[AArch64][PowerPC][Driver] Allow setting crypto feature through -mcrypto.

[tcwang]

Summary

This enables -mcrypto and -mno-crypto to enable/disable crypto feature to Clang.
Before this change, -m(no-)crypto is exclusively for Power8. We want to add this feature
to ARM/AArch64 as well. With -mcrypto is specified, +crypto will be passed as
a feature to ARM/AArch64/Power8, and -mno-cypto will pass -crypto.

clang/include/clang/Driver/Options.td

 def mpower8_vector : Flag<["-"], "mpower8-vector">,
     Group<m_ppc_Features_Group>;
 def mno_power8_vector : Flag<["-"], "mno-power8-vector">,
     Group<m_ppc_Features_Group>;
 def mpower9_vector : Flag<["-"], "mpower9-vector">,
     Group<m_ppc_Features_Group>;
 def mno_power9_vector : Flag<["-"], "mno-power9-vector">,
     Group<m_ppc_Features_Group>;
-def mpower8_crypto : Flag<["-"], "mcrypto">,
-    Group<m_ppc_Features_Group>;
-def mnopower8_crypto : Flag<["-"], "mno-crypto">,
-    Group<m_ppc_Features_Group>;
+def mcrypto : Flag<["-"], "mcrypto">, Group<m_Group>,
+  HelpText<"Add use of cryptographic instructions (ARM/PowerPC only)">;
+def mnocrypto : Flag<["-"], "mno-crypto">, Group<m_Group>,
+  HelpText<"Disallow use of cryptographic instructions (ARM/PowerPC only)">;
 def mdirect_move : Flag<["-"], "mdirect-move">,
     Group<m_ppc_Features_Group>;
 def mnodirect_move : Flag<["-"], "mno-direct-move">,
     Group<m_ppc_Features_Group>;
 def mhtm : Flag<["-"], "mhtm">, Group<m_ppc_Features_Group>;
 def mno_htm : Flag<["-"], "mno-htm">, Group<m_ppc_Features_Group>;
 def mfprnd : Flag<["-"], "mfprnd">, Group<m_ppc_Features_Group>;
 def mno_fprnd : Flag<["-"], "mno-fprnd">, Group<m_ppc_Features_Group>;

clang/lib/Driver/ToolChains/Arch/AArch64.cpp

void aarch64::getAArch64TargetFeatures(const Driver &D,
   else if (success &&
            (Args.hasArg(options::OPT_arch) || isCPUDeterminedByTriple(Triple)))
     success = getAArch64MicroArchFeaturesFromMcpu(
         D, getAArch64TargetCPU(Args, Triple, A), Args, Features);
 
   if (!success)
     D.Diag(diag::err_drv_clang_unsupported) << A->getAsString(Args);
 
+  // En/disable crypto
+  if (Arg *A = Args.getLastArg(options::OPT_mcrypto, options::OPT_mnocrypto,
+                               options::OPT_mgeneral_regs_only)) {
+    if (A->getOption().matches(options::OPT_mcrypto))
+      Features.push_back("+crypto");
+    else
+      Features.push_back("-crypto");
+  }
+
+
   if (Args.getLastArg(options::OPT_mgeneral_regs_only)) {
     Features.push_back("-fp-armv8");
     Features.push_back("-crypto");
     Features.push_back("-neon");
   }
 
   // En/disable crc
   if (Arg *A = Args.getLastArg(options::OPT_mcrc, options::OPT_mnocrc)) {

clang/lib/Driver/ToolChains/Arch/ARM.cpp

fp16_fml_fallthrough:
     // In both of these cases, putting the 'other' feature on the end of the vector will
     // result in the same effect as placing it immediately after the current feature.
     if (ItRNoFullFP16 < ItRFP16FML)
       Features.push_back("-fp16fml");
     else if (ItRNoFullFP16 > ItRFP16FML)
       Features.push_back("+fullfp16");
   }
 
+  // En/disable crypto
+  if (Arg *A = Args.getLastArg(options::OPT_mcrypto, options::OPT_mnocrypto)) {
+    if (A->getOption().matches(options::OPT_mcrypto))
+      Features.push_back("+crypto");
+    else
+      Features.push_back("-crypto");
+  }
+
   // Setting -msoft-float/-mfloat-abi=soft effectively disables the FPU (GCC
   // ignores the -mfpu options in this case).
   // Note that the ABI can also be set implicitly by the target selected.
   if (ABI == arm::FloatABI::Soft) {
     llvm::ARM::getFPUFeatures(llvm::ARM::FK_NONE, Features);
 
     // Disable hardware FP features which have been enabled.
     // FIXME: Disabling vfp2 and neon should be enough as all the other

clang/lib/Driver/ToolChains/Arch/PPC.h

 
 namespace clang {
 namespace driver {
 namespace tools {
 namespace ppc {
 
 bool hasPPCAbiArg(const llvm::opt::ArgList &Args, const char *Value);
 
+bool hasCryptoFeatureEnabled(const llvm::opt::ArgList &Args);
+
 enum class FloatABI {
   Invalid,
   Soft,
   Hard,
 };
 
 enum class ReadGOTPtrMode {
   Bss,

clang/lib/Driver/ToolChains/Arch/PPC.cpp

void ppc::getPPCTargetFeatures(const Driver &D, const llvm::Triple &Triple,
 
   ppc::FloatABI FloatABI = ppc::getPPCFloatABI(D, Args);
   if (FloatABI == ppc::FloatABI::Soft)
     Features.push_back("-hard-float");
 
   ppc::ReadGOTPtrMode ReadGOT = ppc::getPPCReadGOTPtrMode(D, Triple, Args);
   if (ReadGOT == ppc::ReadGOTPtrMode::SecurePlt)
     Features.push_back("+secure-plt");
+
+  if (ppc::hasCryptoFeatureEnabled(Args))
+    Features.push_back("+crypto");
 }
 
 ppc::ReadGOTPtrMode ppc::getPPCReadGOTPtrMode(const Driver &D, const llvm::Triple &Triple,
                                               const ArgList &Args) {
   if (Args.getLastArg(options::OPT_msecure_plt))
     return ppc::ReadGOTPtrMode::SecurePlt;
   if (Triple.isOSNetBSD() || Triple.isOSOpenBSD())
     return ppc::ReadGOTPtrMode::SecurePlt;
ppc::FloatABI ppc::getPPCFloatABI(const Driver &D, const ArgList &Args) {
 
   return ABI;
 }
 
 bool ppc::hasPPCAbiArg(const ArgList &Args, const char *Value) {
   Arg *A = Args.getLastArg(options::OPT_mabi_EQ);
   return A && (A->getValue() == StringRef(Value));
 }
+
+bool ppc::hasCryptoFeatureEnabled(const ArgList &Args) {
+  if (Arg *A = Args.getLastArg(options::OPT_mcrypto, options::OPT_mnocrypto))
+    if (A->getOption().matches(options::OPT_mcrypto))
+      return true;
+  return false;
+}

clang/test/Driver/aarch64-crypto.c

+// REQUIRES: aarch64-registered-target
+// RUN: %clang -target aarch64 -mcrypto -### %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-AARCH64-CRYPTO < %t %s
+// CHECK-AARCH64-CRYPTO: "-target-feature" "+crypto"
+
+// RUN: %clang -target aarch64 -mno-crypto -### %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-AARCH64-NOCRYPTO < %t %s
+// CHECK-AARCH64-NOCRYPTO: "-target-feature" "-crypto"

clang/test/Driver/armv8-crypto.c

+// REQUIRES: arm-registered-target
+// RUN: %clang -target armv8 -mcrypto -mhard-float -### %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-V8-CRYPTO < %t %s
+// CHECK-V8-CRYPTO: "-target-feature" "+crypto"
+
+// RUN: %clang -target armv8 -mno-crypto -mhard-float -### %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-V8-NOCRYPTO < %t %s
+// CHECK-V8-NOCRYPTO: "-target-feature" "-crypto"

lld/ELF/CallGraphSort.cpp

DenseMap<const InputSectionBase *, int> CallGraphSort::run() {
   // Generate order.
   DenseMap<const InputSectionBase *, int> OrderMap;
   ssize_t CurOrder = 1;
 
   for (const Cluster &C : Clusters)
     for (int SecIndex : C.Sections)
       OrderMap[Sections[SecIndex]] = CurOrder++;
 
+  if (!Config->PrintSymbolOrder.empty()) {
+    std::error_code EC;
+    raw_fd_ostream OS(Config->PrintSymbolOrder, EC, sys::fs::F_None);
+    if (EC) {
+      error("cannot open " + Config->PrintSymbolOrder + ": " + EC.message());
+      return OrderMap;
+    }
+
+    // Print the symbols ordered by C3, in the order of increasing CurOrder
+    // Instead of sorting all the OrderMap, just repeat the loops above.
+    for (const Cluster &C : Clusters)
+      for (int SecIndex : C.Sections)
+        // Search all the symbols in the file of the section
+        // and find out a Defined symbol with name that is within the section.
+        for (Symbol *Sym: Sections[SecIndex]->File->getSymbols())
+          if (!Sym->isSection()) // Filter out section-type symbols here.
+            if (auto *D = dyn_cast<Defined>(Sym))
+              if (Sections[SecIndex] == D->Section)
+                OS << Sym->getName() << "\n";
+  }
   return OrderMap;
 }
 
 // Sort sections by the profile data provided by -callgraph-profile-file
 //
 // This first builds a call graph based on the profile data then merges sections
 // according to the C³ huristic. All clusters are then sorted by a density
 // metric to further improve locality.
 DenseMap<const InputSectionBase *, int> elf::computeCallGraphProfileOrder() {
   return CallGraphSort().run();
 }

lld/ELF/Config.h

struct Configuration {
   llvm::StringRef LTONewPmPasses;
   llvm::StringRef LTOObjPath;
   llvm::StringRef LTOSampleProfile;
   llvm::StringRef MapFile;
   llvm::StringRef OutputFile;
   llvm::StringRef OptRemarksFilename;
   llvm::StringRef OptRemarksPasses;
   llvm::StringRef ProgName;
+  llvm::StringRef PrintSymbolOrder;
   llvm::StringRef SoName;
   llvm::StringRef Sysroot;
   llvm::StringRef ThinLTOCacheDir;
   llvm::StringRef ThinLTOIndexOnlyArg;
   std::pair<llvm::StringRef, llvm::StringRef> ThinLTOObjectSuffixReplace;
   std::pair<llvm::StringRef, llvm::StringRef> ThinLTOPrefixReplace;
   std::string Rpath;
   std::vector<VersionDefinition> VersionDefinitions;

lld/ELF/Driver.cpp

void LinkerDriver::readConfigs(opt::InputArgList &Args) {
   Config->Optimize = args::getInteger(Args, OPT_O, 1);
   Config->OrphanHandling = getOrphanHandling(Args);
   Config->OutputFile = Args.getLastArgValue(OPT_o);
   Config->Pie = Args.hasFlag(OPT_pie, OPT_no_pie, false);
   Config->PrintIcfSections =
       Args.hasFlag(OPT_print_icf_sections, OPT_no_print_icf_sections, false);
   Config->PrintGcSections =
       Args.hasFlag(OPT_print_gc_sections, OPT_no_print_gc_sections, false);
+  Config->PrintSymbolOrder =
+      Args.getLastArgValue(OPT_print_symbol_order);
   Config->Rpath = getRpath(Args);
   Config->Relocatable = Args.hasArg(OPT_relocatable);
   Config->SaveTemps = Args.hasArg(OPT_save_temps);
   Config->SearchPaths = args::getStrings(Args, OPT_library_path);
   Config->SectionStartMap = getSectionStartMap(Args);
   Config->Shared = Args.hasArg(OPT_shared);
   Config->SingleRoRx = Args.hasArg(OPT_no_rosegment);
   Config->SoName = Args.getLastArgValue(OPT_soname);

lld/ELF/Options.td

 defm print_gc_sections: B<"print-gc-sections",
     "List removed unused sections",
     "Do not list removed unused sections (default)">;
 
 defm print_icf_sections: B<"print-icf-sections",
     "List identical folded sections",
     "Do not list identical folded sections (default)">;
 
+defm print_symbol_order:
+  Eq<"print-symbol-order",
+  "Print a symbol order specified by --call-graph-ordering-file into the speficied file">;
+  
 def pop_state: F<"pop-state">,
   HelpText<"Undo the effect of -push-state">;
 
 def push_state: F<"push-state">,
   HelpText<"Save the current state of -as-needed, -static and -whole-archive">;
 
 def print_map: F<"print-map">,
   HelpText<"Print a link map to the standard output">;

lld/test/ELF/cgprofile-print.s

+# REQUIRES: x86
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t
+# RUN: echo "A B 5" > %t.call_graph
+# RUN: echo "B C 50" >> %t.call_graph
+# RUN: echo "C D 40" >> %t.call_graph
+# RUN: echo "D B 10" >> %t.call_graph
+# RUN: ld.lld -e A %t --call-graph-ordering-file %t.call_graph -o %t2 --print-symbol-order=%t3
+# RUN: FileCheck %s --input-file %t3
+
+# CHECK: B
+# CHECK-NEXT: C
+# CHECK-NEXT: D
+# CHECK-NEXT: A
+
+.section    .text.A,"ax",@progbits
+.globl  A
+A:
+ nop
+
+.section    .text.B,"ax",@progbits
+.globl  B
+B:
+ nop
+
+.section    .text.C,"ax",@progbits
+.globl  C
+C:
+ nop
+
+.section    .text.D,"ax",@progbits
+.globl  D
+D:
+ nop
+
+
+

lld/test/ELF/cgprofile-reproduce.s

+# REQUIRES: x86
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t
+# RUN: echo "A B 5" > %t.call_graph
+# RUN: echo "B C 50" >> %t.call_graph
+# RUN: echo "C D 40" >> %t.call_graph
+# RUN: echo "D B 10" >> %t.call_graph
+# RUN: ld.lld -e A %t --call-graph-ordering-file %t.call_graph -o %t2 --print-symbol-order=%t3
+# RUN: ld.lld -e A %t --symbol-ordering-file %t3 -o %t2
+# RUN: llvm-readobj -symbols %t2 | FileCheck %s 
+
+# CHECK:      Name: A
+# CHECK-NEXT: Value: 0x201003
+# CHECK:      Name: B
+# CHECK-NEXT: Value: 0x201000
+# CHECK:      Name: C
+# CHECK-NEXT: Value: 0x201001
+# CHECK:      Name: D
+# CHECK-NEXT: Value: 0x201002
+
+.section    .text.A,"ax",@progbits
+.globl  A
+A:
+ nop
+
+.section    .text.B,"ax",@progbits
+.globl  B
+B:
+ nop
+
+.section    .text.C,"ax",@progbits
+.globl  C
+C:
+ nop
+
+.section    .text.D,"ax",@progbits
+.globl  D
+D:
+ nop
+
+
+