.IsSurrogate = false;
-  Candidate.IgnoreObjectArgument = false;
-  Candidate.TookAddressOfOverload = false;
   std::copy(ParamTys, ParamTys + Args.size(), Candidate.BuiltinParamTypes);
 
   // Determine the implicit conversion sequences for each of the
diff --git a/compiler-rt/lib/builtins/README.txt b/compiler-rt/lib/builtins/README.txt
index 2d213d95f333..19f26c92a0f9 100644
--- a/compiler-rt/lib/builtins/README.txt
+++ b/compiler-rt/lib/builtins/README.txt
@@ -272,6 +272,11 @@ switch32
 switch8
 switchu8
 
+// This function generates a custom trampoline function with the specific
+// realFunc and localsPtr values.
+void __trampoline_setup(uint32_t* trampOnStack, int trampSizeAllocated,
+                        const void* realFunc, void* localsPtr);
+
 // There is no C interface to the *_vfp_d8_d15_regs functions.  There are
 // called in the prolog and epilog of Thumb1 functions.  When the C++ ABI use
 // SJLJ for exceptions, each function with a catch clause or destructors needs
diff --git a/compiler-rt/lib/builtins/aarch64/sme-abi-vg.c b/compiler-rt/lib/builtins/aarch64/sme-abi-vg.c
index 062cf80fc684..20061012e16c 100644
--- a/compiler-rt/lib/builtins/aarch64/sme-abi-vg.c
+++ b/compiler-rt/lib/builtins/aarch64/sme-abi-vg.c
@@ -10,15 +10,6 @@ struct FEATURES {
 
 extern struct FEATURES __aarch64_cpu_features;
 
-struct SME_STATE {
-  long PSTATE;
-  long TPIDR2_EL0;
-};
-
-extern struct SME_STATE __arm_sme_state(void) __arm_streaming_compatible;
-
-extern bool __aarch64_has_sme_and_tpidr2_el0;
-
 #if __GNUC__ >= 9
 #pragma GCC diagnostic ignored "-Wprio-ctor-dtor"
 #endif
@@ -28,22 +19,3 @@ __attribute__((constructor(90))) static void get_aarch64_cpu_features(void) {
 
   __init_cpu_features();
 }
-
-__attribute__((target("sve"))) long
-__arm_get_current_vg(void) __arm_streaming_compatible {
-  struct SME_STATE State = __arm_sme_state();
-  unsigned long long features =
-      __atomic_load_n(&__aarch64_cpu_features.features, __ATOMIC_RELAXED);
-  bool HasSVE = features & (1ULL << FEAT_SVE);
-
-  if (!HasSVE && !__aarch64_has_sme_and_tpidr2_el0)
-    return 0;
-
-  if (HasSVE || (State.PSTATE & 1)) {
-    long vl;
-    __asm__ __volatile__("cntd %0" : "=r"(vl));
-    return vl;
-  }
-
-  return 0;
-}
diff --git a/compiler-rt/lib/builtins/aarch64/sme-abi.S b/compiler-rt/lib/builtins/aarch64/sme-abi.S
index 4c0ff66931db..cd8153f60670 100644
--- a/compiler-rt/lib/builtins/aarch64/sme-abi.S
+++ b/compiler-rt/lib/builtins/aarch64/sme-abi.S
@@ -12,11 +12,15 @@
 #if !defined(__APPLE__)
 #define TPIDR2_SYMBOL SYMBOL_NAME(__aarch64_has_sme_and_tpidr2_el0)
 #define TPIDR2_SYMBOL_OFFSET :lo12:SYMBOL_NAME(__aarch64_has_sme_and_tpidr2_el0)
+#define CPU_FEATS_SYMBOL SYMBOL_NAME(__aarch64_cpu_features)
+#define CPU_FEATS_SYMBOL_OFFSET :lo12:SYMBOL_NAME(__aarch64_cpu_features)
 #else
 // MachO requires @page/@pageoff directives because the global is defined
 // in a different file. Otherwise this file may fail to build.
 #define TPIDR2_SYMBOL SYMBOL_NAME(__aarch64_has_sme_and_tpidr2_el0)@page
 #define TPIDR2_SYMBOL_OFFSET SYMBOL_NAME(__aarch64_has_sme_and_tpidr2_el0)@pageoff
+#define CPU_FEATS_SYMBOL SYMBOL_NAME(__aarch64_cpu_features)@page
+#define CPU_FEATS_SYMBOL_OFFSET SYMBOL_NAME(__aarch64_cpu_features)@pageoff
 #endif
 
 .arch armv9-a+sme
@@ -180,6 +184,46 @@ DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_za_disable)
   ret
 END_COMPILERRT_OUTLINE_FUNCTION(__arm_za_disable)
 
+DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_get_current_vg)
+  .variant_pcs __arm_get_current_vg
+  BTI_C
+
+  stp     x29, x30, [sp, #-16]!
+  .cfi_def_cfa_offset 16
+  mov     x29, sp
+  .cfi_def_cfa w29, 16
+  .cfi_offset w30, -8
+  .cfi_offset w29, -16
+  adrp    x17, CPU_FEATS_SYMBOL
+  ldr     w17, [x17, CPU_FEATS_SYMBOL_OFFSET]
+  tbnz    w17, #30, 0f
+  adrp    x16, TPIDR2_SYMBOL
+  ldrb    w16, [x16, TPIDR2_SYMBOL_OFFSET]
+  cbz     w16, 1f
+0:
+  mov     x18, x1
+  bl      __arm_sme_state
+  mov     x1, x18
+  and     x17, x17, #0x40000000
+  bfxil   x17, x0, #0, #1
+  cbz     x17, 1f
+  cntd    x0
+  .cfi_def_cfa wsp, 16
+  ldp     x29, x30, [sp], #16
+  .cfi_def_cfa_offset 0
+  .cfi_restore w30
+  .cfi_restore w29
+  ret
+1:
+  mov     x0, xzr
+  .cfi_def_cfa wsp, 16
+  ldp     x29, x30, [sp], #16
+  .cfi_def_cfa_offset 0
+  .cfi_restore w30
+  .cfi_restore w29
+  ret
+END_COMPILERRT_OUTLINE_FUNCTION(__arm_get_current_vg)
+
 NO_EXEC_STACK_DIRECTIVE
 
 // GNU property note for BTI and PAC
diff --git a/compiler-rt/lib/builtins/trampoline_setup.c b/compiler-rt/lib/builtins/trampoline_setup.c
index 844eb2794414..830e25e4c030 100644
--- a/compiler-rt/lib/builtins/trampoline_setup.c
+++ b/compiler-rt/lib/builtins/trampoline_setup.c
@@ -41,3 +41,45 @@ COMPILER_RT_ABI void __trampoline_setup(uint32_t *trampOnStack,
   __clear_cache(trampOnStack, &trampOnStack[10]);
 }
 #endif // __powerpc__ && !defined(__powerpc64__)
+
+// The AArch64 compiler generates calls to __trampoline_setup() when creating
+// trampoline functions on the stack for use with nested functions.
+// This function creates a custom 36-byte trampoline function on the stack
+// which loads x18 with a pointer to the outer function's locals
+// and then jumps to the target nested function.
+// Note: x18 is a reserved platform register on Windows and macOS.
+
+#if defined(__aarch64__) && defined(__ELF__)
+COMPILER_RT_ABI void __trampoline_setup(uint32_t *trampOnStack,
+                                        int trampSizeAllocated,
+                                        const void *realFunc, void *localsPtr) {
+  // This should never happen, but if compiler did not allocate
+  // enough space on stack for the trampoline, abort.
+  if (trampSizeAllocated < 36)
+    compilerrt_abort();
+
+  // create trampoline
+  // Load realFunc into x17. mov/movk 16 bits at a time.
+  trampOnStack[0] =
+      0xd2800000u | ((((uint64_t)realFunc >> 0) & 0xffffu) << 5) | 0x11;
+  trampOnStack[1] =
+      0xf2a00000u | ((((uint64_t)realFunc >> 16) & 0xffffu) << 5) | 0x11;
+  trampOnStack[2] =
+      0xf2c00000u | ((((uint64_t)realFunc >> 32) & 0xffffu) << 5) | 0x11;
+  trampOnStack[3] =
+      0xf2e00000u | ((((uint64_t)realFunc >> 48) & 0xffffu) << 5) | 0x11;
+  // Load localsPtr into x18
+  trampOnStack[4] =
+      0xd2800000u | ((((uint64_t)localsPtr >> 0) & 0xffffu) << 5) | 0x12;
+  trampOnStack[5] =
+      0xf2a00000u | ((((uint64_t)localsPtr >> 16) & 0xffffu) << 5) | 0x12;
+  trampOnStack[6] =
+      0xf2c00000u | ((((uint64_t)localsPtr >> 32) & 0xffffu) << 5) | 0x12;
+  trampOnStack[7] =
+      0xf2e00000u | ((((uint64_t)localsPtr >> 48) & 0xffffu) << 5) | 0x12;
+  trampOnStack[8] = 0xd61f0220; // br x17
+
+  // Clear instruction cache.
+  __clear_cache(trampOnStack, &trampOnStack[9]);
+}
+#endif // defined(__aarch64__) && !defined(__APPLE__) && !defined(_WIN64)
diff --git a/compiler-rt/lib/sanitizer_common/sanitizer_ptrauth.h b/compiler-rt/lib/sanitizer_common/sanitizer_ptrauth.h
index 520035469485..265a9925a15a 100644
--- a/compiler-rt/lib/sanitizer_common/sanitizer_ptrauth.h
+++ b/compiler-rt/lib/sanitizer_common/sanitizer_ptrauth.h
@@ -9,31 +9,33 @@
 #ifndef SANITIZER_PTRAUTH_H
 #define SANITIZER_PTRAUTH_H
 
-#if __has_feature(ptrauth_calls)
-#include <ptrauth.h>
+#if __has_feature(ptrauth_intrinsics)
+#  include <ptrauth.h>
 #elif defined(__ARM_FEATURE_PAC_DEFAULT) && !defined(__APPLE__)
-inline unsigned long ptrauth_strip(void* __value, unsigned int __key) {
-  // On the stack the link register is protected with Pointer
-  // Authentication Code when compiled with -mbranch-protection.
-  // Let's stripping the PAC unconditionally because xpaclri is in
-  // the NOP space so will do nothing when it is not enabled or not available.
-  unsigned long ret;
-  asm volatile(
-      "mov x30, %1\n\t"
-      "hint #7\n\t"  // xpaclri
-      "mov %0, x30\n\t"
-      : "=r"(ret)
-      : "r"(__value)
-      : "x30");
-  return ret;
-}
-#define ptrauth_auth_data(__value, __old_key, __old_data) __value
-#define ptrauth_string_discriminator(__string) ((int)0)
+// On the stack the link register is protected with Pointer
+// Authentication Code when compiled with -mbranch-protection.
+// Let's stripping the PAC unconditionally because xpaclri is in
+// the NOP space so will do nothing when it is not enabled or not available.
+#  define ptrauth_strip(__value, __key) \
+    ({                                  \
+      __typeof(__value) ret;            \
+      asm volatile(                     \
+          "mov x30, %1\n\t"             \
+          "hint #7\n\t"                 \
+          "mov %0, x30\n\t"             \
+          "mov x30, xzr\n\t"            \
+          : "=r"(ret)                   \
+          : "r"(__value)                \
+          : "x30");                     \
+      ret;                              \
+    })
+#  define ptrauth_auth_data(__value, __old_key, __old_data) __value
+#  define ptrauth_string_discriminator(__string) ((int)0)
 #else
 // Copied from <ptrauth.h>
-#define ptrauth_strip(__value, __key) __value
-#define ptrauth_auth_data(__value, __old_key, __old_data) __value
-#define ptrauth_string_discriminator(__string) ((int)0)
+#  define ptrauth_strip(__value, __key) __value
+#  define ptrauth_auth_data(__value, __old_key, __old_data) __value
+#  define ptrauth_string_discriminator(__string) ((int)0)
 #endif
 
 #define STRIP_PAC_PC(pc) ((uptr)ptrauth_strip(pc, 0))
diff --git a/compiler-rt/lib/ubsan/ubsan_type_hash_itanium.cpp b/compiler-rt/lib/ubsan/ubsan_type_hash_itanium.cpp
index 468a8fcd603f..15788574dd99 100644
--- a/compiler-rt/lib/ubsan/ubsan_type_hash_itanium.cpp
+++ b/compiler-rt/lib/ubsan/ubsan_type_hash_itanium.cpp
@@ -207,7 +207,7 @@ struct VtablePrefix {
   std::type_info *TypeInfo;
 };
 VtablePrefix *getVtablePrefix(void *Vtable) {
-  Vtable = ptrauth_auth_data(Vtable, ptrauth_key_cxx_vtable_pointer, 0);
+  Vtable = ptrauth_strip(Vtable, ptrauth_key_cxx_vtable_pointer);
   VtablePrefix *Vptr = reinterpret_cast<VtablePrefix*>(Vtable);
   VtablePrefix *Prefix = Vptr - 1;
   if (!IsAccessibleMemoryRange((uptr)Prefix, sizeof(VtablePrefix)))
diff --git a/libcxx/include/__bit_reference b/libcxx/include/__bit_reference
index 606069d98be7..22637d439741 100644
--- a/libcxx/include/__bit_reference
+++ b/libcxx/include/__bit_reference
@@ -16,6 +16,7 @@
 #include <__bit/countr.h>
 #include <__bit/invert_if.h>
 #include <__bit/popcount.h>
+#include <__compare/ordering.h>
 #include <__config>
 #include <__fwd/bit_reference.h>
 #include <__iterator/iterator_traits.h>
@@ -913,6 +914,7 @@ public:
     return __x.__seg_ == __y.__seg_ && __x.__ctz_ == __y.__ctz_;
   }
 
+#if _LIBCPP_STD_VER <= 17
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 friend bool
   operator!=(const __bit_iterator& __x, const __bit_iterator& __y) {
     return !(__x == __y);
@@ -937,6 +939,18 @@ public:
   operator>=(const __bit_iterator& __x, const __bit_iterator& __y) {
     return !(__x < __y);
   }
+#else  // _LIBCPP_STD_VER <= 17
+  _LIBCPP_HIDE_FROM_ABI constexpr friend strong_ordering
+  operator<=>(const __bit_iterator& __x, const __bit_iterator& __y) {
+    if (__x.__seg_ < __y.__seg_)
+      return strong_ordering::less;
+
+    if (__x.__seg_ == __y.__seg_)
+      return __x.__ctz_ <=> __y.__ctz_;
+
+    return strong_ordering::greater;
+  }
+#endif // _LIBCPP_STD_VER <= 17
 
 private:
   _LIBCPP_HIDE_FROM_ABI
diff --git a/libcxx/include/__config b/libcxx/include/__config
index 108f700823cb..661af5be3c22 100644
--- a/libcxx/include/__config
+++ b/libcxx/include/__config
@@ -27,7 +27,7 @@
 // _LIBCPP_VERSION represents the version of libc++, which matches the version of LLVM.
 // Given a LLVM release LLVM XX.YY.ZZ (e.g. LLVM 17.0.1 == 17.00.01), _LIBCPP_VERSION is
 // defined to XXYYZZ.
-#  define _LIBCPP_VERSION 190000
+#  define _LIBCPP_VERSION 190100
 
 #  define _LIBCPP_CONCAT_IMPL(_X, _Y) _X##_Y
 #  define _LIBCPP_CONCAT(_X, _Y) _LIBCPP_CONCAT_IMPL(_X, _Y)
diff --git a/libcxx/include/__iterator/bounded_iter.h b/libcxx/include/__iterator/bounded_iter.h
index ce0823b8c97e..8a81c9ffbfc3 100644
--- a/libcxx/include/__iterator/bounded_iter.h
+++ b/libcxx/include/__iterator/bounded_iter.h
@@ -11,6 +11,8 @@
 #define _LIBCPP___ITERATOR_BOUNDED_ITER_H
 
 #include <__assert>
+#include <__compare/ordering.h>
+#include <__compare/three_way_comparable.h>
 #include <__config>
 #include <__iterator/iterator_traits.h>
 #include <__memory/pointer_traits.h>
@@ -201,10 +203,15 @@ public:
   operator==(__bounded_iter const& __x, __bounded_iter const& __y) _NOEXCEPT {
     return __x.__current_ == __y.__current_;
   }
+
+#if _LIBCPP_STD_VER <= 17
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR friend bool
   operator!=(__bounded_iter const& __x, __bounded_iter const& __y) _NOEXCEPT {
     return __x.__current_ != __y.__current_;
   }
+#endif
+
+  // TODO(mordante) disable these overloads in the LLVM 20 release.
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR friend bool
   operator<(__bounded_iter const& __x, __bounded_iter const& __y) _NOEXCEPT {
     return __x.__current_ < __y.__current_;
@@ -222,6 +229,23 @@ public:
     return __x.__current_ >= __y.__current_;
   }
 
+#if _LIBCPP_STD_VER >= 20
+  _LIBCPP_HIDE_FROM_ABI constexpr friend strong_ordering
+  operator<=>(__bounded_iter const& __x, __bounded_iter const& __y) noexcept {
+    if constexpr (three_way_comparable<_Iterator, strong_ordering>) {
+      return __x.__current_ <=> __y.__current_;
+    } else {
+      if (__x.__current_ < __y.__current_)
+        return strong_ordering::less;
+
+      if (__x.__current_ == __y.__current_)
+        return strong_ordering::equal;
+
+      return strong_ordering::greater;
+    }
+  }
+#endif // _LIBCPP_STD_VER >= 20
+
 private:
   template <class>
   friend struct pointer_traits;
diff --git a/libcxx/include/__iterator/wrap_iter.h b/libcxx/include/__iterator/wrap_iter.h
index 252d13b26c9e..56183c0ee794 100644
--- a/libcxx/include/__iterator/wrap_iter.h
+++ b/libcxx/include/__iterator/wrap_iter.h
@@ -10,6 +10,8 @@
 #ifndef _LIBCPP___ITERATOR_WRAP_ITER_H
 #define _LIBCPP___ITERATOR_WRAP_ITER_H
 
+#include <__compare/ordering.h>
+#include <__compare/three_way_comparable.h>
 #include <__config>
 #include <__iterator/iterator_traits.h>
 #include <__memory/addressof.h>
@@ -131,6 +133,7 @@ operator<(const __wrap_iter<_Iter1>& __x, const __wrap_iter<_Iter2>& __y) _NOEXC
   return __x.base() < __y.base();
 }
 
+#if _LIBCPP_STD_VER <= 17
 template <class _Iter1>
 _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR bool
 operator!=(const __wrap_iter<_Iter1>& __x, const __wrap_iter<_Iter1>& __y) _NOEXCEPT {
@@ -142,7 +145,9 @@ _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR bool
 operator!=(const __wrap_iter<_Iter1>& __x, const __wrap_iter<_Iter2>& __y) _NOEXCEPT {
   return !(__x == __y);
 }
+#endif
 
+// TODO(mordante) disable these overloads in the LLVM 20 release.
 template <class _Iter1>
 _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR bool
 operator>(const __wrap_iter<_Iter1>& __x, const __wrap_iter<_Iter1>& __y) _NOEXCEPT {
@@ -179,6 +184,24 @@ operator<=(const __wrap_iter<_Iter1>& __x, const __wrap_iter<_Iter2>& __y) _NOEX
   return !(__y < __x);
 }
 
+#if _LIBCPP_STD_VER >= 20
+template <class _Iter1, class _Iter2>
+_LIBCPP_HIDE_FROM_ABI constexpr strong_ordering
+operator<=>(const __wrap_iter<_Iter1>& __x, const __wrap_iter<_Iter2>& __y) noexcept {
+  if constexpr (three_way_comparable_with<_Iter1, _Iter2, strong_ordering>) {
+    return __x.base() <=> __y.base();
+  } else {
+    if (__x.base() < __y.base())
+      return strong_ordering::less;
+
+    if (__x.base() == __y.base())
+      return strong_ordering::equal;
+
+    return strong_ordering::greater;
+  }
+}
+#endif // _LIBCPP_STD_VER >= 20
+
 template <class _Iter1, class _Iter2>
 _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14
 #ifndef _LIBCPP_CXX03_LANG
diff --git a/libcxx/include/__math/hypot.h b/libcxx/include/__math/hypot.h
index 1bf193a9ab7e..61fd260c5940 100644
--- a/libcxx/include/__math/hypot.h
+++ b/libcxx/include/__math/hypot.h
@@ -15,10 +15,21 @@
 #include <__type_traits/is_same.h>
 #include <__type_traits/promote.h>
 
+#if _LIBCPP_STD_VER >= 17
+#  include <__algorithm/max.h>
+#  include <__math/abs.h>
+#  include <__math/roots.h>
+#  include <__utility/pair.h>
+#  include <limits>
+#endif
+
 #if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
 #  pragma GCC system_header
 #endif
 
+_LIBCPP_PUSH_MACROS
+#include <__undef_macros>
+
 _LIBCPP_BEGIN_NAMESPACE_STD
 
 namespace __math {
@@ -41,8 +52,86 @@ inline _LIBCPP_HIDE_FROM_ABI typename __promote<_A1, _A2>::type hypot(_A1 __x, _
   return __math::hypot((__result_type)__x, (__result_type)__y);
 }
 
+#if _LIBCPP_STD_VER >= 17
+// Factors needed to determine if over-/underflow might happen for `std::hypot(x,y,z)`.
+// returns [overflow_threshold, overflow_scale]
+template <class _Real>
+_LIBCPP_HIDE_FROM_ABI std::pair<_Real, _Real> __hypot_factors() {
+  static_assert(std::numeric_limits<_Real>::is_iec559);
+
+  if constexpr (std::is_same_v<_Real, float>) {
+    static_assert(-125 == std::numeric_limits<_Real>::min_exponent);
+    static_assert(+128 == std::numeric_limits<_Real>::max_exponent);
+    return {0x1.0p+62f, 0x1.0p-70f};
+  } else if constexpr (std::is_same_v<_Real, double>) {
+    static_assert(-1021 == std::numeric_limits<_Real>::min_exponent);
+    static_assert(+1024 == std::numeric_limits<_Real>::max_exponent);
+    return {0x1.0p+510, 0x1.0p-600};
+  } else { // long double
+    static_assert(std::is_same_v<_Real, long double>);
+
+    // preprocessor guard necessary, otherwise literals (e.g. `0x1.0p+8'190l`) throw warnings even when shielded by `if
+    // constexpr`
+#  if __DBL_MAX_EXP__ == __LDBL_MAX_EXP__
+    static_assert(sizeof(_Real) == sizeof(double));
+    return static_cast<std::pair<_Real, _Real>>(__math::__hypot_factors<double>());
+#  else
+    static_assert(sizeof(_Real) > sizeof(double));
+    static_assert(-16381 == std::numeric_limits<_Real>::min_exponent);
+    static_assert(+16384 == std::numeric_limits<_Real>::max_exponent);
+    return {0x1.0p+8190l, 0x1.0p-9000l};
+#  endif
+  }
+}
+
+// Computes the three-dimensional hypotenuse: `std::hypot(x,y,z)`.
+// The naive implementation might over-/underflow which is why this implementation is more involved:
+//    If the square of an argument might run into issues, we scale the arguments appropriately.
+// See https://github.com/llvm/llvm-project/issues/92782 for a detailed discussion and summary.
+template <class _Real>
+_LIBCPP_HIDE_FROM_ABI _Real __hypot(_Real __x, _Real __y, _Real __z) {
+  const _Real __max_abs = std::max(__math::fabs(__x), std::max(__math::fabs(__y), __math::fabs(__z)));
+  const auto [__overflow_threshold, __overflow_scale] = __math::__hypot_factors<_Real>();
+  _Real __scale;
+  if (__max_abs > __overflow_threshold) { // x*x + y*y + z*z might overflow
+    __scale = __overflow_scale;
+    __x *= __scale;
+    __y *= __scale;
+    __z *= __scale;
+  } else if (__max_abs < 1 / __overflow_threshold) { // x*x + y*y + z*z might underflow
+    __scale = 1 / __overflow_scale;
+    __x *= __scale;
+    __y *= __scale;
+    __z *= __scale;
+  } else
+    __scale = 1;
+  return __math::sqrt(__x * __x + __y * __y + __z * __z) / __scale;
+}
+
+inline _LIBCPP_HIDE_FROM_ABI float hypot(float __x, float __y, float __z) { return __math::__hypot(__x, __y, __z); }
+
+inline _LIBCPP_HIDE_FROM_ABI double hypot(double __x, double __y, double __z) { return __math::__hypot(__x, __y, __z); }
+
+inline _LIBCPP_HIDE_FROM_ABI long double hypot(long double __x, long double __y, long double __z) {
+  return __math::__hypot(__x, __y, __z);
+}
+
+template <class _A1,
+          class _A2,
+          class _A3,
+          std::enable_if_t< is_arithmetic_v<_A1> && is_arithmetic_v<_A2> && is_arithmetic_v<_A3>, int> = 0 >
+_LIBCPP_HIDE_FROM_ABI typename __promote<_A1, _A2, _A3>::type hypot(_A1 __x, _A2 __y, _A3 __z) _NOEXCEPT {
+  using __result_type = typename __promote<_A1, _A2, _A3>::type;
+  static_assert(!(
+      std::is_same_v<_A1, __result_type> && std::is_same_v<_A2, __result_type> && std::is_same_v<_A3, __result_type>));
+  return __math::__hypot(
+      static_cast<__result_type>(__x), static_cast<__result_type>(__y), static_cast<__result_type>(__z));
+}
+#endif
+
 } // namespace __math
 
 _LIBCPP_END_NAMESPACE_STD
+_LIBCPP_POP_MACROS
 
 #endif // _LIBCPP___MATH_HYPOT_H
diff --git a/libcxx/include/cmath b/libcxx/include/cmath
index 3c22604a683c..6480c4678ce3 100644
--- a/libcxx/include/cmath
+++ b/libcxx/include/cmath
@@ -313,6 +313,7 @@ constexpr long double lerp(long double a, long double b, long double t) noexcept
 */
 
 #include <__config>
+#include <__math/hypot.h>
 #include <__type_traits/enable_if.h>
 #include <__type_traits/is_arithmetic.h>
 #include <__type_traits/is_constant_evaluated.h>
@@ -553,30 +554,6 @@ using ::scalbnl _LIBCPP_USING_IF_EXISTS;
 using ::tgammal _LIBCPP_USING_IF_EXISTS;
 using ::truncl _LIBCPP_USING_IF_EXISTS;
 
-#if _LIBCPP_STD_VER >= 17
-inline _LIBCPP_HIDE_FROM_ABI float hypot(float __x, float __y, float __z) {
-  return sqrt(__x * __x + __y * __y + __z * __z);
-}
-inline _LIBCPP_HIDE_FROM_ABI double hypot(double __x, double __y, double __z) {
-  return sqrt(__x * __x + __y * __y + __z * __z);
-}
-inline _LIBCPP_HIDE_FROM_ABI long double hypot(long double __x, long double __y, long double __z) {
-  return sqrt(__x * __x + __y * __y + __z * __z);
-}
-
-template <class _A1, class _A2, class _A3>
-inline _LIBCPP_HIDE_FROM_ABI
-typename enable_if_t< is_arithmetic<_A1>::value && is_arithmetic<_A2>::value && is_arithmetic<_A3>::value,
-                      __promote<_A1, _A2, _A3> >::type
-hypot(_A1 __lcpp_x, _A2 __lcpp_y, _A3 __lcpp_z) _NOEXCEPT {
-  typedef typename __promote<_A1, _A2, _A3>::type __result_type;
-  static_assert(
-      !(is_same<_A1, __result_type>::value && is_same<_A2, __result_type>::value && is_same<_A3, __result_type>::value),
-      "");
-  return std::hypot((__result_type)__lcpp_x, (__result_type)__lcpp_y, (__result_type)__lcpp_z);
-}
-#endif
-
 template <class _A1, __enable_if_t<is_floating_point<_A1>::value, int> = 0>
 _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR bool __constexpr_isnan(_A1 __lcpp_x) _NOEXCEPT {
 #if __has_builtin(__builtin_isnan)
diff --git a/libcxx/include/deque b/libcxx/include/deque
index 4fc994a6e229..e73135a8647b 100644
--- a/libcxx/include/deque
+++ b/libcxx/include/deque
@@ -376,10 +376,13 @@ public:
     return __x.__ptr_ == __y.__ptr_;
   }
 
+#if _LIBCPP_STD_VER <= 17
   _LIBCPP_HIDE_FROM_ABI friend bool operator!=(const __deque_iterator& __x, const __deque_iterator& __y) {
     return !(__x == __y);
   }
+#endif
 
+  // TODO(mordante) disable these overloads in the LLVM 20 release.
   _LIBCPP_HIDE_FROM_ABI friend bool operator<(const __deque_iterator& __x, const __deque_iterator& __y) {
     return __x.__m_iter_ < __y.__m_iter_ || (__x.__m_iter_ == __y.__m_iter_ && __x.__ptr_ < __y.__ptr_);
   }
@@ -396,6 +399,29 @@ public:
     return !(__x < __y);
   }
 
+#if _LIBCPP_STD_VER >= 20
+  _LIBCPP_HIDE_FROM_ABI friend strong_ordering operator<=>(const __deque_iterator& __x, const __deque_iterator& __y) {
+    if (__x.__m_iter_ < __y.__m_iter_)
+      return strong_ordering::less;
+
+    if (__x.__m_iter_ == __y.__m_iter_) {
+      if constexpr (three_way_comparable<pointer, strong_ordering>) {
+        return __x.__ptr_ <=> __y.__ptr_;
+      } else {
+        if (__x.__ptr_ < __y.__ptr_)
+          return strong_ordering::less;
+
+        if (__x.__ptr_ == __y.__ptr_)
+          return strong_ordering::equal;
+
+        return strong_ordering::greater;
+      }
+    }
+
+    return strong_ordering::greater;
+  }
+#endif // _LIBCPP_STD_VER >= 20
+
 private:
   _LIBCPP_HIDE_FROM_ABI explicit __deque_iterator(__map_iterator __m, pointer __p) _NOEXCEPT
       : __m_iter_(__m),
@@ -2530,8 +2556,7 @@ inline _LIBCPP_HIDE_FROM_ABI bool operator<=(const deque<_Tp, _Allocator>& __x,
 template <class _Tp, class _Allocator>
 _LIBCPP_HIDE_FROM_ABI __synth_three_way_result<_Tp>
 operator<=>(const deque<_Tp, _Allocator>& __x, const deque<_Tp, _Allocator>& __y) {
-  return std::lexicographical_compare_three_way(
-      __x.begin(), __x.end(), __y.begin(), __y.end(), std::__synth_three_way);
+  return std::lexicographical_compare_three_way(__x.begin(), __x.end(), __y.begin(), __y.end(), std::__synth_three_way);
 }
 
 #endif // _LIBCPP_STD_VER <= 17
diff --git a/libcxx/include/locale b/libcxx/include/locale
index dbec23a2c936..573910a85bef 100644
--- a/libcxx/include/locale
+++ b/libcxx/include/locale
@@ -232,6 +232,10 @@ template <class charT> class messages_byname;
 #    include <__locale_dir/locale_base_api/bsd_locale_fallbacks.h>
 #  endif
 
+#  if defined(__APPLE__) || defined(__FreeBSD__)
+#    include <xlocale.h>
+#  endif
+
 #  if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
 #    pragma GCC system_header
 #  endif
diff --git a/libcxx/include/string b/libcxx/include/string
index ba86a3209082..9fa979e3a517 100644
--- a/libcxx/include/string
+++ b/libcxx/include/string
@@ -3358,23 +3358,34 @@ basic_string<_CharT, _Traits, _Allocator>::__shrink_or_extend(size_type __target
     __p        = __get_long_pointer();
   } else {
     if (__target_capacity > __cap) {
+      // Extend
+      // - called from reserve should propagate the exception thrown.
       auto __allocation = std::__allocate_at_least(__alloc(), __target_capacity + 1);
       __new_data        = __allocation.ptr;
       __target_capacity = __allocation.count - 1;
     } else {
+      // Shrink
+      // - called from shrink_to_fit should not throw.
+      // - called from reserve may throw but is not required to.
 #ifndef _LIBCPP_HAS_NO_EXCEPTIONS
       try {
 #endif // _LIBCPP_HAS_NO_EXCEPTIONS
         auto __allocation = std::__allocate_at_least(__alloc(), __target_capacity + 1);
+
+        // The Standard mandates shrink_to_fit() does not increase the capacity.
+        // With equal capacity keep the existing buffer. This avoids extra work
+        // due to swapping the elements.
+        if (__allocation.count - 1 > __target_capacity) {
+          __alloc_traits::deallocate(__alloc(), __allocation.ptr, __allocation.count);
+          __annotate_new(__sz); // Undoes the __annotate_delete()
+          return;
+        }
         __new_data        = __allocation.ptr;
         __target_capacity = __allocation.count - 1;
 #ifndef _LIBCPP_HAS_NO_EXCEPTIONS
       } catch (...) {
         return;
       }
-#else  // _LIBCPP_HAS_NO_EXCEPTIONS
-      if (__new_data == nullptr)
-        return;
 #endif // _LIBCPP_HAS_NO_EXCEPTIONS
     }
     __begin_lifetime(__new_data, __target_capacity + 1);
diff --git a/llvm/include/llvm/Analysis/AliasAnalysis.h b/llvm/include/llvm/Analysis/AliasAnalysis.h
index 812b5a9f72a3..4140387a1f34 100644
--- a/llvm/include/llvm/Analysis/AliasAnalysis.h
+++ b/llvm/include/llvm/Analysis/AliasAnalysis.h
@@ -244,12 +244,23 @@ class AAQueryInfo {
 public:
   using LocPair = std::pair<AACacheLoc, AACacheLoc>;
   struct CacheEntry {
+    /// Cache entry is neither an assumption nor does it use a (non-definitive)
+    /// assumption.
+    static constexpr int Definitive = -2;
+    /// Cache entry is not an assumption itself, but may be using an assumption
+    /// from higher up the stack.
+    static constexpr int AssumptionBased = -1;
+
     AliasResult Result;
-    /// Number of times a NoAlias assumption has been used.
-    /// 0 for assumptions that have not been used, -1 for definitive results.
+    /// Number of times a NoAlias assumption has been used, 0 for assumptions
+    /// that have not been used. Can also take one of the Definitive or
+    /// AssumptionBased values documented above.
     int NumAssumptionUses;
+
     /// Whether this is a definitive (non-assumption) result.
-    bool isDefinitive() const { return NumAssumptionUses < 0; }
+    bool isDefinitive() const { return NumAssumptionUses == Definitive; }
+    /// Whether this is an assumption that has not been proven yet.
+    bool isAssumption() const { return NumAssumptionUses >= 0; }
   };
 
   // Alias analysis result aggregration using which this query is performed.
diff --git a/llvm/include/llvm/Analysis/SimplifyQuery.h b/llvm/include/llvm/Analysis/SimplifyQuery.h
index a560744f0122..e8f43c8c2e91 100644
--- a/llvm/include/llvm/Analysis/SimplifyQuery.h
+++ b/llvm/include/llvm/Analysis/SimplifyQuery.h
@@ -130,6 +130,12 @@ struct SimplifyQuery {
     Copy.CC = &CC;
     return Copy;
   }
+
+  SimplifyQuery getWithoutCondContext() const {
+    SimplifyQuery Copy(*this);
+    Copy.CC = nullptr;
+    return Copy;
+  }
 };
 
 } // end namespace llvm
diff --git a/llvm/include/llvm/CodeGen/MachineFrameInfo.h b/llvm/include/llvm/CodeGen/MachineFrameInfo.h
index 466fed7fb3a2..213b7ec6b3fb 100644
--- a/llvm/include/llvm/CodeGen/MachineFrameInfo.h
+++ b/llvm/include/llvm/CodeGen/MachineFrameInfo.h
@@ -251,7 +251,7 @@ private:
   /// targets, this value is only used when generating debug info (via
   /// TargetRegisterInfo::getFrameIndexReference); when generating code, the
   /// corresponding adjustments are performed directly.
-  int OffsetAdjustment = 0;
+  int64_t OffsetAdjustment = 0;
 
   /// The prolog/epilog code inserter may process objects that require greater
   /// alignment than the default alignment the target provides.
@@ -280,7 +280,7 @@ private:
   /// setup/destroy pseudo instructions (as defined in the TargetFrameInfo
   /// class).  This information is important for frame pointer elimination.
   /// It is only valid during and after prolog/epilog code insertion.
-  unsigned MaxCallFrameSize = ~0u;
+  uint64_t MaxCallFrameSize = ~UINT64_C(0);
 
   /// The number of bytes of callee saved registers that the target wants to
   /// report for the current function in the CodeView S_FRAMEPROC record.
@@ -593,10 +593,10 @@ public:
   uint64_t estimateStackSize(const MachineFunction &MF) const;
 
   /// Return the correction for frame offsets.
-  int getOffsetAdjustment() const { return OffsetAdjustment; }
+  int64_t getOffsetAdjustment() const { return OffsetAdjustment; }
 
   /// Set the correction for frame offsets.
-  void setOffsetAdjustment(int Adj) { OffsetAdjustment = Adj; }
+  void setOffsetAdjustment(int64_t Adj) { OffsetAdjustment = Adj; }
 
   /// Return the alignment in bytes that this function must be aligned to,
   /// which is greater than the default stack alignment provided by the target.
@@ -663,7 +663,7 @@ public:
   /// CallFrameSetup/Destroy pseudo instructions are used by the target, and
   /// then only during or after prolog/epilog code insertion.
   ///
-  unsigned getMaxCallFrameSize() const {
+  uint64_t getMaxCallFrameSize() const {
     // TODO: Enable this assert when targets are fixed.
     //assert(isMaxCallFrameSizeComputed() && "MaxCallFrameSize not computed yet");
     if (!isMaxCallFrameSizeComputed())
@@ -671,9 +671,9 @@ public:
     return MaxCallFrameSize;
   }
   bool isMaxCallFrameSizeComputed() const {
-    return MaxCallFrameSize != ~0u;
+    return MaxCallFrameSize != ~UINT64_C(0);
   }
-  void setMaxCallFrameSize(unsigned S) { MaxCallFrameSize = S; }
+  void setMaxCallFrameSize(uint64_t S) { MaxCallFrameSize = S; }
 
   /// Returns how many bytes of callee-saved registers the target pushed in the
   /// prologue. Only used for debug info.
diff --git a/llvm/include/llvm/CodeGen/TargetFrameLowering.h b/llvm/include/llvm/CodeGen/TargetFrameLowering.h
index 0b9cacecc7cb..72978b2f746d 100644
--- a/llvm/include/llvm/CodeGen/TargetFrameLowering.h
+++ b/llvm/include/llvm/CodeGen/TargetFrameLowering.h
@@ -51,7 +51,7 @@ public:
   // Maps a callee saved register to a stack slot with a fixed offset.
   struct SpillSlot {
     unsigned Reg;
-    int Offset; // Offset relative to stack pointer on function entry.
+    int64_t Offset; // Offset relative to stack pointer on function entry.
   };
 
   struct DwarfFrameBase {
@@ -66,7 +66,7 @@ public:
       // Used with FrameBaseKind::Register.
       unsigned Reg;
       // Used with FrameBaseKind::CFA.
-      int Offset;
+      int64_t Offset;
       struct WasmFrameBase WasmLoc;
     } Location;
   };
diff --git a/llvm/include/llvm/MC/MCAsmBackend.h b/llvm/include/llvm/MC/MCAsmBackend.h
index 736f44686689..d1d1814dd8b5 100644
--- a/llvm/include/llvm/MC/MCAsmBackend.h
+++ b/llvm/include/llvm/MC/MCAsmBackend.h
@@ -225,7 +225,7 @@ public:
   virtual void handleAssemblerFlag(MCAssemblerFlag Flag) {}
 
   /// Generate the compact unwind encoding for the CFI instructions.
-  virtual uint32_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
+  virtual uint64_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
                                                  const MCContext *Ctxt) const {
     return 0;
   }
diff --git a/llvm/include/llvm/MC/MCDwarf.h b/llvm/include/llvm/MC/MCDwarf.h
index d0e45ab59a92..7dba67efa22f 100644
--- a/llvm/include/llvm/MC/MCDwarf.h
+++ b/llvm/include/llvm/MC/MCDwarf.h
@@ -509,11 +509,11 @@ private:
   union {
     struct {
       unsigned Register;
-      int Offset;
+      int64_t Offset;
     } RI;
     struct {
       unsigned Register;
-      int Offset;
+      int64_t Offset;
       unsigned AddressSpace;
     } RIA;
     struct {
@@ -527,7 +527,7 @@ private:
   std::vector<char> Values;
   std::string Comment;
 
-  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int O, SMLoc Loc,
+  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int64_t O, SMLoc Loc,
                    StringRef V = "", StringRef Comment = "")
       : Label(L), Operation(Op), Loc(Loc), Values(V.begin(), V.end()),
         Comment(Comment) {
@@ -539,7 +539,7 @@ private:
     assert(Op == OpRegister);
     U.RR = {R1, R2};
   }
-  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int O, unsigned AS,
+  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int64_t O, unsigned AS,
                    SMLoc Loc)
       : Label(L), Operation(Op), Loc(Loc) {
     assert(Op == OpLLVMDefAspaceCfa);
@@ -555,8 +555,8 @@ private:
 public:
   /// .cfi_def_cfa defines a rule for computing CFA as: take address from
   /// Register and add Offset to it.
-  static MCCFIInstruction cfiDefCfa(MCSymbol *L, unsigned Register, int Offset,
-                                    SMLoc Loc = {}) {
+  static MCCFIInstruction cfiDefCfa(MCSymbol *L, unsigned Register,
+                                    int64_t Offset, SMLoc Loc = {}) {
     return MCCFIInstruction(OpDefCfa, L, Register, Offset, Loc);
   }
 
@@ -564,13 +564,13 @@ public:
   /// on Register will be used instead of the old one. Offset remains the same.
   static MCCFIInstruction createDefCfaRegister(MCSymbol *L, unsigned Register,
                                                SMLoc Loc = {}) {
-    return MCCFIInstruction(OpDefCfaRegister, L, Register, 0, Loc);
+    return MCCFIInstruction(OpDefCfaRegister, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_def_cfa_offset modifies a rule for computing CFA. Register
   /// remains the same, but offset is new. Note that it is the absolute offset
   /// that will be added to a defined register to the compute CFA address.
-  static MCCFIInstruction cfiDefCfaOffset(MCSymbol *L, int Offset,
+  static MCCFIInstruction cfiDefCfaOffset(MCSymbol *L, int64_t Offset,
                                           SMLoc Loc = {}) {
     return MCCFIInstruction(OpDefCfaOffset, L, 0, Offset, Loc);
   }
@@ -578,7 +578,7 @@ public:
   /// .cfi_adjust_cfa_offset Same as .cfi_def_cfa_offset, but
   /// Offset is a relative value that is added/subtracted from the previous
   /// offset.
-  static MCCFIInstruction createAdjustCfaOffset(MCSymbol *L, int Adjustment,
+  static MCCFIInstruction createAdjustCfaOffset(MCSymbol *L, int64_t Adjustment,
                                                 SMLoc Loc = {}) {
     return MCCFIInstruction(OpAdjustCfaOffset, L, 0, Adjustment, Loc);
   }
@@ -588,7 +588,7 @@ public:
   /// be the result of evaluating the DWARF operation expression
   /// `DW_OP_constu AS; DW_OP_aspace_bregx R, B` as a location description.
   static MCCFIInstruction createLLVMDefAspaceCfa(MCSymbol *L, unsigned Register,
-                                                 int Offset,
+                                                 int64_t Offset,
                                                  unsigned AddressSpace,
                                                  SMLoc Loc) {
     return MCCFIInstruction(OpLLVMDefAspaceCfa, L, Register, Offset,
@@ -598,7 +598,7 @@ public:
   /// .cfi_offset Previous value of Register is saved at offset Offset
   /// from CFA.
   static MCCFIInstruction createOffset(MCSymbol *L, unsigned Register,
-                                       int Offset, SMLoc Loc = {}) {
+                                       int64_t Offset, SMLoc Loc = {}) {
     return MCCFIInstruction(OpOffset, L, Register, Offset, Loc);
   }
 
@@ -606,7 +606,7 @@ public:
   /// Offset from the current CFA register. This is transformed to .cfi_offset
   /// using the known displacement of the CFA register from the CFA.
   static MCCFIInstruction createRelOffset(MCSymbol *L, unsigned Register,
-                                          int Offset, SMLoc Loc = {}) {
+                                          int64_t Offset, SMLoc Loc = {}) {
     return MCCFIInstruction(OpRelOffset, L, Register, Offset, Loc);
   }
 
@@ -619,12 +619,12 @@ public:
 
   /// .cfi_window_save SPARC register window is saved.
   static MCCFIInstruction createWindowSave(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpWindowSave, L, 0, 0, Loc);
+    return MCCFIInstruction(OpWindowSave, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_negate_ra_state AArch64 negate RA state.
   static MCCFIInstruction createNegateRAState(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpNegateRAState, L, 0, 0, Loc);
+    return MCCFIInstruction(OpNegateRAState, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_restore says that the rule for Register is now the same as it
@@ -632,31 +632,31 @@ public:
   /// by .cfi_startproc were executed.
   static MCCFIInstruction createRestore(MCSymbol *L, unsigned Register,
                                         SMLoc Loc = {}) {
-    return MCCFIInstruction(OpRestore, L, Register, 0, Loc);
+    return MCCFIInstruction(OpRestore, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_undefined From now on the previous value of Register can't be
   /// restored anymore.
   static MCCFIInstruction createUndefined(MCSymbol *L, unsigned Register,
                                           SMLoc Loc = {}) {
-    return MCCFIInstruction(OpUndefined, L, Register, 0, Loc);
+    return MCCFIInstruction(OpUndefined, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_same_value Current value of Register is the same as in the
   /// previous frame. I.e., no restoration is needed.
   static MCCFIInstruction createSameValue(MCSymbol *L, unsigned Register,
                                           SMLoc Loc = {}) {
-    return MCCFIInstruction(OpSameValue, L, Register, 0, Loc);
+    return MCCFIInstruction(OpSameValue, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_remember_state Save all current rules for all registers.
   static MCCFIInstruction createRememberState(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpRememberState, L, 0, 0, Loc);
+    return MCCFIInstruction(OpRememberState, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_restore_state Restore the previously saved state.
   static MCCFIInstruction createRestoreState(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpRestoreState, L, 0, 0, Loc);
+    return MCCFIInstruction(OpRestoreState, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_escape Allows the user to add arbitrary bytes to the unwind
@@ -667,7 +667,7 @@ public:
   }
 
   /// A special wrapper for .cfi_escape that indicates GNU_ARGS_SIZE
-  static MCCFIInstruction createGnuArgsSize(MCSymbol *L, int Size,
+  static MCCFIInstruction createGnuArgsSize(MCSymbol *L, int64_t Size,
                                             SMLoc Loc = {}) {
     return MCCFIInstruction(OpGnuArgsSize, L, 0, Size, Loc);
   }
@@ -702,7 +702,7 @@ public:
     return U.RIA.AddressSpace;
   }
 
-  int getOffset() const {
+  int64_t getOffset() const {
     if (Operation == OpLLVMDefAspaceCfa)
       return U.RIA.Offset;
     assert(Operation == OpDefCfa || Operation == OpOffset ||
@@ -736,7 +736,7 @@ struct MCDwarfFrameInfo {
   unsigned CurrentCfaRegister = 0;
   unsigned PersonalityEncoding = 0;
   unsigned LsdaEncoding = 0;
-  uint32_t CompactUnwindEncoding = 0;
+  uint64_t CompactUnwindEncoding = 0;
   bool IsSignalFrame = false;
   bool IsSimple = false;
   unsigned RAReg = static_cast<unsigned>(INT_MAX);
diff --git a/llvm/include/llvm/TargetParser/PPCTargetParser.def b/llvm/include/llvm/TargetParser/PPCTargetParser.def
index 44e97d56a059..df956a68d75d 100644
--- a/llvm/include/llvm/TargetParser/PPCTargetParser.def
+++ b/llvm/include/llvm/TargetParser/PPCTargetParser.def
@@ -40,6 +40,7 @@
 #undef AIX_PPC8_VALUE
 #undef AIX_PPC9_VALUE
 #undef AIX_PPC10_VALUE
+#undef AIX_PPC11_VALUE
 #else
 #ifndef PPC_LNX_FEATURE
 #define PPC_LNX_FEATURE(NAME, DESC, ENUMNAME, ENUMVAL, HWCAPN)
@@ -84,6 +85,7 @@
 #define AIX_PPC8_VALUE 0x00010000
 #define AIX_PPC9_VALUE 0x00020000
 #define AIX_PPC10_VALUE 0x00040000
+#define AIX_PPC11_VALUE 0x00080000
 
 // __builtin_cpu_is() and __builtin_cpu_supports() are supported only on Power7 and up on AIX.
 // PPC_CPU(Name, Linux_SUPPORT_METHOD, LinuxID, AIX_SUPPORT_METHOD, AIXID)
@@ -103,6 +105,7 @@ PPC_CPU("ppc476",SYS_CALL,44,BUILTIN_PPC_FALSE,0)
 PPC_CPU("power8",SYS_CALL,45,USE_SYS_CONF,AIX_PPC8_VALUE)
 PPC_CPU("power9",SYS_CALL,46,USE_SYS_CONF,AIX_PPC9_VALUE)
 PPC_CPU("power10",SYS_CALL,47,USE_SYS_CONF,AIX_PPC10_VALUE)
+PPC_CPU("power11",SYS_CALL,48,USE_SYS_CONF,AIX_PPC11_VALUE)
 #undef PPC_CPU
 
 // PPC features on Linux:
diff --git a/llvm/lib/Analysis/BasicAliasAnalysis.cpp b/llvm/lib/Analysis/BasicAliasAnalysis.cpp
index 161a3034e482..e474899fb548 100644
--- a/llvm/lib/Analysis/BasicAliasAnalysis.cpp
+++ b/llvm/lib/Analysis/BasicAliasAnalysis.cpp
@@ -1692,9 +1692,12 @@ AliasResult BasicAAResult::aliasCheck(const Value *V1, LocationSize V1Size,
   if (!Pair.second) {
     auto &Entry = Pair.first->second;
     if (!Entry.isDefinitive()) {
-      // Remember that we used an assumption.
-      ++Entry.NumAssumptionUses;
+      // Remember that we used an assumption. This may either be a direct use
+      // of an assumption, or a use of an entry that may itself be based on an
+      // assumption.
       ++AAQI.NumAssumptionUses;
+      if (Entry.isAssumption())
+        ++Entry.NumAssumptionUses;
     }
     // Cache contains sorted {V1,V2} pairs but we should return original order.
     auto Result = Entry.Result;
@@ -1722,7 +1725,6 @@ AliasResult BasicAAResult::aliasCheck(const Value *V1, LocationSize V1Size,
   Entry.Result = Result;
   // Cache contains sorted {V1,V2} pairs.
   Entry.Result.swap(Swapped);
-  Entry.NumAssumptionUses = -1;
 
   // If the assumption has been disproven, remove any results that may have
   // been based on this assumption. Do this after the Entry updates above to
@@ -1734,8 +1736,26 @@ AliasResult BasicAAResult::aliasCheck(const Value *V1, LocationSize V1Size,
   // The result may still be based on assumptions higher up in the chain.
   // Remember it, so it can be purged from the cache later.
   if (OrigNumAssumptionUses != AAQI.NumAssumptionUses &&
-      Result != AliasResult::MayAlias)
+      Result != AliasResult::MayAlias) {
     AAQI.AssumptionBasedResults.push_back(Locs);
+    Entry.NumAssumptionUses = AAQueryInfo::CacheEntry::AssumptionBased;
+  } else {
+    Entry.NumAssumptionUses = AAQueryInfo::CacheEntry::Definitive;
+  }
+
+  // Depth is incremented before this function is called, so Depth==1 indicates
+  // a root query.
+  if (AAQI.Depth == 1) {
+    // Any remaining assumption based results must be based on proven
+    // assumptions, so convert them to definitive results.
+    for (const auto &Loc : AAQI.AssumptionBasedResults) {
+      auto It = AAQI.AliasCache.find(Loc);
+      if (It != AAQI.AliasCache.end())
+        It->second.NumAssumptionUses = AAQueryInfo::CacheEntry::Definitive;
+    }
+    AAQI.AssumptionBasedResults.clear();
+    AAQI.NumAssumptionUses = 0;
+  }
   return Result;
 }
 
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index 40fe1ffe13f1..4b77c0046cc7 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -1435,7 +1435,7 @@ static void computeKnownBitsFromOperator(const Operator *I,
         // inferred hold at original context instruction.  TODO: It may be
         // correct to use the original context.  IF warranted, explore and
         // add sufficient tests to cover.
-        SimplifyQuery RecQ = Q;
+        SimplifyQuery RecQ = Q.getWithoutCondContext();
         RecQ.CxtI = P;
         computeKnownBits(R, DemandedElts, Known2, Depth + 1, RecQ);
         switch (Opcode) {
@@ -1468,7 +1468,7 @@ static void computeKnownBitsFromOperator(const Operator *I,
         // phi. This is important because that is where the value is actually
         // "evaluated" even though it is used later somewhere else. (see also
         // D69571).
-        SimplifyQuery RecQ = Q;
+        SimplifyQuery RecQ = Q.getWithoutCondContext();
 
         unsigned OpNum = P->getOperand(0) == R ? 0 : 1;
         Instruction *RInst = P->getIncomingBlock(OpNum)->getTerminator();
@@ -1546,7 +1546,7 @@ static void computeKnownBitsFromOperator(const Operator *I,
         // phi. This is important because that is where the value is actually
         // "evaluated" even though it is used later somewhere else. (see also
         // D69571).
-        SimplifyQuery RecQ = Q;
+        SimplifyQuery RecQ = Q.getWithoutCondContext();
         RecQ.CxtI = P->getIncomingBlock(u)->getTerminator();
 
         Known2 = KnownBits(BitWidth);
@@ -2329,7 +2329,7 @@ bool isKnownToBeAPowerOfTwo(const Value *V, bool OrZero, unsigned Depth,
     // it is an induction variable where in each step its value is a power of
     // two.
     auto *PN = cast<PHINode>(I);
-    SimplifyQuery RecQ = Q;
+    SimplifyQuery RecQ = Q.getWithoutCondContext();
 
     // Check if it is an induction variable and always power of two.
     if (isPowerOfTwoRecurrence(PN, OrZero, Depth, RecQ))
@@ -2943,7 +2943,7 @@ static bool isKnownNonZeroFromOperator(const Operator *I,
       return true;
 
     // Check if all incoming values are non-zero using recursion.
-    SimplifyQuery RecQ = Q;
+    SimplifyQuery RecQ = Q.getWithoutCondContext();
     unsigned NewDepth = std::max(Depth, MaxAnalysisRecursionDepth - 1);
     return llvm::all_of(PN->operands(), [&](const Use &U) {
       if (U.get() == PN)
@@ -3509,7 +3509,7 @@ static bool isNonEqualPHIs(const PHINode *PN1, const PHINode *PN2,
     if (UsedFullRecursion)
       return false;
 
-    SimplifyQuery RecQ = Q;
+    SimplifyQuery RecQ = Q.getWithoutCondContext();
     RecQ.CxtI = IncomBB->getTerminator();
     if (!isKnownNonEqual(IV1, IV2, DemandedElts, Depth + 1, RecQ))
       return false;
@@ -4001,7 +4001,7 @@ static unsigned ComputeNumSignBitsImpl(const Value *V,
 
       // Take the minimum of all incoming values.  This can't infinitely loop
       // because of our depth threshold.
-      SimplifyQuery RecQ = Q;
+      SimplifyQuery RecQ = Q.getWithoutCondContext();
       Tmp = TyBits;
       for (unsigned i = 0, e = NumIncomingValues; i != e; ++i) {
         if (Tmp == 1) return Tmp;
@@ -5909,10 +5909,10 @@ void computeKnownFPClass(const Value *V, const APInt &DemandedElts,
         // Recurse, but cap the recursion to two levels, because we don't want
         // to waste time spinning around in loops. We need at least depth 2 to
         // detect known sign bits.
-        computeKnownFPClass(
-            IncValue, DemandedElts, InterestedClasses, KnownSrc,
-            PhiRecursionLimit,
-            Q.getWithInstruction(P->getIncomingBlock(U)->getTerminator()));
+        computeKnownFPClass(IncValue, DemandedElts, InterestedClasses, KnownSrc,
+                            PhiRecursionLimit,
+                            Q.getWithoutCondContext().getWithInstruction(
+                                P->getIncomingBlock(U)->getTerminator()));
 
         if (First) {
           Known = KnownSrc;
diff --git a/llvm/lib/CodeGen/CFIInstrInserter.cpp b/llvm/lib/CodeGen/CFIInstrInserter.cpp
index 1ff01ad34b30..06de92515c04 100644
--- a/llvm/lib/CodeGen/CFIInstrInserter.cpp
+++ b/llvm/lib/CodeGen/CFIInstrInserter.cpp
@@ -68,9 +68,9 @@ class CFIInstrInserter : public MachineFunctionPass {
   struct MBBCFAInfo {
     MachineBasicBlock *MBB;
     /// Value of cfa offset valid at basic block entry.
-    int IncomingCFAOffset = -1;
+    int64_t IncomingCFAOffset = -1;
     /// Value of cfa offset valid at basic block exit.
-    int OutgoingCFAOffset = -1;
+    int64_t OutgoingCFAOffset = -1;
     /// Value of cfa register valid at basic block entry.
     unsigned IncomingCFARegister = 0;
     /// Value of cfa register valid at basic block exit.
@@ -120,7 +120,7 @@ class CFIInstrInserter : public MachineFunctionPass {
   /// Return the cfa offset value that should be set at the beginning of a MBB
   /// if needed. The negated value is needed when creating CFI instructions that
   /// set absolute offset.
-  int getCorrectCFAOffset(MachineBasicBlock *MBB) {
+  int64_t getCorrectCFAOffset(MachineBasicBlock *MBB) {
     return MBBVector[MBB->getNumber()].IncomingCFAOffset;
   }
 
@@ -175,7 +175,7 @@ void CFIInstrInserter::calculateCFAInfo(MachineFunction &MF) {
 
 void CFIInstrInserter::calculateOutgoingCFAInfo(MBBCFAInfo &MBBInfo) {
   // Outgoing cfa offset set by the block.
-  int SetOffset = MBBInfo.IncomingCFAOffset;
+  int64_t SetOffset = MBBInfo.IncomingCFAOffset;
   // Outgoing cfa register set by the block.
   unsigned SetRegister = MBBInfo.IncomingCFARegister;
   MachineFunction *MF = MBBInfo.MBB->getParent();
@@ -188,7 +188,7 @@ void CFIInstrInserter::calculateOutgoingCFAInfo(MBBCFAInfo &MBBInfo) {
   for (MachineInstr &MI : *MBBInfo.MBB) {
     if (MI.isCFIInstruction()) {
       std::optional<unsigned> CSRReg;
-      std::optional<int> CSROffset;
+      std::optional<int64_t> CSROffset;
       unsigned CFIIndex = MI.getOperand(0).getCFIIndex();
       const MCCFIInstruction &CFI = Instrs[CFIIndex];
       switch (CFI.getOperation()) {
diff --git a/llvm/lib/CodeGen/MachineFrameInfo.cpp b/llvm/lib/CodeGen/MachineFrameInfo.cpp
index 853de4c88cae..e4b993850f73 100644
--- a/llvm/lib/CodeGen/MachineFrameInfo.cpp
+++ b/llvm/lib/CodeGen/MachineFrameInfo.cpp
@@ -197,7 +197,7 @@ void MachineFrameInfo::computeMaxCallFrameSize(
     for (MachineInstr &MI : MBB) {
       unsigned Opcode = MI.getOpcode();
       if (Opcode == FrameSetupOpcode || Opcode == FrameDestroyOpcode) {
-        unsigned Size = TII.getFrameSize(MI);
+        uint64_t Size = TII.getFrameSize(MI);
         MaxCallFrameSize = std::max(MaxCallFrameSize, Size);
         if (FrameSDOps != nullptr)
           FrameSDOps->push_back(&MI);
diff --git a/llvm/lib/CodeGen/PrologEpilogInserter.cpp b/llvm/lib/CodeGen/PrologEpilogInserter.cpp
index 3db5e17615fd..cd5d877e53d8 100644
--- a/llvm/lib/CodeGen/PrologEpilogInserter.cpp
+++ b/llvm/lib/CodeGen/PrologEpilogInserter.cpp
@@ -366,8 +366,8 @@ void PEI::calculateCallFrameInfo(MachineFunction &MF) {
     return;
 
   // (Re-)Compute the MaxCallFrameSize.
-  [[maybe_unused]] uint32_t MaxCFSIn =
-      MFI.isMaxCallFrameSizeComputed() ? MFI.getMaxCallFrameSize() : UINT32_MAX;
+  [[maybe_unused]] uint64_t MaxCFSIn =
+      MFI.isMaxCallFrameSizeComputed() ? MFI.getMaxCallFrameSize() : UINT64_MAX;
   std::vector<MachineBasicBlock::iterator> FrameSDOps;
   MFI.computeMaxCallFrameSize(MF, &FrameSDOps);
   assert(MFI.getMaxCallFrameSize() <= MaxCFSIn &&
diff --git a/llvm/lib/MC/MCDwarf.cpp b/llvm/lib/MC/MCDwarf.cpp
index efafd555c5c5..1297dc3828b5 100644
--- a/llvm/lib/MC/MCDwarf.cpp
+++ b/llvm/lib/MC/MCDwarf.cpp
@@ -1299,8 +1299,8 @@ static void EmitPersonality(MCStreamer &streamer, const MCSymbol &symbol,
 namespace {
 
 class FrameEmitterImpl {
-  int CFAOffset = 0;
-  int InitialCFAOffset = 0;
+  int64_t CFAOffset = 0;
+  int64_t InitialCFAOffset = 0;
   bool IsEH;
   MCObjectStreamer &Streamer;
 
@@ -1414,7 +1414,7 @@ void FrameEmitterImpl::emitCFIInstruction(const MCCFIInstruction &Instr) {
     if (!IsEH)
       Reg = MRI->getDwarfRegNumFromDwarfEHRegNum(Reg);
 
-    int Offset = Instr.getOffset();
+    int64_t Offset = Instr.getOffset();
     if (IsRelative)
       Offset -= CFAOffset;
     Offset = Offset / dataAlignmentFactor;
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 87e7750768d2..6d413a09407a 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -1080,6 +1080,10 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
   // Try to create BICs for vector ANDs.
   setTargetDAGCombine(ISD::AND);
 
+  // llvm.init.trampoline and llvm.adjust.trampoline
+  setOperationAction(ISD::INIT_TRAMPOLINE, MVT::Other, Custom);
+  setOperationAction(ISD::ADJUST_TRAMPOLINE, MVT::Other, Custom);
+
   // Vector add and sub nodes may conceal a high-half opportunity.
   // Also, try to fold ADD into CSINC/CSINV..
   setTargetDAGCombine({ISD::ADD, ISD::ABS, ISD::SUB, ISD::XOR, ISD::SINT_TO_FP,
@@ -6688,6 +6692,56 @@ static SDValue LowerFLDEXP(SDValue Op, SelectionDAG &DAG) {
   return Final;
 }
 
+SDValue AArch64TargetLowering::LowerADJUST_TRAMPOLINE(SDValue Op,
+                                                      SelectionDAG &DAG) const {
+  // Note: x18 cannot be used for the Nest parameter on Windows and macOS.
+  if (Subtarget->isTargetDarwin() || Subtarget->isTargetWindows())
+    report_fatal_error(
+        "ADJUST_TRAMPOLINE operation is only supported on Linux.");
+
+  return Op.getOperand(0);
+}
+
+SDValue AArch64TargetLowering::LowerINIT_TRAMPOLINE(SDValue Op,
+                                                    SelectionDAG &DAG) const {
+
+  // Note: x18 cannot be used for the Nest parameter on Windows and macOS.
+  if (Subtarget->isTargetDarwin() || Subtarget->isTargetWindows())
+    report_fatal_error("INIT_TRAMPOLINE operation is only supported on Linux.");
+
+  SDValue Chain = Op.getOperand(0);
+  SDValue Trmp = Op.getOperand(1); // trampoline
+  SDValue FPtr = Op.getOperand(2); // nested function
+  SDValue Nest = Op.getOperand(3); // 'nest' parameter value
+  SDLoc dl(Op);
+
+  EVT PtrVT = getPointerTy(DAG.getDataLayout());
+  Type *IntPtrTy = DAG.getDataLayout().getIntPtrType(*DAG.getContext());
+
+  TargetLowering::ArgListTy Args;
+  TargetLowering::ArgListEntry Entry;
+
+  Entry.Ty = IntPtrTy;
+  Entry.Node = Trmp;
+  Args.push_back(Entry);
+  Entry.Node = DAG.getConstant(20, dl, MVT::i64);
+  Args.push_back(Entry);
+
+  Entry.Node = FPtr;
+  Args.push_back(Entry);
+  Entry.Node = Nest;
+  Args.push_back(Entry);
+
+  // Lower to a call to __trampoline_setup(Trmp, TrampSize, FPtr, ctx_reg)
+  TargetLowering::CallLoweringInfo CLI(DAG);
+  CLI.setDebugLoc(dl).setChain(Chain).setLibCallee(
+      CallingConv::C, Type::getVoidTy(*DAG.getContext()),
+      DAG.getExternalSymbol("__trampoline_setup", PtrVT), std::move(Args));
+
+  std::pair<SDValue, SDValue> CallResult = LowerCallTo(CLI);
+  return CallResult.second;
+}
+
 SDValue AArch64TargetLowering::LowerOperation(SDValue Op,
                                               SelectionDAG &DAG) const {
   LLVM_DEBUG(dbgs() << "Custom lowering: ");
@@ -6705,6 +6759,10 @@ SDValue AArch64TargetLowering::LowerOperation(SDValue Op,
     return LowerGlobalTLSAddress(Op, DAG);
   case ISD::PtrAuthGlobalAddress:
     return LowerPtrAuthGlobalAddress(Op, DAG);
+  case ISD::ADJUST_TRAMPOLINE:
+    return LowerADJUST_TRAMPOLINE(Op, DAG);
+  case ISD::INIT_TRAMPOLINE:
+    return LowerINIT_TRAMPOLINE(Op, DAG);
   case ISD::SETCC:
   case ISD::STRICT_FSETCC:
   case ISD::STRICT_FSETCCS:
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
index ef45e4f01ecd..81e15185f985 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -1143,6 +1143,8 @@ private:
   SDValue LowerSELECT_CC(ISD::CondCode CC, SDValue LHS, SDValue RHS,
                          SDValue TVal, SDValue FVal, const SDLoc &dl,
                          SelectionDAG &DAG) const;
+  SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerADJUST_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerBR_JT(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerBRIND(SDValue Op, SelectionDAG &DAG) const;
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
index 1b301a4a05fc..377bcd5868fb 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -8339,7 +8339,8 @@ AArch64InstrInfo::getOutliningCandidateInfo(
     NumBytesToCreateFrame += 8;
 
     // PAuth is enabled - set extra tail call cost, if any.
-    auto LRCheckMethod = Subtarget.getAuthenticatedLRCheckMethod();
+    auto LRCheckMethod = Subtarget.getAuthenticatedLRCheckMethod(
+        *RepeatedSequenceLocs[0].getMF());
     NumBytesToCheckLRInTCEpilogue =
         AArch64PAuth::getCheckerSizeInBytes(LRCheckMethod);
     // Checking the authenticated LR value may significantly impact
@@ -8700,6 +8701,10 @@ void AArch64InstrInfo::mergeOutliningCandidateAttributes(
   // behaviour of one of them
   const auto &CFn = Candidates.front().getMF()->getFunction();
 
+  if (CFn.hasFnAttribute("ptrauth-returns"))
+    F.addFnAttr(CFn.getFnAttribute("ptrauth-returns"));
+  if (CFn.hasFnAttribute("ptrauth-auth-traps"))
+    F.addFnAttr(CFn.getFnAttribute("ptrauth-auth-traps"));
   // Since all candidates belong to the same module, just copy the
   // function-level attributes of an arbitrary function.
   if (CFn.hasFnAttribute("sign-return-address"))
diff --git a/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.cpp b/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.cpp
index 201e8047b368..e96c5a953ff2 100644
--- a/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.cpp
@@ -38,6 +38,8 @@ void AArch64FunctionInfo::initializeBaseYamlFields(
 }
 
 static std::pair<bool, bool> GetSignReturnAddress(const Function &F) {
+  if (F.hasFnAttribute("ptrauth-returns"))
+    return {true, false}; // non-leaf
   // The function should be signed in the following situations:
   // - sign-return-address=all
   // - sign-return-address=non-leaf and the functions spills the LR
@@ -56,6 +58,8 @@ static std::pair<bool, bool> GetSignReturnAddress(const Function &F) {
 }
 
 static bool ShouldSignWithBKey(const Function &F, const AArch64Subtarget &STI) {
+  if (F.hasFnAttribute("ptrauth-returns"))
+    return true;
   if (!F.hasFnAttribute("sign-return-address-key")) {
     if (STI.getTargetTriple().isOSWindows())
       return true;
diff --git a/llvm/lib/Target/AArch64/AArch64PointerAuth.cpp b/llvm/lib/Target/AArch64/AArch64PointerAuth.cpp
index 465e689d4a7a..92ab4b5c3d25 100644
--- a/llvm/lib/Target/AArch64/AArch64PointerAuth.cpp
+++ b/llvm/lib/Target/AArch64/AArch64PointerAuth.cpp
@@ -341,7 +341,8 @@ bool AArch64PointerAuth::checkAuthenticatedLR(
   AArch64PACKey::ID KeyId =
       MFnI->shouldSignWithBKey() ? AArch64PACKey::IB : AArch64PACKey::IA;
 
-  AuthCheckMethod Method = Subtarget->getAuthenticatedLRCheckMethod();
+  AuthCheckMethod Method =
+      Subtarget->getAuthenticatedLRCheckMethod(*TI->getMF());
 
   if (Method == AuthCheckMethod::None)
     return false;
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index 32a355fe38f1..642006e706c1 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -565,8 +565,13 @@ bool AArch64Subtarget::useAA() const { return UseAA; }
 // exception on its own. Later, if the callee spills the signed LR value and
 // neither FEAT_PAuth2 nor FEAT_EPAC are implemented, the valid PAC replaces
 // the higher bits of LR thus hiding the authentication failure.
-AArch64PAuth::AuthCheckMethod
-AArch64Subtarget::getAuthenticatedLRCheckMethod() const {
+AArch64PAuth::AuthCheckMethod AArch64Subtarget::getAuthenticatedLRCheckMethod(
+    const MachineFunction &MF) const {
+  // TODO: Check subtarget for the scheme. Present variant is a default for
+  // pauthtest ABI.
+  if (MF.getFunction().hasFnAttribute("ptrauth-returns") &&
+      MF.getFunction().hasFnAttribute("ptrauth-auth-traps"))
+    return AArch64PAuth::AuthCheckMethod::HighBitsNoTBI;
   if (AuthenticatedLRCheckMethod.getNumOccurrences())
     return AuthenticatedLRCheckMethod;
 
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index e585aad2f7a6..0f3a637f98fb 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -413,7 +413,8 @@ public:
   }
 
   /// Choose a method of checking LR before performing a tail call.
-  AArch64PAuth::AuthCheckMethod getAuthenticatedLRCheckMethod() const;
+  AArch64PAuth::AuthCheckMethod
+  getAuthenticatedLRCheckMethod(const MachineFunction &MF) const;
 
   /// Compute the integer discriminator for a given BlockAddress constant, if
   /// blockaddress signing is enabled, or std::nullopt otherwise.
diff --git a/llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp b/llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp
index be470c71ae8b..be34a649e1c4 100644
--- a/llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp
+++ b/llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp
@@ -599,7 +599,7 @@ public:
   }
 
   /// Generate the compact unwind encoding from the CFI directives.
-  uint32_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
+  uint64_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
                                          const MCContext *Ctxt) const override {
     ArrayRef<MCCFIInstruction> Instrs = FI->Instructions;
     if (Instrs.empty())
@@ -609,10 +609,10 @@ public:
       return CU::UNWIND_ARM64_MODE_DWARF;
 
     bool HasFP = false;
-    unsigned StackSize = 0;
+    uint64_t StackSize = 0;
 
-    uint32_t CompactUnwindEncoding = 0;
-    int CurOffset = 0;
+    uint64_t CompactUnwindEncoding = 0;
+    int64_t CurOffset = 0;
     for (size_t i = 0, e = Instrs.size(); i != e; ++i) {
       const MCCFIInstruction &Inst = Instrs[i];
 
diff --git a/llvm/lib/Target/ARM/ARMFrameLowering.cpp b/llvm/lib/Target/ARM/ARMFrameLowering.cpp
index 62d01b9f7e90..40354f995598 100644
--- a/llvm/lib/Target/ARM/ARMFrameLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMFrameLowering.cpp
@@ -1166,7 +1166,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
         if (STI.splitFramePushPop(MF)) {
           unsigned DwarfReg = MRI->getDwarfRegNum(
               Reg == ARM::R12 ? ARM::RA_AUTH_CODE : Reg, true);
-          unsigned Offset = MFI.getObjectOffset(FI);
+          int64_t Offset = MFI.getObjectOffset(FI);
           unsigned CFIIndex = MF.addFrameInst(
               MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
           BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
@@ -1188,7 +1188,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
       if ((Reg >= ARM::D0 && Reg <= ARM::D31) &&
           (Reg < ARM::D8 || Reg >= ARM::D8 + AFI->getNumAlignedDPRCS2Regs())) {
         unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
-        unsigned Offset = MFI.getObjectOffset(FI);
+        int64_t Offset = MFI.getObjectOffset(FI);
         unsigned CFIIndex = MF.addFrameInst(
             MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
         BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
diff --git a/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp b/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp
index eb55a2b5e70b..994b43f1abb4 100644
--- a/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp
+++ b/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp
@@ -1146,7 +1146,7 @@ enum CompactUnwindEncodings {
 /// instructions. If the CFI instructions describe a frame that cannot be
 /// encoded in compact unwind, the method returns UNWIND_ARM_MODE_DWARF which
 /// tells the runtime to fallback and unwind using dwarf.
-uint32_t ARMAsmBackendDarwin::generateCompactUnwindEncoding(
+uint64_t ARMAsmBackendDarwin::generateCompactUnwindEncoding(
     const MCDwarfFrameInfo *FI, const MCContext *Ctxt) const {
   DEBUG_WITH_TYPE("compact-unwind", llvm::dbgs() << "generateCU()\n");
   // Only armv7k uses CFI based unwinding.
diff --git a/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackendDarwin.h b/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackendDarwin.h
index ac0c9b101cae..9c958003ca75 100644
--- a/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackendDarwin.h
+++ b/llvm/lib/Target/ARM/MCTargetDesc/ARMAsmBackendDarwin.h
@@ -34,7 +34,7 @@ public:
         /*Is64Bit=*/false, cantFail(MachO::getCPUType(TT)), Subtype);
   }
 
-  uint32_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
+  uint64_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
                                          const MCContext *Ctxt) const override;
 };
 } // end namespace llvm
diff --git a/llvm/lib/Target/ARM/MCTargetDesc/ARMELFStreamer.cpp b/llvm/lib/Target/ARM/MCTargetDesc/ARMELFStreamer.cpp
index 3182fecffecf..de343a7d72ad 100644
--- a/llvm/lib/Target/ARM/MCTargetDesc/ARMELFStreamer.cpp
+++ b/llvm/lib/Target/ARM/MCTargetDesc/ARMELFStreamer.cpp
@@ -670,8 +670,7 @@ private:
   }
 
   void EmitMappingSymbol(StringRef Name) {
-    auto *Symbol = cast<MCSymbolELF>(getContext().getOrCreateSymbol(
-        Name + "." + Twine(MappingSymbolCounter++)));
+    auto *Symbol = cast<MCSymbolELF>(getContext().createLocalSymbol(Name));
     emitLabel(Symbol);
 
     Symbol->setType(ELF::STT_NOTYPE);
@@ -679,8 +678,7 @@ private:
   }
 
   void emitMappingSymbol(StringRef Name, MCDataFragment &F, uint64_t Offset) {
-    auto *Symbol = cast<MCSymbolELF>(getContext().getOrCreateSymbol(
-        Name + "." + Twine(MappingSymbolCounter++)));
+    auto *Symbol = cast<MCSymbolELF>(getContext().createLocalSymbol(Name));
     emitLabelAtPos(Symbol, SMLoc(), F, Offset);
     Symbol->setType(ELF::STT_NOTYPE);
     Symbol->setBinding(ELF::STB_LOCAL);
@@ -710,7 +708,6 @@ private:
 
   bool IsThumb;
   bool IsAndroid;
-  int64_t MappingSymbolCounter = 0;
 
   DenseMap<const MCSection *, std::unique_ptr<ElfMappingSymbolInfo>>
       LastMappingSymbols;
@@ -1121,7 +1118,6 @@ void ARMELFStreamer::reset() {
   MCTargetStreamer &TS = *getTargetStreamer();
   ARMTargetStreamer &ATS = static_cast<ARMTargetStreamer &>(TS);
   ATS.reset();
-  MappingSymbolCounter = 0;
   MCELFStreamer::reset();
   LastMappingSymbols.clear();
   LastEMSInfo.reset();
diff --git a/llvm/lib/Target/Hexagon/HexagonFrameLowering.cpp b/llvm/lib/Target/Hexagon/HexagonFrameLowering.cpp
index 6ca18528591a..05357de40e3a 100644
--- a/llvm/lib/Target/Hexagon/HexagonFrameLowering.cpp
+++ b/llvm/lib/Target/Hexagon/HexagonFrameLowering.cpp
@@ -1659,7 +1659,7 @@ bool HexagonFrameLowering::assignCalleeSavedSpillSlots(MachineFunction &MF,
   using SpillSlot = TargetFrameLowering::SpillSlot;
 
   unsigned NumFixed;
-  int MinOffset = 0;  // CS offsets are negative.
+  int64_t MinOffset = 0; // CS offsets are negative.
   const SpillSlot *FixedSlots = getCalleeSavedSpillSlots(NumFixed);
   for (const SpillSlot *S = FixedSlots; S != FixedSlots+NumFixed; ++S) {
     if (!SRegs[S->Reg])
@@ -1678,7 +1678,7 @@ bool HexagonFrameLowering::assignCalleeSavedSpillSlots(MachineFunction &MF,
     Register R = x;
     const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(R);
     unsigned Size = TRI->getSpillSize(*RC);
-    int Off = MinOffset - Size;
+    int64_t Off = MinOffset - Size;
     Align Alignment = std::min(TRI->getSpillAlign(*RC), getStackAlign());
     Off &= -Alignment.value();
     int FI = MFI.CreateFixedSpillStackObject(Size, Off);
diff --git a/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td b/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
index 97f0e8d6a10c..ec0d071453c3 100644
--- a/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
+++ b/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
@@ -1144,7 +1144,6 @@ def : PatGprGpr<urem, MOD_DU>;
 def : PatGprGpr<loongarch_mod_wu, MOD_WU>;
 def : PatGprGpr<rotr, ROTR_D>;
 def : PatGprGpr<loongarch_rotr_w, ROTR_W>;
-def : PatGprGpr_32<rotr, ROTR_W>;
 def : PatGprImm<rotr, ROTRI_D, uimm6>;
 def : PatGprImm_32<rotr, ROTRI_W, uimm5>;
 def : PatGprImm<loongarch_rotr_w, ROTRI_W, uimm5>;
diff --git a/llvm/lib/Target/MSP430/MSP430FrameLowering.cpp b/llvm/lib/Target/MSP430/MSP430FrameLowering.cpp
index f4d703ebeeab..d0dc6dd146ef 100644
--- a/llvm/lib/Target/MSP430/MSP430FrameLowering.cpp
+++ b/llvm/lib/Target/MSP430/MSP430FrameLowering.cpp
@@ -293,7 +293,7 @@ void MSP430FrameLowering::emitEpilogue(MachineFunction &MF,
 
   if (!hasFP(MF)) {
     MBBI = FirstCSPop;
-    int64_t Offset = -CSSize - 2;
+    int64_t Offset = -(int64_t)CSSize - 2;
     // Mark callee-saved pop instruction.
     // Define the current CFA rule to use the provided offset.
     while (MBBI != MBB.end()) {
diff --git a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
index 44c1a2e50486..6975412ce5d3 100644
--- a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -1429,7 +1429,6 @@ std::string NVPTXTargetLowering::getPrototype(
 
   bool first = true;
 
-  const Function *F = CB.getFunction();
   unsigned NumArgs = VAInfo ? VAInfo->first : Args.size();
   for (unsigned i = 0, OIdx = 0; i != NumArgs; ++i, ++OIdx) {
     Type *Ty = Args[i].Ty;
@@ -1471,10 +1470,12 @@ std::string NVPTXTargetLowering::getPrototype(
       continue;
     }
 
+    // Indirect calls need strict ABI alignment so we disable optimizations by
+    // not providing a function to optimize.
     Type *ETy = Args[i].IndirectType;
     Align InitialAlign = Outs[OIdx].Flags.getNonZeroByValAlign();
     Align ParamByValAlign =
-        getFunctionByValParamAlign(F, ETy, InitialAlign, DL);
+        getFunctionByValParamAlign(/*F=*/nullptr, ETy, InitialAlign, DL);
 
     O << ".param .align " << ParamByValAlign.value() << " .b8 ";
     O << "_";
diff --git a/llvm/lib/Target/PowerPC/PPC.td b/llvm/lib/Target/PowerPC/PPC.td
index 84ef582c029d..da31a993b9c6 100644
--- a/llvm/lib/Target/PowerPC/PPC.td
+++ b/llvm/lib/Target/PowerPC/PPC.td
@@ -52,6 +52,7 @@ def DirectivePwr7: SubtargetFeature<"", "CPUDirective", "PPC::DIR_PWR7", "">;
 def DirectivePwr8: SubtargetFeature<"", "CPUDirective", "PPC::DIR_PWR8", "">;
 def DirectivePwr9: SubtargetFeature<"", "CPUDirective", "PPC::DIR_PWR9", "">;
 def DirectivePwr10: SubtargetFeature<"", "CPUDirective", "PPC::DIR_PWR10", "">;
+def DirectivePwr11: SubtargetFeature<"", "CPUDirective", "PPC::DIR_PWR11", "">;
 def DirectivePwrFuture
     : SubtargetFeature<"", "CPUDirective", "PPC::DIR_PWR_FUTURE", "">;
 
@@ -467,13 +468,25 @@ def ProcessorFeatures {
   list<SubtargetFeature> P10Features =
     !listconcat(P10InheritableFeatures, P10SpecificFeatures);
 
-  // Future
-  // For future CPU we assume that all of the existing features from Power10
+  // Power11
+  // For P11 CPU we assume that all the existing features from Power10
   // still exist with the exception of those we know are Power10 specific.
+  list<SubtargetFeature> P11AdditionalFeatures =
+    [DirectivePwr11];
+  list<SubtargetFeature> P11SpecificFeatures =
+    [];
+  list<SubtargetFeature> P11InheritableFeatures =
+    !listconcat(P10InheritableFeatures, P11AdditionalFeatures);
+  list<SubtargetFeature> P11Features =
+    !listconcat(P11InheritableFeatures, P11SpecificFeatures);
+
+  // Future
+  // For future CPU we assume that all of the existing features from Power11
+  // still exist with the exception of those we know are Power11 specific.
   list<SubtargetFeature> FutureAdditionalFeatures = [FeatureISAFuture];
   list<SubtargetFeature> FutureSpecificFeatures = [];
   list<SubtargetFeature> FutureInheritableFeatures =
-    !listconcat(P10InheritableFeatures, FutureAdditionalFeatures);
+    !listconcat(P11InheritableFeatures, FutureAdditionalFeatures);
   list<SubtargetFeature> FutureFeatures =
     !listconcat(FutureInheritableFeatures, FutureSpecificFeatures);
 }
@@ -672,6 +685,7 @@ def : ProcessorModel<"pwr7", P7Model, ProcessorFeatures.P7Features>;
 def : ProcessorModel<"pwr8", P8Model, ProcessorFeatures.P8Features>;
 def : ProcessorModel<"pwr9", P9Model, ProcessorFeatures.P9Features>;
 def : ProcessorModel<"pwr10", P10Model, ProcessorFeatures.P10Features>;
+def : ProcessorModel<"pwr11", P10Model, ProcessorFeatures.P11Features>;
 // No scheduler model for future CPU.
 def : ProcessorModel<"future", NoSchedModel,
                   ProcessorFeatures.FutureFeatures>;
diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 898d1f80d056..aaf0449a5538 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -1469,6 +1469,7 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
   case PPC::DIR_PWR8:
   case PPC::DIR_PWR9:
   case PPC::DIR_PWR10:
+  case PPC::DIR_PWR11:
   case PPC::DIR_PWR_FUTURE:
     setPrefLoopAlignment(Align(16));
     setPrefFunctionAlignment(Align(16));
@@ -16664,6 +16665,7 @@ Align PPCTargetLowering::getPrefLoopAlignment(MachineLoop *ML) const {
   case PPC::DIR_PWR8:
   case PPC::DIR_PWR9:
   case PPC::DIR_PWR10:
+  case PPC::DIR_PWR11:
   case PPC::DIR_PWR_FUTURE: {
     if (!ML)
       break;
@@ -18046,6 +18048,7 @@ SDValue PPCTargetLowering::combineMUL(SDNode *N, DAGCombinerInfo &DCI) const {
       return true;
     case PPC::DIR_PWR9:
     case PPC::DIR_PWR10:
+    case PPC::DIR_PWR11:
     case PPC::DIR_PWR_FUTURE:
       //  type        mul     add    shl
       // scalar        5       2      2
diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp b/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
index 2d3c520429f2..81f16eb1a905 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
@@ -3485,6 +3485,7 @@ unsigned PPCInstrInfo::getSpillTarget() const {
   // With P10, we may need to spill paired vector registers or accumulator
   // registers. MMA implies paired vectors, so we can just check that.
   bool IsP10Variant = Subtarget.isISA3_1() || Subtarget.pairedVectorMemops();
+  // P11 uses the P10 target.
   return Subtarget.isISAFuture() ? 3 : IsP10Variant ?
                                    2 : Subtarget.hasP9Vector() ?
                                    1 : 0;
diff --git a/llvm/lib/Target/PowerPC/PPCSubtarget.h b/llvm/lib/Target/PowerPC/PPCSubtarget.h
index bf35f8ec151b..2079dc0acc3c 100644
--- a/llvm/lib/Target/PowerPC/PPCSubtarget.h
+++ b/llvm/lib/Target/PowerPC/PPCSubtarget.h
@@ -61,6 +61,7 @@ enum {
   DIR_PWR8,
   DIR_PWR9,
   DIR_PWR10,
+  DIR_PWR11,
   DIR_PWR_FUTURE,
   DIR_64
 };
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index 3fa35efc2d15..b7bdbeb535d5 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -504,7 +504,7 @@ unsigned PPCTTIImpl::getCacheLineSize() const {
   // Assume that Future CPU has the same cache line size as the others.
   if (Directive == PPC::DIR_PWR7 || Directive == PPC::DIR_PWR8 ||
       Directive == PPC::DIR_PWR9 || Directive == PPC::DIR_PWR10 ||
-      Directive == PPC::DIR_PWR_FUTURE)
+      Directive == PPC::DIR_PWR11 || Directive == PPC::DIR_PWR_FUTURE)
     return 128;
 
   // On other processors return a default of 64 bytes.
@@ -538,7 +538,7 @@ unsigned PPCTTIImpl::getMaxInterleaveFactor(ElementCount VF) {
   // Assume that future is the same as the others.
   if (Directive == PPC::DIR_PWR7 || Directive == PPC::DIR_PWR8 ||
       Directive == PPC::DIR_PWR9 || Directive == PPC::DIR_PWR10 ||
-      Directive == PPC::DIR_PWR_FUTURE)
+      Directive == PPC::DIR_PWR11 || Directive == PPC::DIR_PWR_FUTURE)
     return 12;
 
   // For most things, modern systems have two execution units (and
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoC.td b/llvm/lib/Target/RISCV/RISCVInstrInfoC.td
index 9257ee5a09a8..3f279b7a58ca 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoC.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoC.td
@@ -764,9 +764,9 @@ def InsnCR : DirectiveInsnCR<(outs AnyReg:$rd), (ins uimm2_opcode:$opcode,
                                                      uimm4:$funct4,
                                                      AnyReg:$rs2),
                              "$opcode, $funct4, $rd, $rs2">;
-def InsnCI : DirectiveInsnCI<(outs AnyRegC:$rd), (ins uimm2_opcode:$opcode,
-                                                      uimm3:$funct3,
-                                                      simm6:$imm6),
+def InsnCI : DirectiveInsnCI<(outs AnyReg:$rd), (ins uimm2_opcode:$opcode,
+                                                     uimm3:$funct3,
+                                                     simm6:$imm6),
                              "$opcode, $funct3, $rd, $imm6">;
 def InsnCIW : DirectiveInsnCIW<(outs AnyRegC:$rd), (ins uimm2_opcode:$opcode,
                                                         uimm3:$funct3,
@@ -818,7 +818,7 @@ def : InstAlias<".insn_cr $opcode, $funct4, $rd, $rs2",
                 (InsnCR AnyReg:$rd, uimm2_opcode:$opcode, uimm4:$funct4,
                         AnyReg:$rs2)>;
 def : InstAlias<".insn_ci $opcode, $funct3, $rd, $imm6",
-                (InsnCI AnyRegC:$rd, uimm2_opcode:$opcode, uimm3:$funct3,
+                (InsnCI AnyReg:$rd, uimm2_opcode:$opcode, uimm3:$funct3,
                         simm6:$imm6)>;
 def : InstAlias<".insn_ciw $opcode, $funct3, $rd, $imm8",
                 (InsnCIW AnyRegC:$rd, uimm2_opcode:$opcode, uimm3:$funct3,
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index a3ef11b2cab4..fcc61d0a5e2f 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -1312,7 +1312,7 @@ public:
 
   /// Implementation of algorithm to generate the compact unwind encoding
   /// for the CFI instructions.
-  uint32_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
+  uint64_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
                                          const MCContext *Ctxt) const override {
     ArrayRef<MCCFIInstruction> Instrs = FI->Instructions;
     if (Instrs.empty()) return 0;
@@ -1327,13 +1327,13 @@ public:
     bool HasFP = false;
 
     // Encode that we are using EBP/RBP as the frame pointer.
-    uint32_t CompactUnwindEncoding = 0;
+    uint64_t CompactUnwindEncoding = 0;
 
     unsigned SubtractInstrIdx = Is64Bit ? 3 : 2;
     unsigned InstrOffset = 0;
     unsigned StackAdjust = 0;
-    unsigned StackSize = 0;
-    int MinAbsOffset = std::numeric_limits<int>::max();
+    uint64_t StackSize = 0;
+    int64_t MinAbsOffset = std::numeric_limits<int64_t>::max();
 
     for (const MCCFIInstruction &Inst : Instrs) {
       switch (Inst.getOperation()) {
@@ -1360,7 +1360,7 @@ public:
         memset(SavedRegs, 0, sizeof(SavedRegs));
         StackAdjust = 0;
         SavedRegIdx = 0;
-        MinAbsOffset = std::numeric_limits<int>::max();
+        MinAbsOffset = std::numeric_limits<int64_t>::max();
         InstrOffset += MoveInstrSize;
         break;
       }
@@ -1403,7 +1403,7 @@ public:
         unsigned Reg = *MRI.getLLVMRegNum(Inst.getRegister(), true);
         SavedRegs[SavedRegIdx++] = Reg;
         StackAdjust += OffsetSize;
-        MinAbsOffset = std::min(MinAbsOffset, abs(Inst.getOffset()));
+        MinAbsOffset = std::min(MinAbsOffset, std::abs(Inst.getOffset()));
         InstrOffset += PushInstrSize(Reg);
         break;
       }
diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
index 0ff50d8ef678..bdc9a0d29670 100644
--- a/llvm/lib/Target/X86/X86FrameLowering.cpp
+++ b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -473,7 +473,7 @@ void X86FrameLowering::emitCalleeSavedFrameMovesFullCFA(
                                : FramePtr;
   unsigned DwarfReg = MRI->getDwarfRegNum(MachineFramePtr, true);
   // Offset = space for return address + size of the frame pointer itself.
-  unsigned Offset = (Is64Bit ? 8 : 4) + (Uses64BitFramePtr ? 8 : 4);
+  int64_t Offset = (Is64Bit ? 8 : 4) + (Uses64BitFramePtr ? 8 : 4);
   BuildCFI(MBB, MBBI, DebugLoc{},
            MCCFIInstruction::createOffset(nullptr, DwarfReg, -Offset));
   emitCalleeSavedFrameMoves(MBB, MBBI, DebugLoc{}, true);
@@ -2553,7 +2553,7 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
 
   if (!HasFP && NeedsDwarfCFI) {
     MBBI = FirstCSPop;
-    int64_t Offset = -CSSize - SlotSize;
+    int64_t Offset = -(int64_t)CSSize - SlotSize;
     // Mark callee-saved pop instruction.
     // Define the current CFA rule to use the provided offset.
     while (MBBI != MBB.end()) {
diff --git a/llvm/lib/TargetParser/Host.cpp b/llvm/lib/TargetParser/Host.cpp
index fda085f88009..7e637cba4cfb 100644
--- a/llvm/lib/TargetParser/Host.cpp
+++ b/llvm/lib/TargetParser/Host.cpp
@@ -150,6 +150,7 @@ StringRef sys::detail::getHostCPUNameForPowerPC(StringRef ProcCpuinfoContent) {
       .Case("POWER8NVL", "pwr8")
       .Case("POWER9", "pwr9")
       .Case("POWER10", "pwr10")
+      .Case("POWER11", "pwr11")
       // FIXME: If we get a simulator or machine with the capabilities of
       // mcpu=future, we should revisit this and add the name reported by the
       // simulator/machine.
@@ -1549,6 +1550,12 @@ StringRef sys::getHostCPUName() {
   case 0x40000:
 #endif
     return "pwr10";
+#ifdef POWER_11
+  case POWER_11:
+#else
+  case 0x80000:
+#endif
+    return "pwr11";
   default:
     return "generic";
   }
diff --git a/llvm/lib/Transforms/Scalar/LICM.cpp b/llvm/lib/Transforms/Scalar/LICM.cpp
index fe264503dee9..91ef2b4b7c18 100644
--- a/llvm/lib/Transforms/Scalar/LICM.cpp
+++ b/llvm/lib/Transforms/Scalar/LICM.cpp
@@ -113,8 +113,6 @@ STATISTIC(NumFPAssociationsHoisted, "Number of invariant FP expressions "
 STATISTIC(NumIntAssociationsHoisted,
           "Number of invariant int expressions "
           "reassociated and hoisted out of the loop");
-STATISTIC(NumBOAssociationsHoisted, "Number of invariant BinaryOp expressions "
-                                    "reassociated and hoisted out of the loop");
 
 /// Memory promotion is enabled by default.
 static cl::opt<bool>
@@ -2781,60 +2779,6 @@ static bool hoistMulAddAssociation(Instruction &I, Loop &L,
   return true;
 }
 
-/// Reassociate general associative binary expressions of the form
-///
-/// 1. "(LV op C1) op C2" ==> "LV op (C1 op C2)"
-///
-/// where op is an associative binary op, LV is a loop variant, and C1 and C2
-/// are loop invariants that we want to hoist.
-///
-/// TODO: This can be extended to more cases such as
-/// 2. "C1 op (C2 op LV)" ==> "(C1 op C2) op LV"
-/// 3. "(C1 op LV) op C2" ==> "LV op (C1 op C2)" if op is commutative
-/// 4. "C1 op (LV op C2)" ==> "(C1 op C2) op LV" if op is commutative
-static bool hoistBOAssociation(Instruction &I, Loop &L,
-                               ICFLoopSafetyInfo &SafetyInfo,
-                               MemorySSAUpdater &MSSAU, AssumptionCache *AC,
-                               DominatorTree *DT) {
-  BinaryOperator *BO = dyn_cast<BinaryOperator>(&I);
-  if (!BO || !BO->isAssociative())
-    return false;
-
-  Instruction::BinaryOps Opcode = BO->getOpcode();
-  BinaryOperator *Op0 = dyn_cast<BinaryOperator>(BO->getOperand(0));
-
-  // Transform: "(LV op C1) op C2" ==> "LV op (C1 op C2)"
-  if (Op0 && Op0->getOpcode() == Opcode) {
-    Value *LV = Op0->getOperand(0);
-    Value *C1 = Op0->getOperand(1);
-    Value *C2 = BO->getOperand(1);
-
-    if (L.isLoopInvariant(LV) || !L.isLoopInvariant(C1) ||
-        !L.isLoopInvariant(C2))
-      return false;
-
-    auto *Preheader = L.getLoopPreheader();
-    assert(Preheader && "Loop is not in simplify form?");
-    IRBuilder<> Builder(Preheader->getTerminator());
-    Value *Inv = Builder.CreateBinOp(Opcode, C1, C2, "invariant.op");
-
-    auto *NewBO =
-        BinaryOperator::Create(Opcode, LV, Inv, BO->getName() + ".reass", BO);
-    NewBO->copyIRFlags(BO);
-    BO->replaceAllUsesWith(NewBO);
-    eraseInstruction(*BO, SafetyInfo, MSSAU);
-
-    // Note: (LV op C1) might not be erased if it has more uses than the one we
-    //       just replaced.
-    if (Op0->use_empty())
-      eraseInstruction(*Op0, SafetyInfo, MSSAU);
-
-    return true;
-  }
-
-  return false;
-}
-
 static bool hoistArithmetics(Instruction &I, Loop &L,
                              ICFLoopSafetyInfo &SafetyInfo,
                              MemorySSAUpdater &MSSAU, AssumptionCache *AC,
@@ -2872,12 +2816,6 @@ static bool hoistArithmetics(Instruction &I, Loop &L,
     return true;
   }
 
-  if (hoistBOAssociation(I, L, SafetyInfo, MSSAU, AC, DT)) {
-    ++NumHoisted;
-    ++NumBOAssociationsHoisted;
-    return true;
-  }
-
   return false;
 }
 
diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 11f9f7822a15..91461d1ed275 100644
--- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -946,13 +946,15 @@ static Immediate ExtractImmediate(const SCEV *&S, ScalarEvolution &SE) {
                            // FIXME: AR->getNoWrapFlags(SCEV::FlagNW)
                            SCEV::FlagAnyWrap);
     return Result;
-  } else if (EnableVScaleImmediates)
-    if (const SCEVMulExpr *M = dyn_cast<SCEVMulExpr>(S))
+  } else if (const SCEVMulExpr *M = dyn_cast<SCEVMulExpr>(S)) {
+    if (EnableVScaleImmediates && M->getNumOperands() == 2) {
       if (const SCEVConstant *C = dyn_cast<SCEVConstant>(M->getOperand(0)))
         if (isa<SCEVVScale>(M->getOperand(1))) {
           S = SE.getConstant(M->getType(), 0);
           return Immediate::getScalable(C->getValue()->getSExtValue());
         }
+    }
+  }
   return Immediate::getZero();
 }
 
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 6d28b8fabe42..68363abdb817 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -206,7 +206,7 @@ static cl::opt<unsigned> VectorizeMemoryCheckThreshold(
     cl::desc("The maximum allowed number of runtime memory checks"));
 
 static cl::opt<bool> UseLegacyCostModel(
-    "vectorize-use-legacy-cost-model", cl::init(false), cl::Hidden,
+    "vectorize-use-legacy-cost-model", cl::init(true), cl::Hidden,
     cl::desc("Use the legacy cost model instead of the VPlan-based cost model. "
              "This option will be removed in the future."));